Pub Date : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101614
Saika Afrin Sumona, Wahida Binte Naz Aurthy
Sleep apnea resulting from obstructions in the upper respiratory tract during sleep is one of the most common sleep disorders that result in poor sleep and a significant degradation of our quality of life. Sleep apnea patients have frequent pauses in breathing during sleeping and very often face snoring problem. Usually, these short lapses cause a person to wake up at irregular intervals reducing their sleep quality, the older patients, however, find it very difficult to cope with such sleep apnea periods. The traditional monitoring and detection system is both expensive and complicated to be used regularly and at home. This study proposes a novel, low-cost monitoring system for sleep apnea patients which comes in the form of a wearable belt incorporating 3 different sensors to collect physiological signals correlated to sleep apnea. Electrocardiogram (ECG) sensor, photoplethysmog-raphy (PPG) sensor, and accelerometer are used with a bluetooth sensor so that the obtained data can be easily sent to a computer or mobile application where physicians, nurses, caregivers can monitor the patients without being present all the time. Using the assortment of the physiological signals, the onset of sleep apnea can be easily detected and the concerned people can be alerted instantaneously. The proposed system is affordable and can be used at home very easily.
{"title":"A Novel Low-Cost Monitoring System for Sleep Apnea Patients","authors":"Saika Afrin Sumona, Wahida Binte Naz Aurthy","doi":"10.1109/ECCE57851.2023.10101614","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101614","url":null,"abstract":"Sleep apnea resulting from obstructions in the upper respiratory tract during sleep is one of the most common sleep disorders that result in poor sleep and a significant degradation of our quality of life. Sleep apnea patients have frequent pauses in breathing during sleeping and very often face snoring problem. Usually, these short lapses cause a person to wake up at irregular intervals reducing their sleep quality, the older patients, however, find it very difficult to cope with such sleep apnea periods. The traditional monitoring and detection system is both expensive and complicated to be used regularly and at home. This study proposes a novel, low-cost monitoring system for sleep apnea patients which comes in the form of a wearable belt incorporating 3 different sensors to collect physiological signals correlated to sleep apnea. Electrocardiogram (ECG) sensor, photoplethysmog-raphy (PPG) sensor, and accelerometer are used with a bluetooth sensor so that the obtained data can be easily sent to a computer or mobile application where physicians, nurses, caregivers can monitor the patients without being present all the time. Using the assortment of the physiological signals, the onset of sleep apnea can be easily detected and the concerned people can be alerted instantaneously. The proposed system is affordable and can be used at home very easily.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130263037","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 : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101559
Md. Shabir Khan Akash, Md. Al Mamun
It is still challenging to differentiate between normal cells and tumor demarcation in everyday clinical practice. With the use of the FLAIR modality known as Fluid Attenuated Inversion Recovery, a medical professional can learn more about tumor infiltration. Because the preponderance of the cerebrospinal fluid effect can be suppressed by the FLAIR modality. Moreover, one of the advantages of using FLAIR images is that they can be used for both 3D and 2D medical imagery. Therefore, this paper explores the idea of assessing and predicting brain tumors by implementing several types of deep learning CNN architectures, such as VGG16, ResNet50, DenseNet121 and others in a user-friendly functional U-Net architecture. The flexibility of using different pre-trained neural network models in a single architecture is the key advantage of our U-Net architecture. Hyperparameters of the architecture are adjusted and fine-tuned for the segmentation process in order to extract the core features of the tumor contour according to our problem. Having said that, this study's segmentation result on the dice similarity coefficient is 0.9165, 0.9175, 0.9137 and 0.9148 in the BraTS 2018, 2019, 2020 and 2021 datasets respectively.
{"title":"A Comparative Analysis on Predicting Brain Tumor from MRI FLAIR Images Using Deep Learning","authors":"Md. Shabir Khan Akash, Md. Al Mamun","doi":"10.1109/ECCE57851.2023.10101559","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101559","url":null,"abstract":"It is still challenging to differentiate between normal cells and tumor demarcation in everyday clinical practice. With the use of the FLAIR modality known as Fluid Attenuated Inversion Recovery, a medical professional can learn more about tumor infiltration. Because the preponderance of the cerebrospinal fluid effect can be suppressed by the FLAIR modality. Moreover, one of the advantages of using FLAIR images is that they can be used for both 3D and 2D medical imagery. Therefore, this paper explores the idea of assessing and predicting brain tumors by implementing several types of deep learning CNN architectures, such as VGG16, ResNet50, DenseNet121 and others in a user-friendly functional U-Net architecture. The flexibility of using different pre-trained neural network models in a single architecture is the key advantage of our U-Net architecture. Hyperparameters of the architecture are adjusted and fine-tuned for the segmentation process in order to extract the core features of the tumor contour according to our problem. Having said that, this study's segmentation result on the dice similarity coefficient is 0.9165, 0.9175, 0.9137 and 0.9148 in the BraTS 2018, 2019, 2020 and 2021 datasets respectively.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131328107","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 : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101512
Diba Das, Aditta Chowdhury, A. I. Sanka, M. Chowdhury
Electrooculogram (EOG) is an electrophysiological signal produced around the eyes due to eyeball motion. This signal can be utilized to study eye movements which is bene-ficial in many medical and bio-electrical applications such as controlling human-computer interfaces and diagnosing different ocular diseases. However, the EOG is often contaminated with high-frequency motion artifacts, 50/60 Hz grid interference, and baseline wander. Hence, the collected signals are required to be preprocessed before finally being used in applications. This paper proposes an efficient FPGA-based EOG processor for fast and real-time processing of EOG signals, especially for medical diagnosis. To the best of our knowledge, this is the first work to implement EOG serial preprocessing by FIR and IIR filters on FPGA. MATLAB's FDA tool is used for mathematical validation and primary simulation. The proposed system was implemented on the Xilinx Zynq-7000 FPGA by hardware/software co-design. By statistical analysis, the software and hardware results were found to have the Pearson Correlation Coefficient of 0.99 and a Mean Root Squared Error in the 10–3 range. The resource utilization and power consumption are presented. The on-chip power consumption for this design is 0.271 watts where dynamic power is 0.163 watts (60%), and static power is 0.108 watts (40%). Performance evaluation and comparative study of the software-hardware results revealed the efficacy of the designed EOG preprocessor.
{"title":"Design and Performance Evaluation of an FPGA based EOG Signal Preprocessor","authors":"Diba Das, Aditta Chowdhury, A. I. Sanka, M. Chowdhury","doi":"10.1109/ECCE57851.2023.10101512","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101512","url":null,"abstract":"Electrooculogram (EOG) is an electrophysiological signal produced around the eyes due to eyeball motion. This signal can be utilized to study eye movements which is bene-ficial in many medical and bio-electrical applications such as controlling human-computer interfaces and diagnosing different ocular diseases. However, the EOG is often contaminated with high-frequency motion artifacts, 50/60 Hz grid interference, and baseline wander. Hence, the collected signals are required to be preprocessed before finally being used in applications. This paper proposes an efficient FPGA-based EOG processor for fast and real-time processing of EOG signals, especially for medical diagnosis. To the best of our knowledge, this is the first work to implement EOG serial preprocessing by FIR and IIR filters on FPGA. MATLAB's FDA tool is used for mathematical validation and primary simulation. The proposed system was implemented on the Xilinx Zynq-7000 FPGA by hardware/software co-design. By statistical analysis, the software and hardware results were found to have the Pearson Correlation Coefficient of 0.99 and a Mean Root Squared Error in the 10–3 range. The resource utilization and power consumption are presented. The on-chip power consumption for this design is 0.271 watts where dynamic power is 0.163 watts (60%), and static power is 0.108 watts (40%). Performance evaluation and comparative study of the software-hardware results revealed the efficacy of the designed EOG preprocessor.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134245191","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 : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101634
S. Haq, M. K. Hosain, S. P. Biswas
In this research work, a new modulation technique is proposed to control the switching of a 3-phase modular multilevel converter (MMC) based solar photovoltaic (PV) fed induction motor (IM) drive system. Multilevel inverters (MLIs) are gaining popularity in the industry as medium-voltage and high-power electronic power conversion solutions. Different multilevel inverter topologies have grown in prominence in recent years, owing to a variety of advantages, particularly in induction motor driving systems. Inverter switching strategies are critical for improving power quality. In this paper, a new switching method for a 5-level MMC is proposed that ensures high power quality, improves speed and torque performance, and reduces total harmonic distortion (THD) in the voltage and current waveforms of the stator of a PV-based IM. The practicality of this modulation method is demonstrated by comparing its performance to that of several existing popular switching strategies. The design, implementation, and comparisons are done by using MATLAB/Simulink simulation. A laboratory-scale prototype is developed and tested to evaluate the performance of the proposed switching technique.
{"title":"An Efficient Modulation Strategy for Modular Multilevel Cascaded Inverter Used in Solar PV Fed Induction Motor Drive Systems","authors":"S. Haq, M. K. Hosain, S. P. Biswas","doi":"10.1109/ECCE57851.2023.10101634","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101634","url":null,"abstract":"In this research work, a new modulation technique is proposed to control the switching of a 3-phase modular multilevel converter (MMC) based solar photovoltaic (PV) fed induction motor (IM) drive system. Multilevel inverters (MLIs) are gaining popularity in the industry as medium-voltage and high-power electronic power conversion solutions. Different multilevel inverter topologies have grown in prominence in recent years, owing to a variety of advantages, particularly in induction motor driving systems. Inverter switching strategies are critical for improving power quality. In this paper, a new switching method for a 5-level MMC is proposed that ensures high power quality, improves speed and torque performance, and reduces total harmonic distortion (THD) in the voltage and current waveforms of the stator of a PV-based IM. The practicality of this modulation method is demonstrated by comparing its performance to that of several existing popular switching strategies. The design, implementation, and comparisons are done by using MATLAB/Simulink simulation. A laboratory-scale prototype is developed and tested to evaluate the performance of the proposed switching technique.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123253484","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 : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101648
Nosin Ibna Mahbub, Feroza Naznin, Md. Imran Hasan, Syed Mahfuzur Rahman Shifat, Md. Alamgir Hossain, M. Islam
This research concentrates on the diagnosis of common mango leaf diseases in Bangladesh using image processing via deep learning. Mango production could be raised by at least 28% globally if the crop could be safeguarded from a variety of diseases. However, without the assistance of an expert, it is challenging for the farmer to detect the disease at the appropriate time. Few studies have been conducted to identify the mango leaf disease present in Bangladesh. So far, no study has been done to identify the seven distinct mango leaf diseases reported in Bangladesh. We proposed a lightweight convolutional neural network (LCNN) in this paper to accurately classify seven distinct mango leaf diseases as well as normal mango leaf. To assess the proposed LCNN model, performance is compared to several pre-trained models such as VGG16, Resnet50, Resnet101, and Xception, and it is found that LCNN achieves the highest testing accuracy (98%).
{"title":"Detect Bangladeshi Mango Leaf Diseases Using Lightweight Convolutional Neural Network","authors":"Nosin Ibna Mahbub, Feroza Naznin, Md. Imran Hasan, Syed Mahfuzur Rahman Shifat, Md. Alamgir Hossain, M. Islam","doi":"10.1109/ECCE57851.2023.10101648","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101648","url":null,"abstract":"This research concentrates on the diagnosis of common mango leaf diseases in Bangladesh using image processing via deep learning. Mango production could be raised by at least 28% globally if the crop could be safeguarded from a variety of diseases. However, without the assistance of an expert, it is challenging for the farmer to detect the disease at the appropriate time. Few studies have been conducted to identify the mango leaf disease present in Bangladesh. So far, no study has been done to identify the seven distinct mango leaf diseases reported in Bangladesh. We proposed a lightweight convolutional neural network (LCNN) in this paper to accurately classify seven distinct mango leaf diseases as well as normal mango leaf. To assess the proposed LCNN model, performance is compared to several pre-trained models such as VGG16, Resnet50, Resnet101, and Xception, and it is found that LCNN achieves the highest testing accuracy (98%).","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124698382","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}
Digital modulation schemes determine how bits are mapped to the phase and amplitude of transmitted signals. This research comprehensively analyzes the necessity of studying various modulation schemes and a comparative investigation using appropriate simulations. The goal is to obtain the most effective modulation scheme for 5G technology. In the development phase of 5G technology, different candidates of modulation schemes like OFDM, F-OFDM, UFMC, FBMC, and others are being studied. For 5G communication, the modulation scheme that performs effectively across all dimensions will be evaluated. This research aims to compare several 4G and 5G modulation methods to determine the best modulation strategy for 5G technology. The comparative research for modulation schemes was carried out using modern technologies. Here, we transmit 5G data to evaluate the performance of several 4G and 5G modulation schemes to determine which Modulation Scheme is best for implementing 5G technology. Our research covered three modulation schemes: OFDM, F-OFDM, and UFMC. We employed PSD, PAPR, BER, and Constellation Diagrams to compare OFDM, which is currently used in 4G technology, with F-OFDM and UFMC, respectively. Following the comparative investigation, we discovered that F-OFDM significantly outperforms UFMC and OFDM, both modulation techniques. We also determined that F-OFDM promises enhanced efficiency in 5G technology by accurately proving all simulations for a potential application.
{"title":"Study of Different Candidates of Modulation Schemes for 5G Communication Systems","authors":"Tamanna Sultana, Rahela Akhter Akhi, Jubayed Hossain Turag, Suhail Najeeb","doi":"10.1109/ECCE57851.2023.10101611","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101611","url":null,"abstract":"Digital modulation schemes determine how bits are mapped to the phase and amplitude of transmitted signals. This research comprehensively analyzes the necessity of studying various modulation schemes and a comparative investigation using appropriate simulations. The goal is to obtain the most effective modulation scheme for 5G technology. In the development phase of 5G technology, different candidates of modulation schemes like OFDM, F-OFDM, UFMC, FBMC, and others are being studied. For 5G communication, the modulation scheme that performs effectively across all dimensions will be evaluated. This research aims to compare several 4G and 5G modulation methods to determine the best modulation strategy for 5G technology. The comparative research for modulation schemes was carried out using modern technologies. Here, we transmit 5G data to evaluate the performance of several 4G and 5G modulation schemes to determine which Modulation Scheme is best for implementing 5G technology. Our research covered three modulation schemes: OFDM, F-OFDM, and UFMC. We employed PSD, PAPR, BER, and Constellation Diagrams to compare OFDM, which is currently used in 4G technology, with F-OFDM and UFMC, respectively. Following the comparative investigation, we discovered that F-OFDM significantly outperforms UFMC and OFDM, both modulation techniques. We also determined that F-OFDM promises enhanced efficiency in 5G technology by accurately proving all simulations for a potential application.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115680785","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 : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101632
Amita Singha, M. A. Ullah
This article presents an audio watermarking technique. The proposed technique can ensure the security of audio by using multiple images as watermarks as it is comparatively difficult to remove more than one watermark. Therefore, the originality of the audio signal can be ensured to a significant level. This technique is developed by the modified use of discrete wavelet transform (DWT) and singular value decomposition (SVD). By that modification, the whole energy spectrum of the watermarks is utilized. By doing so, the watermarks are inserted in parts in various regions of the host audio that will make the removal of the mark images difficult and the modified use of SVD, as well as DWT, ensures the creation of those different regions. The robustness of the technique is tested against some real-life scenarios.
{"title":"Security of an Audio using Multiple Watermarking","authors":"Amita Singha, M. A. Ullah","doi":"10.1109/ECCE57851.2023.10101632","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101632","url":null,"abstract":"This article presents an audio watermarking technique. The proposed technique can ensure the security of audio by using multiple images as watermarks as it is comparatively difficult to remove more than one watermark. Therefore, the originality of the audio signal can be ensured to a significant level. This technique is developed by the modified use of discrete wavelet transform (DWT) and singular value decomposition (SVD). By that modification, the whole energy spectrum of the watermarks is utilized. By doing so, the watermarks are inserted in parts in various regions of the host audio that will make the removal of the mark images difficult and the modified use of SVD, as well as DWT, ensures the creation of those different regions. The robustness of the technique is tested against some real-life scenarios.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116645373","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 e-commerce has grown in recent years, so online shopping has increased with the number of product reviews posted online. The consumer's recommendations or complaints influence significantly customers and their decision to purchase. Sentiment polarity analysis is the interpretation and classification of text-based data. The main goal of our work is to categorize each customer's review into a class that represents its quality (positive or negative). Our sentiment polarity detection consists of the following steps: preprocessing, feature extraction, training, classification and generalization. First, the reviews were transformed into vector representation using different techniques of Tf-Idf and Tokenizer. Then, we trained with a machine learning model of SVM Linear, RBF, Sigmoid kernel and a deep learning model LSTM. After that, we evaluated the models using accuracy, f1-score, precision, recall. Our LSTM model predicts an accuracy of 86% for Amazon-based customer reviews and an accuracy of 85% for Yelp customer reviews.
{"title":"Sentiment Polarity Detection Using Machine Learning and Deep Learning","authors":"Ahasanur Rahman Mehul, Syed Montasir Mahmood, Tajri Tabassum, Puja Chakraborty","doi":"10.1109/ECCE57851.2023.10101494","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101494","url":null,"abstract":"As e-commerce has grown in recent years, so online shopping has increased with the number of product reviews posted online. The consumer's recommendations or complaints influence significantly customers and their decision to purchase. Sentiment polarity analysis is the interpretation and classification of text-based data. The main goal of our work is to categorize each customer's review into a class that represents its quality (positive or negative). Our sentiment polarity detection consists of the following steps: preprocessing, feature extraction, training, classification and generalization. First, the reviews were transformed into vector representation using different techniques of Tf-Idf and Tokenizer. Then, we trained with a machine learning model of SVM Linear, RBF, Sigmoid kernel and a deep learning model LSTM. After that, we evaluated the models using accuracy, f1-score, precision, recall. Our LSTM model predicts an accuracy of 86% for Amazon-based customer reviews and an accuracy of 85% for Yelp customer reviews.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114422810","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 : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101640
K. M. Z. Rahman, Md. Akhter Uz Zaman, Sunjida Sultana, Md. Soyaeb Hasan, Shahriar Bin Salim, Wasi Mashrur, Md. Rafiqul Islam
The impact of recessed gate metal on the performance of double-gate junctionless MOSFET (DG-JLMOSFET) has been studied considering GaAs as channel material. The geometry of the gate metal is changed to obtain the best performance by recessing it to gate oxide for 1 nm vertically and extending it up to 9 nm horizontally on both sides. Changing the gate's geometrical shape and physical dimension, the leakage current is found to be reduced significantly for a fixed channel length of 10 nm. This results in a higher ION/IoFF ratio of ~ 1010 which in turn mitigates the drain induced barrier lowering (DIBL). The calculated results on various short channel effects (SCEs) indicate that the proposed model seems to have a greater drain current and a decreased subthreshold swing (SS) of 71 mV/Dec. The results of various figure of merits (FOMs) show that GaAs-based recessed gate DG-JLMOSFETs are extremely viable for the advancement of the upcoming nano-technology.
{"title":"Effect of Recessed Gate Metal on Performance Analysis of GaAs Based DG-JLMOSFET","authors":"K. M. Z. Rahman, Md. Akhter Uz Zaman, Sunjida Sultana, Md. Soyaeb Hasan, Shahriar Bin Salim, Wasi Mashrur, Md. Rafiqul Islam","doi":"10.1109/ECCE57851.2023.10101640","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101640","url":null,"abstract":"The impact of recessed gate metal on the performance of double-gate junctionless MOSFET (DG-JLMOSFET) has been studied considering GaAs as channel material. The geometry of the gate metal is changed to obtain the best performance by recessing it to gate oxide for 1 nm vertically and extending it up to 9 nm horizontally on both sides. Changing the gate's geometrical shape and physical dimension, the leakage current is found to be reduced significantly for a fixed channel length of 10 nm. This results in a higher ION/IoFF ratio of ~ 1010 which in turn mitigates the drain induced barrier lowering (DIBL). The calculated results on various short channel effects (SCEs) indicate that the proposed model seems to have a greater drain current and a decreased subthreshold swing (SS) of 71 mV/Dec. The results of various figure of merits (FOMs) show that GaAs-based recessed gate DG-JLMOSFETs are extremely viable for the advancement of the upcoming nano-technology.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130379648","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 : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101539
R. A. Hridhee, Biddut Bhowmik, Q. D. Hossain
Alzheimer's Disease (AD) is a neurological disorder which causes brain cells to die, resulting in memory loss associ-ated with cognitive impairment. Typical symptoms of Alzheimer's disease are- memory loss, language difficulties, and impulsive or erratic behaviour. AD varies from a mild disorder to moderate deterioration, until a severe cognitive impairment finally occurs. Currently, there is no cure to this disease. Only early diagnosis can help provide timely medical support and facilitate necessary healthcare. Magnetic Resonance Imaging (MRI) is widely used in the diagnosis of Alzheimer's Disease. Several image processing techniques are used to develop automated systems for detection and classification of AD from brain MRI. In this paper, we proposed three Convolutional Neural Network (CNN) models to detect and classify four stages of Alzheimer's disease from 2D MRI. We used the VGG16 and the Xception models with transfer learning approach, and a fully customised CNN model for the classification task. The customised model performed the best with accuracy of 0.9477, and F1-score of 0.9481. The proposed method performed better than the conventional Support Vector Machine (SVM) techniques. It is less complex, and less time consuming with better efficiencies than CNN techniques utilizing 3D MRI images.
{"title":"Alzheimer's Disease Classification From 2D MRI Brain Scans Using Convolutional Neural Networks","authors":"R. A. Hridhee, Biddut Bhowmik, Q. D. Hossain","doi":"10.1109/ECCE57851.2023.10101539","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101539","url":null,"abstract":"Alzheimer's Disease (AD) is a neurological disorder which causes brain cells to die, resulting in memory loss associ-ated with cognitive impairment. Typical symptoms of Alzheimer's disease are- memory loss, language difficulties, and impulsive or erratic behaviour. AD varies from a mild disorder to moderate deterioration, until a severe cognitive impairment finally occurs. Currently, there is no cure to this disease. Only early diagnosis can help provide timely medical support and facilitate necessary healthcare. Magnetic Resonance Imaging (MRI) is widely used in the diagnosis of Alzheimer's Disease. Several image processing techniques are used to develop automated systems for detection and classification of AD from brain MRI. In this paper, we proposed three Convolutional Neural Network (CNN) models to detect and classify four stages of Alzheimer's disease from 2D MRI. We used the VGG16 and the Xception models with transfer learning approach, and a fully customised CNN model for the classification task. The customised model performed the best with accuracy of 0.9477, and F1-score of 0.9481. The proposed method performed better than the conventional Support Vector Machine (SVM) techniques. It is less complex, and less time consuming with better efficiencies than CNN techniques utilizing 3D MRI images.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125913962","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：