Pub Date : 2019-01-01DOI: 10.1109/ICREST.2019.8644339
M. Fahmida, Md. Samiul Alam, M. Hoque
The main objective of the paper is that it deals with the designing of a Photovoltaic array connected to a Brushless DC (BLDC) motor using an easy and feasible Maximum Power Point Tracking (MPPT) algorithm. At present, Photovoltaic energy is one of the most vital energy resources in electrical power applications around the world. It is essential to operate the Photovoltaic (PV) system at the Maximum Power Point (MPP) so that maximum power can be secured from the solar panel because the output power from the PV arrays is sensitive to temperature changes and solar irradiance. In this paper, the Perturb and Observe (P&O) algorithm, a buck converter and a three phase inverter are used which are modelled in Simulink tool of MATLAB.
{"title":"MATLAB Simscape Simulation of Solar Photovoltaic array fed BLDC Motor using Maximum Power Point Tracker","authors":"M. Fahmida, Md. Samiul Alam, M. Hoque","doi":"10.1109/ICREST.2019.8644339","DOIUrl":"https://doi.org/10.1109/ICREST.2019.8644339","url":null,"abstract":"The main objective of the paper is that it deals with the designing of a Photovoltaic array connected to a Brushless DC (BLDC) motor using an easy and feasible Maximum Power Point Tracking (MPPT) algorithm. At present, Photovoltaic energy is one of the most vital energy resources in electrical power applications around the world. It is essential to operate the Photovoltaic (PV) system at the Maximum Power Point (MPP) so that maximum power can be secured from the solar panel because the output power from the PV arrays is sensitive to temperature changes and solar irradiance. In this paper, the Perturb and Observe (P&O) algorithm, a buck converter and a three phase inverter are used which are modelled in Simulink tool of MATLAB.","PeriodicalId":108842,"journal":{"name":"2019 International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120957649","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 : 2019-01-01DOI: 10.1109/ICREST.2019.8644305
Md. Mehzabul Hoque Nahid, Arnob Zahid, A. Abdullah
Digitalization in agriculture can eliminate many malicious effects in the agricultural industry and reduce uncertainty due to the uncertainty in weather and complex agriculture system. This study designs a PIC based web-service oriented architecture to achieve achieves more flexibility, affordability as well as usability through adapting the Web services and PIC based Sensor integrated with GSM/GPRS based mobile application model to take progressive data of temperature, level of soil moisture, photo taken from the harvest field and renders these data into a web server to produce report for farmers or agriculture experts through android devices. These data are then stored in the web server as per date and time. Besides, the ratio of soil moisture in a specific area is calculated and displayed in a graph in the web page. Moreover, an android application "Smart Agriculture BD" has been constructed to incorporate the field images along with other data in the web server. In order to collect the data for the humidity of soil grove-moisture sensor, a temperature sensor for calculating temperature, android app for retrieving collected images and SIM900A kit (GSM/GPRS module) has been integrated with PIC Microcontroller 16f877A to forward the data to a web server for immediate use. Henceforth, a user can predict the field condition by manipulating the data and take the imperative decision to overcome any detrimental effect on crops due to nature.
{"title":"Digital Moisture Monitoring System Embedded in PIC","authors":"Md. Mehzabul Hoque Nahid, Arnob Zahid, A. Abdullah","doi":"10.1109/ICREST.2019.8644305","DOIUrl":"https://doi.org/10.1109/ICREST.2019.8644305","url":null,"abstract":"Digitalization in agriculture can eliminate many malicious effects in the agricultural industry and reduce uncertainty due to the uncertainty in weather and complex agriculture system. This study designs a PIC based web-service oriented architecture to achieve achieves more flexibility, affordability as well as usability through adapting the Web services and PIC based Sensor integrated with GSM/GPRS based mobile application model to take progressive data of temperature, level of soil moisture, photo taken from the harvest field and renders these data into a web server to produce report for farmers or agriculture experts through android devices. These data are then stored in the web server as per date and time. Besides, the ratio of soil moisture in a specific area is calculated and displayed in a graph in the web page. Moreover, an android application \"Smart Agriculture BD\" has been constructed to incorporate the field images along with other data in the web server. In order to collect the data for the humidity of soil grove-moisture sensor, a temperature sensor for calculating temperature, android app for retrieving collected images and SIM900A kit (GSM/GPRS module) has been integrated with PIC Microcontroller 16f877A to forward the data to a web server for immediate use. Henceforth, a user can predict the field condition by manipulating the data and take the imperative decision to overcome any detrimental effect on crops due to nature.","PeriodicalId":108842,"journal":{"name":"2019 International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST)","volume":"35 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121004002","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 : 2019-01-01DOI: 10.1109/icrest.2019.8644473
{"title":"ICREST 2019 Cover Page","authors":"","doi":"10.1109/icrest.2019.8644473","DOIUrl":"https://doi.org/10.1109/icrest.2019.8644473","url":null,"abstract":"","PeriodicalId":108842,"journal":{"name":"2019 International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131371181","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 : 2019-01-01DOI: 10.1109/ICREST.2019.8644493
Sadia Sultana, R. Basak
A novel structure meander line antenna is investigated in this paper for anatomically realistic human head phantom of implantable Brain Machine Interference (BMI) applications. Head phantoms imitating electrical properties of brain tissues and their anatomical configuration are highly requisited for verification of numerous biomedical devices. To approve the analysis of implantable antennas more accurately, simulation is examined using anatomical realistic human head phantom. The main integrity of this antenna specifies to its subtle dimension, flexibility and subordinate thickness that makes it perfectly applicable for implementing inside human head phantom operating ultra-wideband frequency spectrum. Meander line technique is imposed in implantable scenarios. Dimension of the antenna structure is (15.2 * 8.8 * 0.8) mm3, where Roger RO3035 is selected as the substrate material. Copper is selected for Patch material. And the antenna is encapsulated by silicon material for maintaining biocompatibility. Crucial parameters are analyzed such as S11 parameter, Radiation pattern, VSWR, Gain, Efficiency, Directivity, SAR values of the proposed antenna for anatomical realistic human head phantom. This improved design of MLA configuration reducing Specific absorption rate for safety concerns.
{"title":"Numerical Investigations of Implan Meander Line Antenna of Three-Dimensional Human Head Phantom for Brain Machine Interference","authors":"Sadia Sultana, R. Basak","doi":"10.1109/ICREST.2019.8644493","DOIUrl":"https://doi.org/10.1109/ICREST.2019.8644493","url":null,"abstract":"A novel structure meander line antenna is investigated in this paper for anatomically realistic human head phantom of implantable Brain Machine Interference (BMI) applications. Head phantoms imitating electrical properties of brain tissues and their anatomical configuration are highly requisited for verification of numerous biomedical devices. To approve the analysis of implantable antennas more accurately, simulation is examined using anatomical realistic human head phantom. The main integrity of this antenna specifies to its subtle dimension, flexibility and subordinate thickness that makes it perfectly applicable for implementing inside human head phantom operating ultra-wideband frequency spectrum. Meander line technique is imposed in implantable scenarios. Dimension of the antenna structure is (15.2 * 8.8 * 0.8) mm3, where Roger RO3035 is selected as the substrate material. Copper is selected for Patch material. And the antenna is encapsulated by silicon material for maintaining biocompatibility. Crucial parameters are analyzed such as S11 parameter, Radiation pattern, VSWR, Gain, Efficiency, Directivity, SAR values of the proposed antenna for anatomical realistic human head phantom. This improved design of MLA configuration reducing Specific absorption rate for safety concerns.","PeriodicalId":108842,"journal":{"name":"2019 International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133574883","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 : 2019-01-01DOI: 10.1109/ICREST.2019.8644107
M. Hasan, Md.Rabiul Islam, T. Hossain, Kefayet Ullah, Nafis Farhan Rashid, Silvee Quraishi, P. Ghosh, M. Hossain
This project focused on installing of lightning protection system and its equipment’s. This project was implanted for both shade building and full building with a rooftop. The objective of replacing air-terminal is to catch the strike of lightning and conveyed the current through the down conductor to earth pit. The whole process was followed by BNBC-2006 to make sure a structure or building safe from lightning. As it is essential for factories and industries to take protective action to make ensure the industrial electrical equipment’s, as well as the life of the workers, do work there. To monitor the working process, the Lightning counter device was used to detect how many strikes it caught. The risk assessment of lightning protection system has been done considering 7 index factor (A, B, C, D, E, F, and G), which recommended LPS is essential by calculating total index figure. The diameter of air-terminal was selected as 8 mm and air terminal height was varied 500 mm, 700 mm, 800 mm, 2 meters and 2.5 meters. Therefore, adopting the meshing technology following the BNBC-2006 can be the challenging and easily adaptable for the perspective of Bangladesh.
{"title":"Design and Performance Analysis: Lightning Protection-Marking of Air Terminals and Down Conductor-Perspective of Bangladesh","authors":"M. Hasan, Md.Rabiul Islam, T. Hossain, Kefayet Ullah, Nafis Farhan Rashid, Silvee Quraishi, P. Ghosh, M. Hossain","doi":"10.1109/ICREST.2019.8644107","DOIUrl":"https://doi.org/10.1109/ICREST.2019.8644107","url":null,"abstract":"This project focused on installing of lightning protection system and its equipment’s. This project was implanted for both shade building and full building with a rooftop. The objective of replacing air-terminal is to catch the strike of lightning and conveyed the current through the down conductor to earth pit. The whole process was followed by BNBC-2006 to make sure a structure or building safe from lightning. As it is essential for factories and industries to take protective action to make ensure the industrial electrical equipment’s, as well as the life of the workers, do work there. To monitor the working process, the Lightning counter device was used to detect how many strikes it caught. The risk assessment of lightning protection system has been done considering 7 index factor (A, B, C, D, E, F, and G), which recommended LPS is essential by calculating total index figure. The diameter of air-terminal was selected as 8 mm and air terminal height was varied 500 mm, 700 mm, 800 mm, 2 meters and 2.5 meters. Therefore, adopting the meshing technology following the BNBC-2006 can be the challenging and easily adaptable for the perspective of Bangladesh.","PeriodicalId":108842,"journal":{"name":"2019 International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132788891","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 : 2019-01-01DOI: 10.1109/ICREST.2019.8644318
C. Burke, Hung T. Nguyen, Mary Magilligan, R. Noorani
This paper describes a novel way to reliably deliver packages using a drone. For years, companies such as Amazon and Google have been hard at work developing a safe and practical way of utilizing the potential of unmanned aerial vehicles to improve upon their current network of delivery services. Transportation of even the largest package has become feasible due to the advances in drone-based robotics. The biggest problem left unanswered is how to best release the package once the drone has arrived at the drop off location. The solution presented in this paper details a basket that is capable of holding onto the package until the drone is rapidly flipped upside down in an aerial maneuver (oftentimes called a roll) and the centrifugal force ejects the payload from the basket. A practical, inexpensive, and robust solution to this problem was devised, modeled, researched, and tested with a 100% success rate. This solution will provide aerial robotics professionals with an alternative to the more standard method of using additional motors to actuate a payload delivery, thus cutting down on the cost, complexity, and failure rate associated with drone delivery. This paper will also present the design and manufacturing philosophy of the drone, and video clips will demonstrate the performance of the drone.
{"title":"Study of A Drone’s Payload Delivery Capabilities Utilizing Rotational Movement","authors":"C. Burke, Hung T. Nguyen, Mary Magilligan, R. Noorani","doi":"10.1109/ICREST.2019.8644318","DOIUrl":"https://doi.org/10.1109/ICREST.2019.8644318","url":null,"abstract":"This paper describes a novel way to reliably deliver packages using a drone. For years, companies such as Amazon and Google have been hard at work developing a safe and practical way of utilizing the potential of unmanned aerial vehicles to improve upon their current network of delivery services. Transportation of even the largest package has become feasible due to the advances in drone-based robotics. The biggest problem left unanswered is how to best release the package once the drone has arrived at the drop off location. The solution presented in this paper details a basket that is capable of holding onto the package until the drone is rapidly flipped upside down in an aerial maneuver (oftentimes called a roll) and the centrifugal force ejects the payload from the basket. A practical, inexpensive, and robust solution to this problem was devised, modeled, researched, and tested with a 100% success rate. This solution will provide aerial robotics professionals with an alternative to the more standard method of using additional motors to actuate a payload delivery, thus cutting down on the cost, complexity, and failure rate associated with drone delivery. This paper will also present the design and manufacturing philosophy of the drone, and video clips will demonstrate the performance of the drone.","PeriodicalId":108842,"journal":{"name":"2019 International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116893664","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 : 2019-01-01DOI: 10.1109/ICREST.2019.8644414
Md Abdullah Al Maruf, Sabbir Ahmed, Md. Tangir Ahmed, Antor Roy, Zannatul Ferdous Nitu
The Integrated Smart Parking System (ISPS) incorporates detection of empty parking spot and inappropriate parking, finds the available and different kind of parking spaces in various zones and suggest the most shortest way to reach the location. The ISPS mainly focuses on minimizing the time and maintaining a strategic distance from unnecessary traveling. There are lots of smart parking systems and a greater part of the solutions are following the conventional design approach focusing on a single parking center. However, existing single parking concentrating approached framework can’t satisfy the prerequisites of the incorporated smart parking system. In this study, for ISPS the structure has been defined with the utilization of best innovations. The ISPS can help the users to search the unoccupied spaces in the user-specific area within a very short time and also can suggest the nearest location from user destination. Additionally, ISPS supports the users with automated management of parking spaces and cares about fuel utilization.
{"title":"A Proposed Model of Integrated Smart Parking Solution for a city","authors":"Md Abdullah Al Maruf, Sabbir Ahmed, Md. Tangir Ahmed, Antor Roy, Zannatul Ferdous Nitu","doi":"10.1109/ICREST.2019.8644414","DOIUrl":"https://doi.org/10.1109/ICREST.2019.8644414","url":null,"abstract":"The Integrated Smart Parking System (ISPS) incorporates detection of empty parking spot and inappropriate parking, finds the available and different kind of parking spaces in various zones and suggest the most shortest way to reach the location. The ISPS mainly focuses on minimizing the time and maintaining a strategic distance from unnecessary traveling. There are lots of smart parking systems and a greater part of the solutions are following the conventional design approach focusing on a single parking center. However, existing single parking concentrating approached framework can’t satisfy the prerequisites of the incorporated smart parking system. In this study, for ISPS the structure has been defined with the utilization of best innovations. The ISPS can help the users to search the unoccupied spaces in the user-specific area within a very short time and also can suggest the nearest location from user destination. Additionally, ISPS supports the users with automated management of parking spaces and cares about fuel utilization.","PeriodicalId":108842,"journal":{"name":"2019 International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST)","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123487906","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 : 2019-01-01DOI: 10.1109/ICREST.2019.8644312
Md. Sifatul Muktadir, Shakerul Islam, Ar Rafi Alam Chowdhury
In this paper, a system is proposed for a Nuclear facility which is comprised of multiple detectors, controlled from a single receiver end with DHCP Address Reservation Network protocol. The radiation sensor is based on Geiger Muller tube (GMT) which is a reliable detector for the radioactive particulates in the gaseous effluent vented from nuclear facilities. The detectors are interconnected and controlled from a server by a remote operator. A real-time log can be generated from respective data sent by these multiple detectors. The detectors are also implemented such a way that it is able to interact with the operator through a graphical user interface. The generated data have been further used to plot a real-time graph with MATLAB which is integrated into the system. The system is tested under several radioactive sources considering the background radiation. The graphical interpretation of the radiation pattern in terms of count per minutes versus time was obtained from the received data. This proposed system allows the remote operator to record and store the data of different radiation levels emitted from the radioactive in different time which may be used to create a radiation emission curve of a whole year. The system may be used to detect any abnormal radiation level which may be harmful to the environment and associated with the warning system for the early detection during those adverse situations.
{"title":"Development of a Wireless Safety System Based on Multiple Radiation Detector for Nuclear Facilities","authors":"Md. Sifatul Muktadir, Shakerul Islam, Ar Rafi Alam Chowdhury","doi":"10.1109/ICREST.2019.8644312","DOIUrl":"https://doi.org/10.1109/ICREST.2019.8644312","url":null,"abstract":"In this paper, a system is proposed for a Nuclear facility which is comprised of multiple detectors, controlled from a single receiver end with DHCP Address Reservation Network protocol. The radiation sensor is based on Geiger Muller tube (GMT) which is a reliable detector for the radioactive particulates in the gaseous effluent vented from nuclear facilities. The detectors are interconnected and controlled from a server by a remote operator. A real-time log can be generated from respective data sent by these multiple detectors. The detectors are also implemented such a way that it is able to interact with the operator through a graphical user interface. The generated data have been further used to plot a real-time graph with MATLAB which is integrated into the system. The system is tested under several radioactive sources considering the background radiation. The graphical interpretation of the radiation pattern in terms of count per minutes versus time was obtained from the received data. This proposed system allows the remote operator to record and store the data of different radiation levels emitted from the radioactive in different time which may be used to create a radiation emission curve of a whole year. The system may be used to detect any abnormal radiation level which may be harmful to the environment and associated with the warning system for the early detection during those adverse situations.","PeriodicalId":108842,"journal":{"name":"2019 International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124662934","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 : 2019-01-01DOI: 10.1109/ICREST.2019.8644161
K. A. Taher, Billal Mohammed Yasin Jisan, M. Rahman
A novel supervised machine learning system is developed to classify network traffic whether it is malicious or benign. To find the best model considering detection success rate, combination of supervised learning algorithm and feature selection method have been used. Through this study, it is found that Artificial Neural Network (ANN) based machine learning with wrapper feature selection outperform support vector machine (SVM) technique while classifying network traffic. To evaluate the performance, NSL-KDD dataset is used to classify network traffic using SVM and ANN supervised machine learning techniques. Comparative study shows that the proposed model is efficient than other existing models with respect to intrusion detection success rate.
{"title":"Network Intrusion Detection using Supervised Machine Learning Technique with Feature Selection","authors":"K. A. Taher, Billal Mohammed Yasin Jisan, M. Rahman","doi":"10.1109/ICREST.2019.8644161","DOIUrl":"https://doi.org/10.1109/ICREST.2019.8644161","url":null,"abstract":"A novel supervised machine learning system is developed to classify network traffic whether it is malicious or benign. To find the best model considering detection success rate, combination of supervised learning algorithm and feature selection method have been used. Through this study, it is found that Artificial Neural Network (ANN) based machine learning with wrapper feature selection outperform support vector machine (SVM) technique while classifying network traffic. To evaluate the performance, NSL-KDD dataset is used to classify network traffic using SVM and ANN supervised machine learning techniques. Comparative study shows that the proposed model is efficient than other existing models with respect to intrusion detection success rate.","PeriodicalId":108842,"journal":{"name":"2019 International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130499301","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 : 2019-01-01DOI: 10.1109/ICREST.2019.8644337
Apu Nandy, Mohammad Ashik Alahe, S. M. Nasim Uddin, S. Alam, Adullah-Al Nahid, M. Awal
Epileptic seizure is a neurological disorder characterized by abnormal synchronous discharge of the neuronal activities in the brain structures. These abnormal electrical activities can be recorded via multi-channel electroencephalography (EEG) signals placed on the scalp of the brain. Usually, these signals, recorded from this EEG device, are interpreted by the neurologist which require their availability and it is very time consuming especially for long duration signals. This study presents a fully automatic system for the detection of seizure from non-seizure signals. Firstly, it pre-processes the signal to remove noise and artefacts from the raw-EEG signals and then extracts features. Features are extracted from time-domain, spectral domain, wavelet domain. In addition, connectivity and entropy based feature have also been extracted. After that, prominent features have been selected from this large feature set by a multi-objective evolutionary algorithm and finally, Support Vector Machine (SVM) classifier has been used for classification. A Bayesian optimization algorithm has been used to optimize the hyper-parameters of SVM. Linear Discriminant Analysis (LDA) and Quadratic Linear Discriminant Analysis (QLDA) have also been used for comparison. The proposed system is tested on a publicly available CHB-MIT database and results show the significance of the proposed system. The distinguished accuracy of the classifier is 76.41%, 80.79% and 97.05% in LDA, QLDA and SVM, respectively.
{"title":"Feature Extraction and Classification of EEG Signals for Seizure Detection","authors":"Apu Nandy, Mohammad Ashik Alahe, S. M. Nasim Uddin, S. Alam, Adullah-Al Nahid, M. Awal","doi":"10.1109/ICREST.2019.8644337","DOIUrl":"https://doi.org/10.1109/ICREST.2019.8644337","url":null,"abstract":"Epileptic seizure is a neurological disorder characterized by abnormal synchronous discharge of the neuronal activities in the brain structures. These abnormal electrical activities can be recorded via multi-channel electroencephalography (EEG) signals placed on the scalp of the brain. Usually, these signals, recorded from this EEG device, are interpreted by the neurologist which require their availability and it is very time consuming especially for long duration signals. This study presents a fully automatic system for the detection of seizure from non-seizure signals. Firstly, it pre-processes the signal to remove noise and artefacts from the raw-EEG signals and then extracts features. Features are extracted from time-domain, spectral domain, wavelet domain. In addition, connectivity and entropy based feature have also been extracted. After that, prominent features have been selected from this large feature set by a multi-objective evolutionary algorithm and finally, Support Vector Machine (SVM) classifier has been used for classification. A Bayesian optimization algorithm has been used to optimize the hyper-parameters of SVM. Linear Discriminant Analysis (LDA) and Quadratic Linear Discriminant Analysis (QLDA) have also been used for comparison. The proposed system is tested on a publicly available CHB-MIT database and results show the significance of the proposed system. The distinguished accuracy of the classifier is 76.41%, 80.79% and 97.05% in LDA, QLDA and SVM, respectively.","PeriodicalId":108842,"journal":{"name":"2019 International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130030792","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：