Zeitschriften und Ausgaben

Volumen 22 (2022): Heft 3 (September 2022)

Volumen 22 (2022): Heft 2 (June 2022)

Volumen 22 (2022): Heft 1 (March 2022)

Volumen 21 (2021): Heft 4 (December 2021)

Volumen 21 (2021): Heft 3 (September 2021)

Volumen 21 (2021): Heft 2 (June 2021)

Volumen 21 (2021): Heft 1 (March 2021)

Volumen 20 (2020): Heft 6 (December 2020)
Special Heft on New Developments in Scalable Computing

Volumen 20 (2020): Heft 5 (December 2020)
Special issue on Innovations in Intelligent Systems and Applications

Volumen 20 (2020): Heft 4 (November 2020)

Volumen 20 (2020): Heft 3 (September 2020)

Volumen 20 (2020): Heft 2 (June 2020)

Volumen 20 (2020): Heft 1 (March 2020)

Volumen 19 (2019): Heft 4 (November 2019)

Volumen 19 (2019): Heft 3 (September 2019)

Volumen 19 (2019): Heft 2 (June 2019)

Volumen 19 (2019): Heft 1 (March 2019)

Volumen 18 (2018): Heft 5 (May 2018)
Special Thematic Heft on Optimal Codes and Related Topics

Volumen 18 (2018): Heft 4 (November 2018)

Volumen 18 (2018): Heft 3 (September 2018)

Volumen 18 (2018): Heft 2 (June 2018)

Volumen 18 (2018): Heft 1 (March 2018)

Volumen 17 (2017): Heft 5 (December 2017)
Special Heft With Selected Papers From The Workshop “Two Years Avitohol: Advanced High Performance Computing Applications 2017

Volumen 17 (2017): Heft 4 (November 2017)

Volumen 17 (2017): Heft 3 (September 2017)

Volumen 17 (2017): Heft 2 (June 2017)

Volumen 17 (2017): Heft 1 (March 2017)

Volumen 16 (2016): Heft 6 (December 2016)
Special issue with selection of extended papers from 6th International Conference on Logistic, Informatics and Service Science LISS’2016

Volumen 16 (2016): Heft 5 (October 2016)
Heft Title: Special Heft on Application of Advanced Computing and Simulation in Information Systems

Volumen 16 (2016): Heft 4 (December 2016)

Volumen 16 (2016): Heft 3 (September 2016)

Volumen 16 (2016): Heft 2 (June 2016)

Volumen 16 (2016): Heft 1 (March 2016)

Volumen 15 (2015): Heft 7 (December 2015)
Special Heft on Information Fusion

Volumen 15 (2015): Heft 6 (December 2015)
Special Heft on Logistics, Informatics and Service Science

Volumen 15 (2015): Heft 5 (April 2015)
Special Heft on Control in Transportation Systems

Volumen 15 (2015): Heft 4 (November 2015)

Volumen 15 (2015): Heft 3 (September 2015)

Volumen 15 (2015): Heft 2 (June 2015)

Volumen 15 (2015): Heft 1 (March 2015)

Volumen 14 (2014): Heft 5 (December 2014)
Special Heft

Volumen 14 (2014): Heft 4 (December 2014)

Volumen 14 (2014): Heft 3 (September 2014)

Volumen 14 (2014): Heft 2 (June 2014)

Volumen 14 (2014): Heft 1 (March 2014)

Volumen 13 (2013): Heft Special-Heft (December 2013)

Volumen 13 (2013): Heft 4 (December 2013)
The publishing of the present issue (Volumen 13, No 4, 2013) of the journal “Cybernetics and Information Technologies” is financially supported by FP7 project “Advanced Computing for Innovation” (ACOMIN), grant agreement 316087 of Call FP7 REGPOT-2012-2013-1.

Volumen 13 (2013): Heft 3 (September 2013)

Volumen 13 (2013): Heft 2 (June 2013)

Volumen 13 (2013): Heft 1 (March 2013)

Volumen 12 (2012): Heft 4 (December 2012)

Volumen 12 (2012): Heft 3 (September 2012)

Volumen 12 (2012): Heft 2 (June 2012)

Volumen 12 (2012): Heft 1 (March 2012)

Zeitschriftendaten
Format
Zeitschrift
eISSN
1314-4081
Erstveröffentlichung
13 Mar 2012
Erscheinungsweise
4 Hefte pro Jahr
Sprachen
Englisch

Suche

Volumen 15 (2015): Heft 3 (September 2015)

Zeitschriftendaten
Format
Zeitschrift
eISSN
1314-4081
Erstveröffentlichung
13 Mar 2012
Erscheinungsweise
4 Hefte pro Jahr
Sprachen
Englisch

Suche

12 Artikel
Uneingeschränkter Zugang

A Survey on Group Key Management Schemes

Online veröffentlicht: 05 Oct 2015
Seitenbereich: 3 - 25

Zusammenfassung

Abstract

Cryptographic key management needs utmost security in generating, exchanging, using, rekeying, storing of keys, being used for communication purposes. Successful key management is critical to the security of a cryptosystem. This paper presents a detailed survey on group key management and its challenges in network independent and network dependent approaches. The paper also focuses on the advantages, disadvantages and security vulnerabilities of these protocols.

Schlüsselwörter

  • Group key
  • security
  • rekeying
  • multicast
  • key management
Uneingeschränkter Zugang

Attribute-Based Parallel Key-Insulated Signature

Online veröffentlicht: 05 Oct 2015
Seitenbereich: 26 - 40

Zusammenfassung

Abstract

To deal with the key-exposure protection problem in attribute-based signature systems, we extend the parallel key-insulated mechanism to attribute-based signature scenarios, and then introduce the primitive of an Attribute-Based Parallel Key-Insulated Signature (ABPKIS). After formalizing the definition and security notions for ABPKIS, a concrete ABPKIS scheme is presented. The security of our proposed ABPKIS scheme can be proved on a standard model. According to our knowledge, this is the first ABPKIS scheme up to now. Moreover, this is also the first concrete attribute-based key-insulated signature construction supporting multi-helpers.

Schlüsselwörter

  • Parallel key-insulated
  • attribute-based signature
  • key-exposure
Uneingeschränkter Zugang

A Multi-Step Procedure for Asset Allocation in Case of Limited Resources

Online veröffentlicht: 05 Oct 2015
Seitenbereich: 41 - 51

Zusammenfassung

Abstract

Portfolio management is a process involving decision making in dynamic and unpredictable environment. Asset allocation plays a key role in this process, since the optimal use of the capital is a complex and resource-consuming problem. During our research in this field we have detected some problems that lead to biased results and one of them occurs in case of limited financial resources. In this paper a mathematical assessment of the dependence of the capital, used on asset prices is derived, and a multi-step procedure for asset allocation, aiming at optimization of the investor’s utility in case of limited resources is described. The procedure is implemented as a module in a decision support system based on fuzzy logic. The paper contains comparison of the obtained test results with results from the classical Markowitz portfolio model. The conducted tests are on real data from the Bulgarian stock exchange.

Schlüsselwörter

  • Asset allocation
  • FSSAM
  • capital optimization
  • fuzzy systems
Uneingeschränkter Zugang

Improving QoS Routing in Hybrid Wireless Mesh Networks, Using Cross-Layer Interaction and MAC Scheduling

Online veröffentlicht: 05 Oct 2015
Seitenbereich: 52 - 67

Zusammenfassung

Abstract

Delivering Quality of Services (QoS) for cooperative Wireless Mesh Networks (WMN) is an important issue when enabling heterogeneous wireless technologies on the client side. A standard approach for satisfying the QoS requirements of different wireless clients appears to be a complex task due to the capacity variations. In addition to the routing layer, the information at the lower layers, such as Physical and Medium Access Control (MAC) layers must be considered for providing the QoS guarantee. The strength of a signal received from heterogeneous clients at the physical layer and the coupled network capacity at the MAC layer plays an important role in the efficient path assignment and time scheduling management for routing. Therefore, this paper proposes an Adaptive Multipath-Dynamic Source Routing (AM-DSR) protocol. It supports Cross-Layer Interaction (CLI) for path assignment and MAC scheduling mechanism for slot assignment to improve the mesh backbone performance for providing multimedia services to various wireless clients in a hybrid WMN. The proposed strategy measures the cross-layer parameter, such as the network capacity, using the Signal to Noise Ratio (SINR) and assigns a route that maximizes the efficiency of the multimedia services. Finally, the performance evaluation shows that the proposed cross-layer based AM-DSR protocol provides efficient QoS support for the mesh backbone enabling connections to multiple clients.

Schlüsselwörter

  • Wireless mesh networks
  • mesh backbone
  • cross-layer issues
  • interference
  • signal strength
  • MAC scheduling
Uneingeschränkter Zugang

Efficient Emergency Event Tracking Using Features of Web Data

Online veröffentlicht: 05 Oct 2015
Seitenbereich: 68 - 87

Zusammenfassung

Abstract

Huge amount of information has become now available in web services due to their popularity. This web data contains user-contributed information for a variety of emergency events. However, tracking these emergency events is often limited by the lack of efficient tools to analyze the potential events or topics over time, since these events are inherently difficult to predict due to the interference of other unpredictable evolutions. In this paper we propose a two-phase approach, in which we first introduce a novel extraction algorithm to acquire relevant web data and then we utilize a limit theory to determine the periodical convergence time of a specific event, and an event tracking model is constructed using the extracted web data. Based on the significance of multiple features weights and clustering solutions, the interplay between the ordinary events and latent events is discovered to efficiently track the emergency events. Finally, we conduct extensive experiments to verify the effectiveness and efficiency of our approach.

Schlüsselwörter

  • Emergency event
  • event tracking
  • web data extraction
  • clustering
Uneingeschränkter Zugang

A Neuro Fuzzy Based Intrusion Detection System for a Cloud Data Center Using Adaptive Learning

Online veröffentlicht: 05 Oct 2015
Seitenbereich: 88 - 103

Zusammenfassung

Abstract

With its continuous improvements, the cloud computing system leaves an open door for malicious activities. This promotes the significance of constructing a malware action detection component to discover the anomalies in the virtual environment. Besides, the traditional intrusion detection system does not suit for the cloud environment. So, the proposed scheme develops an anomaly detection system, named Hypervisor Detector at a hypervisor layer to detect the abnormalities in the virtual network. Besides, the fuzzy systems have the ability to detect the presence of uncertain and imprecise nature of anomalies; they are not able to construct models based on target data. One of the successful approaches, which integrate fuzzy systems with adaptation and learning proficiencies of a neural network, such as ANFIS (Adaptive Neuro Fuzzy Inference System) model, is based on target values. The Hypervisor Detector is designed and developed with an ANFIS and practised with a hybrid algorithm, a combination of the back propagation gradient descent technique with the least square method. For the experiments and performance analysis, DARPA’s KDD cup data set is used. The performance analysis and results show that the model proposed is well designed to detect the abnormalities in virtual environment with the minimum false alarm rate and reduced overhead.

Schlüsselwörter

  • Cloud computing
  • intrusion detection system
  • ANFIS
  • hypervisor
  • false alarm rate
Uneingeschränkter Zugang

Selecting Discriminative Binary Patterns for a Local Feature

Online veröffentlicht: 05 Oct 2015
Seitenbereich: 104 - 113

Zusammenfassung

Abstract

The local descriptors based on a binary pattern feature have state-of-the-art distinctiveness. However, their high dimensionality resists them from matching faster and being used in a low-end device. In this paper we propose an efficient and feasible learning method to select discriminative binary patterns for constructing a compact local descriptor. In the selection, a searching tree with Branch&Bound is used instead of the exhaustive enumeration, in order to avoid tremendous computation in training. New local descriptors are constructed based on the selected patterns. The efficiency of selecting binary patterns has been confirmed by the evaluation of these new local descriptors’ performance in experiments of image matching and object recognition.

Schlüsselwörter

  • Selecting patterns
  • searching tree
  • local descriptor
  • matching
  • binary pattern
Uneingeschränkter Zugang

Trends and Opportunities in Computer Science OER Development

Online veröffentlicht: 05 Oct 2015
Seitenbereich: 114 - 126

Zusammenfassung

Abstract

The world is embracing an open education model. The success of this process implies an adequate awareness, an assumption that is inconsistent with recent reports and statistical facts. Despite the major advances in recent years, Open Educational Resources (OER) are still not in the mainstream of Computer Science course development. Motivated by the need to fill this gap, this paper analyzes the evolution of the OER development and the emerging trends relevant to Computer Science education. The aim is to raise the awareness and promote a practical transition process towards an adequate model that aligns the interests of all stakeholders.

Schlüsselwörter

  • Open education
  • Open Educational Resources
  • Computer Science education
Uneingeschränkter Zugang

AAM Based Facial Feature Tracking with Kinect

Online veröffentlicht: 05 Oct 2015
Seitenbereich: 127 - 139

Zusammenfassung

Abstract

Facial features tracking is widely used in face recognition, gesture, expression analysis, etc. AAM (Active Appearance Model) is one of the powerful methods for objects feature localization. Nevertheless, AAM still suffers from a few drawbacks, such as the view angle change problem. We present a method to solve it by using the depth data acquired from Kinect. We use the depth data to get the head pose information and RGB data to match the AAM result. We establish an approximate facial 3D gird model and then initialize the subsequent frames with this model and head pose information. To avoid the local extremum, we divide the model into several parts by the poses and match the facial features with the closest model. The experimental results show improvement of AAM performance when rotating the head.

Schlüsselwörter

  • Facial feature tracking
  • active appearance model
  • view based model
  • Kinect
Uneingeschränkter Zugang

Parameter Selection of a Support Vector Machine, Based on a Chaotic Particle Swarm Optimization Algorithm

Online veröffentlicht: 05 Oct 2015
Seitenbereich: 140 - 149

Zusammenfassung

Abstract

This paper proposes a SVM (Support Vector Machine) parameter selection based on CPSO (Chaotic Particle Swarm Optimization), in order to determine the optimal parameters of the support vector machine quickly and efficiently. SVMs are new methods being developed, based on statistical learning theory. Training a SVM can be formulated as a quadratic programming problem. The parameter selection of SVMs must be done before solving the QP (Quadratic Programming) problem. The PSO (Particle Swarm Optimization) algorithm is applied in the course of SVM parameter selection. Due to the sensitivity and frequency of the initial value of the chaotic motion, the PSO algorithm is also applied to improve the particle swarm optimization, so as to improve the global search ability of the particles. The simulation results show that the improved CPSO can find more easily the global optimum and reduce the number of iterations, which also makes the search for a group of optimal parameters of SVM quicker and more efficient.

Schlüsselwörter

  • Support vector machine
  • parameter selection
  • particle swarm optimization
  • chaotic optimization
Uneingeschränkter Zugang

Performance Guarantee Mechanism for Multi-Tenancy SaaS Service Based on Kalman Filtering

Online veröffentlicht: 05 Oct 2015
Seitenbereich: 150 - 164

Zusammenfassung

Abstract

This paper proposes a special System Architecture for Multi-tenancy SaaS Service (SAMSS), which studies the performance security issues at the business logic layer and data processing layer respectively. The Kalman filtering Admission Control algorithm (KAC) and the Greedy Copy Management algorithm (GCM) are proposed. At the business logic layer, Kalman filtering admission control algorithm is presented. It uses a Kalman filter to conduct the dynamic evaluation for the CPU resource for multi-tenancy SaaS service and reduces the unnecessary performance expenses caused by direct measurement of CPU resources. At the data processing layer, the Greedy Copy Management algorithm (GCM) is presented. It changes the copy placement as a K-partitioning set partitioning problem and adopts a greedy strategy to reduce the number of times for creating a data copy. Finally, the experimental analysis and results prove the feasibility and efficiency of the algorithms proposed.

Schlüsselwörter

  • Kalman filtering
  • business logic layer
  • data processing layer
  • multi-tenancy
  • SaaS
Uneingeschränkter Zugang

Solving Multicriteria Optimization Problems with WebOptim Software System

Online veröffentlicht: 05 Oct 2015
Seitenbereich: 165 - 177

Zusammenfassung

Abstract

This paper is a presentation of a web based decision support system “WebOptim” for solving single and multiple criteria optimization problems. It targets a wide range of user typeseducators, researchers, managers and business people. It also provides two types of communication interfaces user friendly graphical interface for human interaction and programming interface for machine communication with other third party software systems. The interfaces facilitate the problem solving process of different types of optimization problems, mainly single and multi-objective programming optimization problems with continuous or integer variables.

Schlüsselwörter

  • Multiple criteria optimization
  • web-based decision support system
12 Artikel
Uneingeschränkter Zugang

A Survey on Group Key Management Schemes

Online veröffentlicht: 05 Oct 2015
Seitenbereich: 3 - 25

Zusammenfassung

Abstract

Cryptographic key management needs utmost security in generating, exchanging, using, rekeying, storing of keys, being used for communication purposes. Successful key management is critical to the security of a cryptosystem. This paper presents a detailed survey on group key management and its challenges in network independent and network dependent approaches. The paper also focuses on the advantages, disadvantages and security vulnerabilities of these protocols.

Schlüsselwörter

  • Group key
  • security
  • rekeying
  • multicast
  • key management
Uneingeschränkter Zugang

Attribute-Based Parallel Key-Insulated Signature

Online veröffentlicht: 05 Oct 2015
Seitenbereich: 26 - 40

Zusammenfassung

Abstract

To deal with the key-exposure protection problem in attribute-based signature systems, we extend the parallel key-insulated mechanism to attribute-based signature scenarios, and then introduce the primitive of an Attribute-Based Parallel Key-Insulated Signature (ABPKIS). After formalizing the definition and security notions for ABPKIS, a concrete ABPKIS scheme is presented. The security of our proposed ABPKIS scheme can be proved on a standard model. According to our knowledge, this is the first ABPKIS scheme up to now. Moreover, this is also the first concrete attribute-based key-insulated signature construction supporting multi-helpers.

Schlüsselwörter

  • Parallel key-insulated
  • attribute-based signature
  • key-exposure
Uneingeschränkter Zugang

A Multi-Step Procedure for Asset Allocation in Case of Limited Resources

Online veröffentlicht: 05 Oct 2015
Seitenbereich: 41 - 51

Zusammenfassung

Abstract

Portfolio management is a process involving decision making in dynamic and unpredictable environment. Asset allocation plays a key role in this process, since the optimal use of the capital is a complex and resource-consuming problem. During our research in this field we have detected some problems that lead to biased results and one of them occurs in case of limited financial resources. In this paper a mathematical assessment of the dependence of the capital, used on asset prices is derived, and a multi-step procedure for asset allocation, aiming at optimization of the investor’s utility in case of limited resources is described. The procedure is implemented as a module in a decision support system based on fuzzy logic. The paper contains comparison of the obtained test results with results from the classical Markowitz portfolio model. The conducted tests are on real data from the Bulgarian stock exchange.

Schlüsselwörter

  • Asset allocation
  • FSSAM
  • capital optimization
  • fuzzy systems
Uneingeschränkter Zugang

Improving QoS Routing in Hybrid Wireless Mesh Networks, Using Cross-Layer Interaction and MAC Scheduling

Online veröffentlicht: 05 Oct 2015
Seitenbereich: 52 - 67

Zusammenfassung

Abstract

Delivering Quality of Services (QoS) for cooperative Wireless Mesh Networks (WMN) is an important issue when enabling heterogeneous wireless technologies on the client side. A standard approach for satisfying the QoS requirements of different wireless clients appears to be a complex task due to the capacity variations. In addition to the routing layer, the information at the lower layers, such as Physical and Medium Access Control (MAC) layers must be considered for providing the QoS guarantee. The strength of a signal received from heterogeneous clients at the physical layer and the coupled network capacity at the MAC layer plays an important role in the efficient path assignment and time scheduling management for routing. Therefore, this paper proposes an Adaptive Multipath-Dynamic Source Routing (AM-DSR) protocol. It supports Cross-Layer Interaction (CLI) for path assignment and MAC scheduling mechanism for slot assignment to improve the mesh backbone performance for providing multimedia services to various wireless clients in a hybrid WMN. The proposed strategy measures the cross-layer parameter, such as the network capacity, using the Signal to Noise Ratio (SINR) and assigns a route that maximizes the efficiency of the multimedia services. Finally, the performance evaluation shows that the proposed cross-layer based AM-DSR protocol provides efficient QoS support for the mesh backbone enabling connections to multiple clients.

Schlüsselwörter

  • Wireless mesh networks
  • mesh backbone
  • cross-layer issues
  • interference
  • signal strength
  • MAC scheduling
Uneingeschränkter Zugang

Efficient Emergency Event Tracking Using Features of Web Data

Online veröffentlicht: 05 Oct 2015
Seitenbereich: 68 - 87

Zusammenfassung

Abstract

Huge amount of information has become now available in web services due to their popularity. This web data contains user-contributed information for a variety of emergency events. However, tracking these emergency events is often limited by the lack of efficient tools to analyze the potential events or topics over time, since these events are inherently difficult to predict due to the interference of other unpredictable evolutions. In this paper we propose a two-phase approach, in which we first introduce a novel extraction algorithm to acquire relevant web data and then we utilize a limit theory to determine the periodical convergence time of a specific event, and an event tracking model is constructed using the extracted web data. Based on the significance of multiple features weights and clustering solutions, the interplay between the ordinary events and latent events is discovered to efficiently track the emergency events. Finally, we conduct extensive experiments to verify the effectiveness and efficiency of our approach.

Schlüsselwörter

  • Emergency event
  • event tracking
  • web data extraction
  • clustering
Uneingeschränkter Zugang

A Neuro Fuzzy Based Intrusion Detection System for a Cloud Data Center Using Adaptive Learning

Online veröffentlicht: 05 Oct 2015
Seitenbereich: 88 - 103

Zusammenfassung

Abstract

With its continuous improvements, the cloud computing system leaves an open door for malicious activities. This promotes the significance of constructing a malware action detection component to discover the anomalies in the virtual environment. Besides, the traditional intrusion detection system does not suit for the cloud environment. So, the proposed scheme develops an anomaly detection system, named Hypervisor Detector at a hypervisor layer to detect the abnormalities in the virtual network. Besides, the fuzzy systems have the ability to detect the presence of uncertain and imprecise nature of anomalies; they are not able to construct models based on target data. One of the successful approaches, which integrate fuzzy systems with adaptation and learning proficiencies of a neural network, such as ANFIS (Adaptive Neuro Fuzzy Inference System) model, is based on target values. The Hypervisor Detector is designed and developed with an ANFIS and practised with a hybrid algorithm, a combination of the back propagation gradient descent technique with the least square method. For the experiments and performance analysis, DARPA’s KDD cup data set is used. The performance analysis and results show that the model proposed is well designed to detect the abnormalities in virtual environment with the minimum false alarm rate and reduced overhead.

Schlüsselwörter

  • Cloud computing
  • intrusion detection system
  • ANFIS
  • hypervisor
  • false alarm rate
Uneingeschränkter Zugang

Selecting Discriminative Binary Patterns for a Local Feature

Online veröffentlicht: 05 Oct 2015
Seitenbereich: 104 - 113

Zusammenfassung

Abstract

The local descriptors based on a binary pattern feature have state-of-the-art distinctiveness. However, their high dimensionality resists them from matching faster and being used in a low-end device. In this paper we propose an efficient and feasible learning method to select discriminative binary patterns for constructing a compact local descriptor. In the selection, a searching tree with Branch&Bound is used instead of the exhaustive enumeration, in order to avoid tremendous computation in training. New local descriptors are constructed based on the selected patterns. The efficiency of selecting binary patterns has been confirmed by the evaluation of these new local descriptors’ performance in experiments of image matching and object recognition.

Schlüsselwörter

  • Selecting patterns
  • searching tree
  • local descriptor
  • matching
  • binary pattern
Uneingeschränkter Zugang

Trends and Opportunities in Computer Science OER Development

Online veröffentlicht: 05 Oct 2015
Seitenbereich: 114 - 126

Zusammenfassung

Abstract

The world is embracing an open education model. The success of this process implies an adequate awareness, an assumption that is inconsistent with recent reports and statistical facts. Despite the major advances in recent years, Open Educational Resources (OER) are still not in the mainstream of Computer Science course development. Motivated by the need to fill this gap, this paper analyzes the evolution of the OER development and the emerging trends relevant to Computer Science education. The aim is to raise the awareness and promote a practical transition process towards an adequate model that aligns the interests of all stakeholders.

Schlüsselwörter

  • Open education
  • Open Educational Resources
  • Computer Science education
Uneingeschränkter Zugang

AAM Based Facial Feature Tracking with Kinect

Online veröffentlicht: 05 Oct 2015
Seitenbereich: 127 - 139

Zusammenfassung

Abstract

Facial features tracking is widely used in face recognition, gesture, expression analysis, etc. AAM (Active Appearance Model) is one of the powerful methods for objects feature localization. Nevertheless, AAM still suffers from a few drawbacks, such as the view angle change problem. We present a method to solve it by using the depth data acquired from Kinect. We use the depth data to get the head pose information and RGB data to match the AAM result. We establish an approximate facial 3D gird model and then initialize the subsequent frames with this model and head pose information. To avoid the local extremum, we divide the model into several parts by the poses and match the facial features with the closest model. The experimental results show improvement of AAM performance when rotating the head.

Schlüsselwörter

  • Facial feature tracking
  • active appearance model
  • view based model
  • Kinect
Uneingeschränkter Zugang

Parameter Selection of a Support Vector Machine, Based on a Chaotic Particle Swarm Optimization Algorithm

Online veröffentlicht: 05 Oct 2015
Seitenbereich: 140 - 149

Zusammenfassung

Abstract

This paper proposes a SVM (Support Vector Machine) parameter selection based on CPSO (Chaotic Particle Swarm Optimization), in order to determine the optimal parameters of the support vector machine quickly and efficiently. SVMs are new methods being developed, based on statistical learning theory. Training a SVM can be formulated as a quadratic programming problem. The parameter selection of SVMs must be done before solving the QP (Quadratic Programming) problem. The PSO (Particle Swarm Optimization) algorithm is applied in the course of SVM parameter selection. Due to the sensitivity and frequency of the initial value of the chaotic motion, the PSO algorithm is also applied to improve the particle swarm optimization, so as to improve the global search ability of the particles. The simulation results show that the improved CPSO can find more easily the global optimum and reduce the number of iterations, which also makes the search for a group of optimal parameters of SVM quicker and more efficient.

Schlüsselwörter

  • Support vector machine
  • parameter selection
  • particle swarm optimization
  • chaotic optimization
Uneingeschränkter Zugang

Performance Guarantee Mechanism for Multi-Tenancy SaaS Service Based on Kalman Filtering

Online veröffentlicht: 05 Oct 2015
Seitenbereich: 150 - 164

Zusammenfassung

Abstract

This paper proposes a special System Architecture for Multi-tenancy SaaS Service (SAMSS), which studies the performance security issues at the business logic layer and data processing layer respectively. The Kalman filtering Admission Control algorithm (KAC) and the Greedy Copy Management algorithm (GCM) are proposed. At the business logic layer, Kalman filtering admission control algorithm is presented. It uses a Kalman filter to conduct the dynamic evaluation for the CPU resource for multi-tenancy SaaS service and reduces the unnecessary performance expenses caused by direct measurement of CPU resources. At the data processing layer, the Greedy Copy Management algorithm (GCM) is presented. It changes the copy placement as a K-partitioning set partitioning problem and adopts a greedy strategy to reduce the number of times for creating a data copy. Finally, the experimental analysis and results prove the feasibility and efficiency of the algorithms proposed.

Schlüsselwörter

  • Kalman filtering
  • business logic layer
  • data processing layer
  • multi-tenancy
  • SaaS
Uneingeschränkter Zugang

Solving Multicriteria Optimization Problems with WebOptim Software System

Online veröffentlicht: 05 Oct 2015
Seitenbereich: 165 - 177

Zusammenfassung

Abstract

This paper is a presentation of a web based decision support system “WebOptim” for solving single and multiple criteria optimization problems. It targets a wide range of user typeseducators, researchers, managers and business people. It also provides two types of communication interfaces user friendly graphical interface for human interaction and programming interface for machine communication with other third party software systems. The interfaces facilitate the problem solving process of different types of optimization problems, mainly single and multi-objective programming optimization problems with continuous or integer variables.

Schlüsselwörter

  • Multiple criteria optimization
  • web-based decision support system

Planen Sie Ihre Fernkonferenz mit Scienceendo