Pub Date : 2021-12-29DOI: 10.1109/ICSPIS54653.2021.9729384
K. A. Vakilian
Accurate and reliable determination of foodborne pathogens (FBPs) is necessary for food safety. Spectroscopic methods such as FT-IR and Raman spectroscopy are among the label-free and sensitive methods for diagnosing FBPs. Although Raman spectroscopy equipped with confocal microscopy is developed for multiplex detection of FBPs, machine learning methods optimized by advanced optimization algorithms can be useful for the efficient determination of FBPs in food. In this study, genetic algorithm (GA) and particle swarm optimization (PSO) were used to optimize the architecture of artificial neural networks (ANNs) to predict the type of FBPs based on their Raman data. Raman spectra of single cells of 12 common strains from five genera were obtained to create a dataset. The results showed that the average accuracy of GA-ANN and PSO-ANN hybrid models was 0.89 and 0.93, respectively. Moreover, ATCC 14028 and ATCC 19112, the strains of Shigella and Listeria bacteria, were predicted with the highest performance (0.96) based on the Raman spectra of their corresponding cells. The method presented in this study included Raman spectroscopy combined with neuron-based machine learning methods for the FBP efficient diagnosis.
{"title":"Metaheuristic Optimization to Improve Machine Learning in Raman Spectroscopic-based Detection of Foodborne Pathogens","authors":"K. A. Vakilian","doi":"10.1109/ICSPIS54653.2021.9729384","DOIUrl":"https://doi.org/10.1109/ICSPIS54653.2021.9729384","url":null,"abstract":"Accurate and reliable determination of foodborne pathogens (FBPs) is necessary for food safety. Spectroscopic methods such as FT-IR and Raman spectroscopy are among the label-free and sensitive methods for diagnosing FBPs. Although Raman spectroscopy equipped with confocal microscopy is developed for multiplex detection of FBPs, machine learning methods optimized by advanced optimization algorithms can be useful for the efficient determination of FBPs in food. In this study, genetic algorithm (GA) and particle swarm optimization (PSO) were used to optimize the architecture of artificial neural networks (ANNs) to predict the type of FBPs based on their Raman data. Raman spectra of single cells of 12 common strains from five genera were obtained to create a dataset. The results showed that the average accuracy of GA-ANN and PSO-ANN hybrid models was 0.89 and 0.93, respectively. Moreover, ATCC 14028 and ATCC 19112, the strains of Shigella and Listeria bacteria, were predicted with the highest performance (0.96) based on the Raman spectra of their corresponding cells. The method presented in this study included Raman spectroscopy combined with neuron-based machine learning methods for the FBP efficient diagnosis.","PeriodicalId":286966,"journal":{"name":"2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129090412","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}
Pub Date : 2021-12-29DOI: 10.1109/ICSPIS54653.2021.9729363
Mohammad Hassan Ahmad Yarandi, Mahdi Amani Tehrani, S. H. Sardouie
According to WHO 2019 announcement, around 50 million people are suffering from epilepsy worldwide. As epilepsy causes some seizures in the brain, seizure detection can play an essential role in treating patients. In this paper, we concentrated on different graph-based methods intending to classify seizure and non-seizure states of the brain based on recorded EEG signals. We worked on Temple University Hospital (TUH) dataset which includes both focal and generalized seizures. Our goal was to reach a comprehensive comparison between these methods. Three methods were discussed: graph features, graph kernels, and graph multi-kernels. We considered each EEG channel as a node in the graph model. Also, graph edges were built through functional connectivity between every two nodes' signals. Therefore, we constructed one graph for each second of every patients' recorded EEG. Then, by using constructed graphs, we extracted some features from them, or calculated kernel matrix for each couple of them which reflects the similarity between graphs. In the multi-kernel method, these two approaches gathered together. After comparing the outcomes, we found kernel and multi-kernel methods more effective on this dataset. The best result is attained by multi-kernel method which has an accuracy of 72.1 % and a sensitivity of 71.9%.
{"title":"Automatic Epileptic Seizure Detection: Graph F eatures Versus Graph Kernels","authors":"Mohammad Hassan Ahmad Yarandi, Mahdi Amani Tehrani, S. H. Sardouie","doi":"10.1109/ICSPIS54653.2021.9729363","DOIUrl":"https://doi.org/10.1109/ICSPIS54653.2021.9729363","url":null,"abstract":"According to WHO 2019 announcement, around 50 million people are suffering from epilepsy worldwide. As epilepsy causes some seizures in the brain, seizure detection can play an essential role in treating patients. In this paper, we concentrated on different graph-based methods intending to classify seizure and non-seizure states of the brain based on recorded EEG signals. We worked on Temple University Hospital (TUH) dataset which includes both focal and generalized seizures. Our goal was to reach a comprehensive comparison between these methods. Three methods were discussed: graph features, graph kernels, and graph multi-kernels. We considered each EEG channel as a node in the graph model. Also, graph edges were built through functional connectivity between every two nodes' signals. Therefore, we constructed one graph for each second of every patients' recorded EEG. Then, by using constructed graphs, we extracted some features from them, or calculated kernel matrix for each couple of them which reflects the similarity between graphs. In the multi-kernel method, these two approaches gathered together. After comparing the outcomes, we found kernel and multi-kernel methods more effective on this dataset. The best result is attained by multi-kernel method which has an accuracy of 72.1 % and a sensitivity of 71.9%.","PeriodicalId":286966,"journal":{"name":"2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132873064","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}
Pub Date : 2021-12-29DOI: 10.1109/ICSPIS54653.2021.9729375
Ali Abdari, H. Mohammadzade, Seyed Ali Hashemian
Adding functional analysis to the videos captured by surveillance cameras can provide handy information to their users. Mining the existing trajectories in a video is one of the most valuable features, discovering the prevalent patterns and their density in the video, and it helps reveal some unusual and abnormal movements more easily. In this paper, the data obtained through the execution of detection and tracking algorithms are processed in various steps and used to train a hierarchical clustering model by deploying a modified version of the DTW algorithm. This practical approach does not need massive datasets for the training procedure and can be applied to any surveillance video containing different types of objects. The proposed method utilizes information extracted from the objects in a video to generate the existing primary trajectories. Additionally, a practical algorithm for modeling the background in surveillance movies is proposed to illustrate clustering outputs.
{"title":"Trajectory Clustering in Surveillance Videos Using Dynamic Time Warping","authors":"Ali Abdari, H. Mohammadzade, Seyed Ali Hashemian","doi":"10.1109/ICSPIS54653.2021.9729375","DOIUrl":"https://doi.org/10.1109/ICSPIS54653.2021.9729375","url":null,"abstract":"Adding functional analysis to the videos captured by surveillance cameras can provide handy information to their users. Mining the existing trajectories in a video is one of the most valuable features, discovering the prevalent patterns and their density in the video, and it helps reveal some unusual and abnormal movements more easily. In this paper, the data obtained through the execution of detection and tracking algorithms are processed in various steps and used to train a hierarchical clustering model by deploying a modified version of the DTW algorithm. This practical approach does not need massive datasets for the training procedure and can be applied to any surveillance video containing different types of objects. The proposed method utilizes information extracted from the objects in a video to generate the existing primary trajectories. Additionally, a practical algorithm for modeling the background in surveillance movies is proposed to illustrate clustering outputs.","PeriodicalId":286966,"journal":{"name":"2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130236430","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}
Pub Date : 2021-12-29DOI: 10.1109/ICSPIS54653.2021.9729358
Parisa Kavianpour, M. Kavianpour, E. Jahani, Amin Ramezani
Earthquakes are a very catastrophic natural event that occurs due to sudden changes in the earth's crust, leading to human, financial, and environmental losses in society. Therefore, employing an efficient and dependable method for earthquake prediction can significantly reduce casualties. In this regard, we proposed a deep neural network called the hybrid convolutional neural network and bi-directional long-short-term memory (HC-BiLSTM) to predict the mean magnitude of the future earthquake in a specific area of Japan. To achieve this goal, we suggest a strategy based on four key steps: the division of areas, the preprocessing, the spatial and temporal feature learning, and the prediction. In the division of areas step, The part of Japan is divided into 49 smaller areas to better predict the next earthquake's location. The preprocessing step uses the zero-order hold method in the time series of the mean magnitude of the earthquake. In the next step, the learning spatial and temporal characteristics between earthquake data include three layers of CNN and pooling and two layers of LSTM. Finally, the prediction step has two fully connected layers that combine information supplied by HC-BiLSTMs to predict the mean magnitude for the earthquake next month. As a result, using a comparative method, this study demonstrates the superiority of the proposed method over other common earthquake prediction methods.
{"title":"Earthquake Magnitude Prediction using Spatia-temporal Features Learning Based on Hybrid CNN- BiLSTM Model","authors":"Parisa Kavianpour, M. Kavianpour, E. Jahani, Amin Ramezani","doi":"10.1109/ICSPIS54653.2021.9729358","DOIUrl":"https://doi.org/10.1109/ICSPIS54653.2021.9729358","url":null,"abstract":"Earthquakes are a very catastrophic natural event that occurs due to sudden changes in the earth's crust, leading to human, financial, and environmental losses in society. Therefore, employing an efficient and dependable method for earthquake prediction can significantly reduce casualties. In this regard, we proposed a deep neural network called the hybrid convolutional neural network and bi-directional long-short-term memory (HC-BiLSTM) to predict the mean magnitude of the future earthquake in a specific area of Japan. To achieve this goal, we suggest a strategy based on four key steps: the division of areas, the preprocessing, the spatial and temporal feature learning, and the prediction. In the division of areas step, The part of Japan is divided into 49 smaller areas to better predict the next earthquake's location. The preprocessing step uses the zero-order hold method in the time series of the mean magnitude of the earthquake. In the next step, the learning spatial and temporal characteristics between earthquake data include three layers of CNN and pooling and two layers of LSTM. Finally, the prediction step has two fully connected layers that combine information supplied by HC-BiLSTMs to predict the mean magnitude for the earthquake next month. As a result, using a comparative method, this study demonstrates the superiority of the proposed method over other common earthquake prediction methods.","PeriodicalId":286966,"journal":{"name":"2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126340796","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}
Pub Date : 2021-12-29DOI: 10.1109/ICSPIS54653.2021.9729347
Nazila Razzaghi-Asl, J. Tanha, Mehdi Nabatian, Negin Samadi
Increased penetration of distributed energy resources (DERs) in smart grids (SG) has sparked a new movement to consumer-centric structure as marketplaces based on peer-to-peer (P2P) models. Participants can directly agree bilateral power transactions in P2P markets to balance producers and consumers. The trading mechanism should be well-designed to encourage participants to operate actively in the trading activity. This article proposes a trading strategy for P2P strategy in SG. The proposed framework is modeled using the Whale optimization algorithm (WOA). In order to evaluate the proposed optimization method, particle swarm optimization (PSO) and classical optimization methods are carried out. The compared results show that the convergency of proposed method is faster than PSO algorithm.
{"title":"Smart Grid based decentralized Peer-to-Peer Energy Trading Using Whale Optimization Algorithm","authors":"Nazila Razzaghi-Asl, J. Tanha, Mehdi Nabatian, Negin Samadi","doi":"10.1109/ICSPIS54653.2021.9729347","DOIUrl":"https://doi.org/10.1109/ICSPIS54653.2021.9729347","url":null,"abstract":"Increased penetration of distributed energy resources (DERs) in smart grids (SG) has sparked a new movement to consumer-centric structure as marketplaces based on peer-to-peer (P2P) models. Participants can directly agree bilateral power transactions in P2P markets to balance producers and consumers. The trading mechanism should be well-designed to encourage participants to operate actively in the trading activity. This article proposes a trading strategy for P2P strategy in SG. The proposed framework is modeled using the Whale optimization algorithm (WOA). In order to evaluate the proposed optimization method, particle swarm optimization (PSO) and classical optimization methods are carried out. The compared results show that the convergency of proposed method is faster than PSO algorithm.","PeriodicalId":286966,"journal":{"name":"2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121800241","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}
Pub Date : 2021-12-29DOI: 10.1109/ICSPIS54653.2021.9729372
Mostafa Balouchzehi Shahbakhsh, H. Hassanpour
Face super-resolution, known as face hallucination, is a domain-specific image super-resolution problem, which refers to generating high resolution face images from their low resolution. State-of-the-art face super-resolution methods used deep convolutional neural networks. However, due to significant pose changes and difficulty in recovering high-frequency details in facial areas, most of these methods do not deploy facial structures and identity information well, and it is tough for them to reconstruct super-resolved face images. According to previous researches, proper use of low-resolution image edges can be a solution for these problems. EIPNet (Edge and Identity Preserving Network) is one of the newest methods to achieve outstanding results in this area. In the EIPNet method, the authors used a lightweight edge extraction block in the proposed GAN structure. In this research, we intend to improve the performance of the EIPNet method by presenting a simple but efficient technique. Our proposed technique divides the face images into upper and lower parts. We train a separate network for each area. This technique reduces the number of face components to train from each area, and the networks can better be trained from their components. The results show that this technique can have an excellent effect on visual quality and quantitative measurements in face super-resolution.
{"title":"Enhancing Face Super-Resolution via Improving the Edge and Identity Preserving Network","authors":"Mostafa Balouchzehi Shahbakhsh, H. Hassanpour","doi":"10.1109/ICSPIS54653.2021.9729372","DOIUrl":"https://doi.org/10.1109/ICSPIS54653.2021.9729372","url":null,"abstract":"Face super-resolution, known as face hallucination, is a domain-specific image super-resolution problem, which refers to generating high resolution face images from their low resolution. State-of-the-art face super-resolution methods used deep convolutional neural networks. However, due to significant pose changes and difficulty in recovering high-frequency details in facial areas, most of these methods do not deploy facial structures and identity information well, and it is tough for them to reconstruct super-resolved face images. According to previous researches, proper use of low-resolution image edges can be a solution for these problems. EIPNet (Edge and Identity Preserving Network) is one of the newest methods to achieve outstanding results in this area. In the EIPNet method, the authors used a lightweight edge extraction block in the proposed GAN structure. In this research, we intend to improve the performance of the EIPNet method by presenting a simple but efficient technique. Our proposed technique divides the face images into upper and lower parts. We train a separate network for each area. This technique reduces the number of face components to train from each area, and the networks can better be trained from their components. The results show that this technique can have an excellent effect on visual quality and quantitative measurements in face super-resolution.","PeriodicalId":286966,"journal":{"name":"2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134272073","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}
Pub Date : 2021-12-29DOI: 10.1109/ICSPIS54653.2021.9729348
Nayereh Ghazi, H. Soltanian-Zadeh
Transcranial magnetic stimulation (TMS) is increasingly used in basic as well as clinical research. Intermittent theta burst stimulation (iTBS) with high stimulation intensities are typically applied on frontal cortex as therapy for the modulation of functional connectivity of brain in patients with mood disorders. However, there are not yet sufficient understanding of the impacts of this technique on brain neuronal activities. In this study, we aimed to investigate the network reorganization following the offline application of iTBS to prefrontal cortex at two different intensities. The network architecture was analyzed using resting state functional magnetic resonance imaging as well as graph theory analysis. Results show that the offline iTBS, applied to just one node of the brain network, changes the whole organization of the network. Furthermore, the reorganization followed by the stimulation is dependent on the intensity of the applied stimulation. Moreover, our research suggests that the network analysis can bring new insights into the mechanism of transcranial magnetic stimulation, and improves our understanding of its local as well as global effects.
{"title":"Transcranial Magnetic Stimulation of Prefrontal Cortex Alters Functional Brain Network Architecture: Graph Theoretical Analysis","authors":"Nayereh Ghazi, H. Soltanian-Zadeh","doi":"10.1109/ICSPIS54653.2021.9729348","DOIUrl":"https://doi.org/10.1109/ICSPIS54653.2021.9729348","url":null,"abstract":"Transcranial magnetic stimulation (TMS) is increasingly used in basic as well as clinical research. Intermittent theta burst stimulation (iTBS) with high stimulation intensities are typically applied on frontal cortex as therapy for the modulation of functional connectivity of brain in patients with mood disorders. However, there are not yet sufficient understanding of the impacts of this technique on brain neuronal activities. In this study, we aimed to investigate the network reorganization following the offline application of iTBS to prefrontal cortex at two different intensities. The network architecture was analyzed using resting state functional magnetic resonance imaging as well as graph theory analysis. Results show that the offline iTBS, applied to just one node of the brain network, changes the whole organization of the network. Furthermore, the reorganization followed by the stimulation is dependent on the intensity of the applied stimulation. Moreover, our research suggests that the network analysis can bring new insights into the mechanism of transcranial magnetic stimulation, and improves our understanding of its local as well as global effects.","PeriodicalId":286966,"journal":{"name":"2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115667070","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}
Pub Date : 2021-12-29DOI: 10.1109/ICSPIS54653.2021.9729367
Behnam Gholami, Mohammad Hossein Behboudi, M. G. Mahjani, Ali Khadem
Sleep apnea is the most popular sleep disorders which may lead to physical and mental problems. A quick and accurate diagnosis helps physicians to make a suitable remedy for it. Electroencephalogram (EEG) is the electrical activity recorded from the surface of the skull. The identity of EEG is non-linear and complex, thus the study of complexity of EEG signal can be helpful to access valuable information from it. In this paper, 12 entropies (Shannon, Renyi, Tsallis, threshold, permutation, spectral, wavelet, SURE, norm, log energy, fuzzy, and sample), complexity features, are extracted from six frequency bands (delta, theta, alpha, sigma, beta, and gamma) in three different EEG channels. Finally, 72 features were applied to detect apneic subjects from normal ones by using support vector machine classifier (SVM), 90% accuracy was obtained in O1-A2 channel with whole features which is an acceptable accuracy in comparison with other works. Also to select the most effective features, the minimum-redundancy maximum-relevance (mRMR) algorithm was used and 89.07% accuracy with 28 selected features was acquired.
{"title":"Diagnosis of Sleep Apnea Syndrome from EEG Signals using Different Entropy measures","authors":"Behnam Gholami, Mohammad Hossein Behboudi, M. G. Mahjani, Ali Khadem","doi":"10.1109/ICSPIS54653.2021.9729367","DOIUrl":"https://doi.org/10.1109/ICSPIS54653.2021.9729367","url":null,"abstract":"Sleep apnea is the most popular sleep disorders which may lead to physical and mental problems. A quick and accurate diagnosis helps physicians to make a suitable remedy for it. Electroencephalogram (EEG) is the electrical activity recorded from the surface of the skull. The identity of EEG is non-linear and complex, thus the study of complexity of EEG signal can be helpful to access valuable information from it. In this paper, 12 entropies (Shannon, Renyi, Tsallis, threshold, permutation, spectral, wavelet, SURE, norm, log energy, fuzzy, and sample), complexity features, are extracted from six frequency bands (delta, theta, alpha, sigma, beta, and gamma) in three different EEG channels. Finally, 72 features were applied to detect apneic subjects from normal ones by using support vector machine classifier (SVM), 90% accuracy was obtained in O1-A2 channel with whole features which is an acceptable accuracy in comparison with other works. Also to select the most effective features, the minimum-redundancy maximum-relevance (mRMR) algorithm was used and 89.07% accuracy with 28 selected features was acquired.","PeriodicalId":286966,"journal":{"name":"2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124838265","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}
Pub Date : 2021-12-29DOI: 10.1109/ICSPIS54653.2021.9729338
Sakineh Pashaee, A. Ramezani, Mina Ekresh, Saeid Jorkesh
The detection and classification of induction motor faults using a one-dimensional convolutional neural network is discussed in this paper. A one-dimensional deep neural network is learned utilizing three-phase current and voltage signals from an induction motor system. The results of experiments show that the one-dimensional deep convolutional neural network method effectively diagnoses the induction motor conditions (Bearing fault, Rotor bar broken, short circuit stator winding 8% and 12.5 %).
{"title":"Fault Diagnosing Of An Induction Motor Based On Signal Fusion Using One-Dimensional Convolutional Neural Network","authors":"Sakineh Pashaee, A. Ramezani, Mina Ekresh, Saeid Jorkesh","doi":"10.1109/ICSPIS54653.2021.9729338","DOIUrl":"https://doi.org/10.1109/ICSPIS54653.2021.9729338","url":null,"abstract":"The detection and classification of induction motor faults using a one-dimensional convolutional neural network is discussed in this paper. A one-dimensional deep neural network is learned utilizing three-phase current and voltage signals from an induction motor system. The results of experiments show that the one-dimensional deep convolutional neural network method effectively diagnoses the induction motor conditions (Bearing fault, Rotor bar broken, short circuit stator winding 8% and 12.5 %).","PeriodicalId":286966,"journal":{"name":"2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130213516","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}
Pub Date : 2021-12-29DOI: 10.1109/ICSPIS54653.2021.9729357
Milad Pazira, Y. Baleghi, Abouzar Akbari
A Hardware Trojan (HT) is a malicious modification of the circuitry of an integrated circuit. The importance of Hardware Trojan detection increases with increase in the complexity of integrated circuits. The possible effects of the insertion of a Hardware Trojan involve a range of harms from leakage of sensitive information to the complete destruction of the integrated circuit itself. Non-invasive methods of Hardware Trojan detection are divided into two general categories: performance testing and side channel analysis. Hardware Trojan detection using thermal imagery is one of the side channel analysis methods which have recently been considered. In this paper, we propose a Hardware Trojan detection method on FPGA, based on thermal image processing of defected and authentic chips assuming that a golden chip is available. We also provide a dataset of thermal images captured from multiple experiments on a certain FPGA board. Each experiment contains 12 images taken in 55 seconds of working FPGA. The Hardware Trojan detection method relies on extracting two different features from images and detecting the presence of a Hardware Trojan using machine learning techniques. Results shows that if proposed method is combined with a basic method, hardware Trojan detection accuracy can be increased, significantly.
{"title":"Hardware Trojan Detection Using Thermal Imaging in FPGAs with Combined Features","authors":"Milad Pazira, Y. Baleghi, Abouzar Akbari","doi":"10.1109/ICSPIS54653.2021.9729357","DOIUrl":"https://doi.org/10.1109/ICSPIS54653.2021.9729357","url":null,"abstract":"A Hardware Trojan (HT) is a malicious modification of the circuitry of an integrated circuit. The importance of Hardware Trojan detection increases with increase in the complexity of integrated circuits. The possible effects of the insertion of a Hardware Trojan involve a range of harms from leakage of sensitive information to the complete destruction of the integrated circuit itself. Non-invasive methods of Hardware Trojan detection are divided into two general categories: performance testing and side channel analysis. Hardware Trojan detection using thermal imagery is one of the side channel analysis methods which have recently been considered. In this paper, we propose a Hardware Trojan detection method on FPGA, based on thermal image processing of defected and authentic chips assuming that a golden chip is available. We also provide a dataset of thermal images captured from multiple experiments on a certain FPGA board. Each experiment contains 12 images taken in 55 seconds of working FPGA. The Hardware Trojan detection method relies on extracting two different features from images and detecting the presence of a Hardware Trojan using machine learning techniques. Results shows that if proposed method is combined with a basic method, hardware Trojan detection accuracy can be increased, significantly.","PeriodicalId":286966,"journal":{"name":"2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121117900","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：