Pub Date : 2022-02-24DOI: 10.1109/icaeee54957.2022.9836427
Reana Raen, Muhammad Muinul Islam, Redwanul Islam
Optical Coherence Tomography (OCT) was first introduced in the 1990’. It utilizes the concept of interferometry to create a cross-sectional map of the retina., accurate within 10–15 microns. Identifying the actual diseases occurring in retina layer., is a challenging task. There exist several automated techniques for disease classification like image processing., deep learning. Unfortunately., these techniques often produce error., lower precision., excessive memory localization., inefficiency in computation., further interpretation of human experts. In this paper., we have proposed a method for automatic classification of 3 categories of retinal diseases that include diabetic macular edema., Drusen., Choroidal Neovascularization. A modified ResNet architecture with transfer learning framework is used to make better feature extraction for small patches. This modification includes adding three new layers which are Convolution layer., Batch Normalization and Activation function relu layers. Modification is added at the end of convolution layers in a pretrained Resnet framework. These layers are inserted in the ResNet50 architecture for accurate discrimination and robust feature extraction of OCT images with better efficiency than the traditional networks. Experimental results demonstrate that our method obtained accuracy value 99.81%. Our proposed model provides reliable classification for small lesions., helpful in clinical diagnostic to provide user-friendly eye check-ups.
{"title":"Diagnosis of Retinal Diseases by Classifying Lesions in Retinal Layers using a Modified ResNet Architecture","authors":"Reana Raen, Muhammad Muinul Islam, Redwanul Islam","doi":"10.1109/icaeee54957.2022.9836427","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836427","url":null,"abstract":"Optical Coherence Tomography (OCT) was first introduced in the 1990’. It utilizes the concept of interferometry to create a cross-sectional map of the retina., accurate within 10–15 microns. Identifying the actual diseases occurring in retina layer., is a challenging task. There exist several automated techniques for disease classification like image processing., deep learning. Unfortunately., these techniques often produce error., lower precision., excessive memory localization., inefficiency in computation., further interpretation of human experts. In this paper., we have proposed a method for automatic classification of 3 categories of retinal diseases that include diabetic macular edema., Drusen., Choroidal Neovascularization. A modified ResNet architecture with transfer learning framework is used to make better feature extraction for small patches. This modification includes adding three new layers which are Convolution layer., Batch Normalization and Activation function relu layers. Modification is added at the end of convolution layers in a pretrained Resnet framework. These layers are inserted in the ResNet50 architecture for accurate discrimination and robust feature extraction of OCT images with better efficiency than the traditional networks. Experimental results demonstrate that our method obtained accuracy value 99.81%. Our proposed model provides reliable classification for small lesions., helpful in clinical diagnostic to provide user-friendly eye check-ups.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115827948","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 : 2022-02-24DOI: 10.1109/icaeee54957.2022.9836357
Kaisarul Islam, Ajan Ahmed, Mohammad Monirujjaman Khan
A 60 GHz millimeter-wave patch antenna design is evaluated in both free space and on a skin-equivalent phantom. For achieving transparency, a glass substrate of a thickness of 2 mm is used. At 60 GHz, the relative permittivity of the substrate is 4.7. The antenna achieved a resonant frequency of 60.01 GHz in free space with an impedance bandwidth of 5.951 GHz. The impedance bandwidth increased by 0.178 GHz when the antenna was placed 4 mm away from a skin-equivalent phantom. The peak gain at 60 GHz is 7.42 dB and the radiation efficiency is 65.77%. The overall size of the patch antenna is 5.85 mm × 9 mm.
{"title":"Design Evaluation of a Millimeter-wave 60 GHz Transparent Antenna for Body-centric Communication in Healthcare Application","authors":"Kaisarul Islam, Ajan Ahmed, Mohammad Monirujjaman Khan","doi":"10.1109/icaeee54957.2022.9836357","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836357","url":null,"abstract":"A 60 GHz millimeter-wave patch antenna design is evaluated in both free space and on a skin-equivalent phantom. For achieving transparency, a glass substrate of a thickness of 2 mm is used. At 60 GHz, the relative permittivity of the substrate is 4.7. The antenna achieved a resonant frequency of 60.01 GHz in free space with an impedance bandwidth of 5.951 GHz. The impedance bandwidth increased by 0.178 GHz when the antenna was placed 4 mm away from a skin-equivalent phantom. The peak gain at 60 GHz is 7.42 dB and the radiation efficiency is 65.77%. The overall size of the patch antenna is 5.85 mm × 9 mm.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"73 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130342342","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 : 2022-02-24DOI: 10.1109/icaeee54957.2022.9836350
Md. Rahatul Islam, Rafi Afzal, Asaduzzaman, Ferdib-Al-Islam, Jimmy Majumder
Only vaccination can not prevent COVID-19 infection. Social distancing and other preventive measures like - frequent hand washing, wearing a face mask can reduce the rising infection rate of COVID-19. It is not feasible to maintain social distancing and ensure hand sanitization in public places by humans as COVID-19 can affect that person or be contaminated by him/her. An automated social distancing system will play an essential role in maintaining social distance within certain boundaries. An automatic social distancing system called “COV-SSDS” has been proposed in this work. In COV-SSDS, a person has to disinfect the hands with a sanitizer after being detected by the infrared sensor because the servo motor control door does not open without hand sanitization. If the person does not stand in the proper place, he/she will be notified. A liquid crystal display module has been used to display the number of people in the queue and the occupied slots. An alert generation system to alert the people about occupying the empty slot and a power backup unit was also attached to this system which was not found in previous studies. According to the features, feasibility, maintenance, and cost analysis, “COV-SSDS” is worthy of the previous works.
{"title":"COV-SSDS: Design and Construction of Automatic Social Distancing System to Minimize COVID-19 Infection","authors":"Md. Rahatul Islam, Rafi Afzal, Asaduzzaman, Ferdib-Al-Islam, Jimmy Majumder","doi":"10.1109/icaeee54957.2022.9836350","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836350","url":null,"abstract":"Only vaccination can not prevent COVID-19 infection. Social distancing and other preventive measures like - frequent hand washing, wearing a face mask can reduce the rising infection rate of COVID-19. It is not feasible to maintain social distancing and ensure hand sanitization in public places by humans as COVID-19 can affect that person or be contaminated by him/her. An automated social distancing system will play an essential role in maintaining social distance within certain boundaries. An automatic social distancing system called “COV-SSDS” has been proposed in this work. In COV-SSDS, a person has to disinfect the hands with a sanitizer after being detected by the infrared sensor because the servo motor control door does not open without hand sanitization. If the person does not stand in the proper place, he/she will be notified. A liquid crystal display module has been used to display the number of people in the queue and the occupied slots. An alert generation system to alert the people about occupying the empty slot and a power backup unit was also attached to this system which was not found in previous studies. According to the features, feasibility, maintenance, and cost analysis, “COV-SSDS” is worthy of the previous works.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123366729","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 : 2022-02-24DOI: 10.1109/icaeee54957.2022.9836394
B. Biswas, Joydeb Das, Md. Saiful Islam, M. Abedin
CMOS Nano/Molecular scale technology is going to the end of its journey soon. The current technology strives for fast speed., high device density., high energy efficient and ease of use. Memristor enabled the development of these types of properties for its non-volatility., size and good switching behavior. In this work., a Memristor-MOS based Octonary memory cell has been proposed that provides 3-bit data or eight different states storage in the single cell. Data erasing technique is used for write operation by eliminating feedback read-based writing operations. Voltage division based read methodology is used for total read write operation and verification of the proposed cell were performed using LTspice simulation.
{"title":"Design of Octonary Memory Cell using Memristor-MOS Hybrid Structure","authors":"B. Biswas, Joydeb Das, Md. Saiful Islam, M. Abedin","doi":"10.1109/icaeee54957.2022.9836394","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836394","url":null,"abstract":"CMOS Nano/Molecular scale technology is going to the end of its journey soon. The current technology strives for fast speed., high device density., high energy efficient and ease of use. Memristor enabled the development of these types of properties for its non-volatility., size and good switching behavior. In this work., a Memristor-MOS based Octonary memory cell has been proposed that provides 3-bit data or eight different states storage in the single cell. Data erasing technique is used for write operation by eliminating feedback read-based writing operations. Voltage division based read methodology is used for total read write operation and verification of the proposed cell were performed using LTspice simulation.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116712464","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 : 2022-02-24DOI: 10.1109/icaeee54957.2022.9836429
M. H. Rahman, Masuma Akter, Md. Rashedul Islam, S. Alam, Md. Arifur Rahman, Fariha Tabassum, Mahmudur Rahman
Most of the malarial diagnostic methods either depend on manual counting of infected red blood cells or requires complex laboratory facilities. In both cases, the diagnostic is time-consuming, expensive, requires trained personnel, sometimes produce erroneous results due to manual intervention, and hinders rapid diagnostics of malarial infection. Malaria is mostly fatal if not diagnosed and treated promptly, therefore, it is imperative to devise a methodology that provides a rapid, cost-effective, and accurate malarial diagnosis with proper quantification. Here, we propose an image processing-based malaria detection methodology using support vector machine (SVM) that can detect and quantify malarial infection with up to 96% accuracy. The image processing algorithm is implemented on a range of images and the outcomes are in good agreement with the actual diagnostic results thereby, validating the methodology.
{"title":"Development of an Auto-detection and Quantification Algorithm Of Malaria Infection Using Image Processing","authors":"M. H. Rahman, Masuma Akter, Md. Rashedul Islam, S. Alam, Md. Arifur Rahman, Fariha Tabassum, Mahmudur Rahman","doi":"10.1109/icaeee54957.2022.9836429","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836429","url":null,"abstract":"Most of the malarial diagnostic methods either depend on manual counting of infected red blood cells or requires complex laboratory facilities. In both cases, the diagnostic is time-consuming, expensive, requires trained personnel, sometimes produce erroneous results due to manual intervention, and hinders rapid diagnostics of malarial infection. Malaria is mostly fatal if not diagnosed and treated promptly, therefore, it is imperative to devise a methodology that provides a rapid, cost-effective, and accurate malarial diagnosis with proper quantification. Here, we propose an image processing-based malaria detection methodology using support vector machine (SVM) that can detect and quantify malarial infection with up to 96% accuracy. The image processing algorithm is implemented on a range of images and the outcomes are in good agreement with the actual diagnostic results thereby, validating the methodology.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127406144","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 : 2022-02-24DOI: 10.1109/icaeee54957.2022.9836438
S. Akther, Priyangka Talukder, Moloy Cgandra Dey, Afshana Begum, M. Rashid
AC power devices are needed in various industrial, commercial, and residential sectors. A multilevel inverter can get smooth AC power from DC. In this study, the topology of a novel 31-level asymmetrical multilevel inverter (MLI) has been proposed. The biggest advantage of this proposed new asymmetrical MLI topology is that its total harmonic distortion (THD) is much lower without any type of controller. In this topology, a lower number of switches and other components have been used. To design this novel 31-level asymmetrical MLI, twelve IGBT switches, and four asymmetrical voltage sources (2:4:8:16) have been used which resulted in 31 levels of output voltages. The pulse width modulation (PWM) technique is used to generate triggering pulses in the switches. Simulation and performance analysis of the proposed new asymmetric MLI has been performed by the MATLAB-Simulink platform. The precision of work of the inverter can be understood through the simulation results.
{"title":"Designing a Novel 31-Level Asymmetrical Multilevel Inverter Topology with Comparative Analysis","authors":"S. Akther, Priyangka Talukder, Moloy Cgandra Dey, Afshana Begum, M. Rashid","doi":"10.1109/icaeee54957.2022.9836438","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836438","url":null,"abstract":"AC power devices are needed in various industrial, commercial, and residential sectors. A multilevel inverter can get smooth AC power from DC. In this study, the topology of a novel 31-level asymmetrical multilevel inverter (MLI) has been proposed. The biggest advantage of this proposed new asymmetrical MLI topology is that its total harmonic distortion (THD) is much lower without any type of controller. In this topology, a lower number of switches and other components have been used. To design this novel 31-level asymmetrical MLI, twelve IGBT switches, and four asymmetrical voltage sources (2:4:8:16) have been used which resulted in 31 levels of output voltages. The pulse width modulation (PWM) technique is used to generate triggering pulses in the switches. Simulation and performance analysis of the proposed new asymmetric MLI has been performed by the MATLAB-Simulink platform. The precision of work of the inverter can be understood through the simulation results.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126957573","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 : 2022-02-22DOI: 10.1109/tcset55632.2022.9767052
Libraries are permitted to photocopy beyond the limit of U.S. copyright law for private use of patrons those articles in this volume that carry a code at the bottom of the first page, provided the per-copy fee indicated in the code is paid through Copyright Clearance Center, 222 Rosewood Drive, Danvers, MA 01923. For reprint or republication permission, email to IEEE Copyrights Manager at pubs-permissions@ieee.org.
在美国版权法的限制之外，图书馆允许影印本卷中第一页底部带有代码的文章，供用户私人使用，前提是代码中显示的每本费用由版权清算中心支付，地址:222 Rosewood Drive, Danvers, MA 01923。如需转载或转载许可，请发送电子邮件至IEEE版权经理pubs-permissions@ieee.org。
{"title":"Copyright and Reprint Permission","authors":"","doi":"10.1109/tcset55632.2022.9767052","DOIUrl":"https://doi.org/10.1109/tcset55632.2022.9767052","url":null,"abstract":"Libraries are permitted to photocopy beyond the limit of U.S. copyright law for private use of patrons those articles in this volume that carry a code at the bottom of the first page, provided the per-copy fee indicated in the code is paid through Copyright Clearance Center, 222 Rosewood Drive, Danvers, MA 01923. For reprint or republication permission, email to IEEE Copyrights Manager at pubs-permissions@ieee.org.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127759011","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}
People undergoing neuromuscular dysfunctions and amputated limbs require automatic prosthetic appliances. In developing such prostheses, the precise detection of brain motor actions is imperative for the Grasp-and-Lift (GAL) tasks. Because of the low-cost and non-invasive essence of Electroencephalogra-phy (EEG), it is widely preferred for detecting motor actions while controlling prosthetic tools. This article has automated the hand movement activity viz GAL detection method from the 32-channel EEG signals. The proposed pipeline essentially combines preprocessing and end-to-end detection steps, eliminating the requirement of hand-crafted feature engineering. Preprocessing action consists of raw signal denoising, using either Discrete Wavelet Transform (DWT) or highpass or bandpass filtering and data standardization. The detection step consists of Convolutional Neural Network (CNN)- or Long Short Term Memory (LSTM)-based model. All the investigations utilize the publicly available WAY-EEG-GAL dataset, having six different GAL events. The best experiment reveals that the proposed framework achieves an average area under the ROC curve of 0.944, employing the DWT-based denoising filter, data standardization, and CNN-based detection model. The obtained outcome designates an excellent achievement of the introduced method in detecting GAL events from the EEG signals, turning it applicable to prosthetic appliances, brain-computer interfaces, robotic arms, etc.
{"title":"Grasp-and-Lift Detection from EEG Signal Using Convolutional Neural Network","authors":"Md. Kamrul Hasan, Sifat Redwan Wahid, Faria Rahman, Shanjida Khan Maliha, Sauda Binte Rahman","doi":"10.1109/icaeee54957.2022.9836375","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836375","url":null,"abstract":"People undergoing neuromuscular dysfunctions and amputated limbs require automatic prosthetic appliances. In developing such prostheses, the precise detection of brain motor actions is imperative for the Grasp-and-Lift (GAL) tasks. Because of the low-cost and non-invasive essence of Electroencephalogra-phy (EEG), it is widely preferred for detecting motor actions while controlling prosthetic tools. This article has automated the hand movement activity viz GAL detection method from the 32-channel EEG signals. The proposed pipeline essentially combines preprocessing and end-to-end detection steps, eliminating the requirement of hand-crafted feature engineering. Preprocessing action consists of raw signal denoising, using either Discrete Wavelet Transform (DWT) or highpass or bandpass filtering and data standardization. The detection step consists of Convolutional Neural Network (CNN)- or Long Short Term Memory (LSTM)-based model. All the investigations utilize the publicly available WAY-EEG-GAL dataset, having six different GAL events. The best experiment reveals that the proposed framework achieves an average area under the ROC curve of 0.944, employing the DWT-based denoising filter, data standardization, and CNN-based detection model. The obtained outcome designates an excellent achievement of the introduced method in detecting GAL events from the EEG signals, turning it applicable to prosthetic appliances, brain-computer interfaces, robotic arms, etc.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116397502","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：