Zeszyty czasopisma

Tom 15 (2022): Zeszyt 1 (January 2022)

Tom 14 (2021): Zeszyt 1 (January 2021)

Tom 13 (2020): Zeszyt 1 (January 2020)

Tom 12 (2019): Zeszyt 1 (January 2019)

Tom 11 (2018): Zeszyt 1 (January 2018)

Tom 10 (2017): Zeszyt 5 (January 2017)

Tom 10 (2017): Zeszyt 4 (January 2017)

Tom 10 (2017): Zeszyt 3 (January 2017)

Tom 10 (2017): Zeszyt 2 (January 2017)

Tom 10 (2017): Zeszyt 1 (January 2017)

Tom 9 (2016): Zeszyt 4 (January 2016)

Tom 9 (2016): Zeszyt 3 (January 2016)

Tom 9 (2016): Zeszyt 2 (January 2016)

Tom 9 (2016): Zeszyt 1 (January 2016)

Tom 8 (2015): Zeszyt 4 (January 2015)

Tom 8 (2015): Zeszyt 3 (January 2015)

Tom 8 (2015): Zeszyt 2 (January 2015)

Tom 8 (2015): Zeszyt 1 (January 2015)

Tom 7 (2014): Zeszyt 5 (January 2014)

Tom 7 (2014): Zeszyt 4 (January 2014)

Tom 7 (2022): Zeszyt 3 (January 2022)

Tom 7 (2022): Zeszyt 2 (January 2022)

Tom 7 (2014): Zeszyt 1 (January 2014)

Tom 6 (2013): Zeszyt 5 (January 2013)

Tom 6 (2013): Zeszyt 4 (January 2013)

Tom 6 (2013): Zeszyt 3 (January 2013)

Tom 6 (2013): Zeszyt 2 (January 2013)

Tom 6 (2013): Zeszyt 1 (January 2013)

Tom 5 (2012): Zeszyt 4 (January 2012)

Tom 5 (2012): Zeszyt 3 (January 2012)

Tom 5 (2012): Zeszyt 2 (January 2012)

Tom 5 (2012): Zeszyt 1 (January 2012)

Tom 4 (2011): Zeszyt 4 (January 2011)

Tom 4 (2011): Zeszyt 3 (January 2011)

Tom 4 (2011): Zeszyt 2 (January 2011)

Tom 4 (2011): Zeszyt 1 (January 2011)

Tom 3 (2010): Zeszyt 4 (January 2010)

Tom 3 (2010): Zeszyt 3 (January 2010)

Tom 3 (2010): Zeszyt 2 (January 2010)

Tom 3 (2010): Zeszyt 1 (January 2010)

Tom 2 (2009): Zeszyt 4 (January 2009)

Tom 2 (2009): Zeszyt 3 (January 2009)

Tom 2 (2009): Zeszyt 2 (January 2009)

Tom 2 (2009): Zeszyt 1 (January 2009)

Tom 1 (2008): Zeszyt 4 (January 2008)

Tom 1 (2008): Zeszyt 3 (January 2008)

Tom 1 (2008): Zeszyt 2 (January 2008)

Tom 1 (2008): Zeszyt 1 (January 2008)

Informacje o czasopiśmie
Format
Czasopismo
eISSN
1178-5608
Pierwsze wydanie
01 Jan 2008
Częstotliwość wydawania
1 raz w roku
Języki
Angielski

Wyszukiwanie

Tom 8 (2015): Zeszyt 1 (January 2015)

Informacje o czasopiśmie
Format
Czasopismo
eISSN
1178-5608
Pierwsze wydanie
01 Jan 2008
Częstotliwość wydawania
1 raz w roku
Języki
Angielski

Wyszukiwanie

39 Artykułów
Otwarty dostęp

An Assistance System For Building Intelligent Spaces Based On Mapsharing Among A Mobile Robot And Distributed Sensors

Data publikacji: 01 Mar 2015
Zakres stron: 1 - 25

Abstrakt

Abstract

An intelligent space is a space constructed with many networked sensors. Humans and robots in the space are extracted and tracked cooperatively by the networked sensors. The intelligent space can achieve position-based supports to humans and robots according to integration of networked sensors. Generally, the networked sensors are distributed and fixed on the structures in the space such as walls, ceilings and etc. In order to track moving objects such as humans and robots in the intelligent space, all networked sensors have to obtain objects positions in the unified world coordinate. In that case, positions and orientations of the networked sensors must be also known in the unified world coordinate system. However, it is time-consuming to measure positions of many sensors in the world coordinate accurately and manually. This study aims to develop a system for supporting estimation of positions and orientations of the networked sensors in the intelligent space.

In this paper, a configuration of the proposed system is introduced. The proposed system consists of map building systems of the mobile robot and the distributed sensors. A global map from the robot and local maps from the distributed sensors are compared. Then, the local maps of the distributed sensors are associated with the global map and the positions of the distributed sensors are estimated in the global map. For improvement of map matching, angle differences between maps are evaluated. Some experimental results in an actual environment show that the proposed system achieve sensor position estimation easily.

Index terms

  • Intelligent Space
  • Mobile Robot
  • SLAM!
Otwarty dostęp

Low-Power Wireless Liquid Monitoring System using Ultrasonic Sensors

Data publikacji: 01 Mar 2015
Zakres stron: 26 - 44

Abstrakt

Abstract

Monitoring Systems are necessary to understand the changes that take place in environments. Remote monitoring and data collection systems are useful and effective tools to collect information from bulk storage tanks and to monitor the same. The measurement of liquid inside the tank is most important and such systems are useful in industries which are categorized as safety critical systems. This paper presents the architecture and initial testing results of a low power wireless system for tank level monitoring using ultrasonic sensors.

Index terms

  • GSM
  • remote monitoring
  • ultrasonic sensors
  • tanks
  • low-power
Otwarty dostęp

A Study of X-Ray Machine Image Local Semantic Features Extraction Model based on bag-of-words for Airport Security

Data publikacji: 01 Mar 2015
Zakres stron: 45 - 64

Abstrakt

Abstract

The aviation security at the airport has been faced with increasingly severe situations since the 9-11 event. It’s of utmost importance to train airport X-ray machine screener’s image recognition competency. So they can prevent terrorists from bringing dangerous articles in their carry-on or checked bags. However, usually the luggages are placed in different positions and the density & volume of articles differ greatly. As a result, dangerous articles show a variety of X-ray image features. It’s easy for the confused screeners to miss or incorrectly detect dangerous articles. This has been a hidden danger for civil aviation safety. For image recognition improvement, the researcher analyzed the visual semantics of dangerous goods images and applied a local semantic features extraction method. After classification and summarization, the method was used to train the screeners for particular image recognition. The comparison showed the improved accuracy and efficiency of image recognition for the screeners and demonstrated a satisfactory effect.

Index terms

  • airport security
  • bag-of-words
  • semantic analysis
  • image features
Otwarty dostęp

L-Shaped Cantilever Parallel - Plate MEMS Accelerometer Design Parameters using A Gravitational Search Algorithm

Data publikacji: 01 Mar 2015
Zakres stron: 65 - 89

Abstrakt

Abstract

Due to their small size, low weight, low cost and low energy consumption, MEMS (Micro Electro-Mechanical Systems) accelerometers have achieved great commercial success in recent decades. The objective of this paper is to find the optimum design for a typical MEMS accelerometer, which satisfies a set of given constraints. Due to the complex nature of the problem, a gravitational search algorithm (GSA) is developed for optimization. The GSA attempts to optimize the inter-plate gap while satisfying all other engineering goals. The model was constructed in Msc Patran and Nastran software were calculated and model’s response was found. In this paper the optimal design from the theoretically derived gravitational search algorithm is compared to finite element model in order to ascertain its accuracy and verify the results.

Index terms

  • Power system
  • MEMS
  • capacitive accelerometer
  • optimization
  • proof-mass
  • L-shaped beam
  • GSA
  • frequency
Otwarty dostęp

A Novel Approach of Combining Steganography Algorithms

Data publikacji: 01 Mar 2015
Zakres stron: 90 - 106

Abstrakt

Abstract

Steganography is the act of hiding a message inside another message in such a way that the hidden message can only be detected by its intended recipient. In this paper, we combined two steganography algorithms namely JSteg and OutGuess algorithms, in order to exploit the beneficial characteristics and features of both algorithms to enhance the protection level for secret images. In our proposed approach, the secret message (image) is first concealed inside another image using JSteg algorithm and the resultant stego-image is further hidden inside a final image using OutGuess 0.1 algorithm. In this combine approach, the tricky nature of hiding an already hidden message is using two different algorithms increases the level of difficulty for a third party to suspect the existence of a secret image in the first place or even successful decode the it. Besides that, the priority given to the choice of a good image size and type in this approach further disguises the secret image and increases the chances that the image could go unnoticed. Results after calculating the capacity and PSNR for images proved that our approach is a good and acceptable steganography system. The model presented here is based on JPEG images.

Index terms

  • Transform Domain Technique
  • Jsteg
  • OutGuess0.1
  • MSE
  • peak-signal-to-noise ratio (PSNR)
Otwarty dostęp

Sparse Representation Theory and its Application for Face Recognition

Data publikacji: 01 Mar 2015
Zakres stron: 107 - 124

Abstrakt

Abstract

Face recognition aims at endowing computers with the ability to identify different human beings according to their face images. However, recognition rate will decrease sharply when it refers to the non-ideal imaging environments or the incorporation of users, such as illumination, pose, expression variations and so on. Besides, it will be also influence the recognition results when the database is too large or small. Sparse representation based classification for face images has been one of efficient approaches for face recognition in recent years. Discrimination performance by using the sparse representation can also be applied to the face recognition, and any test sample can be expressed as a linear span of the all training samples. Experimental results show that face recognition method based on sparse representation is comparable to others.

Index terms

  • Face recognition
  • recognition rate
  • non-ideal imaging environments
  • sparse representation
Otwarty dostęp

Survey of Semantic Similarity Measures in Pervasive Computing

Data publikacji: 01 Mar 2015
Zakres stron: 125 - 158

Abstrakt

Abstract

Semantic similarity measures usage is prevalent in pervasive computing with the following aims: 1) to compare the components of an application; 2) to recommend and rank services by degree of relevance; 3) to identify services by matching the description of a query with the available services; 5) to compare the current context with already known contexts. The existing works that apply semantic similarity measures to pervasive computing focus on one particular issue. Furthermore, surveys in this domain are limited to the recommendation or discovery of context-aware services. In this article, we therefore present a survey of context-aware semantic similarity measures used in various areas of pervasive computing.

Index terms

  • pervasive computing
  • semantic similarity
  • context-aware
  • service discovery
  • service recommendation
Otwarty dostęp

Image Fusion and Recognition based on Compressed Sensing Theory

Data publikacji: 01 Mar 2015
Zakres stron: 159 - 180

Abstrakt

Abstract

As the compressed sensing theory can offer a better performance than Nyquist sampling theorem when dealing with large amounts of data, it becomes very popular for image fusion and target recognition in image processing. In this paper, a new image fusion algorithm based on compressed sensing was proposed. By discrete cosine transform, it fused images through weighted coefficient, recovered the fusion images by basic pursuit algorithm. Moreover, a recognition algorithm in compressed sensing was also studied, which obtained a sample matrix using preprocessing based on a wavelet transform, calculated the approximate coefficient by orthogonal matching pursuit, and made a classification using the with minimum distance formula. Finally, experiments were designed to demonstrate the effectiveness of the proposed algorithms.

Index terms

  • Mage fusion
  • target recognition
  • compressed sensing
  • wavelet transform
Otwarty dostęp

Tracking of Moving Target Based on Video Motion Nuclear Algorithm

Data publikacji: 01 Mar 2015
Zakres stron: 181 - 198

Abstrakt

Abstract

Moving target detection and tracking algorithm research content is very broad and complex applications, without and different target features directly affects the detection of selected tracking algorithm. So far still does not exist a universal algorithm for perfect can be suitable for various applications, so the detection and tracking of moving targets is still a valuable research subject of. The research work in this paper is in the field, the moving target detection spatiotemporal correlation and difference contour tracking algorithm based on a fixed background. The algorithm in the background under the condition of fixed to pay a smaller time complexity, the target detection and tracking has a good effect, so it has higher application value. Based on solving the detection and location of moving target tracking in real-time and accuracy requirements, a new moving target detection spatiotemporal correlation and difference contour tracking scheme based on the practical implementation, at the same time analysis and the experimental results are given. In the moving target tracking, tracking method is mainly traditional correlation method target based on template matching. The matching process is time consuming, so the actual use of more of the improved algorithm of correlation method, the improved algorithm attempts to improve the efficiency of feature matching and search range, and also achieved a certain effect, the some excellent tracking algorithm. This paper presents an improved active contour model tracking algorithm, improve the tracking efficiency and quality, the algorithm first from the frame difference detection results to find the moving target coarse contour, and then the convergence of coarse contour by using improved Snake algorithm, the right edge to get the target in the course of the campaign, in order to achieve the tracking of moving objects.

Index terms

  • Moving object
  • detection
  • active
  • pattern recognition
  • image features
Otwarty dostęp

Digital Image Watermarking Algorithms Based on Dual Transform Domain and Self-Recovery

Data publikacji: 01 Mar 2015
Zakres stron: 199 - 219

Abstrakt

Abstract

In view of dual watermarking algorithm for dual two value image watermarking, the watermark information there is a gray image watermarking in the expression is obviously insufficient. The proposed embedded in the carrier image on the dual watermark includes a two watermark image and a gray image watermarking algorithm, the persuasive power while maintaining the original two values of the watermark robustness at the same time, improve the watermark information. In order to balance the robustness and invisibility of watermarking algorithm, this paper analyzes the embedding position and strategy of transform domain algorithms, the DC coefficient in the carrier image is divided into blocks of DCT spectrum and spectrum on the combination of DWT coefficient method and the advantage of embedded dual watermarking, and use the NEC characteristic of the algorithm is improved adaptive based on the embedded mode. The gray image watermark bit plane decomposition compression high four bit plane information as watermarking, in reducing the original watermark loading and enhance the overall strength of self recovery system. This paper from the working principle, classification of digital watermarking, attack types, performance index, evaluation method and uses six aspects were introduced to the digital watermarking technology. Simulation study of a digital image watermarking algorithm based on DCT transform and Arnold transform, the algorithm’s imperceptibility, robustness and security are analyzed, the algorithm for embedding process.

Index terms

  • Stay cable
  • positive pressure arch effect
  • mechanism
  • friction coefficient
  • ANSYS
  • contact analysis
Otwarty dostęp

Characterization of a Needle-Type Giant Magnetoresistance Sensor for Detection of Escherichia Coli’S Magnetic Marker

Data publikacji: 01 Mar 2015
Zakres stron: 220 - 234

Abstrakt

Abstract

In the recent years, the introduction and development of simple and portable sensors has been the focus of researchers in nearly all scientific domains, particularly in the biomedical settings. Giant magnetoresistance (GMR) provides a cutting-edge sensor technology. The GMR-based sensors are capable to affordably and sensitively detect and quantify micro- and nano-magnetic particles, even in very weak magnetic fields.

In this paper, we introduce a highly sensitive needle-type GMR-based sensor, designed for the identification and quantification of Escherichia coli O157:H7 bacteria covered by superparamagnetic beads, Dynabeads® MAX E.coli O157. The sensor characteristics, measurement system setup and the properties of the magnetic marker solution are discussed in detail.

Index terms

  • Giant magnetoresistance (GMR) sensor
  • Escherichia coli O157:H7
  • magnetic marker
  • sensor sensitivity
  • magnetic fluid weight density
  • magnetic field
Otwarty dostęp

Acoustic-Phonetic Feature Based Dialect Identification in Hindi Speech

Data publikacji: 01 Mar 2015
Zakres stron: 235 - 254

Abstrakt

Abstract

Every individual has some unique speaking style and this variation influences their speech characteristics. Speakers’ native dialect is one of the major factors influencing their speech characteristics that influence the performance of automatic speech recognition system (ASR). In this paper, we describe a method to identify Hindi dialects and examine the contribution of different acoustic-phonetic features for the purpose. Mel frequency cepstral coefficients (MFCC), Perceptual linear prediction coefficients (PLP) and PLP derived from Mel-scale filter bank (MF- PLP) have been extracted as spectral features from the spoken utterances. They are further used to measure the capability of Auto-associative neural networks (AANN) for capturing non-linear relation specific to information from spectral features. Prosodic features are for capturing long - range features. Based on these features efficiency of AANN is measured to model intrinsic characteristics of speech features due to dialects.

Index terms

  • Dialect Identification
  • Auto-associative neural network
  • Feature compression
  • Hindi dialects
  • Spectral and Prosodic features
Otwarty dostęp

Robust Visual Tracking Based on Support Vector Machine and Weighted Sampling Method

Data publikacji: 01 Mar 2015
Zakres stron: 255 - 271

Abstrakt

Abstract

Visual tracking algorithm based on binary classification has become the research hot issue. The tracking algorithm firstly constructs a binary classifier between object and background, then to determine the object’s location by the probability of the classifier. However, such binary classification may not fully handle the outliers, which may cause drifting. To improve the robustness of these tracking methods, a novel object tracking algorithm is proposed based on support vector machine (SVM) and weighted multi-sample sampling method. Our method constructs a classifier by sampling positive and negative samples and then to find the best candidate that has the largest response using SVM classifier. What’s more, the proposed method integrates weighted multi-instance sampling method, which can consider the sample importance by the different weights. The experimental results on many sequences show the robustness and accuracy of the improved method. The proposed target tracking algorithm in video target tracking with a variety of classic popular tracking algorithm, better able to achieve robust target tracking, but also in the infrared video, the infrared target tracking is also has the advantages of stable and accurate.

Index terms

  • Visual tracking
  • support vector machine (SVM)
  • weighted multi-sample sampling method
Otwarty dostęp

Nodes Control Algorithm Design Based Coverage and Connectivity of Wireless Sensor Network

Data publikacji: 01 Mar 2015
Zakres stron: 272 - 290

Abstrakt

Abstract

Coverage and connectivity are two important problems in wireless sensor network. This paper focuses on the wireless sensor network communication radius in the high density of sensor nodes deployed randomly and two times smaller than the sensing radius; put forward a distributed k coverage multi connected node deployment algorithm based on grid. Simulation results show that the algorithm in this paper while guaranteeing the wireless sensor network coverage and connectivity can reduce the number of the active state nodes effectively, prolong the wireless sensor network lifetime. Theoretical analysis results show that this article nodes deployment algorithm achieves multi connected

Index terms

  • Stay cable
  • positive pressure arch effect
  • mechanism
  • friction coefficient
  • ANSYS
  • contact analysis
Otwarty dostęp

A Comprehensive Analysis on Sizing of Solar Energy Harvester Elements for Wireless Sensor Motes

Data publikacji: 01 Mar 2015
Zakres stron: 291 - 315

Abstrakt

Abstract

Wireless sensor networks (WSN) have limited lifetime due to on board battery. The lifetime can be improved by energy harvesting solutions. In this paper the solar energy harvester requirements for TelosB mote has been analyzed and calculated. Photovoltaic (PV) panel and battery sizing requirements are calculated by assuming that the mote follows SMAC and TDMA-MAC schedule for image communication. The calculations are validated by comparing it with the parameters calculated from the real time current consumption measurement of the mote. Lifetime has been predicted with the physical design of energy harvester. The analysis confirms that the lifetime of the network can be increased to a greater extent, by proper sizing of the harvester and efficient utilization of the available energy.

Index terms

  • WSN
  • energy harvester
  • lifetime prediction
  • battery
  • PV source
Otwarty dostęp

Feature Selection Algorithm Based on Conditional Dynamic Mutual Information

Data publikacji: 01 Mar 2015
Zakres stron: 316 - 337

Abstrakt

Abstract

Aim at existing selection algorithm mutual information inaccurate valuation problem, a condition dynamic concept of mutual information. On this basis, the conditions proposed based on dynamic mutual information (CDMI) feature selection algorithm to overcome the traditional mutual information selection process dynamic correlation problem; conditions of dynamic mutual information throughout the selection process is dynamic valuation, those the samples can be identified after each selection features removed so that they no longer participate in conditional mutual information calculation process, accurate measurement sample. Accurate measurement sample on the degree of importance characteristics and at the same time ensure that the characteristics of information content. The experimental results verify the correctness and effectiveness of the algorithm.

Index terms

  • Dalgaard-Strulik model
  • energy
  • economic growth
  • time delay
  • limit cycle
Otwarty dostęp

Review on Modeling and Controller Design of Hydraulic Actuator Systems

Data publikacji: 01 Mar 2015
Zakres stron: 338 - 367

Abstrakt

Abstract

The purpose of this paper is to review the literature on modeling and previous control strategies of the hydraulic actuator system proposed by most of the researchers around the world. Before comes to the main discussion, some background information related to hydraulic actuator will be presented. This review includes a short summary and conclusion for hydraulic actuator system. The repercussion of this review is for future inventions of a better and robust hydraulic actuator system.

Index terms

  • hydraulic actuator system
  • motion control
  • load variation
  • nonlinear system
  • modeling
  • controller
Otwarty dostęp

Recommender Algorithms Based on Boosting Ensemble Learning

Data publikacji: 01 Mar 2015
Zakres stron: 368 - 386

Abstrakt

Abstract

This article introduces ensemble learning algorithms in recommender systems, and in boosting algorithm framework of this article, shows how to filter the basic recommendation algorithm according to the characteristics of boosting algorithm. By comparing the rational choice of the two recommended boosting algorithm is applied to the frame. And then it determines the main parameters of the algorithm through the experiments, ultimately to obtain a more effective integration of the recommendation algorithm. Experimental results on Netflix validate the effectiveness of the proposed algorithm.

Index terms

  • Recommended System
  • Ensemble learning
  • Collaborative filtering
  • boosting
Otwarty dostęp

Iris-Face Fusion and Security Analysis Based on Fisher Discriminant

Data publikacji: 01 Mar 2015
Zakres stron: 387 - 407

Abstrakt

Abstract

With the development of society and science technology, the information security becomes more and more important for people and nation. In this paper, we focus on the technology of iris-face fusion in multi-mode sense in order to find an algorithm to get a better recognition performance. Firstly, we introduce the feature extraction of iris and face, and fusion the features using different algorithms. By simulation, we find out the recognition performance with different fusion methods, which provide some new conclusions. In order to improve the performance of recognition system, we classify these features with fisher discriminant analysis again. Then we analyze the security of recognition system from the aspect of influence of leak in biology features. Finally, experiments were designed to demonstrate the effectiveness of the proposed algorithms.

Index terms

  • iris feature
  • face feature
  • fisher discriminant analysis
  • fusion
Otwarty dostęp

Aptive Image Segmentation based on Saliency Detection

Data publikacji: 01 Mar 2015
Zakres stron: 408 - 428

Abstrakt

Abstract

in this article, we propose an adaptive image segmentation method based on saliency. First of all, we obtain the saliency map of an image via four bottom-layer feature tunnels, i.e. color, intensity, direction and energy. The energy tunnel helps to describe the outline of objects better in the saliency map. Then, we construct the target detection masks according to the greyness of pixels in the saliency map. Each mask is applied to the original image as the result of pre-segmentation, then corresponding image entropy is calculated. Predict the expected entropy according to maximum entropy criteria and select the optimal segmentation according to the entropies of pre-segmented images and the expected entropy. A large number of experiments have proved the effectiveness and advantages of this algorithm.

Index terms

  • Visual feature
  • image segment
  • maximum energy criteria
  • saliency detection
Otwarty dostęp

Geometric Deep Particle Filter for Motorcycle Tracking: Development of Intelligent Traffic System in Jakarta

Data publikacji: 01 Mar 2015
Zakres stron: 429 - 463

Abstrakt

Abstract

Intelligent Transportation Systems (ITS) is the combination of transportation systems with Information and Communication Technology (ICT). In Jakarta traffic, there is unique issue that does not arise in developed countries: very large number of motorcycles. Nevertheless, the enabling technologies for the detection, measurement, recording, and information distribution of motorcycle have not been fully developed in the existing researches. With the above considerations, we establish research which aimed to develop enabling technology especially in here for tracking motorcycle using camera.

This paper is presented our proposed tracker which called as Geometric Deep Particle Filter (GDPF) for tracking motorcycle using camera. The tracker is inspired by human visual perception which has nonretinotopic nature. Based on particle filter approach, our goal is to improve the transition model in order to overcome motorcycle maneuver. We will exploit this curved nature of the state space using geometric computing theory, such as Lie groups, and Lie algebras. A number of experiments have been conducted for this research, and it has been found that GDPF has achieved certain degree of success in object tracking.

Index terms

  • visual tracking
  • motorcycle
  • nonretinotopic
  • particle filter
  • deep learning
  • geometric computing
  • affine transformation
Otwarty dostęp

New Stereo Matching Method Based on Improved BP Algorithm

Data publikacji: 01 Mar 2015
Zakres stron: 464 - 479

Abstrakt

Abstract

As stereo matching methods are widely used in computer vision and stereo reconstruction, from the perspective of improving the matching accuracy, this paper focuses on the global optimization algorithm. An improved stereo matching method based on 8- neighbor Belief Propagation method is proposed in this paper, by involving more pixels into information transmission, our method improves the accuracy of stereo matching. The experimental results verify the efficiency and reliability of our method.

Index terms

  • Disparity map
  • stereo vision
  • MRF Model
  • Disparity map
  • Markov Random
Otwarty dostęp

Study on Image Compression and Fusion Based on the Wavelet Transform Technology

Data publikacji: 01 Mar 2015
Zakres stron: 480 - 496

Abstrakt

Abstract

With the development of information technology, the rapid development of microelectronics technology, image information acquisition and use is also increasing, sensor technology also unceasingly to reform. A single sensor information obtained is limited, often can not meet the actual needs, in addition, different sensors have the advantage of the imaging principle and its unique, as in color, shape characteristics, band access, spatial resolution from the aspects of all have their own characteristics. Registration algorithm is proposed in this paper has better robustness to image noise, and can achieve sub-pixel accuracy; the registration time has also been greatly improved. In terms of image fusion, the images to be fused through wavelet transform of different resolution sub image, using a new image fusion method based on energy and correlation coefficient. The high frequency image decomposed using new energy pixels of the window to window energy contribution rate of fusion rules, the low frequency part by using the correlation coefficient of the fusion strategy, finally has carried on the registration of simulation experiments in the Matlab environment, through the simulation experiments of fusion method in this paper can get the image fusion speed and high quality fast fusion image.

Index terms

  • wavelet transform
  • image match
  • image fusion
  • spatial resolution
Otwarty dostęp

Small Target Detection based on Infrared Image Adaptive

Data publikacji: 01 Mar 2015
Zakres stron: 497 - 515

Abstrakt

Abstract

This paper studies the multi-resolution analysis of infrared image preprocessing method based on wavelet transform, wavelet transform infrared image of small target for pretreatment, after pretreatment suppressed image background clutter, improved signal to noise ratio. On this basis, studies based on infrared image sequences generated background Kalman filter and target detection algorithm, given the principle of the algorithm, time-domain method for generating fading background and moving object extraction methods such as recursive least squares method, and the experimental results show that the algorithm capable of detecting small targets in infrared images, with good results. based pretreatment small target motion continuity characteristics studied image sequences small moving target detection algorithm based on weighted dynamic programming, dynamic programming algorithm principle is given, analysis of the direct method and the accumulation of gray dynamic programming algorithm based on similar likelihood function for dynamic programming problems arise energy diffusion gives improved dynamic programming algorithm: weighted dynamic programming algorithm, the algorithm implementation steps, testing and experimental structure the results were analyzed, the results show that the algorithm for small moving target detection with good results. Finally, this paper studied the infrared image reject false target trajectory get the real target trajectory correlation method, so as to improve the detection rate and reduce the false alarm rate the purpose.

Index terms

  • Target enhancement
  • local spectrum suppression
  • regular patches
  • log amplitude spectrum
  • TDI
Otwarty dostęp

A Deployment Algorithm for Mobile Wireless Sensor Networks based on the Electrostatic Field Theory

Data publikacji: 01 Mar 2015
Zakres stron: 516 - 537

Abstrakt

Abstract

This paper proposes a deployment algorithm based on the electrostatic field theory for mobile wireless sensor networks. The nodes and obstacles in the deployment area are taken as the charged particles; and the particles will move due to the Coulomb’s force from other particles or obstacles. Finally, the nodes automatically spread to the whole area by the resultant action and complete the deployment. Four metrics, including coverage, uniformity, deployment time and average displacement distance, are used to evaluate the performance of the algorithm. The simulation results show that the proposed algorithm can give full play to its self-adaptive advantages and achieve the desired deployment effect; it is a kind of deployment algorithm with self-adaptive characteristics.

Index terms

  • Mobile Wireless Sensor Networks
  • Electrostatic field
  • Deployment algorithm
Otwarty dostęp

The Transformer Winding Temperature Monitoring System Based on Fiber Bragg Grating

Data publikacji: 01 Mar 2015
Zakres stron: 538 - 560

Abstrakt

Abstract

High temperature is one of the important reasons causing the fire in power system. Therefore, the early warning could be told by monitoring the temperature and effective measures could be taken. The corresponding accidents will be reduced. The traditional transformer winding temperature monitoring methods are electrical signal measurement and infrared measurement. Such electrical signal sensors are vulnerable to the interference of electromagnetic field, so the result of measurement is bad. Multiplexing optical path is unable to be realized by fluorescence thermometry. The optical fiber Bragg grating technology is used on temperature monitoring of transformer winding in this paper. The transformer winding temperature monitoring system based on optical fiber Bragg grating includes three parts: Temperature monitoring program based on the LabVIEW programming language, a fiber Bragg grating wavelength demodulation system and FBG temperature sensor. When the temperature of the transformer windings changes, the central wavelength of the fiber Bragg grating changes accordingly. Broadband ASE light source emits light, which is transmitted from the optical circulator into the fiber Bragg grating. The reflected light gets into the wavelength demodulation module again through the optical circulator. Wavelength demodulation module could transmit the center wavelength of the spectral reflectance information, peak power information to the computer. The computer analyzes, processes the information and displays the data with XY graph by calling the LabVIEW program. The program can get center wavelength values at the same time then get temperature by fitting function and display temperature on the front panel of the program. The fitting line of linearity between center wavelength of optical fiber Bragg grating sensor and temperature is above 0.95. The function reveals a good linearity which fitting the wavelength changes of the optical fiber Bragg grating during this temperature range. The experimental results show that the system has high accurate measurement which meeting high precision requirements of transformer winding temperature.

Index terms

  • FBG
  • transformer winding
  • temperature
  • FBGA demodulation
  • LabVIEW
Otwarty dostęp

Security of Wireless Sensor Networks for Health Monitoring Helmets with Anomaly Detection using Power Analysis and Probabilistic Model

Data publikacji: 01 Mar 2015
Zakres stron: 561 - 580

Abstrakt

Abstract

Litigation faced by the NFL has called for better prevention and understanding of concussions and other sports injuries. To achieve this, sports officials have turned to wireless sensor networks, or WSNs, in the form of helmet sensors that automatically report any harmful injuries to attendants on the sidelines. While this approach provides players with a greater assurance of safety and a faster response to their injuries, the security weaknesses of WSNs must be addressed. These systems, being not only recently developed but also highly resource-constrained, may be easily manipulated by those looking to gain information about players (a form of passive attack) or even attempting to remove them from the game through the sending of false reports (a form of active attack). To prevent attacks such as these, we propose a system that uses a modification of the AES-CCM protocol as well as a novel attack detection system that uses probabilistic methods to report any harmful behavior to the user. The system’s power usage due to injury reports is compared to a probability model that is based on past research that recorded the likelihood of injury for the positions played in professional football. This system offers many advantages over conventional cryptography as it is a lightweight approach that costs few resources; individual helmet sensors need only send simple power reports to a central base station which uses on-the-grid power to conduct security analysis. Provided below is detail of the paper which describes the problem in greater detail, a section that details the system architecture, a section that explains the AES-CCM protocol, and an explanation of the probabilistic approach. This is followed by a security analysis that compares the approach to several other approaches found in the literature, and finally a conclusion.

Index terms

  • Sensor networks
  • AES
  • Probabilistic model
Otwarty dostęp

Intelligent Detection of Facial Expression based on Image

Data publikacji: 01 Mar 2015
Zakres stron: 581 - 601

Abstrakt

Abstract

Human facial expressions detection plays a central role in pervasive health care and it is an active research field in computer vision. In this paper, a novel method for facial expression detection from dynamic facial images is proposed, which includes two stages of feature extraction and facial expression detection. Firstly, Active Shape Model (ASM) is used to extract the local texture feature, and optical flow technique is determined facial velocity information, which is used to characterize facial expression. Then, fusing the local texture feature and facial velocity information get the hybrid characteristics using Bag of Words. Finally, Multi-Instance Boosting model is used to recognize facial expression from video sequences. In order to be learned quickly and complete the detection, the class label information is used for the learning of the Multi-Instance Boosting model. Experiments were performed on a facial expression dataset built by ourselves and on the JAFFE database to evaluate the proposed method. The proposed method shows substantially higher accuracy at facial expression detection than has been previously achieved and gets a detection accuracy of 95.3%, which validates its effectiveness and meets the requirements of stable, reliable, high precision and anti-interference ability etc.

Index terms

  • Facial expression
  • ASM model
  • Optical flow model
  • Bag of Words
Otwarty dostęp

Adjustment of the Parallelism of two Mirrors for Wide Angle Divided Mirror Michelson Wind Imaging Interferometer

Data publikacji: 01 Mar 2015
Zakres stron: 602 - 619

Abstrakt

Abstract

Many ways have been developed to measure atmospheric winds by detecting the Doppler shifts of airglow emission lines. The Michelson Interferometer is widely used because of its simple principle. To get the Doppler shifts to calculate the wind velocity, researchers developed four-phase-step and divided mirror technology respectively. But they face challenges in many fields. So a wide angle Michelson Interferometer combining with divided mirror and phase stepping technique is used in this paper. A new algorithm is proposed in this paper to adjust the parallelism of the two mirrors for the Michelson Interferometer. Thus a high precision parallelism of the two mirrors can be obtained to get the phase shift and calculate wind velocity. The interval of the two mirrors has maximum difference less than one tenth wavelength. The experiments were performed in visible channel to prove the feasibility of this proposed algorithm. It can also be used in other fields demanding two surfaces parallel with high precision.

Index terms

  • parallelism
  • phase shift
  • divided mirror
  • phase stepping
Otwarty dostęp

Cyber-Awareness Improvement Using Artificial Intelligence Techniques

Data publikacji: 01 Mar 2015
Zakres stron: 620 - 636

Abstrakt

Abstract

The primary contribution of this experiment is the development of a framework on which a variety of multitasking processes can be mapped. A software model named SHOWAN is developed to represent, capture and learn the cyber awareness behavior of a computer process against multiple concurrent threads. At the beginning of the experiment, the examined process outperformed, and tended to manage numerous tasks poorly, but it gradually learned to handle fewer tasks and excelling in each of them.

Index terms

  • Cyber Security
  • Queuing Management
  • Task Prioritization
  • Normative Model
  • Cyber Multitasking Performance
  • Non-maskable task
Otwarty dostęp

The Bending Mode Control Method of AFS System Based on Preview Control

Data publikacji: 01 Mar 2015
Zakres stron: 637 - 657

Abstrakt

Abstract

Due to the time-lag of both the mechanical transmission and controller area network (CAN) bus transmission of the Adaptive Front Lighting System (AFS), the actual bending angle of AFS invariably lags behind the steering-wheel angle, which not only makes the real-time response speed of the AFS system slow, but also makes the system stability and the active safety of the vehicle poor.

To solve the problem, firstly, the geometrical relations among safety braking distance and the rate of steering-wheel angle and turning radius of the vehicle are analyzed. Secondly, the mathematics model among these variables has been set up. Finally, in order to improve the road illumination of the curve, the control method of bending mode of AFS system based on preview control is proposed. Based on preview control algorithm, the simulation model of the AFS has been built as well as the AFS control experiment platform. After the comparison between preview control and servo control, it can be proved that the preview control method proposed is superior to traditional servo control in AFS system.

Index terms

  • AFS headlamp
  • lag of Steering-wheel angle
  • road illumination
  • preview model
  • preview control
Otwarty dostęp

Travel Time Prediction Based on Pattern Matching Method

Data publikacji: 01 Mar 2015
Zakres stron: 658 - 676

Abstrakt

Abstract

The microwave detection technology has become an effective tool for monitoring highway traffic flow in China. The cross section traffic data collected provides models opportunity for travel time prediction. However, the sparseness of data somewhat constrains the prediction accuracy. To tackle this problem, the paper presents a highway travel time prediction algorithm based on pattern matching method. First, a pattern library is established by choosing traffic volume and speed as its certain state components and time as its uncertain state component. Then, the space-time two-dimensional linear interpolation method is used to calculate the mean speed and subsequently the travel time. Finally, similar patterns are obtained using K Nearest Neighbor approach and predicted travel time is calculated by the Weighted Average method. The case study shows that the pattern matching method for travel time prediction based on microwave detection data produces sufficient accuracy, which solves the problem of sparse detectors effectively.

Index terms

  • Travel time prediction
  • Pattern matching method
  • Microwave detection data
  • Two-dimensional linear interpolation method
Otwarty dostęp

Object Tracking Based on Machine Vision and improved SVDD Algorithm

Data publikacji: 01 Mar 2015
Zakres stron: 677 - 696

Abstrakt

Abstract

Object tracking is an important research topic in the applications of machine vision, and has made great progress in the past decades, among which the technique based on classification is a very efficient way to solve the tracking problem. The classifier classifies the objects and background into two different classes, where the tracking drift caused by noisy background can be effectively handled by one-class SVM. But the time and space complexities of traditional one-class SVM methods tend to be high, which makes it do not scale well with the number of training sample, and limits its wide applications. Based on the idea proposed by Support Vector Data Description, we present an improved SVDD algorithm to handle object tracking efficiently. The experimental results on synthetic data, tracking results on car and plane demonstrate the validity of the proposed algorithm.

Index terms

  • Object tracking
  • machine vision
  • Support Vector Data Description
  • one-class SVM
  • classification
Otwarty dostęp

Automated Telehealth System for Fetal Growth Detection and Approximation of Ultrasound Images

Data publikacji: 01 Mar 2015
Zakres stron: 697 - 719

Abstrakt

Abstract

One of the most profound use of ultrasound imaging is fetal growth monitoring. Conventionally, physicians will perform manual measurements of several parameters of the ultrasound images to draw some conclusion of the fetal condition by manually annotating the fetal images on the ultrasound device interface. However, performing manual annotation of fetal images will require significant amount of time considering the number of patients an obstetrician can have. In this paper, an integrated automatic system for fetal growth monitoring and detection is proposed. This system will be able to automatically measuring the parameters of fetal head, abdomen, femur, and humerus. In addition to automated image detection, we also propose an integrated telehealth monitoring system to provide better access of ultrasound monitoring for patients that lives in rural areas. A new approach of fetal image detection is also proposed by using AdaBoost.MH boosting algorithm that is combined with an improved efficient Hough Transform for detecting ellipse-like organs such as head and abdomen. Experiments of the method are tested on real ultrasound image dataset. The detection was applied on 2D ultrasound images to perform fetal object measurement to approximate the Head Circumference (HC) and Biparietal Diameter (BPD), Femur Length (FL), and Humerus Length (HL).

Index terms

  • ultrasound
  • automated system
  • fetal organ detection
  • fetal parameters measurement
  • telehealth
Otwarty dostęp

Automatic Fetal Organs Detection and Approximation in Ultrasound Image

Data publikacji: 01 Mar 2015
Zakres stron: 720 - 748

Abstrakt

Abstract

This paper proposed a system for detecting and approximating of a fetus in an ultrasound image. The fetal organs in the ultrasound image are detected using Multi Boundary Classifier based Adaboost.MH. The results of the fetal detection is then approximated Randomized Hough Transform and the whole showed a mean accuracy of 95.80%. The mean of the Hamming Error 0.019 and the Kappa coefficient value reaches 0.890.The proposed method has the best performancefor fetal organ detection. This is proven by the Hamming Error, the accuracy, and tthe Kappa Coefficient. The hitrate for fetal’s head, fetal’s femur, fetal’s humerus, and fetal’s abdomen are 95%, 97%, 97%, and 93% respectively. From the Experiment result, it is concluded that using detection by only usig the approximation method could not perform better than the previous methods.

Index terms

  • ultrasound
  • automated system
  • fetal organ
  • detection
  • approximation
  • boosting
  • Hough transform
Otwarty dostęp

Research of the Forklift Power-Assisted Steering System Based on Safety Steering Speed Control

Data publikacji: 01 Mar 2015
Zakres stron: 749 - 765

Abstrakt

Abstract

Enhancing the safety of forklift power-assisted steering system is a problem urgently to be solved in practice. First of all, forklift power-assisted steering system model is established according to Lagrange dynamical equations, and three variable assistance characteristics curve fitted for reach trucks is designed combined with fuzzy control algorithm. Then sliding mode variable-structure control method based on motor current control is used tracking the target current and making contrast with the traditional PID in order to justify the validity of the algorithm. Finally, the expression of speed with tri-function is built. Optimization of safety speed is added on the basis of traditional power-assisted steering to ensure the stability and security of forklift steering.

Index terms

  • Dynamical characteristic curve
  • EPS of forklift
  • safety speed
  • sliding mode control based on reaching law
Otwarty dostęp

In-Situ Test of Pressure Pipeline Vibration based on Data Acquisition and Signal Processing

Data publikacji: 01 Mar 2015
Zakres stron: 766 - 781

Abstrakt

Abstract

Pipeline vibration of high frequency and large amplitude is an important factor that impacts the safe operation of pumping station and the efficiency of the pumps. Through conducting the vibration in-situ test of pipeline system in the pumping station, we can objectively analyze the mechanism of pipeline vibration and evaluate the stability of pipeline operation. By using DASP (data acquisition & signal processing) in the in-situ test on the 2# pipeline of the third pumping station in the general main line of Jingtaichuan electric-lifting irrigation project in Gansu Province (later known as “the general trunk third pumping station in Jingtai electric project”) and then adopting time-domain analysis and cross-spectrum analysis to deal with collected data, we can acquire the vibration state in different positions of pipeline. Tests have shown that, the application of DASP in the vibration test of pressure pipeline of the pumping station, compared to the traditional test systems, can not only obtain higher test accuracy and efficiency, but can also provide theory basis and technical support for solving the vibration problems of the same-type pipeline operation. It has a good promotion value in the engineering practice.

Index terms

  • DASP software
  • time-domain analysis
  • cross-spectrum analysis
  • pressure pipeline
Otwarty dostęp

Construction of Traceability System for Maintenance of Quality and Safety of Beef

Data publikacji: 01 Mar 2015
Zakres stron: 782 - 800

Abstrakt

Abstract

In order to allow consumers to trace to the whole process of beef breeding, production and processing after purchasing beef, to achieve smart, fast and practical goals for quality and safety of beef traceability system, B / S (Browser / Server) mode architecture is used to build quality beef traceability system based on RFID technology in this paper. First, the system is analyzed, the structure and database system are designed and the key technologies to achieve traceability system is explored, including the individual identification of cattle, data encoding, data synchronization technology between the business and the central database and multi-platform tracing techniques. Through the use of RFID technology, all aspects of information for each head of beef cattle from breeding, slaughtering, processing, cold chain storage and transportation can be tracked and traced, and a quality retrospective file which can be queried on the Internet network for each head of beef cattle is formed. Solve the problem which the origin of beef production can be quality controlled and is traceability. The system implements safety warning function for cattle breeding epidemic and product quality, so it can ensure the safety of beef products from all aspects of production management. Finally, the renderings of system implementation are gained.

Index terms

  • RFID technology
  • beef quality
  • traceability system
  • ear tag
  • product safety
Otwarty dostęp

Transmission Power Control in Wireless Sensor Networks under the Minimum Connected Average Node Degree Constraint

Data publikacji: 01 Mar 2015
Zakres stron: 801 - 821

Abstrakt

Abstract

As a branch of topology control, power control is of great importance to prolong the survival time of the network. A transmission power control algorithm is proposed under the minimum connected average node degree constraint in this paper. Using a Poisson point process in two dimensions, we derive an analytical expression that determines the required transmission range to achieve a specified connectivity probability for a given node density, and then the minimum connected average node degree is obtained. Based on the above results, an algorithm named MCAND is designed to achieve the given connected probability by adjusting the transmission power of each node dynamically, with the node degree equal to the minimum connected average node degree. Simulation results show that the performance of our algorithm is superior to that of the related algorithms based on node degree in terms of coverage and connectivity.

Index terms

  • Wireless sensor networks
  • power control
  • connectivity
  • coverage
  • node degree
39 Artykułów
Otwarty dostęp

An Assistance System For Building Intelligent Spaces Based On Mapsharing Among A Mobile Robot And Distributed Sensors

Data publikacji: 01 Mar 2015
Zakres stron: 1 - 25

Abstrakt

Abstract

An intelligent space is a space constructed with many networked sensors. Humans and robots in the space are extracted and tracked cooperatively by the networked sensors. The intelligent space can achieve position-based supports to humans and robots according to integration of networked sensors. Generally, the networked sensors are distributed and fixed on the structures in the space such as walls, ceilings and etc. In order to track moving objects such as humans and robots in the intelligent space, all networked sensors have to obtain objects positions in the unified world coordinate. In that case, positions and orientations of the networked sensors must be also known in the unified world coordinate system. However, it is time-consuming to measure positions of many sensors in the world coordinate accurately and manually. This study aims to develop a system for supporting estimation of positions and orientations of the networked sensors in the intelligent space.

In this paper, a configuration of the proposed system is introduced. The proposed system consists of map building systems of the mobile robot and the distributed sensors. A global map from the robot and local maps from the distributed sensors are compared. Then, the local maps of the distributed sensors are associated with the global map and the positions of the distributed sensors are estimated in the global map. For improvement of map matching, angle differences between maps are evaluated. Some experimental results in an actual environment show that the proposed system achieve sensor position estimation easily.

Index terms

  • Intelligent Space
  • Mobile Robot
  • SLAM!
Otwarty dostęp

Low-Power Wireless Liquid Monitoring System using Ultrasonic Sensors

Data publikacji: 01 Mar 2015
Zakres stron: 26 - 44

Abstrakt

Abstract

Monitoring Systems are necessary to understand the changes that take place in environments. Remote monitoring and data collection systems are useful and effective tools to collect information from bulk storage tanks and to monitor the same. The measurement of liquid inside the tank is most important and such systems are useful in industries which are categorized as safety critical systems. This paper presents the architecture and initial testing results of a low power wireless system for tank level monitoring using ultrasonic sensors.

Index terms

  • GSM
  • remote monitoring
  • ultrasonic sensors
  • tanks
  • low-power
Otwarty dostęp

A Study of X-Ray Machine Image Local Semantic Features Extraction Model based on bag-of-words for Airport Security

Data publikacji: 01 Mar 2015
Zakres stron: 45 - 64

Abstrakt

Abstract

The aviation security at the airport has been faced with increasingly severe situations since the 9-11 event. It’s of utmost importance to train airport X-ray machine screener’s image recognition competency. So they can prevent terrorists from bringing dangerous articles in their carry-on or checked bags. However, usually the luggages are placed in different positions and the density & volume of articles differ greatly. As a result, dangerous articles show a variety of X-ray image features. It’s easy for the confused screeners to miss or incorrectly detect dangerous articles. This has been a hidden danger for civil aviation safety. For image recognition improvement, the researcher analyzed the visual semantics of dangerous goods images and applied a local semantic features extraction method. After classification and summarization, the method was used to train the screeners for particular image recognition. The comparison showed the improved accuracy and efficiency of image recognition for the screeners and demonstrated a satisfactory effect.

Index terms

  • airport security
  • bag-of-words
  • semantic analysis
  • image features
Otwarty dostęp

L-Shaped Cantilever Parallel - Plate MEMS Accelerometer Design Parameters using A Gravitational Search Algorithm

Data publikacji: 01 Mar 2015
Zakres stron: 65 - 89

Abstrakt

Abstract

Due to their small size, low weight, low cost and low energy consumption, MEMS (Micro Electro-Mechanical Systems) accelerometers have achieved great commercial success in recent decades. The objective of this paper is to find the optimum design for a typical MEMS accelerometer, which satisfies a set of given constraints. Due to the complex nature of the problem, a gravitational search algorithm (GSA) is developed for optimization. The GSA attempts to optimize the inter-plate gap while satisfying all other engineering goals. The model was constructed in Msc Patran and Nastran software were calculated and model’s response was found. In this paper the optimal design from the theoretically derived gravitational search algorithm is compared to finite element model in order to ascertain its accuracy and verify the results.

Index terms

  • Power system
  • MEMS
  • capacitive accelerometer
  • optimization
  • proof-mass
  • L-shaped beam
  • GSA
  • frequency
Otwarty dostęp

A Novel Approach of Combining Steganography Algorithms

Data publikacji: 01 Mar 2015
Zakres stron: 90 - 106

Abstrakt

Abstract

Steganography is the act of hiding a message inside another message in such a way that the hidden message can only be detected by its intended recipient. In this paper, we combined two steganography algorithms namely JSteg and OutGuess algorithms, in order to exploit the beneficial characteristics and features of both algorithms to enhance the protection level for secret images. In our proposed approach, the secret message (image) is first concealed inside another image using JSteg algorithm and the resultant stego-image is further hidden inside a final image using OutGuess 0.1 algorithm. In this combine approach, the tricky nature of hiding an already hidden message is using two different algorithms increases the level of difficulty for a third party to suspect the existence of a secret image in the first place or even successful decode the it. Besides that, the priority given to the choice of a good image size and type in this approach further disguises the secret image and increases the chances that the image could go unnoticed. Results after calculating the capacity and PSNR for images proved that our approach is a good and acceptable steganography system. The model presented here is based on JPEG images.

Index terms

  • Transform Domain Technique
  • Jsteg
  • OutGuess0.1
  • MSE
  • peak-signal-to-noise ratio (PSNR)
Otwarty dostęp

Sparse Representation Theory and its Application for Face Recognition

Data publikacji: 01 Mar 2015
Zakres stron: 107 - 124

Abstrakt

Abstract

Face recognition aims at endowing computers with the ability to identify different human beings according to their face images. However, recognition rate will decrease sharply when it refers to the non-ideal imaging environments or the incorporation of users, such as illumination, pose, expression variations and so on. Besides, it will be also influence the recognition results when the database is too large or small. Sparse representation based classification for face images has been one of efficient approaches for face recognition in recent years. Discrimination performance by using the sparse representation can also be applied to the face recognition, and any test sample can be expressed as a linear span of the all training samples. Experimental results show that face recognition method based on sparse representation is comparable to others.

Index terms

  • Face recognition
  • recognition rate
  • non-ideal imaging environments
  • sparse representation
Otwarty dostęp

Survey of Semantic Similarity Measures in Pervasive Computing

Data publikacji: 01 Mar 2015
Zakres stron: 125 - 158

Abstrakt

Abstract

Semantic similarity measures usage is prevalent in pervasive computing with the following aims: 1) to compare the components of an application; 2) to recommend and rank services by degree of relevance; 3) to identify services by matching the description of a query with the available services; 5) to compare the current context with already known contexts. The existing works that apply semantic similarity measures to pervasive computing focus on one particular issue. Furthermore, surveys in this domain are limited to the recommendation or discovery of context-aware services. In this article, we therefore present a survey of context-aware semantic similarity measures used in various areas of pervasive computing.

Index terms

  • pervasive computing
  • semantic similarity
  • context-aware
  • service discovery
  • service recommendation
Otwarty dostęp

Image Fusion and Recognition based on Compressed Sensing Theory

Data publikacji: 01 Mar 2015
Zakres stron: 159 - 180

Abstrakt

Abstract

As the compressed sensing theory can offer a better performance than Nyquist sampling theorem when dealing with large amounts of data, it becomes very popular for image fusion and target recognition in image processing. In this paper, a new image fusion algorithm based on compressed sensing was proposed. By discrete cosine transform, it fused images through weighted coefficient, recovered the fusion images by basic pursuit algorithm. Moreover, a recognition algorithm in compressed sensing was also studied, which obtained a sample matrix using preprocessing based on a wavelet transform, calculated the approximate coefficient by orthogonal matching pursuit, and made a classification using the with minimum distance formula. Finally, experiments were designed to demonstrate the effectiveness of the proposed algorithms.

Index terms

  • Mage fusion
  • target recognition
  • compressed sensing
  • wavelet transform
Otwarty dostęp

Tracking of Moving Target Based on Video Motion Nuclear Algorithm

Data publikacji: 01 Mar 2015
Zakres stron: 181 - 198

Abstrakt

Abstract

Moving target detection and tracking algorithm research content is very broad and complex applications, without and different target features directly affects the detection of selected tracking algorithm. So far still does not exist a universal algorithm for perfect can be suitable for various applications, so the detection and tracking of moving targets is still a valuable research subject of. The research work in this paper is in the field, the moving target detection spatiotemporal correlation and difference contour tracking algorithm based on a fixed background. The algorithm in the background under the condition of fixed to pay a smaller time complexity, the target detection and tracking has a good effect, so it has higher application value. Based on solving the detection and location of moving target tracking in real-time and accuracy requirements, a new moving target detection spatiotemporal correlation and difference contour tracking scheme based on the practical implementation, at the same time analysis and the experimental results are given. In the moving target tracking, tracking method is mainly traditional correlation method target based on template matching. The matching process is time consuming, so the actual use of more of the improved algorithm of correlation method, the improved algorithm attempts to improve the efficiency of feature matching and search range, and also achieved a certain effect, the some excellent tracking algorithm. This paper presents an improved active contour model tracking algorithm, improve the tracking efficiency and quality, the algorithm first from the frame difference detection results to find the moving target coarse contour, and then the convergence of coarse contour by using improved Snake algorithm, the right edge to get the target in the course of the campaign, in order to achieve the tracking of moving objects.

Index terms

  • Moving object
  • detection
  • active
  • pattern recognition
  • image features
Otwarty dostęp

Digital Image Watermarking Algorithms Based on Dual Transform Domain and Self-Recovery

Data publikacji: 01 Mar 2015
Zakres stron: 199 - 219

Abstrakt

Abstract

In view of dual watermarking algorithm for dual two value image watermarking, the watermark information there is a gray image watermarking in the expression is obviously insufficient. The proposed embedded in the carrier image on the dual watermark includes a two watermark image and a gray image watermarking algorithm, the persuasive power while maintaining the original two values of the watermark robustness at the same time, improve the watermark information. In order to balance the robustness and invisibility of watermarking algorithm, this paper analyzes the embedding position and strategy of transform domain algorithms, the DC coefficient in the carrier image is divided into blocks of DCT spectrum and spectrum on the combination of DWT coefficient method and the advantage of embedded dual watermarking, and use the NEC characteristic of the algorithm is improved adaptive based on the embedded mode. The gray image watermark bit plane decomposition compression high four bit plane information as watermarking, in reducing the original watermark loading and enhance the overall strength of self recovery system. This paper from the working principle, classification of digital watermarking, attack types, performance index, evaluation method and uses six aspects were introduced to the digital watermarking technology. Simulation study of a digital image watermarking algorithm based on DCT transform and Arnold transform, the algorithm’s imperceptibility, robustness and security are analyzed, the algorithm for embedding process.

Index terms

  • Stay cable
  • positive pressure arch effect
  • mechanism
  • friction coefficient
  • ANSYS
  • contact analysis
Otwarty dostęp

Characterization of a Needle-Type Giant Magnetoresistance Sensor for Detection of Escherichia Coli’S Magnetic Marker

Data publikacji: 01 Mar 2015
Zakres stron: 220 - 234

Abstrakt

Abstract

In the recent years, the introduction and development of simple and portable sensors has been the focus of researchers in nearly all scientific domains, particularly in the biomedical settings. Giant magnetoresistance (GMR) provides a cutting-edge sensor technology. The GMR-based sensors are capable to affordably and sensitively detect and quantify micro- and nano-magnetic particles, even in very weak magnetic fields.

In this paper, we introduce a highly sensitive needle-type GMR-based sensor, designed for the identification and quantification of Escherichia coli O157:H7 bacteria covered by superparamagnetic beads, Dynabeads® MAX E.coli O157. The sensor characteristics, measurement system setup and the properties of the magnetic marker solution are discussed in detail.

Index terms

  • Giant magnetoresistance (GMR) sensor
  • Escherichia coli O157:H7
  • magnetic marker
  • sensor sensitivity
  • magnetic fluid weight density
  • magnetic field
Otwarty dostęp

Acoustic-Phonetic Feature Based Dialect Identification in Hindi Speech

Data publikacji: 01 Mar 2015
Zakres stron: 235 - 254

Abstrakt

Abstract

Every individual has some unique speaking style and this variation influences their speech characteristics. Speakers’ native dialect is one of the major factors influencing their speech characteristics that influence the performance of automatic speech recognition system (ASR). In this paper, we describe a method to identify Hindi dialects and examine the contribution of different acoustic-phonetic features for the purpose. Mel frequency cepstral coefficients (MFCC), Perceptual linear prediction coefficients (PLP) and PLP derived from Mel-scale filter bank (MF- PLP) have been extracted as spectral features from the spoken utterances. They are further used to measure the capability of Auto-associative neural networks (AANN) for capturing non-linear relation specific to information from spectral features. Prosodic features are for capturing long - range features. Based on these features efficiency of AANN is measured to model intrinsic characteristics of speech features due to dialects.

Index terms

  • Dialect Identification
  • Auto-associative neural network
  • Feature compression
  • Hindi dialects
  • Spectral and Prosodic features
Otwarty dostęp

Robust Visual Tracking Based on Support Vector Machine and Weighted Sampling Method

Data publikacji: 01 Mar 2015
Zakres stron: 255 - 271

Abstrakt

Abstract

Visual tracking algorithm based on binary classification has become the research hot issue. The tracking algorithm firstly constructs a binary classifier between object and background, then to determine the object’s location by the probability of the classifier. However, such binary classification may not fully handle the outliers, which may cause drifting. To improve the robustness of these tracking methods, a novel object tracking algorithm is proposed based on support vector machine (SVM) and weighted multi-sample sampling method. Our method constructs a classifier by sampling positive and negative samples and then to find the best candidate that has the largest response using SVM classifier. What’s more, the proposed method integrates weighted multi-instance sampling method, which can consider the sample importance by the different weights. The experimental results on many sequences show the robustness and accuracy of the improved method. The proposed target tracking algorithm in video target tracking with a variety of classic popular tracking algorithm, better able to achieve robust target tracking, but also in the infrared video, the infrared target tracking is also has the advantages of stable and accurate.

Index terms

  • Visual tracking
  • support vector machine (SVM)
  • weighted multi-sample sampling method
Otwarty dostęp

Nodes Control Algorithm Design Based Coverage and Connectivity of Wireless Sensor Network

Data publikacji: 01 Mar 2015
Zakres stron: 272 - 290

Abstrakt

Abstract

Coverage and connectivity are two important problems in wireless sensor network. This paper focuses on the wireless sensor network communication radius in the high density of sensor nodes deployed randomly and two times smaller than the sensing radius; put forward a distributed k coverage multi connected node deployment algorithm based on grid. Simulation results show that the algorithm in this paper while guaranteeing the wireless sensor network coverage and connectivity can reduce the number of the active state nodes effectively, prolong the wireless sensor network lifetime. Theoretical analysis results show that this article nodes deployment algorithm achieves multi connected

Index terms

  • Stay cable
  • positive pressure arch effect
  • mechanism
  • friction coefficient
  • ANSYS
  • contact analysis
Otwarty dostęp

A Comprehensive Analysis on Sizing of Solar Energy Harvester Elements for Wireless Sensor Motes

Data publikacji: 01 Mar 2015
Zakres stron: 291 - 315

Abstrakt

Abstract

Wireless sensor networks (WSN) have limited lifetime due to on board battery. The lifetime can be improved by energy harvesting solutions. In this paper the solar energy harvester requirements for TelosB mote has been analyzed and calculated. Photovoltaic (PV) panel and battery sizing requirements are calculated by assuming that the mote follows SMAC and TDMA-MAC schedule for image communication. The calculations are validated by comparing it with the parameters calculated from the real time current consumption measurement of the mote. Lifetime has been predicted with the physical design of energy harvester. The analysis confirms that the lifetime of the network can be increased to a greater extent, by proper sizing of the harvester and efficient utilization of the available energy.

Index terms

  • WSN
  • energy harvester
  • lifetime prediction
  • battery
  • PV source
Otwarty dostęp

Feature Selection Algorithm Based on Conditional Dynamic Mutual Information

Data publikacji: 01 Mar 2015
Zakres stron: 316 - 337

Abstrakt

Abstract

Aim at existing selection algorithm mutual information inaccurate valuation problem, a condition dynamic concept of mutual information. On this basis, the conditions proposed based on dynamic mutual information (CDMI) feature selection algorithm to overcome the traditional mutual information selection process dynamic correlation problem; conditions of dynamic mutual information throughout the selection process is dynamic valuation, those the samples can be identified after each selection features removed so that they no longer participate in conditional mutual information calculation process, accurate measurement sample. Accurate measurement sample on the degree of importance characteristics and at the same time ensure that the characteristics of information content. The experimental results verify the correctness and effectiveness of the algorithm.

Index terms

  • Dalgaard-Strulik model
  • energy
  • economic growth
  • time delay
  • limit cycle
Otwarty dostęp

Review on Modeling and Controller Design of Hydraulic Actuator Systems

Data publikacji: 01 Mar 2015
Zakres stron: 338 - 367

Abstrakt

Abstract

The purpose of this paper is to review the literature on modeling and previous control strategies of the hydraulic actuator system proposed by most of the researchers around the world. Before comes to the main discussion, some background information related to hydraulic actuator will be presented. This review includes a short summary and conclusion for hydraulic actuator system. The repercussion of this review is for future inventions of a better and robust hydraulic actuator system.

Index terms

  • hydraulic actuator system
  • motion control
  • load variation
  • nonlinear system
  • modeling
  • controller
Otwarty dostęp

Recommender Algorithms Based on Boosting Ensemble Learning

Data publikacji: 01 Mar 2015
Zakres stron: 368 - 386

Abstrakt

Abstract

This article introduces ensemble learning algorithms in recommender systems, and in boosting algorithm framework of this article, shows how to filter the basic recommendation algorithm according to the characteristics of boosting algorithm. By comparing the rational choice of the two recommended boosting algorithm is applied to the frame. And then it determines the main parameters of the algorithm through the experiments, ultimately to obtain a more effective integration of the recommendation algorithm. Experimental results on Netflix validate the effectiveness of the proposed algorithm.

Index terms

  • Recommended System
  • Ensemble learning
  • Collaborative filtering
  • boosting
Otwarty dostęp

Iris-Face Fusion and Security Analysis Based on Fisher Discriminant

Data publikacji: 01 Mar 2015
Zakres stron: 387 - 407

Abstrakt

Abstract

With the development of society and science technology, the information security becomes more and more important for people and nation. In this paper, we focus on the technology of iris-face fusion in multi-mode sense in order to find an algorithm to get a better recognition performance. Firstly, we introduce the feature extraction of iris and face, and fusion the features using different algorithms. By simulation, we find out the recognition performance with different fusion methods, which provide some new conclusions. In order to improve the performance of recognition system, we classify these features with fisher discriminant analysis again. Then we analyze the security of recognition system from the aspect of influence of leak in biology features. Finally, experiments were designed to demonstrate the effectiveness of the proposed algorithms.

Index terms

  • iris feature
  • face feature
  • fisher discriminant analysis
  • fusion
Otwarty dostęp

Aptive Image Segmentation based on Saliency Detection

Data publikacji: 01 Mar 2015
Zakres stron: 408 - 428

Abstrakt

Abstract

in this article, we propose an adaptive image segmentation method based on saliency. First of all, we obtain the saliency map of an image via four bottom-layer feature tunnels, i.e. color, intensity, direction and energy. The energy tunnel helps to describe the outline of objects better in the saliency map. Then, we construct the target detection masks according to the greyness of pixels in the saliency map. Each mask is applied to the original image as the result of pre-segmentation, then corresponding image entropy is calculated. Predict the expected entropy according to maximum entropy criteria and select the optimal segmentation according to the entropies of pre-segmented images and the expected entropy. A large number of experiments have proved the effectiveness and advantages of this algorithm.

Index terms

  • Visual feature
  • image segment
  • maximum energy criteria
  • saliency detection
Otwarty dostęp

Geometric Deep Particle Filter for Motorcycle Tracking: Development of Intelligent Traffic System in Jakarta

Data publikacji: 01 Mar 2015
Zakres stron: 429 - 463

Abstrakt

Abstract

Intelligent Transportation Systems (ITS) is the combination of transportation systems with Information and Communication Technology (ICT). In Jakarta traffic, there is unique issue that does not arise in developed countries: very large number of motorcycles. Nevertheless, the enabling technologies for the detection, measurement, recording, and information distribution of motorcycle have not been fully developed in the existing researches. With the above considerations, we establish research which aimed to develop enabling technology especially in here for tracking motorcycle using camera.

This paper is presented our proposed tracker which called as Geometric Deep Particle Filter (GDPF) for tracking motorcycle using camera. The tracker is inspired by human visual perception which has nonretinotopic nature. Based on particle filter approach, our goal is to improve the transition model in order to overcome motorcycle maneuver. We will exploit this curved nature of the state space using geometric computing theory, such as Lie groups, and Lie algebras. A number of experiments have been conducted for this research, and it has been found that GDPF has achieved certain degree of success in object tracking.

Index terms

  • visual tracking
  • motorcycle
  • nonretinotopic
  • particle filter
  • deep learning
  • geometric computing
  • affine transformation
Otwarty dostęp

New Stereo Matching Method Based on Improved BP Algorithm

Data publikacji: 01 Mar 2015
Zakres stron: 464 - 479

Abstrakt

Abstract

As stereo matching methods are widely used in computer vision and stereo reconstruction, from the perspective of improving the matching accuracy, this paper focuses on the global optimization algorithm. An improved stereo matching method based on 8- neighbor Belief Propagation method is proposed in this paper, by involving more pixels into information transmission, our method improves the accuracy of stereo matching. The experimental results verify the efficiency and reliability of our method.

Index terms

  • Disparity map
  • stereo vision
  • MRF Model
  • Disparity map
  • Markov Random
Otwarty dostęp

Study on Image Compression and Fusion Based on the Wavelet Transform Technology

Data publikacji: 01 Mar 2015
Zakres stron: 480 - 496

Abstrakt

Abstract

With the development of information technology, the rapid development of microelectronics technology, image information acquisition and use is also increasing, sensor technology also unceasingly to reform. A single sensor information obtained is limited, often can not meet the actual needs, in addition, different sensors have the advantage of the imaging principle and its unique, as in color, shape characteristics, band access, spatial resolution from the aspects of all have their own characteristics. Registration algorithm is proposed in this paper has better robustness to image noise, and can achieve sub-pixel accuracy; the registration time has also been greatly improved. In terms of image fusion, the images to be fused through wavelet transform of different resolution sub image, using a new image fusion method based on energy and correlation coefficient. The high frequency image decomposed using new energy pixels of the window to window energy contribution rate of fusion rules, the low frequency part by using the correlation coefficient of the fusion strategy, finally has carried on the registration of simulation experiments in the Matlab environment, through the simulation experiments of fusion method in this paper can get the image fusion speed and high quality fast fusion image.

Index terms

  • wavelet transform
  • image match
  • image fusion
  • spatial resolution
Otwarty dostęp

Small Target Detection based on Infrared Image Adaptive

Data publikacji: 01 Mar 2015
Zakres stron: 497 - 515

Abstrakt

Abstract

This paper studies the multi-resolution analysis of infrared image preprocessing method based on wavelet transform, wavelet transform infrared image of small target for pretreatment, after pretreatment suppressed image background clutter, improved signal to noise ratio. On this basis, studies based on infrared image sequences generated background Kalman filter and target detection algorithm, given the principle of the algorithm, time-domain method for generating fading background and moving object extraction methods such as recursive least squares method, and the experimental results show that the algorithm capable of detecting small targets in infrared images, with good results. based pretreatment small target motion continuity characteristics studied image sequences small moving target detection algorithm based on weighted dynamic programming, dynamic programming algorithm principle is given, analysis of the direct method and the accumulation of gray dynamic programming algorithm based on similar likelihood function for dynamic programming problems arise energy diffusion gives improved dynamic programming algorithm: weighted dynamic programming algorithm, the algorithm implementation steps, testing and experimental structure the results were analyzed, the results show that the algorithm for small moving target detection with good results. Finally, this paper studied the infrared image reject false target trajectory get the real target trajectory correlation method, so as to improve the detection rate and reduce the false alarm rate the purpose.

Index terms

  • Target enhancement
  • local spectrum suppression
  • regular patches
  • log amplitude spectrum
  • TDI
Otwarty dostęp

A Deployment Algorithm for Mobile Wireless Sensor Networks based on the Electrostatic Field Theory

Data publikacji: 01 Mar 2015
Zakres stron: 516 - 537

Abstrakt

Abstract

This paper proposes a deployment algorithm based on the electrostatic field theory for mobile wireless sensor networks. The nodes and obstacles in the deployment area are taken as the charged particles; and the particles will move due to the Coulomb’s force from other particles or obstacles. Finally, the nodes automatically spread to the whole area by the resultant action and complete the deployment. Four metrics, including coverage, uniformity, deployment time and average displacement distance, are used to evaluate the performance of the algorithm. The simulation results show that the proposed algorithm can give full play to its self-adaptive advantages and achieve the desired deployment effect; it is a kind of deployment algorithm with self-adaptive characteristics.

Index terms

  • Mobile Wireless Sensor Networks
  • Electrostatic field
  • Deployment algorithm
Otwarty dostęp

The Transformer Winding Temperature Monitoring System Based on Fiber Bragg Grating

Data publikacji: 01 Mar 2015
Zakres stron: 538 - 560

Abstrakt

Abstract

High temperature is one of the important reasons causing the fire in power system. Therefore, the early warning could be told by monitoring the temperature and effective measures could be taken. The corresponding accidents will be reduced. The traditional transformer winding temperature monitoring methods are electrical signal measurement and infrared measurement. Such electrical signal sensors are vulnerable to the interference of electromagnetic field, so the result of measurement is bad. Multiplexing optical path is unable to be realized by fluorescence thermometry. The optical fiber Bragg grating technology is used on temperature monitoring of transformer winding in this paper. The transformer winding temperature monitoring system based on optical fiber Bragg grating includes three parts: Temperature monitoring program based on the LabVIEW programming language, a fiber Bragg grating wavelength demodulation system and FBG temperature sensor. When the temperature of the transformer windings changes, the central wavelength of the fiber Bragg grating changes accordingly. Broadband ASE light source emits light, which is transmitted from the optical circulator into the fiber Bragg grating. The reflected light gets into the wavelength demodulation module again through the optical circulator. Wavelength demodulation module could transmit the center wavelength of the spectral reflectance information, peak power information to the computer. The computer analyzes, processes the information and displays the data with XY graph by calling the LabVIEW program. The program can get center wavelength values at the same time then get temperature by fitting function and display temperature on the front panel of the program. The fitting line of linearity between center wavelength of optical fiber Bragg grating sensor and temperature is above 0.95. The function reveals a good linearity which fitting the wavelength changes of the optical fiber Bragg grating during this temperature range. The experimental results show that the system has high accurate measurement which meeting high precision requirements of transformer winding temperature.

Index terms

  • FBG
  • transformer winding
  • temperature
  • FBGA demodulation
  • LabVIEW
Otwarty dostęp

Security of Wireless Sensor Networks for Health Monitoring Helmets with Anomaly Detection using Power Analysis and Probabilistic Model

Data publikacji: 01 Mar 2015
Zakres stron: 561 - 580

Abstrakt

Abstract

Litigation faced by the NFL has called for better prevention and understanding of concussions and other sports injuries. To achieve this, sports officials have turned to wireless sensor networks, or WSNs, in the form of helmet sensors that automatically report any harmful injuries to attendants on the sidelines. While this approach provides players with a greater assurance of safety and a faster response to their injuries, the security weaknesses of WSNs must be addressed. These systems, being not only recently developed but also highly resource-constrained, may be easily manipulated by those looking to gain information about players (a form of passive attack) or even attempting to remove them from the game through the sending of false reports (a form of active attack). To prevent attacks such as these, we propose a system that uses a modification of the AES-CCM protocol as well as a novel attack detection system that uses probabilistic methods to report any harmful behavior to the user. The system’s power usage due to injury reports is compared to a probability model that is based on past research that recorded the likelihood of injury for the positions played in professional football. This system offers many advantages over conventional cryptography as it is a lightweight approach that costs few resources; individual helmet sensors need only send simple power reports to a central base station which uses on-the-grid power to conduct security analysis. Provided below is detail of the paper which describes the problem in greater detail, a section that details the system architecture, a section that explains the AES-CCM protocol, and an explanation of the probabilistic approach. This is followed by a security analysis that compares the approach to several other approaches found in the literature, and finally a conclusion.

Index terms

  • Sensor networks
  • AES
  • Probabilistic model
Otwarty dostęp

Intelligent Detection of Facial Expression based on Image

Data publikacji: 01 Mar 2015
Zakres stron: 581 - 601

Abstrakt

Abstract

Human facial expressions detection plays a central role in pervasive health care and it is an active research field in computer vision. In this paper, a novel method for facial expression detection from dynamic facial images is proposed, which includes two stages of feature extraction and facial expression detection. Firstly, Active Shape Model (ASM) is used to extract the local texture feature, and optical flow technique is determined facial velocity information, which is used to characterize facial expression. Then, fusing the local texture feature and facial velocity information get the hybrid characteristics using Bag of Words. Finally, Multi-Instance Boosting model is used to recognize facial expression from video sequences. In order to be learned quickly and complete the detection, the class label information is used for the learning of the Multi-Instance Boosting model. Experiments were performed on a facial expression dataset built by ourselves and on the JAFFE database to evaluate the proposed method. The proposed method shows substantially higher accuracy at facial expression detection than has been previously achieved and gets a detection accuracy of 95.3%, which validates its effectiveness and meets the requirements of stable, reliable, high precision and anti-interference ability etc.

Index terms

  • Facial expression
  • ASM model
  • Optical flow model
  • Bag of Words
Otwarty dostęp

Adjustment of the Parallelism of two Mirrors for Wide Angle Divided Mirror Michelson Wind Imaging Interferometer

Data publikacji: 01 Mar 2015
Zakres stron: 602 - 619

Abstrakt

Abstract

Many ways have been developed to measure atmospheric winds by detecting the Doppler shifts of airglow emission lines. The Michelson Interferometer is widely used because of its simple principle. To get the Doppler shifts to calculate the wind velocity, researchers developed four-phase-step and divided mirror technology respectively. But they face challenges in many fields. So a wide angle Michelson Interferometer combining with divided mirror and phase stepping technique is used in this paper. A new algorithm is proposed in this paper to adjust the parallelism of the two mirrors for the Michelson Interferometer. Thus a high precision parallelism of the two mirrors can be obtained to get the phase shift and calculate wind velocity. The interval of the two mirrors has maximum difference less than one tenth wavelength. The experiments were performed in visible channel to prove the feasibility of this proposed algorithm. It can also be used in other fields demanding two surfaces parallel with high precision.

Index terms

  • parallelism
  • phase shift
  • divided mirror
  • phase stepping
Otwarty dostęp

Cyber-Awareness Improvement Using Artificial Intelligence Techniques

Data publikacji: 01 Mar 2015
Zakres stron: 620 - 636

Abstrakt

Abstract

The primary contribution of this experiment is the development of a framework on which a variety of multitasking processes can be mapped. A software model named SHOWAN is developed to represent, capture and learn the cyber awareness behavior of a computer process against multiple concurrent threads. At the beginning of the experiment, the examined process outperformed, and tended to manage numerous tasks poorly, but it gradually learned to handle fewer tasks and excelling in each of them.

Index terms

  • Cyber Security
  • Queuing Management
  • Task Prioritization
  • Normative Model
  • Cyber Multitasking Performance
  • Non-maskable task
Otwarty dostęp

The Bending Mode Control Method of AFS System Based on Preview Control

Data publikacji: 01 Mar 2015
Zakres stron: 637 - 657

Abstrakt

Abstract

Due to the time-lag of both the mechanical transmission and controller area network (CAN) bus transmission of the Adaptive Front Lighting System (AFS), the actual bending angle of AFS invariably lags behind the steering-wheel angle, which not only makes the real-time response speed of the AFS system slow, but also makes the system stability and the active safety of the vehicle poor.

To solve the problem, firstly, the geometrical relations among safety braking distance and the rate of steering-wheel angle and turning radius of the vehicle are analyzed. Secondly, the mathematics model among these variables has been set up. Finally, in order to improve the road illumination of the curve, the control method of bending mode of AFS system based on preview control is proposed. Based on preview control algorithm, the simulation model of the AFS has been built as well as the AFS control experiment platform. After the comparison between preview control and servo control, it can be proved that the preview control method proposed is superior to traditional servo control in AFS system.

Index terms

  • AFS headlamp
  • lag of Steering-wheel angle
  • road illumination
  • preview model
  • preview control
Otwarty dostęp

Travel Time Prediction Based on Pattern Matching Method

Data publikacji: 01 Mar 2015
Zakres stron: 658 - 676

Abstrakt

Abstract

The microwave detection technology has become an effective tool for monitoring highway traffic flow in China. The cross section traffic data collected provides models opportunity for travel time prediction. However, the sparseness of data somewhat constrains the prediction accuracy. To tackle this problem, the paper presents a highway travel time prediction algorithm based on pattern matching method. First, a pattern library is established by choosing traffic volume and speed as its certain state components and time as its uncertain state component. Then, the space-time two-dimensional linear interpolation method is used to calculate the mean speed and subsequently the travel time. Finally, similar patterns are obtained using K Nearest Neighbor approach and predicted travel time is calculated by the Weighted Average method. The case study shows that the pattern matching method for travel time prediction based on microwave detection data produces sufficient accuracy, which solves the problem of sparse detectors effectively.

Index terms

  • Travel time prediction
  • Pattern matching method
  • Microwave detection data
  • Two-dimensional linear interpolation method
Otwarty dostęp

Object Tracking Based on Machine Vision and improved SVDD Algorithm

Data publikacji: 01 Mar 2015
Zakres stron: 677 - 696

Abstrakt

Abstract

Object tracking is an important research topic in the applications of machine vision, and has made great progress in the past decades, among which the technique based on classification is a very efficient way to solve the tracking problem. The classifier classifies the objects and background into two different classes, where the tracking drift caused by noisy background can be effectively handled by one-class SVM. But the time and space complexities of traditional one-class SVM methods tend to be high, which makes it do not scale well with the number of training sample, and limits its wide applications. Based on the idea proposed by Support Vector Data Description, we present an improved SVDD algorithm to handle object tracking efficiently. The experimental results on synthetic data, tracking results on car and plane demonstrate the validity of the proposed algorithm.

Index terms

  • Object tracking
  • machine vision
  • Support Vector Data Description
  • one-class SVM
  • classification
Otwarty dostęp

Automated Telehealth System for Fetal Growth Detection and Approximation of Ultrasound Images

Data publikacji: 01 Mar 2015
Zakres stron: 697 - 719

Abstrakt

Abstract

One of the most profound use of ultrasound imaging is fetal growth monitoring. Conventionally, physicians will perform manual measurements of several parameters of the ultrasound images to draw some conclusion of the fetal condition by manually annotating the fetal images on the ultrasound device interface. However, performing manual annotation of fetal images will require significant amount of time considering the number of patients an obstetrician can have. In this paper, an integrated automatic system for fetal growth monitoring and detection is proposed. This system will be able to automatically measuring the parameters of fetal head, abdomen, femur, and humerus. In addition to automated image detection, we also propose an integrated telehealth monitoring system to provide better access of ultrasound monitoring for patients that lives in rural areas. A new approach of fetal image detection is also proposed by using AdaBoost.MH boosting algorithm that is combined with an improved efficient Hough Transform for detecting ellipse-like organs such as head and abdomen. Experiments of the method are tested on real ultrasound image dataset. The detection was applied on 2D ultrasound images to perform fetal object measurement to approximate the Head Circumference (HC) and Biparietal Diameter (BPD), Femur Length (FL), and Humerus Length (HL).

Index terms

  • ultrasound
  • automated system
  • fetal organ detection
  • fetal parameters measurement
  • telehealth
Otwarty dostęp

Automatic Fetal Organs Detection and Approximation in Ultrasound Image

Data publikacji: 01 Mar 2015
Zakres stron: 720 - 748

Abstrakt

Abstract

This paper proposed a system for detecting and approximating of a fetus in an ultrasound image. The fetal organs in the ultrasound image are detected using Multi Boundary Classifier based Adaboost.MH. The results of the fetal detection is then approximated Randomized Hough Transform and the whole showed a mean accuracy of 95.80%. The mean of the Hamming Error 0.019 and the Kappa coefficient value reaches 0.890.The proposed method has the best performancefor fetal organ detection. This is proven by the Hamming Error, the accuracy, and tthe Kappa Coefficient. The hitrate for fetal’s head, fetal’s femur, fetal’s humerus, and fetal’s abdomen are 95%, 97%, 97%, and 93% respectively. From the Experiment result, it is concluded that using detection by only usig the approximation method could not perform better than the previous methods.

Index terms

  • ultrasound
  • automated system
  • fetal organ
  • detection
  • approximation
  • boosting
  • Hough transform
Otwarty dostęp

Research of the Forklift Power-Assisted Steering System Based on Safety Steering Speed Control

Data publikacji: 01 Mar 2015
Zakres stron: 749 - 765

Abstrakt

Abstract

Enhancing the safety of forklift power-assisted steering system is a problem urgently to be solved in practice. First of all, forklift power-assisted steering system model is established according to Lagrange dynamical equations, and three variable assistance characteristics curve fitted for reach trucks is designed combined with fuzzy control algorithm. Then sliding mode variable-structure control method based on motor current control is used tracking the target current and making contrast with the traditional PID in order to justify the validity of the algorithm. Finally, the expression of speed with tri-function is built. Optimization of safety speed is added on the basis of traditional power-assisted steering to ensure the stability and security of forklift steering.

Index terms

  • Dynamical characteristic curve
  • EPS of forklift
  • safety speed
  • sliding mode control based on reaching law
Otwarty dostęp

In-Situ Test of Pressure Pipeline Vibration based on Data Acquisition and Signal Processing

Data publikacji: 01 Mar 2015
Zakres stron: 766 - 781

Abstrakt

Abstract

Pipeline vibration of high frequency and large amplitude is an important factor that impacts the safe operation of pumping station and the efficiency of the pumps. Through conducting the vibration in-situ test of pipeline system in the pumping station, we can objectively analyze the mechanism of pipeline vibration and evaluate the stability of pipeline operation. By using DASP (data acquisition & signal processing) in the in-situ test on the 2# pipeline of the third pumping station in the general main line of Jingtaichuan electric-lifting irrigation project in Gansu Province (later known as “the general trunk third pumping station in Jingtai electric project”) and then adopting time-domain analysis and cross-spectrum analysis to deal with collected data, we can acquire the vibration state in different positions of pipeline. Tests have shown that, the application of DASP in the vibration test of pressure pipeline of the pumping station, compared to the traditional test systems, can not only obtain higher test accuracy and efficiency, but can also provide theory basis and technical support for solving the vibration problems of the same-type pipeline operation. It has a good promotion value in the engineering practice.

Index terms

  • DASP software
  • time-domain analysis
  • cross-spectrum analysis
  • pressure pipeline
Otwarty dostęp

Construction of Traceability System for Maintenance of Quality and Safety of Beef

Data publikacji: 01 Mar 2015
Zakres stron: 782 - 800

Abstrakt

Abstract

In order to allow consumers to trace to the whole process of beef breeding, production and processing after purchasing beef, to achieve smart, fast and practical goals for quality and safety of beef traceability system, B / S (Browser / Server) mode architecture is used to build quality beef traceability system based on RFID technology in this paper. First, the system is analyzed, the structure and database system are designed and the key technologies to achieve traceability system is explored, including the individual identification of cattle, data encoding, data synchronization technology between the business and the central database and multi-platform tracing techniques. Through the use of RFID technology, all aspects of information for each head of beef cattle from breeding, slaughtering, processing, cold chain storage and transportation can be tracked and traced, and a quality retrospective file which can be queried on the Internet network for each head of beef cattle is formed. Solve the problem which the origin of beef production can be quality controlled and is traceability. The system implements safety warning function for cattle breeding epidemic and product quality, so it can ensure the safety of beef products from all aspects of production management. Finally, the renderings of system implementation are gained.

Index terms

  • RFID technology
  • beef quality
  • traceability system
  • ear tag
  • product safety
Otwarty dostęp

Transmission Power Control in Wireless Sensor Networks under the Minimum Connected Average Node Degree Constraint

Data publikacji: 01 Mar 2015
Zakres stron: 801 - 821

Abstrakt

Abstract

As a branch of topology control, power control is of great importance to prolong the survival time of the network. A transmission power control algorithm is proposed under the minimum connected average node degree constraint in this paper. Using a Poisson point process in two dimensions, we derive an analytical expression that determines the required transmission range to achieve a specified connectivity probability for a given node density, and then the minimum connected average node degree is obtained. Based on the above results, an algorithm named MCAND is designed to achieve the given connected probability by adjusting the transmission power of each node dynamically, with the node degree equal to the minimum connected average node degree. Simulation results show that the performance of our algorithm is superior to that of the related algorithms based on node degree in terms of coverage and connectivity.

Index terms

  • Wireless sensor networks
  • power control
  • connectivity
  • coverage
  • node degree

Zaplanuj zdalną konferencję ze Sciendo