Pub Date : 2021-12-22DOI: 10.1109/ICEEE54059.2021.9718779
Shah Alam, Mahfuzulhoq Chowdhury, A. Siddique
Metro-rail based rapid transport system is regarded as one of the prominent technology that can minimize the working hour wastage problem of a developed country due to traffic jams. However, to reap the benefits for both passengers and metro-rail authorities, a smart ticketing system with user’s authorization, seat reservation, online payment, and destination announcement system is also required for a metro-rail based transport system. To cope up with the existing challenges, this paper presents a user-friendly android application for metro-rail based rapid transport system in Bangladesh that can offer a smart ticketing, users authorization by verifying QR code, and notify the metro-rail passengers when they arrive close to their final destination. With the proposed system, users can purchase a metro-rail ticket with pre-booking facility by checking suitable seats and monetary balance. A user review result is incorporated to examine the necessity of the proposed system.
{"title":"A User-friendly Android Application Featuring Smart Ticketing System and Destination Announcement for Metro Rail based Rapid Transport System in Bangladesh","authors":"Shah Alam, Mahfuzulhoq Chowdhury, A. Siddique","doi":"10.1109/ICEEE54059.2021.9718779","DOIUrl":"https://doi.org/10.1109/ICEEE54059.2021.9718779","url":null,"abstract":"Metro-rail based rapid transport system is regarded as one of the prominent technology that can minimize the working hour wastage problem of a developed country due to traffic jams. However, to reap the benefits for both passengers and metro-rail authorities, a smart ticketing system with user’s authorization, seat reservation, online payment, and destination announcement system is also required for a metro-rail based transport system. To cope up with the existing challenges, this paper presents a user-friendly android application for metro-rail based rapid transport system in Bangladesh that can offer a smart ticketing, users authorization by verifying QR code, and notify the metro-rail passengers when they arrive close to their final destination. With the proposed system, users can purchase a metro-rail ticket with pre-booking facility by checking suitable seats and monetary balance. A user review result is incorporated to examine the necessity of the proposed system.","PeriodicalId":188366,"journal":{"name":"2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128889388","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 : 2021-12-22DOI: 10.1109/ICEEE54059.2021.9718857
Md. Hasibul Islam, Kusum Tara, H. Rahman, A. K. Sarkar
Human heart is one of the most complex structures of human body deals with unique and indispensable functionality to keep humans alive. Judgment of heart’s efficacy often relies on to what extent sympatho-vagal balance prevails and keeps the heart beating. This work deals with a two-approach-based solution to assess the secretion of acetylcholine (ACh) and norepinephrine (NE) inside heart’s myocardial cell during R-peak formation. Approach-I deals with formation of ECG peak, generation of action potential, and details of ACh and NE secretion inside myocardial cell. Approach-II analyzes and processes obtained cardiac signals in order to find out features necessary to define cardiac condition. Their combined analysis ends up refuting the assessing process with Respiratory sinus arrhythmia (RSA), Cardiac autonomic balance (CAB), and Cardiac autonomic regulation (CAR) in the range respectively of 0.04±0.025, −15.96±1.38, and 16.08±1.37 for NE predominance and 0.086±0.015, −14.63±0.333, and 14.76±0.33 for ACh predominance inside heart’s myocardial cell.
{"title":"An Approach to Assess ACh and NE Secretion inside Heart’s Myocardial Cell during R-peak Formation","authors":"Md. Hasibul Islam, Kusum Tara, H. Rahman, A. K. Sarkar","doi":"10.1109/ICEEE54059.2021.9718857","DOIUrl":"https://doi.org/10.1109/ICEEE54059.2021.9718857","url":null,"abstract":"Human heart is one of the most complex structures of human body deals with unique and indispensable functionality to keep humans alive. Judgment of heart’s efficacy often relies on to what extent sympatho-vagal balance prevails and keeps the heart beating. This work deals with a two-approach-based solution to assess the secretion of acetylcholine (ACh) and norepinephrine (NE) inside heart’s myocardial cell during R-peak formation. Approach-I deals with formation of ECG peak, generation of action potential, and details of ACh and NE secretion inside myocardial cell. Approach-II analyzes and processes obtained cardiac signals in order to find out features necessary to define cardiac condition. Their combined analysis ends up refuting the assessing process with Respiratory sinus arrhythmia (RSA), Cardiac autonomic balance (CAB), and Cardiac autonomic regulation (CAR) in the range respectively of 0.04±0.025, −15.96±1.38, and 16.08±1.37 for NE predominance and 0.086±0.015, −14.63±0.333, and 14.76±0.33 for ACh predominance inside heart’s myocardial cell.","PeriodicalId":188366,"journal":{"name":"2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121296381","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 : 2021-12-22DOI: 10.1109/ICEEE54059.2021.9718788
Nafisa Tabassum, Nazifa Tabassum
Driver drowsiness is one of the major factors behind road accidents. Every year thousands of people lose their lives and property due to this problem. Proper solutions should be taken to minimize this incident. So far some methods have been developed for detecting drowsiness, but proper real-time detection remains a challenge. As a result, we are proposing an FPGA-based approach that can detect drowsiness from EEG signals within nanoseconds. To design the proposed system, the magnitude of the EEG signal frequency is estimated by using 128-FFT, then the data is observed sample by sample by the timing diagram for comparing the duration or distance to detect the existence of theta region equal to the threshold value. After detecting drowsiness, the system would trigger an alarm within nanoseconds to alert the user. As the system is designed on FPGA, it is dynamically adaptable and capable of parallel processing which gives a very fast response (12ns). This proposed system is designed on XILINX VIVADO software by using Verilog HDL language. The design has been simulated on the Artix-7 field-programmable gate array (FPGA) development board by the software. This design offers some outstanding features such as a memory capacity of only 11.32 MB, power consumption of 82.338 mW with low voltage, and current of 1.8V and 1.8mA respectively. The proposed system can be used in real-time drowsiness detection while playing a major role in avoiding road accidents considerably.
{"title":"Real-Time Drowsiness Alert System from EEG Signal Based on FPGA","authors":"Nafisa Tabassum, Nazifa Tabassum","doi":"10.1109/ICEEE54059.2021.9718788","DOIUrl":"https://doi.org/10.1109/ICEEE54059.2021.9718788","url":null,"abstract":"Driver drowsiness is one of the major factors behind road accidents. Every year thousands of people lose their lives and property due to this problem. Proper solutions should be taken to minimize this incident. So far some methods have been developed for detecting drowsiness, but proper real-time detection remains a challenge. As a result, we are proposing an FPGA-based approach that can detect drowsiness from EEG signals within nanoseconds. To design the proposed system, the magnitude of the EEG signal frequency is estimated by using 128-FFT, then the data is observed sample by sample by the timing diagram for comparing the duration or distance to detect the existence of theta region equal to the threshold value. After detecting drowsiness, the system would trigger an alarm within nanoseconds to alert the user. As the system is designed on FPGA, it is dynamically adaptable and capable of parallel processing which gives a very fast response (12ns). This proposed system is designed on XILINX VIVADO software by using Verilog HDL language. The design has been simulated on the Artix-7 field-programmable gate array (FPGA) development board by the software. This design offers some outstanding features such as a memory capacity of only 11.32 MB, power consumption of 82.338 mW with low voltage, and current of 1.8V and 1.8mA respectively. The proposed system can be used in real-time drowsiness detection while playing a major role in avoiding road accidents considerably.","PeriodicalId":188366,"journal":{"name":"2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130650985","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 : 2021-12-22DOI: 10.1109/ICEEE54059.2021.9718775
Simanta Siddha, Abidur Rahman, R. R. Mahmud
By using the size variation technique of the patch, a high gain reflect array antenna which can be easily fit in a small satellite, has been analyzed in this study. The unit cell consisting of a ring patch and a square slotted circular patch has been designed for the best performance of 9×9 reflect array antenna. This unique form of unit cell is constructed on a thin dielectric layer with a 0.183×freespace wavelength thickness and two circular ring patches. By using the size variation technique of the patches, 350° moderate phase variation is obtained by simulating in proper boundary condition. On a square 2D plane, the reflect array antenna has 81-unit cells with a center feed horn antenna. At 10GHz, the planned reflect array offers 96% antenna efficiency. The reflect array antenna’s gain margin is 20dBi at 10GHz, with a 21% 1-dB gain bandwidth and a 28% 3-dB gain bandwidth, according to the simulation results.
{"title":"Design of X-Band Reflect Array Antenna using Circular Ring Patches","authors":"Simanta Siddha, Abidur Rahman, R. R. Mahmud","doi":"10.1109/ICEEE54059.2021.9718775","DOIUrl":"https://doi.org/10.1109/ICEEE54059.2021.9718775","url":null,"abstract":"By using the size variation technique of the patch, a high gain reflect array antenna which can be easily fit in a small satellite, has been analyzed in this study. The unit cell consisting of a ring patch and a square slotted circular patch has been designed for the best performance of 9×9 reflect array antenna. This unique form of unit cell is constructed on a thin dielectric layer with a 0.183×freespace wavelength thickness and two circular ring patches. By using the size variation technique of the patches, 350° moderate phase variation is obtained by simulating in proper boundary condition. On a square 2D plane, the reflect array antenna has 81-unit cells with a center feed horn antenna. At 10GHz, the planned reflect array offers 96% antenna efficiency. The reflect array antenna’s gain margin is 20dBi at 10GHz, with a 21% 1-dB gain bandwidth and a 28% 3-dB gain bandwidth, according to the simulation results.","PeriodicalId":188366,"journal":{"name":"2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE)","volume":"76 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116351051","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 : 2021-12-22DOI: 10.1109/ICEEE54059.2021.9718771
Md. Masrur Saqib, Md Mahmudul Hasan, Md Rafiul Islam, Jayed Hasan Sunny, Siam Shakil, G. M. Saad, Orchi Datta
The world is passing a terrible time while lives are despairing due to coronavirus. In Covid-19, most of the patients suffer from low oxygen saturation. Different types of devices are used to increase the oxygen level. This paper discusses a helmet-based Continuous Positive Airway Pressure (CPAP) device’s design and implementation. A blower generates positive pressure, while a pressure sensor adjusts the required pressure. A TFT display is used to monitor the data, and two rotary encoders are used to set the required value. Two Arduino boards are used as real-time and user interface controllers. The hardware simulations and PCB designs are done in the Proteus software. The mechanical body of the CPAP device was designed in Solidworks software. A helmet is connected to the CPAP, also designed in the Solidworks software. The oxygen mixed pressurized air goes through the pipe to the helmet. Finally, the cost of the device is also presented in this paper.
{"title":"Design and Implementation of a Helmet-based, Noninvasive CPAP Devices for COVID-19","authors":"Md. Masrur Saqib, Md Mahmudul Hasan, Md Rafiul Islam, Jayed Hasan Sunny, Siam Shakil, G. M. Saad, Orchi Datta","doi":"10.1109/ICEEE54059.2021.9718771","DOIUrl":"https://doi.org/10.1109/ICEEE54059.2021.9718771","url":null,"abstract":"The world is passing a terrible time while lives are despairing due to coronavirus. In Covid-19, most of the patients suffer from low oxygen saturation. Different types of devices are used to increase the oxygen level. This paper discusses a helmet-based Continuous Positive Airway Pressure (CPAP) device’s design and implementation. A blower generates positive pressure, while a pressure sensor adjusts the required pressure. A TFT display is used to monitor the data, and two rotary encoders are used to set the required value. Two Arduino boards are used as real-time and user interface controllers. The hardware simulations and PCB designs are done in the Proteus software. The mechanical body of the CPAP device was designed in Solidworks software. A helmet is connected to the CPAP, also designed in the Solidworks software. The oxygen mixed pressurized air goes through the pipe to the helmet. Finally, the cost of the device is also presented in this paper.","PeriodicalId":188366,"journal":{"name":"2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117332139","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 : 2021-12-22DOI: 10.1109/ICEEE54059.2021.9718792
Ruhana Nishad, K. Shaha, Abdul Khaleque, Md. Sarwar Hosen, Md. Tarek Rahman
The effects of the number of rectangular bars in the cladding of an antiresonant hollow core fiber are well discussed, in this work, to optimize the fiber geometry. Adding rectangular bars within the elliptical tubes results in more antiresonant element layers, hence, the fiber maintains stunning accomplishments: a minimal leakage loss of 6.45×10−4 dB per km at 1.50 μm wavelength by keeping a leakage loss of < 6×10−3 dB per km over 250 nm bandwidth (1.32 μm to 1.57 μm). The presented fiber also reports a low bend loss of 9.0×10−3 dB per km for 12 cm bend radius at the same wavelength and an excellent higher order mode extinction ratio of 5.47×103 by having higher than 150 value over the telecom band. The above achievements lead our fiber better than the recently related reported fibers.
本文讨论了抗谐振空心光纤包层中矩形棒数的影响，以优化光纤的几何结构。在椭圆管内增加矩形棒可以产生更多的抗谐振元件层，因此，光纤保持了惊人的成就:在1.50 μm波长处，通过在250 nm带宽(1.32 μm至1.57 μm)范围内保持泄漏损耗< 6×10−3 dB / km，从而保持了最小的泄漏损耗6.45×10−4 dB / km。该光纤在相同波长下，弯曲半径为12 cm，弯曲损耗为9.0×10−3 dB / km，并且在电信频段上具有高于150的高阶模式消光比，达到5.47×103。以上成果使我们的纤维优于最近报道的相关纤维。
{"title":"Impact of Cladding Rectangular Bars on the Antiresonant Hollow Core Fiber","authors":"Ruhana Nishad, K. Shaha, Abdul Khaleque, Md. Sarwar Hosen, Md. Tarek Rahman","doi":"10.1109/ICEEE54059.2021.9718792","DOIUrl":"https://doi.org/10.1109/ICEEE54059.2021.9718792","url":null,"abstract":"The effects of the number of rectangular bars in the cladding of an antiresonant hollow core fiber are well discussed, in this work, to optimize the fiber geometry. Adding rectangular bars within the elliptical tubes results in more antiresonant element layers, hence, the fiber maintains stunning accomplishments: a minimal leakage loss of 6.45×10−4 dB per km at 1.50 μm wavelength by keeping a leakage loss of < 6×10−3 dB per km over 250 nm bandwidth (1.32 μm to 1.57 μm). The presented fiber also reports a low bend loss of 9.0×10−3 dB per km for 12 cm bend radius at the same wavelength and an excellent higher order mode extinction ratio of 5.47×103 by having higher than 150 value over the telecom band. The above achievements lead our fiber better than the recently related reported fibers.","PeriodicalId":188366,"journal":{"name":"2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115673879","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 : 2021-12-22DOI: 10.1109/ICEEE54059.2021.9718795
Mohammad Hanif, N. Mohammad, K. Ahmmed
Due to the involvement of multiple unpredictable factors, optimization in Elevator Group Control System (EGCS) is a challenging task. The major optimization parameters in most previous research articles were the passengers’ average waiting time (AWT) or average journey time (AJT). Owing to the global energy crisis, however, optimizing the energy-consumption in EGCS has become a pivotal issue. In order to overcome this concern, an optimization approach utilizing Artificial Bee Colony (ABC) algorithm, which has never been applied in EGCS, is implemented in this study. Furthermore, the performance of this ABC algorithm in energy-saving EGCS is compared to that of Genetic Algorithm (GA), another popular swarm intelligence algorithm. According to the comparisons, ABC is better at minimizing energy-consumption by avoiding trapping in local minima when compared to GA. Most notably, in 100 independent simulations, this ABC algorithm exhibits substantially lower standard deviation than that of GA.
{"title":"Artificial Bee Colony Algorithm for Optimization in Energy-saving Elevator Group Control System","authors":"Mohammad Hanif, N. Mohammad, K. Ahmmed","doi":"10.1109/ICEEE54059.2021.9718795","DOIUrl":"https://doi.org/10.1109/ICEEE54059.2021.9718795","url":null,"abstract":"Due to the involvement of multiple unpredictable factors, optimization in Elevator Group Control System (EGCS) is a challenging task. The major optimization parameters in most previous research articles were the passengers’ average waiting time (AWT) or average journey time (AJT). Owing to the global energy crisis, however, optimizing the energy-consumption in EGCS has become a pivotal issue. In order to overcome this concern, an optimization approach utilizing Artificial Bee Colony (ABC) algorithm, which has never been applied in EGCS, is implemented in this study. Furthermore, the performance of this ABC algorithm in energy-saving EGCS is compared to that of Genetic Algorithm (GA), another popular swarm intelligence algorithm. According to the comparisons, ABC is better at minimizing energy-consumption by avoiding trapping in local minima when compared to GA. Most notably, in 100 independent simulations, this ABC algorithm exhibits substantially lower standard deviation than that of GA.","PeriodicalId":188366,"journal":{"name":"2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE)","volume":"88 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120980885","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}
At present, we all know that the Recommendation System is essential. Our lives are continuously impacted by the Recommendation System. Its main objective is to suggest a relevant item or item list as per the user’s requirement. In many cases, it recommends the user’s desired item or item list based on rating prediction, and this prediction accuracy is considered to be the system’s actual accuracy. But can the rating prediction accuracy be considered the system’s true accuracy in ordered items prediction? Rating prediction system even after predicting a near-exact rating, there could be a difference between the actual item list and the predicted item list. We attempted to find answers to these issues by working with the College Recommendation System. We have used different machine learning-based models in our work for rating prediction. And we have measured the correlation between the actual item list and the predicted item list using the Longest Common Subsequence algorithm. Our analysis showed that the rating prediction accuracy does not always reflect the system’s actual accuracy in the scenario of ordered items prediction. The accuracy of the system should be verified by how closely the predicted item list matches the actual item list when recommending ordered items. A pattern-matching algorithm like - Longest Common Subsequence can be considered as an accuracy metric in this context.
{"title":"Pattern Matching Based Metric for Recommending Ordered Items","authors":"Md. Mustafizur Rahman, Zanifer Afsana Stephi, Moqsadur Rahman","doi":"10.1109/ICEEE54059.2021.9718931","DOIUrl":"https://doi.org/10.1109/ICEEE54059.2021.9718931","url":null,"abstract":"At present, we all know that the Recommendation System is essential. Our lives are continuously impacted by the Recommendation System. Its main objective is to suggest a relevant item or item list as per the user’s requirement. In many cases, it recommends the user’s desired item or item list based on rating prediction, and this prediction accuracy is considered to be the system’s actual accuracy. But can the rating prediction accuracy be considered the system’s true accuracy in ordered items prediction? Rating prediction system even after predicting a near-exact rating, there could be a difference between the actual item list and the predicted item list. We attempted to find answers to these issues by working with the College Recommendation System. We have used different machine learning-based models in our work for rating prediction. And we have measured the correlation between the actual item list and the predicted item list using the Longest Common Subsequence algorithm. Our analysis showed that the rating prediction accuracy does not always reflect the system’s actual accuracy in the scenario of ordered items prediction. The accuracy of the system should be verified by how closely the predicted item list matches the actual item list when recommending ordered items. A pattern-matching algorithm like - Longest Common Subsequence can be considered as an accuracy metric in this context.","PeriodicalId":188366,"journal":{"name":"2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE)","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133555586","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 : 2021-12-22DOI: 10.1109/ICEEE54059.2021.9718790
Jahidul Islam, Sajjad Bhuiyan, A. Hossain, Amit Shaha Surja, Md. Shahid Iqbal
Gastric cancer (stomach cancer) is now the sixth most common diagnosed cancer and the third leading cause of cancer mortality in the world. Gastric Erosion, Gastric Ulcer, and Stomach Polyp are examples of Gastric Precancerous Diseases (GPDs) that can lead to gastric cancer if not recognized early or misdiagnosed. Classifying these GPDs is a difficult task. Undoubtedly, Deep learning networks (DNNs) have shown to be effective in solving the challenge of image categorization. Next to practical difficulty is the limitation of the availability of medical images for DNN training. In this paper, a hybrid model is proposed to classify GPDs. The model is a combination of Convolution Neural Network (CNN) Gastric Precancerous Diseases Feature Extractor Network (GPDFENet) for feature extraction and Support Vector Machine (SVM) for classification. An open dataset “Data-Open-Access4PLoS-One” including erosion, ulcer, and polyp endoscopic images were utilized to train the network. After evaluation, the network is then compared to various pre-trained networks such as AlexNet, ResNet-50, ResNet-101, and Inception V3. The proposed model (GPDFENet+SVM) has achieved an accuracy of 93.22%.
{"title":"Classification of Gastric Precancerous Diseases using Hybrid CNN-SVM","authors":"Jahidul Islam, Sajjad Bhuiyan, A. Hossain, Amit Shaha Surja, Md. Shahid Iqbal","doi":"10.1109/ICEEE54059.2021.9718790","DOIUrl":"https://doi.org/10.1109/ICEEE54059.2021.9718790","url":null,"abstract":"Gastric cancer (stomach cancer) is now the sixth most common diagnosed cancer and the third leading cause of cancer mortality in the world. Gastric Erosion, Gastric Ulcer, and Stomach Polyp are examples of Gastric Precancerous Diseases (GPDs) that can lead to gastric cancer if not recognized early or misdiagnosed. Classifying these GPDs is a difficult task. Undoubtedly, Deep learning networks (DNNs) have shown to be effective in solving the challenge of image categorization. Next to practical difficulty is the limitation of the availability of medical images for DNN training. In this paper, a hybrid model is proposed to classify GPDs. The model is a combination of Convolution Neural Network (CNN) Gastric Precancerous Diseases Feature Extractor Network (GPDFENet) for feature extraction and Support Vector Machine (SVM) for classification. An open dataset “Data-Open-Access4PLoS-One” including erosion, ulcer, and polyp endoscopic images were utilized to train the network. After evaluation, the network is then compared to various pre-trained networks such as AlexNet, ResNet-50, ResNet-101, and Inception V3. The proposed model (GPDFENet+SVM) has achieved an accuracy of 93.22%.","PeriodicalId":188366,"journal":{"name":"2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129701459","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 : 2021-12-22DOI: 10.1109/ICEEE54059.2021.9718799
Md. Mahmudul Hasan, Md. Shajid Hussain, M. S. Rana, M. H. K. Roni
In this research work, population extremal optimization (PEO) with a hybrid mutation operation was used to optimize the speed loop’s proportional-integral-derivative (PID) controller of the indirect field-oriented control (IFOC) of a three-phase induction motor (IM). A two-degree-of-freedom (2-DOF) structure of the speed control loop for smoothing the electromagnetic torque responses without manipulating the current controllers was proposed. It was formed by considering the q-axis stator current, to which the electromagnetic torque is directly proportional, as a disturbance variable. The sum of integral time absolute error (ITAE) and a chattering penalty function was used as the objective function for controller optimization. The proposed PEO-based 2-DOF control achieved a lower objective function value than designs based on particle swarm optimization (PSO) and a genetic algorithm (GA). Also, appreciably superior performances of the 2-DOF control over the 1-DOF one was observed in terms of torque smoothing as well as speed tracking. The robustness of the proposed controller was examined by simulating a wide range of parameter variations. The modeling and simulation of the system was conducted in a MATLAB/Simulink platform.
{"title":"Population Extremal Optimization Based 2-DOF Control Strategy for Field Oriented Control of Induction Motor","authors":"Md. Mahmudul Hasan, Md. Shajid Hussain, M. S. Rana, M. H. K. Roni","doi":"10.1109/ICEEE54059.2021.9718799","DOIUrl":"https://doi.org/10.1109/ICEEE54059.2021.9718799","url":null,"abstract":"In this research work, population extremal optimization (PEO) with a hybrid mutation operation was used to optimize the speed loop’s proportional-integral-derivative (PID) controller of the indirect field-oriented control (IFOC) of a three-phase induction motor (IM). A two-degree-of-freedom (2-DOF) structure of the speed control loop for smoothing the electromagnetic torque responses without manipulating the current controllers was proposed. It was formed by considering the q-axis stator current, to which the electromagnetic torque is directly proportional, as a disturbance variable. The sum of integral time absolute error (ITAE) and a chattering penalty function was used as the objective function for controller optimization. The proposed PEO-based 2-DOF control achieved a lower objective function value than designs based on particle swarm optimization (PSO) and a genetic algorithm (GA). Also, appreciably superior performances of the 2-DOF control over the 1-DOF one was observed in terms of torque smoothing as well as speed tracking. The robustness of the proposed controller was examined by simulating a wide range of parameter variations. The modeling and simulation of the system was conducted in a MATLAB/Simulink platform.","PeriodicalId":188366,"journal":{"name":"2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE)","volume":"388 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116329168","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：