Quantum cellular automata (QCA) is an alternative promising nanotechnology for semiconductor transistor based technology. QCA benefits from several characteristics, including high speed and low power usage, and could be employed in extremely dense structures. One of the important issues in arithmetic circuits is design of full subtractor/ full adder (FS/ FA), respectively. This paper proposed a 1-bit FS/ FA circuit on the basis of QCA technology that benefits from less cell counts compared to the best peer designs studied in the literature. As well as the mentioned feature, temperature analysis of suggested circuit indications that the presented design is tougher than previous works.
{"title":"A Novel Full Subtractor /Full Adder Design in Quantum Cellular Automata","authors":"M. Sadeghi, K. Navi, M. Dolatshahi","doi":"10.52547/MJEE.15.1.33","DOIUrl":"https://doi.org/10.52547/MJEE.15.1.33","url":null,"abstract":"Quantum cellular automata (QCA) is an alternative promising nanotechnology for semiconductor transistor based technology. QCA benefits from several characteristics, including high speed and low power usage, and could be employed in extremely dense structures. One of the important issues in arithmetic circuits is design of full subtractor/ full adder (FS/ FA), respectively. This paper proposed a 1-bit FS/ FA circuit on the basis of QCA technology that benefits from less cell counts compared to the best peer designs studied in the literature. As well as the mentioned feature, temperature analysis of suggested circuit indications that the presented design is tougher than previous works.","PeriodicalId":37804,"journal":{"name":"Majlesi Journal of Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48050342","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As a real time process, in tuning the coefficients of PID controllers in AVRs, accuracy vs. speed is an important issue. Considering complexity of the problem and real systems requirements, various methods, including exact methods and approximation algorithms, have been implemented for this purpose. Since the conventional methods based on meta-heuristic algorithms solving this problem, generally use population-based algorithms such as GA and PSO, this paper aims to investigate the efficiency and performance of single- solution based metaheuristics to solve this problem. So Simulated Annealing (SA) algorithm is proposed, and implemented for optimizing PID coefficients. In addition, an extension of SA is presented improving the search strategy based on neighborhood adjustment. The results indicate that the proposed algorithms as single based metaheuristics, have a good or even better performance vs. population based metaheuristics, in spite of simplicity in implementation and less computation requirements. This fact implies that the landscape complexity of these problems does not necessarily require population-based algorithms. The presented method is also applied to multiple objective functions regarding different time response criteria in output voltage and leads to better results in less time.
{"title":"Tuning of PID Controller Coefficients for AVR Systems by SA Algorithm","authors":"Maryam Ehsani, Morassae Shafiezad","doi":"10.52547/MJEE.15.1.25","DOIUrl":"https://doi.org/10.52547/MJEE.15.1.25","url":null,"abstract":"As a real time process, in tuning the coefficients of PID controllers in AVRs, accuracy vs. speed is an important issue. Considering complexity of the problem and real systems requirements, various methods, including exact methods and approximation algorithms, have been implemented for this purpose. Since the conventional methods based on meta-heuristic algorithms solving this problem, generally use population-based algorithms such as GA and PSO, this paper aims to investigate the efficiency and performance of single- solution based metaheuristics to solve this problem. So Simulated Annealing (SA) algorithm is proposed, and implemented for optimizing PID coefficients. In addition, an extension of SA is presented improving the search strategy based on neighborhood adjustment. The results indicate that the proposed algorithms as single based metaheuristics, have a good or even better performance vs. population based metaheuristics, in spite of simplicity in implementation and less computation requirements. This fact implies that the landscape complexity of these problems does not necessarily require population-based algorithms. The presented method is also applied to multiple objective functions regarding different time response criteria in output voltage and leads to better results in less time.","PeriodicalId":37804,"journal":{"name":"Majlesi Journal of Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46288741","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Afsaneh Banitalebi Dehkordi, M. Soltanaghaei, F. Z. Boroujeni
DDoS (Distributed Denial-of-Service) attacks are among the cyberattacks that are increasing day by day and have caused problems for computer network servers. With the advent of SDN networks, they are not immune to these attacks, and due to the software-centric nature of these networks, this type of attack can be much more difficult for them, ignoring effective parameters such as port and Source IP in detecting attacks, providing costly solutions which are effective in increasing CPU load, and low accuracy in detecting attacks are of the problems of previously presented methods in detecting DDoS attacks. Given the importance of this issue,the purpose of this paper is to increase the accuracy of DDoS attack detection using the second order correlation coefficient technique based on ∅-entropy according to source IP and selection of optimal features.To select the best features, by examining the types of feature selection algorithms and search methods, the WrapperSubsetEval feature selection algorithm, the BestFirst search method, and the best effective features were selected. This study was performed on CTU-13 and ISOT datasets and the results were compared with other methods. The accuracy of the detection in this work indicates the high efficiency of the proposed approach compared to other similar methods.
{"title":"A Hybrid Mechanism to Detect DDoS Attacks in Software Defined Networks","authors":"Afsaneh Banitalebi Dehkordi, M. Soltanaghaei, F. Z. Boroujeni","doi":"10.52547/MJEE.15.1.1","DOIUrl":"https://doi.org/10.52547/MJEE.15.1.1","url":null,"abstract":"DDoS (Distributed Denial-of-Service) attacks are among the cyberattacks that are increasing day by day and have caused problems for computer network servers. With the advent of SDN networks, they are not immune to these attacks, and due to the software-centric nature of these networks, this type of attack can be much more difficult for them, ignoring effective parameters such as port and Source IP in detecting attacks, providing costly solutions which are effective in increasing CPU load, and low accuracy in detecting attacks are of the problems of previously presented methods in detecting DDoS attacks. Given the importance of this issue,the purpose of this paper is to increase the accuracy of DDoS attack detection using the second order correlation coefficient technique based on ∅-entropy according to source IP and selection of optimal features.To select the best features, by examining the types of feature selection algorithms and search methods, the WrapperSubsetEval feature selection algorithm, the BestFirst search method, and the best effective features were selected. This study was performed on CTU-13 and ISOT datasets and the results were compared with other methods. The accuracy of the detection in this work indicates the high efficiency of the proposed approach compared to other similar methods.","PeriodicalId":37804,"journal":{"name":"Majlesi Journal of Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46883783","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nowadays Vehicular Ad-Hoc Networks (VANETs) are very popular and significantly used, due to their unique abilities to improve road safety. As a consequence, the security of these networks is of great importance and it has become one of the central topics in scientific and research fields such as information exchange. Sybil attack is one of the challenges for Ad-Hoc networks security. In this paper, a cross-layer approach and fuzzy logic method are used to detect the Sybil attacks. The proposed fuzzy logic method has four inputs form different OSI layers: entry time to the network, a number of neighbors, buffer size and signal to noise ratio. These inputs are imported to several membership functions of the fuzzy logic methods and the simulation results indicate that the proposed solution provides a robust technique in Sybil attack detection.
{"title":"Improvement of Sybil Attack Detection in Vehicular Ad-Hoc Networks Using Cross-layer and Fuzzy Logic","authors":"Mohamadreza Karimi, Rasool Sadeghi","doi":"10.52547/MJEE.15.1.9","DOIUrl":"https://doi.org/10.52547/MJEE.15.1.9","url":null,"abstract":"Nowadays Vehicular Ad-Hoc Networks (VANETs) are very popular and significantly used, due to their unique abilities to improve road safety. As a consequence, the security of these networks is of great importance and it has become one of the central topics in scientific and research fields such as information exchange. Sybil attack is one of the challenges for Ad-Hoc networks security. In this paper, a cross-layer approach and fuzzy logic method are used to detect the Sybil attacks. The proposed fuzzy logic method has four inputs form different OSI layers: entry time to the network, a number of neighbors, buffer size and signal to noise ratio. These inputs are imported to several membership functions of the fuzzy logic methods and the simulation results indicate that the proposed solution provides a robust technique in Sybil attack detection.","PeriodicalId":37804,"journal":{"name":"Majlesi Journal of Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48960368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Vali, Seyed Mohammad Hassan Hosseni, J. Olamaei
Under unbalanced grid condition, in a Doubly-Fed Induction Generator (DFIG), voltage, current, and flux of the stator become asymmetric. Therefore, active-reactive power and torque will be oscillating. In DFIG controlling Rotor Side Converter (RSC) aims to eliminate power and torque oscillations. However, simultaneous elimination of the power and torque oscillations is not possible. Also, Grid Side Converter (GSC) aims to regulate DC-Link voltage. In this paper, in order to regulate DC-Link voltage, an Extended State Observer (ESO) based on a Generalized Proportional-Integral (GPI) controller, is employed. In this controlling method, DC-Link voltage is controlled without measuring the GSC current, and due to using the GPI controller, the improved dynamic response is resistant against voltage changes, and the settling time is reduced. To improve the transient stability and Low Voltage Fault Ride Through (LVRT) capability of DFIG, Statistic Fault Current Limiter (S-FCL) and Magnetic Energy Storage Fault Current Limiter (MES-FCL) are proposed in this paper. The proposed FCL does not only limit the fault current but also fasten voltage recovery. The simulations are implemented by MATLAB software in the synchronous positive and negative sequence reference (d-q).
{"title":"Improved Low Voltage Ride-Through Capability of DFIG with ESO Controller under Unbalanced Network Conditions","authors":"A. Vali, Seyed Mohammad Hassan Hosseni, J. Olamaei","doi":"10.52547/MJEE.15.1.53","DOIUrl":"https://doi.org/10.52547/MJEE.15.1.53","url":null,"abstract":"Under unbalanced grid condition, in a Doubly-Fed Induction Generator (DFIG), voltage, current, and flux of the stator become asymmetric. Therefore, active-reactive power and torque will be oscillating. In DFIG controlling Rotor Side Converter (RSC) aims to eliminate power and torque oscillations. However, simultaneous elimination of the power and torque oscillations is not possible. Also, Grid Side Converter (GSC) aims to regulate DC-Link voltage. In this paper, in order to regulate DC-Link voltage, an Extended State Observer (ESO) based on a Generalized Proportional-Integral (GPI) controller, is employed. In this controlling method, DC-Link voltage is controlled without measuring the GSC current, and due to using the GPI controller, the improved dynamic response is resistant against voltage changes, and the settling time is reduced. To improve the transient stability and Low Voltage Fault Ride Through (LVRT) capability of DFIG, Statistic Fault Current Limiter (S-FCL) and Magnetic Energy Storage Fault Current Limiter (MES-FCL) are proposed in this paper. The proposed FCL does not only limit the fault current but also fasten voltage recovery. The simulations are implemented by MATLAB software in the synchronous positive and negative sequence reference (d-q).","PeriodicalId":37804,"journal":{"name":"Majlesi Journal of Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48206733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
G. Manikanta, Ashish Mani, H. P. Singh, D. Chaturvedi
Distribution system supplies power to variety of load depending upon the consumer’s demand, which is increasing day by day and lead to high power losses and poor voltage regulation. The increase in demand can be met by integrating Distributed Generators (DG) into the distribution system. Optimal location and capacity of DG plays an important role in distribution network to minimize the power losses. Some researchers have studied this important optimization problem with constant power load which is independent of voltage. However, majority of consumers at load center uses voltage dependent load models, which are primarily dependent on magnitude of supply voltage. In practical distribution network, the assumption of constant power load can significantly affect the location and size of DG, which in turn can lead to higher power losses and poor voltage regulation. In this study, an investigation has been performed to find the increase in power loss due to the use of inappropriate load models, while solving the optimization problem. Furthermore, an attempt has been made in this study to reduce power losses occurring in large test bus systems with loads being dependent on voltage rather than the constant power load. Different test cases are created to analyse the power losses with appropriate load model and in-appropriate load model (constant power load model). The load at distribution network is not mainly dependent on any single type of load model, it is a combination of all load models. In this study, a class of mix load viz., combination of residential, industrial, constant power, and commercial load, is also considered. In order to solve this critical combinatorial optimization problem with voltage dependent load model, which requires an extensive search, Adaptive Quantum inspired Evolutionary Algorithm (AQiEA) is used. The proposed algorithm uses entanglement and superposition principles, which does not require an operator to avoid premature convergence and tuning parameters for improving the convergence rate. A Quantum Rotation inspired Adaptive Crossover operator has been used as a variation operator for a better convergence. The effectiveness of AQiEA is demonstrated and computer simulations are carried out on two standard benchmark large test bus systems viz., 85 bus system and 118 bus system. In addition to AQiEA, four other algorithms (Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Gravitational Search Algorithm (GSA), Grey Wolf Optimization (GWO), and Ecogeography-based Optimization (EBO) with Classification based on Multiple Association Rules (CMAR)) have also been employed for comparison. Tabulated results show that the location and size of DGs determined using in-appropriate load model (constant power load model) has significantly high power losses when applied in distribution system with different load model (other voltage dependent load models) as compared with the location and size of DGs determined using the appropriate
{"title":"Effect of Voltage Dependent Load Model on Placement and Sizing of Distributed Generator in Large Scale Distribution System","authors":"G. Manikanta, Ashish Mani, H. P. Singh, D. Chaturvedi","doi":"10.29252/MJEE.14.4.97","DOIUrl":"https://doi.org/10.29252/MJEE.14.4.97","url":null,"abstract":"Distribution system supplies power to variety of load depending upon the consumer’s demand, which is increasing day by day and lead to high power losses and poor voltage regulation. The increase in demand can be met by integrating Distributed Generators (DG) into the distribution system. Optimal location and capacity of DG plays an important role in distribution network to minimize the power losses. Some researchers have studied this important optimization problem with constant power load which is independent of voltage. However, majority of consumers at load center uses voltage dependent load models, which are primarily dependent on magnitude of supply voltage. In practical distribution network, the assumption of constant power load can significantly affect the location and size of DG, which in turn can lead to higher power losses and poor voltage regulation. In this study, an investigation has been performed to find the increase in power loss due to the use of inappropriate load models, while solving the optimization problem. Furthermore, an attempt has been made in this study to reduce power losses occurring in large test bus systems with loads being dependent on voltage rather than the constant power load. Different test cases are created to analyse the power losses with appropriate load model and in-appropriate load model (constant power load model). The load at distribution network is not mainly dependent on any single type of load model, it is a combination of all load models. In this study, a class of mix load viz., combination of residential, industrial, constant power, and commercial load, is also considered. In order to solve this critical combinatorial optimization problem with voltage dependent load model, which requires an extensive search, Adaptive Quantum inspired Evolutionary Algorithm (AQiEA) is used. The proposed algorithm uses entanglement and superposition principles, which does not require an operator to avoid premature convergence and tuning parameters for improving the convergence rate. A Quantum Rotation inspired Adaptive Crossover operator has been used as a variation operator for a better convergence. The effectiveness of AQiEA is demonstrated and computer simulations are carried out on two standard benchmark large test bus systems viz., 85 bus system and 118 bus system. In addition to AQiEA, four other algorithms (Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Gravitational Search Algorithm (GSA), Grey Wolf Optimization (GWO), and Ecogeography-based Optimization (EBO) with Classification based on Multiple Association Rules (CMAR)) have also been employed for comparison. Tabulated results show that the location and size of DGs determined using in-appropriate load model (constant power load model) has significantly high power losses when applied in distribution system with different load model (other voltage dependent load models) as compared with the location and size of DGs determined using the appropriate","PeriodicalId":37804,"journal":{"name":"Majlesi Journal of Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45690013","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Emotion speech recognition (SER) is to study the formation and change of speaker’s emotional state from his/her speech signal. The main purpose of this field is to produce a convenient system that is able to effortlessly communicate and interact with humans. The reliability of the current speech emotion recognition systems is far from being achieved. However, this is a challenging task due to the gap between acoustic features and human emotions, which rely strongly on the discriminative acoustic features extracted for a given recognition task. Deep Learning techniques have been recently proposed as an alternative to traditional techniques in SER. In this paper, an overview of Deep Learning techniques that could be used in Emotional Speech recognition is presented. Different extracted features like MFCC as well as feature classifications methods like HMM, GMM, LTSTM and ANN were discussion. Also, the review covers databases used, emotions extracted, contributions made toward speech emotion recognition
{"title":"Emotional Speech Recognition using Deep Learning","authors":"Othman Omran Khalifa, M. Alhamada, A. Abdalla","doi":"10.29252/MJEE.14.4.39","DOIUrl":"https://doi.org/10.29252/MJEE.14.4.39","url":null,"abstract":"Emotion speech recognition (SER) is to study the formation and change of speaker’s emotional state from his/her speech signal. The main purpose of this field is to produce a convenient system that is able to effortlessly communicate and interact with humans. The reliability of the current speech emotion recognition systems is far from being achieved. However, this is a challenging task due to the gap between acoustic features and human emotions, which rely strongly on the discriminative acoustic features extracted for a given recognition task. Deep Learning techniques have been recently proposed as an alternative to traditional techniques in SER. In this paper, an overview of Deep Learning techniques that could be used in Emotional Speech recognition is presented. Different extracted features like MFCC as well as feature classifications methods like HMM, GMM, LTSTM and ANN were discussion. Also, the review covers databases used, emotions extracted, contributions made toward speech emotion recognition","PeriodicalId":37804,"journal":{"name":"Majlesi Journal of Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43855631","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Optical Coherence Tomography (OCT) imaging technique has emerged as a non- or minimally invasive modality in the clinical pathogenesis such as deep tissue examining and optical biopsy etc. The OCT imaging increases the Depth of Focus (DoF) by devising mechanisms to increase an Optical Transfer Function (OTF) of the imaging system. This is achieved through an apodization technique on the surface of lens in conjugation with the femtosecond Bessel-type laser beam. An investigation on postulation of OTF through a masked aperture, or specifically a micro-dot is investigated to measure variations of intensity profile at the optical coordinates in the radial as well as axial directions. The intensity variations in the radial and axial coordinates are calibrated to obtain the information, which significantly helps in devising of OCT imaging system. A theoretical investigation of OTF matching the experimental relationship between spot size and DoF in response to obscuration ratio is presented in this paper. This mathematical approach could be applied to different types of masking functions by meticulously exploring the parameters of optical coordinates.
{"title":"Optical Signal Transmission through Masked Aperture to Extend the Depth of Focus in Optical Coherence Tomography","authors":"P. K. Tiwari, K. P. Parmar, S. Pandey","doi":"10.29252/MJEE.14.4.93","DOIUrl":"https://doi.org/10.29252/MJEE.14.4.93","url":null,"abstract":"Optical Coherence Tomography (OCT) imaging technique has emerged as a non- or minimally invasive modality in the clinical pathogenesis such as deep tissue examining and optical biopsy etc. The OCT imaging increases the Depth of Focus (DoF) by devising mechanisms to increase an Optical Transfer Function (OTF) of the imaging system. This is achieved through an apodization technique on the surface of lens in conjugation with the femtosecond Bessel-type laser beam. An investigation on postulation of OTF through a masked aperture, or specifically a micro-dot is investigated to measure variations of intensity profile at the optical coordinates in the radial as well as axial directions. The intensity variations in the radial and axial coordinates are calibrated to obtain the information, which significantly helps in devising of OCT imaging system. A theoretical investigation of OTF matching the experimental relationship between spot size and DoF in response to obscuration ratio is presented in this paper. This mathematical approach could be applied to different types of masking functions by meticulously exploring the parameters of optical coordinates.","PeriodicalId":37804,"journal":{"name":"Majlesi Journal of Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45364438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Surveillance and security cameras help security forces in public places such as airports, railway stations, universities and office buildings to perform high-level surveillance tasks such as detecting suspicious activity or anticipating undesirable events. Re-Identification (Re-ID) is defined as the process of communicating between images of the person in different cameras in a surveillance environment. Changing the field of view of any camera presents challenges such as changing body posture, changing brightness, noise and blockage. This article focuses on extracting the most distinctive features to overcome these challenges. The features of Hu moment, Zernike moment in 9th order and Legendre moment in 9th order for each image are extracted and merged into a single feature vector to form a single feature vector for each image. Principal Component Analysis (PCA) was used to reduce the vector dimensionality and finally the Mahalanobis distance criterion was used for identification. The proposed method in the VIPeR database has achieved a re-ID rate of 96.5. Although the presented method is simple, the outcome has been superior compared to many of the state-of-the-art methods.
{"title":"Improving Person Re-Identification Rate in Security Cameras by Orthogonal Moments and a Distance-based Criterion","authors":"A. Dadkhah, Saeed Nasri","doi":"10.29252/MJEE.14.4.85","DOIUrl":"https://doi.org/10.29252/MJEE.14.4.85","url":null,"abstract":"Surveillance and security cameras help security forces in public places such as airports, railway stations, universities and office buildings to perform high-level surveillance tasks such as detecting suspicious activity or anticipating undesirable events. Re-Identification (Re-ID) is defined as the process of communicating between images of the person in different cameras in a surveillance environment. Changing the field of view of any camera presents challenges such as changing body posture, changing brightness, noise and blockage. This article focuses on extracting the most distinctive features to overcome these challenges. The features of Hu moment, Zernike moment in 9th order and Legendre moment in 9th order for each image are extracted and merged into a single feature vector to form a single feature vector for each image. Principal Component Analysis (PCA) was used to reduce the vector dimensionality and finally the Mahalanobis distance criterion was used for identification. The proposed method in the VIPeR database has achieved a re-ID rate of 96.5. Although the presented method is simple, the outcome has been superior compared to many of the state-of-the-art methods.","PeriodicalId":37804,"journal":{"name":"Majlesi Journal of Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48381525","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sleep is a normal state in humans and the subconscious level of brain activity increases during sleep. The brain plays a prominent role during sleep, so a variety of mental and brain-related diseases can be identified through sleep analysis. A complete sleep period according to the two world standards R&K and AASM consists of seven and five steps, respectively. To diagnose diseases through sleep, it is necessary to identify different stages of sleep because the disorder at each stage indicates a certain disease. On the other hand, efficient and useful features should be selected to increase the accuracy of sleep stage classification. In this paper, at first, different statistical, entropy, and chaotic features are extracted from sleep data. Afterwards, by introducing and using the Laplacian score selector, the best feature set is selected. At the end, some conventional classification algorithms such as SVM, ANN and KNN are used to classify different sleep stages. Simulation results confirms the superiority of the proposed method based on the classification results. With the proposed algorithm, 2, 3, 4, 5 and 6 stages of sleep were classified by SVM and decision tree with 98.0%, 98.0%, 97.3%, 96.6%, and 95.0% accuracy, which are more superior to previous method’s results.
{"title":"Sleep Stage Classification using Laplacian Score Feature Selection Method by Single Channel EEG","authors":"Mahtab Vaezi, M. Nasri","doi":"10.29252/MJEE.14.4.11","DOIUrl":"https://doi.org/10.29252/MJEE.14.4.11","url":null,"abstract":"Sleep is a normal state in humans and the subconscious level of brain activity increases during sleep. The brain plays a prominent role during sleep, so a variety of mental and brain-related diseases can be identified through sleep analysis. A complete sleep period according to the two world standards R&K and AASM consists of seven and five steps, respectively. To diagnose diseases through sleep, it is necessary to identify different stages of sleep because the disorder at each stage indicates a certain disease. On the other hand, efficient and useful features should be selected to increase the accuracy of sleep stage classification. In this paper, at first, different statistical, entropy, and chaotic features are extracted from sleep data. Afterwards, by introducing and using the Laplacian score selector, the best feature set is selected. At the end, some conventional classification algorithms such as SVM, ANN and KNN are used to classify different sleep stages. Simulation results confirms the superiority of the proposed method based on the classification results. With the proposed algorithm, 2, 3, 4, 5 and 6 stages of sleep were classified by SVM and decision tree with 98.0%, 98.0%, 97.3%, 96.6%, and 95.0% accuracy, which are more superior to previous method’s results.","PeriodicalId":37804,"journal":{"name":"Majlesi Journal of Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44242292","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：