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 3 (January 2015)

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

Wyszukiwanie

21 Artykułów
access type Otwarty dostęp

Modified Clad Optical Fibre Coated With PVA/TiO2 Nano Composite For Humidity Sensing Application

Data publikacji: 01 Sep 2015
Zakres stron: 1424 - 1442

Abstrakt

Abstract

Synthesis of TiO2 nanoparticle through hydrolysis method is presented followed by TiO2- nanoparticle doped polyvinyl alcohol nanocomposite by solution process. FTIR, XRD, DSC-TGA, FESEM, TEM analysis are used to identify the nature of synthesized nanoparticle and loading uniformity of developed composite material. A simple modified clad based optical fibre sensor is developed to measure relative humidity. Coated modified clad optical fibre exhibits excellent relative humidity sensing performance with improved thermal stability of coating material in wide range of 9-95 % RH with good process repeatability. Sensor response is also observed to be very fast and highly reversible. Advantage of our developed composite material become evident when it exhibits wider range of moisture sensitivity compare to pure PVA or pure TiO2 material found in literature. Performance of PVA-TiO2 nanocomposite thick film is also evaluated by capacitance method and result found to agree with coated modified clad optical fibre.

Index terms

  • Polyvinyl alcohol
  • titanium dioxide
  • nanocomposite
  • modified-clad optical fibre
  • relative humidity sensor
access type Otwarty dostęp

Compensation of Capacitive Differential Pressure Sensor using Multi Layer Perceptron Neural Network

Data publikacji: 01 Sep 2015
Zakres stron: 1443 - 1463

Abstrakt

Abstract

Capacitive differential pressure sensor (CPS), which converts an input differential pressure to an output current, is extremely used in different industries. Since the accuracy of CPS is limited due to ambient temperature variations and nonlinear dependency of input and output, compensation is necessary in industries that are sensitive to pressure measurement. This paper proposes a framework for designing of CPS compensation system based on Multi Layer Perceptron (MLP) neural network. Firstly, a test bench for a sample popular CPS is designed and implemented for data acquisition in a real environment. Then, the gathered data are used to train different MLPs as CPS compensation system which inputs are the output current of CPS and temperature value, and the output is compensated current or computed pressure. The experimental results for an ATP3100 smart capacitive pressure transmitter show the trained three layers MLP with Levenberg- Marquardt learning algorithm could effectively compensate the output against variation of temperature as well as nonlinear effects, and reduce the pressure measurement error to about 0.1% FS (Full Scale) , over the temperature range of 5 ~ 60 ° C.

Index terms

  • Capacitive pressure sensors
  • Levenberg-Marquardt training algorithm
  • Multi-Layer Perceptron
  • Temperature compensation
access type Otwarty dostęp

Automatic Recognition of Facial Expression Based on Computer Vision

Data publikacji: 01 Sep 2015
Zakres stron: 1464 - 1483

Abstrakt

Abstract

Automatic facial expression recognition from video sequence is an essential research area in the field of computer vision. In this paper, a novel method for recognition facial expressions is proposed, which includes two stages of facial expression feature extraction and facial expression recognition. Firstly, in order to exact robust facial expression features, we use Active Appearance Model (AAM) to extract the global texture feature and optical flow technique to characterize facial expression which is determined facial velocity information. Then, these two features are integrated and converted to visual words using “bag-of-words” models, and facial expression is represented by a number of visual words. Secondly, the Latent Dirichlet Allocation (LDA) model are utilized to classify different facial expressions such as “anger”, “disgust”, “fear”, “happiness”, “neutral”, “sadness”, and “surprise”. The experimental results show that our proposed method not only performs stably and robustly and improves the recognition rate efficiently, but also needs the least dimension when achieves the highest recognition rate , which demonstrates that our proposed method is superior to others.

Index terms

  • Facial expression recognition
  • Active Appearance Model (AAM)
  • Bag of Words model
  • LDA model
  • computer vision
access type Otwarty dostęp

Modelling of Equipment Failure Rate Accounting for the Uncertainty

Data publikacji: 01 Sep 2015
Zakres stron: 1484 - 1504

Abstrakt

Abstract

A fuzzy model for failure rate with the consideration of the effects of uncertain factors in distribution reliability evaluation is presented. The possibility and credibility distribution analyzed on the basis of sample datum are used for quantifying effects of the uncertainty done to failure rate. Mathematically, the failure rate can be obtained in the interval integration. Moreover, aiming to make the calculating quantity of system reliability evaluation simple and easy, the fuzzy clustering analysis of equipment is adopted. The technique proposed has been implemented in an example distribution system for illustration and the results obtained have been compared with those obtained with average model.

Słowa kluczowe

  • fuzzy model
  • failure rate
  • uncertainty
  • fuzzy clustering analysis
access type Otwarty dostęp

Classification of artificial light sources and estimation of Color Rendering Index using RGB sensors, K Nearest Neighbor and Radial Basis Function

Data publikacji: 01 Sep 2015
Zakres stron: 1505 - 1524

Abstrakt

Abstract

Three types of artificial light sources work with electricity: incandescent, fluorescent and LED. These sources require characterization processes to allow selecting the most suitable for the application, to evaluate their capacity or more recently to tune and adjust their replicability using control algorithms. Therefore, it has been necessary to develop indices that represent these capabilities. The Color Rendering Index (CRI) is a measure used to characterize the color reproducibility of a light source in comparison to an ideal light source. The Correlated Color Temperature (CCT) is used to characterize light sources by representing the color as the temperature of a black body in Kelvin that shows nearly the same chromaticity as the analyzed light source. Using spectral information to determine the values in the XYZ space and deriving the calculation described in the standard is the best way to estimate the value of the CCT and the CRI. In this work, we implement a method to classify light sources and to select an estimation model of the CRI and the CCT using a low cost RGB sensor. The model estimation has been developed in this work and a separated algorithm for each source type has been built. The results show that using a K-Nearest Neighbor classifier, the error resulted less than $3.6%$. The error of the model estimation for the LED was 1.8%, for fluorescent light sources 0.09% and 1.2% for incandescent light sources.

Index terms

  • Color Rendering Index
  • CRI
  • light sources
  • Correlated Color Temperature
  • CCT
  • K Nearest Neighbor
  • Radial Basis Function
  • RBF
  • RGB sensors
access type Otwarty dostęp

Neutrosophic Concept Lattice based Approach for Computing Human Activities from Contexts

Data publikacji: 01 Sep 2015
Zakres stron: 1525 - 1553

Abstrakt

Abstract

Complex human activity recognition suffers from ambiguity of interpretation problem. A novel neutrosophic formal concept analysis method has been proposed to quantify non-determinism leading to ambiguity of interpretation and utilize it in activity recognition. The method works by penalizing performance of non-deterministic activities and rewarding the deterministic ones. Thus, non- deterministic activities are identified during testing due to significantly reduced performance and contexts can be redesigned to improve their description. The proposed method has been implemented on benchmark dataset having both types of activities. Our approach successfully identified nondeterminism in activities description without compromising recognition performance of deterministic activities. It has also been shown that other approaches fail to identify non deterministic activities. Overall accuracy of activity recognition of our approach was comparable to other approaches.

Index terms

  • Sensors Data Streams
  • Concept Lattice
  • Neutrosophic Logic
  • Situation Inference
  • Activity Recognition
access type Otwarty dostęp

Performance Measurement of Photoelectric Detection and Target Tracking Algorithm

Data publikacji: 01 Sep 2015
Zakres stron: 1554 - 1575

Abstrakt

Abstract

To solve the unstable problem of target tracking detection system, this paper proposes an improved mean-shift algorithm for object tracking, establishes object tracking processing model;provides the processing algorithm of object tracking. According to the principal of object tracking, papersets up sky background brightness calculation model in photoelectric tracking optical detection area and detection capability calculation model of space object, analyzes the effect of background illumination on the signal to noise ratio(SNR) of photoelectric tracking system, gives the change curve of detection capability based on the exposure time of CCD camera, SNR threshold of photoelectric detection system and dark current of photoelectric detection system. Through calculation and test , paperprovidesthe comparison results of the improved mean-shift and traditional mean-shift, verifies the correctness of the proposed algorithm and calculation models for photoelectric detection capability in target tracking detection system, the results show the improved mean-shiftobject tracking algorithm and detection capability calculation model are correct.

Index terms

  • photoelectric detection
  • target track
  • detection capability
  • SNR
access type Otwarty dostęp

Simulation of Noise Within BOTDA and Cotdr Systems to Study the Impact on Dynamic Sensing

Data publikacji: 01 Sep 2015
Zakres stron: 1576 - 1600

Abstrakt

Abstract

Real-time structural health monitoring requires dynamic sensing of distributed strain and temperature. Brillouin Optical Time Domain Analysis (BOTDA) and Rayleigh Coherent Optical Time Domain Reflectometry (COTDR) are promising candidates to achieve dynamic sensing. A noise model with specific parametric simulation of independent laser and detector noise sources has been developed. Although ensemble averaging significantly enhances the signal-to-noise ratio (SNR) in both systems, its time-consuming accumulation procedure prevents dynamic sensing. The sequence of averaging in the signal processing workflow varies the SNR for both systems. The system components should be optimized to reduce averaging times and achieve the required system specifications, including dynamic sensing.

Index terms

  • dynamic sensing
  • noise simulation
  • BOTDA
  • COTDR
  • laser fluctuation
  • detection
  • averaging
access type Otwarty dostęp

Fabrication of High Frequency Surface Acoustic Wave (SAW) Devices for Real Time Detection of Highly Toxic Chemical Vapors

Data publikacji: 01 Sep 2015
Zakres stron: 1601 - 1623

Abstrakt

Abstract

In this paper, a low cost fabrication of sub micron features size SAW device with conventional lithography and their application for toxic chemical vapor detection has been presented. The SAW devices with different interdigital transducer (IDT) electrodes line widths were designed and fabricated. The fabricated SAW devices features had an accuracy of ± 0.1 μm. Frequency response of the SAW devices was measured with vector network analyzer for design parameter confirmation. The fabricated devices have been configured in multisensory oscillator configuration and tested with chemical ware fare agents simulants at very low concentration (ppb).

Index terms

  • SAW device
  • Optical lithography
  • RF characterization
  • Mass Loading
  • Chemical sensor
access type Otwarty dostęp

Automatic Human Daily Activity Segmentation Applying Smart Sensing Technology

Data publikacji: 01 Sep 2015
Zakres stron: 1624 - 1640

Abstrakt

Abstract

Human daily activity segmentation utilizing smartphone sensing technology is quite new challenge. In this paper, the segmentation method combining statistical model and time series analysis is designed and implemented. According to designed partition procedure, real measured accelerometer datasets of human daily activities are tested. The segmentation performance of sliding window autocorrelation and minimized contrast algorithms is analysed and compared. Experiments demonstrate the effectiveness of this proposed automatic human activity separation method focusing on the application of mobile sensor. As the properties of signal, mean, variance, frequency and amplitude are all useful features on the case of motion sensor-based human daily activity segmentation. In the end, the suggested work to improve the developed partition model is presented.

Index terms

  • Smart sensing
  • activity segmentation
  • sensor signal processing
  • autocorrelation
  • statistical model
access type Otwarty dostęp

Study of Three-Dimensional on-line path Planning for UAV based on Pythagorean Hodograph Curve

Data publikacji: 01 Sep 2015
Zakres stron: 1641 - 1666

Abstrakt

Abstract

For the demand of the UAV autonomous path planning in dynamic thread environment, the three-dimensional path planning algorithm on-line of UAV based on Pythagorean Hodograph (PH) curve is put forward. According to the UAV’s current flight state such as location and speed, and the interrupt point or the target’s state, a flyable path with continuous curvature is planed out online. The roles of the key parameters are analyzed and the range of the values are given. On this basis, the distribution estimation algorithm is used to optimize the selection of path parameters, which avoid the blindness iterative process and consider the kinematics constraints such as the curvature, torsion and climbing angle. The multiple UAVs’ three dimensional path planning in dynamic environment are tested. Simulation results prove the validity and practicability of the algorithm.

Index terms

  • UAV
  • PH curve
  • three-dimensional path planning
access type Otwarty dostęp

Prototyping using a Pattern Technique and a Context-Based Bayesian Network in Multimodal Systems

Data publikacji: 01 Sep 2015
Zakres stron: 1667 - 1686

Abstrakt

Abstract

Today, technology allows us to produce extensive multimodal systems which are totally under human control. These systems are equipped with multimodal interfaces, which enable more natural and more efficient interaction between man and machine. End users can take advantage of natural modalities (e.g. audio, eye gaze, speech, gestures, etc.) to communicate or exchange information with applications. In this work, we assume that a number of these modalities are available to the user. In this paper, we present a prototype of a multimodal architecture, and show how modality selection and fission algorithms are implemented in such a system. We use a pattern technique to divide a complex command into elementary subtasks and select suitable modalities for each of them. We integrate a context-based method using a Bayesian network to resolve ambiguous or uncertain situations.

Index terms

  • Multimodality
  • Ontology
  • Bayesian Network
  • Pattern
  • User Interface
  • Multimodal Fission
access type Otwarty dostęp

Design and Implementation of Intelligent Integrated Measuring and Controlling System for Sugar Cane Crystallization Process

Data publikacji: 01 Sep 2015
Zakres stron: 1687 - 1705

Abstrakt

Abstract

The deficiency in existing sugar cane crystallization automatic control system is difficult to measure some key parameters on line, such as mother liquor supersaturation, mother liquor purity, crystal content and crystal size distribution. Controlling brix with PID can only reflect the massecuite concentration of sugar cane crystallization process, but it is hard to guarantee the crystal quality. During crystallization process, change of mother liquor purity will affect the crystallization rate and supersaturation. The less mother liquor purity in the final stage is, the better absorption of crystals have. Crystal size distribution, including mean area (MA) and coefficient of variation (CV), influences the quantity and quality of crystals. In order to produce sucrose which has uniform size and small coefficient of variation, it’s necessary to study the law of crystal size for sugar cane crystallization. According to the difficulties in measuring some key parameters, an intelligent integrated measuring and controlling system is researched by this paper. The overall structure of this system is designed at first, and also the monitoring system of host computer is developed. Combining with data-driven modeling and hybrid modeling method, the intelligent soft-sensor component for sugar cane crystallization process is implemented. This system realizes automatic monitoring of sugar cane crystallization process, which includes on-line measurement of mother liquor supersaturation, mother liquor purity, crystal content and crystal size distribution (CSD). Experimental results show that this designed intelligent integrated measuring and controlling system for sugar cane crystallization process has not only achieved great on-line prediction for immeasurable parameters, but also has good openness and scalability, which can provide complete parameter detection for the implementation of sugar cane crystallization automatic control system.

Index terms

  • Sugar cane crystallization
  • soft sensor
  • crystal size distribution
  • hybrid modeling
  • on-line prediction
access type Otwarty dostęp

Computer Vision-Based Color Image Segmentation with Improved Kernel Clustering

Data publikacji: 01 Sep 2015
Zakres stron: 1706 - 1729

Abstrakt

Abstract

Color image segmentation has been widely applied to diverse fields in the past decades for containing more information than gray ones, whose essence is a process of clustering according to the color of pixels. However, traditional clustering methods do not scale well with the number of data, which limits the ability of handling massive data effectively. We developed an improved kernel clustering algorithm for computing the different clusters of given color images in kernel-induced space for image segmentation. Compared to other popular algorithms, it has the competitive performances both on training time and accuracy. The experiments performed on both synthetic and real-world data sets demonstrate the validity of the proposed algorithm.

Index terms

  • Computer vision
  • Color image segmentation
  • Kernel clustering
  • MEB algorithm
  • Support vector data description
access type Otwarty dostęp

Fragrance Measurement of Scented Rice using Electronic Nose

Data publikacji: 01 Sep 2015
Zakres stron: 1730 - 1747

Abstrakt

Abstract

This article describes about an instrument and method for aroma based quality detection of Basmati and other aromatic rice varieties. It comprises few modules such as odour delivery module, sniffing module, water bath module and computing module. Odour handling module helps to deliver odour to the sensor array; a sniffing unit comprising a sensor array module that includes a eight number of metal oxide semiconductor sensors assembled on a printed circuit board, said printed circuit board fitted into a sensor chamber; a water bath module for preparing rice sample, said water bath module including a heater attachment to facilitate cooking; a computing module to quantify the aroma data acquired by sensors; data acquisition module etc. Principal Component Analysis (PCA) implemented for clustering the data sets acquired from sensor array. Also data generated from sensor array was fed to Probabilistic Neural Network (PNN), Back-propagation Multilayer Perceptron (BPMLP) and Linear Discriminant Analysis (LDA) for identification of different rice varieties. Finally, for aroma quantifying, pure-quadratic response surface methodology model used with mean square error (MSE) 0.0028.

Index terms

  • Aromatic rice
  • Sensor
  • Principal Component Analysis
  • Probabilistic Neural Network
  • Back-propagation Multilayer Perceptron
  • Linear Discriminant Analysis
  • response surface methodology
access type Otwarty dostęp

Seladg: Secure Energy Efficient Location Aware Data Gathering Approach for Wireless Sensor Networks

Data publikacji: 01 Sep 2015
Zakres stron: 1748 - 1767

Abstrakt

Abstract

Recent trends in wireless sensor networks leads to the development of new protocols for data gathering. In this paper, a secure energy efficient location aware data gathering approach is introduced to secure data gathering. An Elliptic Curve Diffie Hellman Key Exchange (ECDHKE) algorithm is utilized for key generation and key exchange between the sensor nodes to maintain security and prevent the data from malicious nodes. The performance of the proposed scheme is validated in terms of packet drop, throughput, energy consumption, residual energy and network lifetime. The proposed scheme achieves better performance than the existing EEHA and SMART schemes.

Index terms

  • Data gathering
  • Key exchange
  • Key generation
  • Malicious nodes
  • Network lifetime
  • Residual energy
  • Sensor nodes and Wireless Sensor Networks (WSNs)
access type Otwarty dostęp

Research on Power Characteristic of the Electric Forklift EPS System

Data publikacji: 01 Sep 2015
Zakres stron: 1768 - 1785

Abstrakt

Abstract

This paper has given the structure, operating principle, and force analysis of electric power steering (EPS) system aimed at a type of forklift. Combing with forklift operating characteristic, three variable power characteristics curve based on steering wheel torque, real-time speed, and load is designed, so is the three dimensional diagram of forklift power gradient by using fuzzy rule. The dynamic model of EPS system and two-degree-of-freedom linear model of forklift dynamics are established. This paper presents a simulation on the basis of three variable power characteristics and dynamic model. The results show that forklift EPS system can provide appropriate power according to the changes of speed and load. It also can meet the demands of coordination between steering portability and road sense.

Index terms

  • EPS system of forklift
  • power gradient
  • three variable power characteristics curve
  • modeling
  • simulation
access type Otwarty dostęp

Dynamic Performance Influences on HOPF Bifurcation Characteristics for Vehicles

Data publikacji: 01 Sep 2015
Zakres stron: 1786 - 1805

Abstrakt

Abstract

This study compares the performance influences for four kinds of tread contour features commonly used in High-Speed trains. The Hopf bifurcation characteristic influencing the dynamic performance for VEHICLE 1 and VEHICLE 2 were analyzed using mathematical matrices models. SIMPACK software was used to create two dynamic models for VEHICLE 1 and VEHICLE 2 for high speed trains equipped with four kinds of treads matched with Chinese 60 rail. Dynamic performance indices for these models were studied during operation in straight track conditions with imposed high interference German track irregularity spectra with the premise of dynamic performance normalized indices processing. The study shows that: VEHICLE 1 exhibits a subcritical bifurcation characteristic under different wheel-rail matching conditions. VEHICLE 2 dynamic performance index values do not increase as speed increases, but wear index gradually increased with increased speed. Vehicles with different structural parameters, wheel-rail matching greatly influences bifurcation stability, comfort and wheel-rail wear. This method indicates an important reference value for wheel-rail matching in high-speed trains and structural parameters of stability and safety for these vehicle systems.

Index terms

  • Hopf bifurcation characteristics
  • tread
  • stability and comfort
  • wheel-rail matching
  • dynamic performan
access type Otwarty dostęp

The Use of Artificial Neural Networks in the estimation of the Perception of Sound By the Human Auditory System

Data publikacji: 01 Sep 2015
Zakres stron: 1806 - 1836

Abstrakt

Abstract

The human auditory system perceives sound in a much different manner than how sound is measured by modern audio sensing systems. The most commonly referenced aspects of auditory perception are loudness and pitch, which are related to the objective measures of audio signal frequency and sound pressure level. Here we describe an efficient and accurate method for the conversion of the sensed factors of frequency and sound pressure level to perceived loudness and pitch. This method is achieved through the modeling of the physical auditory system and the biological neural network of the primary auditory cortex using artificial neural networks. The behavior of artificial neural networks both during and after the training process has also been found to mimic that of biological neural networks and this method will be shown to have certain advantages over previous methods in the modeling of auditory perception. This work will describe the nature of artificial neural networks and investigate their suitability over other modeling methods for the task of perception modeling, taking into account development and implementation complexity. It will be shown that while known points on the perception scales of loudness and pitch can be used to objectively test the suitability of artificial neural networks, it is in the estimation of the perception of sound from the unknown (or unseen) data points that this method excels.

Index terms

  • auditory system modeling
  • audio sensors
  • artificial neural networks
  • perception of sound
  • digital signal processing
  • loudness
  • pitch
access type Otwarty dostęp

Sensitivity Analysis of Hierarchical Hybrid Fuzzy - Neural Network

Data publikacji: 01 Sep 2015
Zakres stron: 1837 - 1854

Abstrakt

Abstract

To identify the important attributes of complex system, which is high-dimensional and contain both discrete and continuous variables, this paper proposes a sensitivity analysis method of hierarchical hybrid fuzzy - neural network. We derive the sensitivity indexes of discrete and continuous variables through the differential method. To verify the effectiveness of our method, this study employed a man-made example and a remote sensing image classification example to test the performance of our method. The results show that our method can really identify the important variables of complex system and discover the relations between input and output variables; therefore, they can be applied to simplify the model and improve the classification accuracy of model.

Index terms

  • Hierarchical hybrid fuzzy
  • neural network
  • Sensitivity analysis
  • Differential method
  • Takagi- Sugeno model
  • Triangular membership function
access type Otwarty dostęp

Research on Lateral Stability of four Hubmotor-in-Wheels Drive Electric Vehicle

Data publikacji: 01 Sep 2015
Zakres stron: 1855 - 1875

Abstrakt

Abstract

This paper focuses on the problem of lateral stability of four hub-motor-in-wheels drive electric vehicle, 7 DOF (degrees of freedom) vehicle simulation model which is verified by field test is established based on Matlab/Simulink software. On basis of simulated model, BP neural network PID torque distribution controller of lateral stability is proposed. The sideslip angle at mass center and yaw rate are selected as the control variables, and the BP neural network PID torque distribution controller is designed. The simulation result shows that proposed strategy can control the electric vehicle’s sideslip angle at mass center and yaw rate, avoid the under steer and over steer of the vehicle and improve the vehicle lateral stability.

Index terms

  • Hub-motor-in-wheels drive
  • electric vehicle
  • lateral stability
  • BP neural network
  • PID control
21 Artykułów
access type Otwarty dostęp

Modified Clad Optical Fibre Coated With PVA/TiO2 Nano Composite For Humidity Sensing Application

Data publikacji: 01 Sep 2015
Zakres stron: 1424 - 1442

Abstrakt

Abstract

Synthesis of TiO2 nanoparticle through hydrolysis method is presented followed by TiO2- nanoparticle doped polyvinyl alcohol nanocomposite by solution process. FTIR, XRD, DSC-TGA, FESEM, TEM analysis are used to identify the nature of synthesized nanoparticle and loading uniformity of developed composite material. A simple modified clad based optical fibre sensor is developed to measure relative humidity. Coated modified clad optical fibre exhibits excellent relative humidity sensing performance with improved thermal stability of coating material in wide range of 9-95 % RH with good process repeatability. Sensor response is also observed to be very fast and highly reversible. Advantage of our developed composite material become evident when it exhibits wider range of moisture sensitivity compare to pure PVA or pure TiO2 material found in literature. Performance of PVA-TiO2 nanocomposite thick film is also evaluated by capacitance method and result found to agree with coated modified clad optical fibre.

Index terms

  • Polyvinyl alcohol
  • titanium dioxide
  • nanocomposite
  • modified-clad optical fibre
  • relative humidity sensor
access type Otwarty dostęp

Compensation of Capacitive Differential Pressure Sensor using Multi Layer Perceptron Neural Network

Data publikacji: 01 Sep 2015
Zakres stron: 1443 - 1463

Abstrakt

Abstract

Capacitive differential pressure sensor (CPS), which converts an input differential pressure to an output current, is extremely used in different industries. Since the accuracy of CPS is limited due to ambient temperature variations and nonlinear dependency of input and output, compensation is necessary in industries that are sensitive to pressure measurement. This paper proposes a framework for designing of CPS compensation system based on Multi Layer Perceptron (MLP) neural network. Firstly, a test bench for a sample popular CPS is designed and implemented for data acquisition in a real environment. Then, the gathered data are used to train different MLPs as CPS compensation system which inputs are the output current of CPS and temperature value, and the output is compensated current or computed pressure. The experimental results for an ATP3100 smart capacitive pressure transmitter show the trained three layers MLP with Levenberg- Marquardt learning algorithm could effectively compensate the output against variation of temperature as well as nonlinear effects, and reduce the pressure measurement error to about 0.1% FS (Full Scale) , over the temperature range of 5 ~ 60 ° C.

Index terms

  • Capacitive pressure sensors
  • Levenberg-Marquardt training algorithm
  • Multi-Layer Perceptron
  • Temperature compensation
access type Otwarty dostęp

Automatic Recognition of Facial Expression Based on Computer Vision

Data publikacji: 01 Sep 2015
Zakres stron: 1464 - 1483

Abstrakt

Abstract

Automatic facial expression recognition from video sequence is an essential research area in the field of computer vision. In this paper, a novel method for recognition facial expressions is proposed, which includes two stages of facial expression feature extraction and facial expression recognition. Firstly, in order to exact robust facial expression features, we use Active Appearance Model (AAM) to extract the global texture feature and optical flow technique to characterize facial expression which is determined facial velocity information. Then, these two features are integrated and converted to visual words using “bag-of-words” models, and facial expression is represented by a number of visual words. Secondly, the Latent Dirichlet Allocation (LDA) model are utilized to classify different facial expressions such as “anger”, “disgust”, “fear”, “happiness”, “neutral”, “sadness”, and “surprise”. The experimental results show that our proposed method not only performs stably and robustly and improves the recognition rate efficiently, but also needs the least dimension when achieves the highest recognition rate , which demonstrates that our proposed method is superior to others.

Index terms

  • Facial expression recognition
  • Active Appearance Model (AAM)
  • Bag of Words model
  • LDA model
  • computer vision
access type Otwarty dostęp

Modelling of Equipment Failure Rate Accounting for the Uncertainty

Data publikacji: 01 Sep 2015
Zakres stron: 1484 - 1504

Abstrakt

Abstract

A fuzzy model for failure rate with the consideration of the effects of uncertain factors in distribution reliability evaluation is presented. The possibility and credibility distribution analyzed on the basis of sample datum are used for quantifying effects of the uncertainty done to failure rate. Mathematically, the failure rate can be obtained in the interval integration. Moreover, aiming to make the calculating quantity of system reliability evaluation simple and easy, the fuzzy clustering analysis of equipment is adopted. The technique proposed has been implemented in an example distribution system for illustration and the results obtained have been compared with those obtained with average model.

Słowa kluczowe

  • fuzzy model
  • failure rate
  • uncertainty
  • fuzzy clustering analysis
access type Otwarty dostęp

Classification of artificial light sources and estimation of Color Rendering Index using RGB sensors, K Nearest Neighbor and Radial Basis Function

Data publikacji: 01 Sep 2015
Zakres stron: 1505 - 1524

Abstrakt

Abstract

Three types of artificial light sources work with electricity: incandescent, fluorescent and LED. These sources require characterization processes to allow selecting the most suitable for the application, to evaluate their capacity or more recently to tune and adjust their replicability using control algorithms. Therefore, it has been necessary to develop indices that represent these capabilities. The Color Rendering Index (CRI) is a measure used to characterize the color reproducibility of a light source in comparison to an ideal light source. The Correlated Color Temperature (CCT) is used to characterize light sources by representing the color as the temperature of a black body in Kelvin that shows nearly the same chromaticity as the analyzed light source. Using spectral information to determine the values in the XYZ space and deriving the calculation described in the standard is the best way to estimate the value of the CCT and the CRI. In this work, we implement a method to classify light sources and to select an estimation model of the CRI and the CCT using a low cost RGB sensor. The model estimation has been developed in this work and a separated algorithm for each source type has been built. The results show that using a K-Nearest Neighbor classifier, the error resulted less than $3.6%$. The error of the model estimation for the LED was 1.8%, for fluorescent light sources 0.09% and 1.2% for incandescent light sources.

Index terms

  • Color Rendering Index
  • CRI
  • light sources
  • Correlated Color Temperature
  • CCT
  • K Nearest Neighbor
  • Radial Basis Function
  • RBF
  • RGB sensors
access type Otwarty dostęp

Neutrosophic Concept Lattice based Approach for Computing Human Activities from Contexts

Data publikacji: 01 Sep 2015
Zakres stron: 1525 - 1553

Abstrakt

Abstract

Complex human activity recognition suffers from ambiguity of interpretation problem. A novel neutrosophic formal concept analysis method has been proposed to quantify non-determinism leading to ambiguity of interpretation and utilize it in activity recognition. The method works by penalizing performance of non-deterministic activities and rewarding the deterministic ones. Thus, non- deterministic activities are identified during testing due to significantly reduced performance and contexts can be redesigned to improve their description. The proposed method has been implemented on benchmark dataset having both types of activities. Our approach successfully identified nondeterminism in activities description without compromising recognition performance of deterministic activities. It has also been shown that other approaches fail to identify non deterministic activities. Overall accuracy of activity recognition of our approach was comparable to other approaches.

Index terms

  • Sensors Data Streams
  • Concept Lattice
  • Neutrosophic Logic
  • Situation Inference
  • Activity Recognition
access type Otwarty dostęp

Performance Measurement of Photoelectric Detection and Target Tracking Algorithm

Data publikacji: 01 Sep 2015
Zakres stron: 1554 - 1575

Abstrakt

Abstract

To solve the unstable problem of target tracking detection system, this paper proposes an improved mean-shift algorithm for object tracking, establishes object tracking processing model;provides the processing algorithm of object tracking. According to the principal of object tracking, papersets up sky background brightness calculation model in photoelectric tracking optical detection area and detection capability calculation model of space object, analyzes the effect of background illumination on the signal to noise ratio(SNR) of photoelectric tracking system, gives the change curve of detection capability based on the exposure time of CCD camera, SNR threshold of photoelectric detection system and dark current of photoelectric detection system. Through calculation and test , paperprovidesthe comparison results of the improved mean-shift and traditional mean-shift, verifies the correctness of the proposed algorithm and calculation models for photoelectric detection capability in target tracking detection system, the results show the improved mean-shiftobject tracking algorithm and detection capability calculation model are correct.

Index terms

  • photoelectric detection
  • target track
  • detection capability
  • SNR
access type Otwarty dostęp

Simulation of Noise Within BOTDA and Cotdr Systems to Study the Impact on Dynamic Sensing

Data publikacji: 01 Sep 2015
Zakres stron: 1576 - 1600

Abstrakt

Abstract

Real-time structural health monitoring requires dynamic sensing of distributed strain and temperature. Brillouin Optical Time Domain Analysis (BOTDA) and Rayleigh Coherent Optical Time Domain Reflectometry (COTDR) are promising candidates to achieve dynamic sensing. A noise model with specific parametric simulation of independent laser and detector noise sources has been developed. Although ensemble averaging significantly enhances the signal-to-noise ratio (SNR) in both systems, its time-consuming accumulation procedure prevents dynamic sensing. The sequence of averaging in the signal processing workflow varies the SNR for both systems. The system components should be optimized to reduce averaging times and achieve the required system specifications, including dynamic sensing.

Index terms

  • dynamic sensing
  • noise simulation
  • BOTDA
  • COTDR
  • laser fluctuation
  • detection
  • averaging
access type Otwarty dostęp

Fabrication of High Frequency Surface Acoustic Wave (SAW) Devices for Real Time Detection of Highly Toxic Chemical Vapors

Data publikacji: 01 Sep 2015
Zakres stron: 1601 - 1623

Abstrakt

Abstract

In this paper, a low cost fabrication of sub micron features size SAW device with conventional lithography and their application for toxic chemical vapor detection has been presented. The SAW devices with different interdigital transducer (IDT) electrodes line widths were designed and fabricated. The fabricated SAW devices features had an accuracy of ± 0.1 μm. Frequency response of the SAW devices was measured with vector network analyzer for design parameter confirmation. The fabricated devices have been configured in multisensory oscillator configuration and tested with chemical ware fare agents simulants at very low concentration (ppb).

Index terms

  • SAW device
  • Optical lithography
  • RF characterization
  • Mass Loading
  • Chemical sensor
access type Otwarty dostęp

Automatic Human Daily Activity Segmentation Applying Smart Sensing Technology

Data publikacji: 01 Sep 2015
Zakres stron: 1624 - 1640

Abstrakt

Abstract

Human daily activity segmentation utilizing smartphone sensing technology is quite new challenge. In this paper, the segmentation method combining statistical model and time series analysis is designed and implemented. According to designed partition procedure, real measured accelerometer datasets of human daily activities are tested. The segmentation performance of sliding window autocorrelation and minimized contrast algorithms is analysed and compared. Experiments demonstrate the effectiveness of this proposed automatic human activity separation method focusing on the application of mobile sensor. As the properties of signal, mean, variance, frequency and amplitude are all useful features on the case of motion sensor-based human daily activity segmentation. In the end, the suggested work to improve the developed partition model is presented.

Index terms

  • Smart sensing
  • activity segmentation
  • sensor signal processing
  • autocorrelation
  • statistical model
access type Otwarty dostęp

Study of Three-Dimensional on-line path Planning for UAV based on Pythagorean Hodograph Curve

Data publikacji: 01 Sep 2015
Zakres stron: 1641 - 1666

Abstrakt

Abstract

For the demand of the UAV autonomous path planning in dynamic thread environment, the three-dimensional path planning algorithm on-line of UAV based on Pythagorean Hodograph (PH) curve is put forward. According to the UAV’s current flight state such as location and speed, and the interrupt point or the target’s state, a flyable path with continuous curvature is planed out online. The roles of the key parameters are analyzed and the range of the values are given. On this basis, the distribution estimation algorithm is used to optimize the selection of path parameters, which avoid the blindness iterative process and consider the kinematics constraints such as the curvature, torsion and climbing angle. The multiple UAVs’ three dimensional path planning in dynamic environment are tested. Simulation results prove the validity and practicability of the algorithm.

Index terms

  • UAV
  • PH curve
  • three-dimensional path planning
access type Otwarty dostęp

Prototyping using a Pattern Technique and a Context-Based Bayesian Network in Multimodal Systems

Data publikacji: 01 Sep 2015
Zakres stron: 1667 - 1686

Abstrakt

Abstract

Today, technology allows us to produce extensive multimodal systems which are totally under human control. These systems are equipped with multimodal interfaces, which enable more natural and more efficient interaction between man and machine. End users can take advantage of natural modalities (e.g. audio, eye gaze, speech, gestures, etc.) to communicate or exchange information with applications. In this work, we assume that a number of these modalities are available to the user. In this paper, we present a prototype of a multimodal architecture, and show how modality selection and fission algorithms are implemented in such a system. We use a pattern technique to divide a complex command into elementary subtasks and select suitable modalities for each of them. We integrate a context-based method using a Bayesian network to resolve ambiguous or uncertain situations.

Index terms

  • Multimodality
  • Ontology
  • Bayesian Network
  • Pattern
  • User Interface
  • Multimodal Fission
access type Otwarty dostęp

Design and Implementation of Intelligent Integrated Measuring and Controlling System for Sugar Cane Crystallization Process

Data publikacji: 01 Sep 2015
Zakres stron: 1687 - 1705

Abstrakt

Abstract

The deficiency in existing sugar cane crystallization automatic control system is difficult to measure some key parameters on line, such as mother liquor supersaturation, mother liquor purity, crystal content and crystal size distribution. Controlling brix with PID can only reflect the massecuite concentration of sugar cane crystallization process, but it is hard to guarantee the crystal quality. During crystallization process, change of mother liquor purity will affect the crystallization rate and supersaturation. The less mother liquor purity in the final stage is, the better absorption of crystals have. Crystal size distribution, including mean area (MA) and coefficient of variation (CV), influences the quantity and quality of crystals. In order to produce sucrose which has uniform size and small coefficient of variation, it’s necessary to study the law of crystal size for sugar cane crystallization. According to the difficulties in measuring some key parameters, an intelligent integrated measuring and controlling system is researched by this paper. The overall structure of this system is designed at first, and also the monitoring system of host computer is developed. Combining with data-driven modeling and hybrid modeling method, the intelligent soft-sensor component for sugar cane crystallization process is implemented. This system realizes automatic monitoring of sugar cane crystallization process, which includes on-line measurement of mother liquor supersaturation, mother liquor purity, crystal content and crystal size distribution (CSD). Experimental results show that this designed intelligent integrated measuring and controlling system for sugar cane crystallization process has not only achieved great on-line prediction for immeasurable parameters, but also has good openness and scalability, which can provide complete parameter detection for the implementation of sugar cane crystallization automatic control system.

Index terms

  • Sugar cane crystallization
  • soft sensor
  • crystal size distribution
  • hybrid modeling
  • on-line prediction
access type Otwarty dostęp

Computer Vision-Based Color Image Segmentation with Improved Kernel Clustering

Data publikacji: 01 Sep 2015
Zakres stron: 1706 - 1729

Abstrakt

Abstract

Color image segmentation has been widely applied to diverse fields in the past decades for containing more information than gray ones, whose essence is a process of clustering according to the color of pixels. However, traditional clustering methods do not scale well with the number of data, which limits the ability of handling massive data effectively. We developed an improved kernel clustering algorithm for computing the different clusters of given color images in kernel-induced space for image segmentation. Compared to other popular algorithms, it has the competitive performances both on training time and accuracy. The experiments performed on both synthetic and real-world data sets demonstrate the validity of the proposed algorithm.

Index terms

  • Computer vision
  • Color image segmentation
  • Kernel clustering
  • MEB algorithm
  • Support vector data description
access type Otwarty dostęp

Fragrance Measurement of Scented Rice using Electronic Nose

Data publikacji: 01 Sep 2015
Zakres stron: 1730 - 1747

Abstrakt

Abstract

This article describes about an instrument and method for aroma based quality detection of Basmati and other aromatic rice varieties. It comprises few modules such as odour delivery module, sniffing module, water bath module and computing module. Odour handling module helps to deliver odour to the sensor array; a sniffing unit comprising a sensor array module that includes a eight number of metal oxide semiconductor sensors assembled on a printed circuit board, said printed circuit board fitted into a sensor chamber; a water bath module for preparing rice sample, said water bath module including a heater attachment to facilitate cooking; a computing module to quantify the aroma data acquired by sensors; data acquisition module etc. Principal Component Analysis (PCA) implemented for clustering the data sets acquired from sensor array. Also data generated from sensor array was fed to Probabilistic Neural Network (PNN), Back-propagation Multilayer Perceptron (BPMLP) and Linear Discriminant Analysis (LDA) for identification of different rice varieties. Finally, for aroma quantifying, pure-quadratic response surface methodology model used with mean square error (MSE) 0.0028.

Index terms

  • Aromatic rice
  • Sensor
  • Principal Component Analysis
  • Probabilistic Neural Network
  • Back-propagation Multilayer Perceptron
  • Linear Discriminant Analysis
  • response surface methodology
access type Otwarty dostęp

Seladg: Secure Energy Efficient Location Aware Data Gathering Approach for Wireless Sensor Networks

Data publikacji: 01 Sep 2015
Zakres stron: 1748 - 1767

Abstrakt

Abstract

Recent trends in wireless sensor networks leads to the development of new protocols for data gathering. In this paper, a secure energy efficient location aware data gathering approach is introduced to secure data gathering. An Elliptic Curve Diffie Hellman Key Exchange (ECDHKE) algorithm is utilized for key generation and key exchange between the sensor nodes to maintain security and prevent the data from malicious nodes. The performance of the proposed scheme is validated in terms of packet drop, throughput, energy consumption, residual energy and network lifetime. The proposed scheme achieves better performance than the existing EEHA and SMART schemes.

Index terms

  • Data gathering
  • Key exchange
  • Key generation
  • Malicious nodes
  • Network lifetime
  • Residual energy
  • Sensor nodes and Wireless Sensor Networks (WSNs)
access type Otwarty dostęp

Research on Power Characteristic of the Electric Forklift EPS System

Data publikacji: 01 Sep 2015
Zakres stron: 1768 - 1785

Abstrakt

Abstract

This paper has given the structure, operating principle, and force analysis of electric power steering (EPS) system aimed at a type of forklift. Combing with forklift operating characteristic, three variable power characteristics curve based on steering wheel torque, real-time speed, and load is designed, so is the three dimensional diagram of forklift power gradient by using fuzzy rule. The dynamic model of EPS system and two-degree-of-freedom linear model of forklift dynamics are established. This paper presents a simulation on the basis of three variable power characteristics and dynamic model. The results show that forklift EPS system can provide appropriate power according to the changes of speed and load. It also can meet the demands of coordination between steering portability and road sense.

Index terms

  • EPS system of forklift
  • power gradient
  • three variable power characteristics curve
  • modeling
  • simulation
access type Otwarty dostęp

Dynamic Performance Influences on HOPF Bifurcation Characteristics for Vehicles

Data publikacji: 01 Sep 2015
Zakres stron: 1786 - 1805

Abstrakt

Abstract

This study compares the performance influences for four kinds of tread contour features commonly used in High-Speed trains. The Hopf bifurcation characteristic influencing the dynamic performance for VEHICLE 1 and VEHICLE 2 were analyzed using mathematical matrices models. SIMPACK software was used to create two dynamic models for VEHICLE 1 and VEHICLE 2 for high speed trains equipped with four kinds of treads matched with Chinese 60 rail. Dynamic performance indices for these models were studied during operation in straight track conditions with imposed high interference German track irregularity spectra with the premise of dynamic performance normalized indices processing. The study shows that: VEHICLE 1 exhibits a subcritical bifurcation characteristic under different wheel-rail matching conditions. VEHICLE 2 dynamic performance index values do not increase as speed increases, but wear index gradually increased with increased speed. Vehicles with different structural parameters, wheel-rail matching greatly influences bifurcation stability, comfort and wheel-rail wear. This method indicates an important reference value for wheel-rail matching in high-speed trains and structural parameters of stability and safety for these vehicle systems.

Index terms

  • Hopf bifurcation characteristics
  • tread
  • stability and comfort
  • wheel-rail matching
  • dynamic performan
access type Otwarty dostęp

The Use of Artificial Neural Networks in the estimation of the Perception of Sound By the Human Auditory System

Data publikacji: 01 Sep 2015
Zakres stron: 1806 - 1836

Abstrakt

Abstract

The human auditory system perceives sound in a much different manner than how sound is measured by modern audio sensing systems. The most commonly referenced aspects of auditory perception are loudness and pitch, which are related to the objective measures of audio signal frequency and sound pressure level. Here we describe an efficient and accurate method for the conversion of the sensed factors of frequency and sound pressure level to perceived loudness and pitch. This method is achieved through the modeling of the physical auditory system and the biological neural network of the primary auditory cortex using artificial neural networks. The behavior of artificial neural networks both during and after the training process has also been found to mimic that of biological neural networks and this method will be shown to have certain advantages over previous methods in the modeling of auditory perception. This work will describe the nature of artificial neural networks and investigate their suitability over other modeling methods for the task of perception modeling, taking into account development and implementation complexity. It will be shown that while known points on the perception scales of loudness and pitch can be used to objectively test the suitability of artificial neural networks, it is in the estimation of the perception of sound from the unknown (or unseen) data points that this method excels.

Index terms

  • auditory system modeling
  • audio sensors
  • artificial neural networks
  • perception of sound
  • digital signal processing
  • loudness
  • pitch
access type Otwarty dostęp

Sensitivity Analysis of Hierarchical Hybrid Fuzzy - Neural Network

Data publikacji: 01 Sep 2015
Zakres stron: 1837 - 1854

Abstrakt

Abstract

To identify the important attributes of complex system, which is high-dimensional and contain both discrete and continuous variables, this paper proposes a sensitivity analysis method of hierarchical hybrid fuzzy - neural network. We derive the sensitivity indexes of discrete and continuous variables through the differential method. To verify the effectiveness of our method, this study employed a man-made example and a remote sensing image classification example to test the performance of our method. The results show that our method can really identify the important variables of complex system and discover the relations between input and output variables; therefore, they can be applied to simplify the model and improve the classification accuracy of model.

Index terms

  • Hierarchical hybrid fuzzy
  • neural network
  • Sensitivity analysis
  • Differential method
  • Takagi- Sugeno model
  • Triangular membership function
access type Otwarty dostęp

Research on Lateral Stability of four Hubmotor-in-Wheels Drive Electric Vehicle

Data publikacji: 01 Sep 2015
Zakres stron: 1855 - 1875

Abstrakt

Abstract

This paper focuses on the problem of lateral stability of four hub-motor-in-wheels drive electric vehicle, 7 DOF (degrees of freedom) vehicle simulation model which is verified by field test is established based on Matlab/Simulink software. On basis of simulated model, BP neural network PID torque distribution controller of lateral stability is proposed. The sideslip angle at mass center and yaw rate are selected as the control variables, and the BP neural network PID torque distribution controller is designed. The simulation result shows that proposed strategy can control the electric vehicle’s sideslip angle at mass center and yaw rate, avoid the under steer and over steer of the vehicle and improve the vehicle lateral stability.

Index terms

  • Hub-motor-in-wheels drive
  • electric vehicle
  • lateral stability
  • BP neural network
  • PID control

Zaplanuj zdalną konferencję ze Sciendo