Pub Date : 2022-02-24DOI: 10.1109/icaeee54957.2022.9836392
Reana Raen, Sheikh Md. Rabiul Islam, Redwanul Islam
Human being wants to convey their feelings by interacting with people surrounding them. But this is not a case of speech-hearing impaired people whom we call deaf-dumb. This community face lots of helplessness & discrimination. According to World Federation of the Deaf (WFD), there are approximately 70 million deaf & mute people. Previous research works focused on building a communication system for this community but most are prone to inconveniency, for example, heavyweight, expensive, and user-unfriendly. Our paper focused on introducing a system with simplicity, ease of operability, portability. Overcoming the helplessness, we developed a smart hand talk system through which, hand gestures provided by the user will give text & speech output and send the output to a server for emergency response of doctors or family members. The proposed system can control appliances. It sheds light on measuring actions of deaf-dumb people using flex sensors attached to the glove. The glove is placed in hands, whenever a specific sign/gesture will be commanded for action, the analog value will be obtained and the corresponding function will be identified by the arduino board. A xampp server connected to the system will ensure emergency care by doctors or family members.
{"title":"A Smart Hand Glove that Converts Gesture into Text & Speech to Assist the Handicapped-(Handtalk)","authors":"Reana Raen, Sheikh Md. Rabiul Islam, Redwanul Islam","doi":"10.1109/icaeee54957.2022.9836392","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836392","url":null,"abstract":"Human being wants to convey their feelings by interacting with people surrounding them. But this is not a case of speech-hearing impaired people whom we call deaf-dumb. This community face lots of helplessness & discrimination. According to World Federation of the Deaf (WFD), there are approximately 70 million deaf & mute people. Previous research works focused on building a communication system for this community but most are prone to inconveniency, for example, heavyweight, expensive, and user-unfriendly. Our paper focused on introducing a system with simplicity, ease of operability, portability. Overcoming the helplessness, we developed a smart hand talk system through which, hand gestures provided by the user will give text & speech output and send the output to a server for emergency response of doctors or family members. The proposed system can control appliances. It sheds light on measuring actions of deaf-dumb people using flex sensors attached to the glove. The glove is placed in hands, whenever a specific sign/gesture will be commanded for action, the analog value will be obtained and the corresponding function will be identified by the arduino board. A xampp server connected to the system will ensure emergency care by doctors or family members.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"12 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":"115631217","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/icaeee54957.2022.9836371
Nayem Hasen, Aminur Rahman, Showmik Singha, Tahmid Aziz Chowdhury
Perovskite (CH3NH3PbI3) solar cells (PSCs) have recently been invented due to their desirable characteristics such as high absorption, low cost, ease of fabrication, and rapidly improving efficiencies. In recent years, the effectiveness of organometallic halide perovskite as an absorber layer has already surpassed 20%. Dielectric nanostructures are being considered as a possible option for third generation photovoltaics, such as PSCs, due to lower losses and simpler fabrication. Dielectric nanostructured antireflection coatings, on the other hand, have recently emerged as a method for reducing reflection and improving the power conversion efficiency (PCE) of a thin-film absorber that was previously inefficient. In this research, two different types of nanostructures are used on the perovskite absorber layer that reduced light reflection and enhanced the power absorption, short-circuit current, and efficiency of the solar cells. Furthermore, as demonstrated how changing the nanostructure size has an effect on the absorption enhancement. Utilizing the finite difference time domain (FDTD) and coupled optical-electrical models, the proposed optimum nanostructures exhibit greater than 90% power absorption, with the maximum enhanced photocurrent. Total photocurrent increased by 17-20% compared to conventional planar PSCs, with a maximum PCE of 16.78%, representing 37% enhancement throughout the entire wavelength range.
{"title":"A Comparative Analysis of Two Dielectric Nanostructures to Enhance Efficiency of Perovskite Solar Cells","authors":"Nayem Hasen, Aminur Rahman, Showmik Singha, Tahmid Aziz Chowdhury","doi":"10.1109/icaeee54957.2022.9836371","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836371","url":null,"abstract":"Perovskite (CH3NH3PbI3) solar cells (PSCs) have recently been invented due to their desirable characteristics such as high absorption, low cost, ease of fabrication, and rapidly improving efficiencies. In recent years, the effectiveness of organometallic halide perovskite as an absorber layer has already surpassed 20%. Dielectric nanostructures are being considered as a possible option for third generation photovoltaics, such as PSCs, due to lower losses and simpler fabrication. Dielectric nanostructured antireflection coatings, on the other hand, have recently emerged as a method for reducing reflection and improving the power conversion efficiency (PCE) of a thin-film absorber that was previously inefficient. In this research, two different types of nanostructures are used on the perovskite absorber layer that reduced light reflection and enhanced the power absorption, short-circuit current, and efficiency of the solar cells. Furthermore, as demonstrated how changing the nanostructure size has an effect on the absorption enhancement. Utilizing the finite difference time domain (FDTD) and coupled optical-electrical models, the proposed optimum nanostructures exhibit greater than 90% power absorption, with the maximum enhanced photocurrent. Total photocurrent increased by 17-20% compared to conventional planar PSCs, with a maximum PCE of 16.78%, representing 37% enhancement throughout the entire wavelength range.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"22 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":"124851101","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/icaeee54957.2022.9836418
M.M. Shahiduzzaman, Nowreen Haque Biswas, M. Momin, Raihan Sikdar
The topmost crucial muscular body part is our heart, as it pumps blood to all the other organs in our body. Being the essential organ, mortals suffering from heart disease over the last twenty years has been the deadliest disease globally and top number one destroyer for human. Over the recent years, the health industry and technology have worked together to find ways to cut back the risk of cardiac diseases in humans. For early disease prediction, machine learning is a necessity for healthcare as it functions without human interaction. In this paper, a cardiovascular data set with 70,000 data and 12 attributes are analyzed and implemented for the early prognosis of cardiovascular disease. Using the voting ensemble classifier, we combined five different machine learning algorithms to achieve good overall accuracy. K - nearest neighbor classifier gained an ac-curacy of 75%, which was the best amongst Logistic Regression, Random Forest, Gradient Boosting, and Bernoulli Naive Bayes. This proposal benefits and eases the work for clinicians and doctors and provides appropriate care for heart disease patients.
{"title":"Prognosis of Cardiovascular Disease Using Machine Learning Procedures","authors":"M.M. Shahiduzzaman, Nowreen Haque Biswas, M. Momin, Raihan Sikdar","doi":"10.1109/icaeee54957.2022.9836418","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836418","url":null,"abstract":"The topmost crucial muscular body part is our heart, as it pumps blood to all the other organs in our body. Being the essential organ, mortals suffering from heart disease over the last twenty years has been the deadliest disease globally and top number one destroyer for human. Over the recent years, the health industry and technology have worked together to find ways to cut back the risk of cardiac diseases in humans. For early disease prediction, machine learning is a necessity for healthcare as it functions without human interaction. In this paper, a cardiovascular data set with 70,000 data and 12 attributes are analyzed and implemented for the early prognosis of cardiovascular disease. Using the voting ensemble classifier, we combined five different machine learning algorithms to achieve good overall accuracy. K - nearest neighbor classifier gained an ac-curacy of 75%, which was the best amongst Logistic Regression, Random Forest, Gradient Boosting, and Bernoulli Naive Bayes. This proposal benefits and eases the work for clinicians and doctors and provides appropriate care for heart disease patients.","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":"129900338","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/icaeee54957.2022.9836440
Ummey Hany Ainan, Md. Nur-E-Arefin
Now-a-days banking sector is considered as the back-bone of modern economy of a country. Predicting correct performance of banks of a country can show the nearest future of a country. In past statistical measurement is used to predict bank performance. Nowadays Machine Learning (ML) approaches are used in banking sector for better accuracy. Different Hybrid models are also widely used for better performance. In this work three famous Machine Learning classifiers named Random Forest (RF), Support Vector Machine (SVM) and Logistic Regression (LR) are combined with Genetic Algorithm (GA) to make three hybrid models named GA+RF, GA+SVM and GA+LR. The dataset used in this work are consist of 50 Turkish banks, 30 American banks and 20 European banks. The data have 24 performance indicators that measures performance from the year of 2010 to 2020. CAMEL technique is applied in this dataset in order to find ratings of the banks. In this study Genetic Algorithm is also used as optimizer and feature selector. At the end the models are evaluated with and without feature selection as well as with and without optimization. In this study GA+SVM hybrid model with optimization but without feature selection provides best accuracy among all the models which is 100% test accuracy. On the other hand, GA+LR model provide 81.81 % test accuracy with feature selection but without optimization which is lowest in the whole study.
{"title":"Prediction of Bank Performance Using Machine Learning and Genetic Algorithm Hybrid Models","authors":"Ummey Hany Ainan, Md. Nur-E-Arefin","doi":"10.1109/icaeee54957.2022.9836440","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836440","url":null,"abstract":"Now-a-days banking sector is considered as the back-bone of modern economy of a country. Predicting correct performance of banks of a country can show the nearest future of a country. In past statistical measurement is used to predict bank performance. Nowadays Machine Learning (ML) approaches are used in banking sector for better accuracy. Different Hybrid models are also widely used for better performance. In this work three famous Machine Learning classifiers named Random Forest (RF), Support Vector Machine (SVM) and Logistic Regression (LR) are combined with Genetic Algorithm (GA) to make three hybrid models named GA+RF, GA+SVM and GA+LR. The dataset used in this work are consist of 50 Turkish banks, 30 American banks and 20 European banks. The data have 24 performance indicators that measures performance from the year of 2010 to 2020. CAMEL technique is applied in this dataset in order to find ratings of the banks. In this study Genetic Algorithm is also used as optimizer and feature selector. At the end the models are evaluated with and without feature selection as well as with and without optimization. In this study GA+SVM hybrid model with optimization but without feature selection provides best accuracy among all the models which is 100% test accuracy. On the other hand, GA+LR model provide 81.81 % test accuracy with feature selection but without optimization which is lowest in the whole study.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"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":"130287773","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/icaeee54957.2022.9836424
S. R. Hasan, M. Z. Chowdhury, Md. Saiam
In the near future, the high data rate challenge would not be possible by using the radio frequency (RF) only. As the user will increase, the network traffic will increase proportionally. Visible light communication (VLC) is a good solution to support huge number of indoor users. VLC has high data rate over RF communication. The way internet users are increasing, we have to think over VLC technology. Not only the data rate is a concern but also its security, cost, and reliability have to be considered for a good communication network. Quantum technology makes a great impact on communication and computing in both areas. Quantum communication technology has the ability to support better channel capacity, higher security, and lower latency. This paper combines the quantum technology over the existing VLC and compares the performance between quantum visible light communication performance (QVLC) over the existing VLC system. Research findings clearly show that the performance of QVLC is better than the existing VLC system.
{"title":"A New Quantum Visible Light Communication for Future Wireless Network Systems","authors":"S. R. Hasan, M. Z. Chowdhury, Md. Saiam","doi":"10.1109/icaeee54957.2022.9836424","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836424","url":null,"abstract":"In the near future, the high data rate challenge would not be possible by using the radio frequency (RF) only. As the user will increase, the network traffic will increase proportionally. Visible light communication (VLC) is a good solution to support huge number of indoor users. VLC has high data rate over RF communication. The way internet users are increasing, we have to think over VLC technology. Not only the data rate is a concern but also its security, cost, and reliability have to be considered for a good communication network. Quantum technology makes a great impact on communication and computing in both areas. Quantum communication technology has the ability to support better channel capacity, higher security, and lower latency. This paper combines the quantum technology over the existing VLC and compares the performance between quantum visible light communication performance (QVLC) over the existing VLC system. Research findings clearly show that the performance of QVLC is better than the existing VLC system.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"69 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":"126189482","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/icaeee54957.2022.9836476
Tasnia Hasnat, S. A. Islam, Sumit Hassan Eshan, Raja Rashidul Hasan, Jiadul Islam, M. Rahman
In this paper, a 5G on-body patch has been designed for detecting COVID-19 affected lung. A new material Single Wall Carbon Nanotube (SWCNT) is used to design the patch of the antenna. Copper is used to designing the ground and FR-4 (lossy) is used in the substrate. The antenna has a total thickness of 5.5 mm where the patch thickness is 0.5 mm, the substrate thickness is 4.5 mm, and the ground thickness is 0.5 mm. The total volume (length x width x thickness) of this antenna is 80 mm x 80 mm x 5.5 mm (35200 mm3). For detecting COVID-19, designed two human lung phantom body models such as a COVID-19 affected lung model and a non-affected normal lung model. The patch antenna and all the models were designed in CST Microwave Studio. All the dielectric properties and other valuable parameters of the antenna materials and lung phantom models were collected and used for designing the antenna and phantom lung models. The antenna's return loss (S1,1) is −27.498894 dB, gain is 3.007 dB, VSWR is 1.0880641, directivity is 6.007 dB, resonant frequency is 6.296 GHz, SAR 1.19 W/Kg, bandwidth is 1.8174 GHz and the efficiency is 61% in free space. In this pandemic situation, this antenna can be given a new step for detecting COVID-19 affected lung.
{"title":"SWCNT Based On-Body Antenna For Detecting COVID-19 Affected Lung Using 5G-Band","authors":"Tasnia Hasnat, S. A. Islam, Sumit Hassan Eshan, Raja Rashidul Hasan, Jiadul Islam, M. Rahman","doi":"10.1109/icaeee54957.2022.9836476","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836476","url":null,"abstract":"In this paper, a 5G on-body patch has been designed for detecting COVID-19 affected lung. A new material Single Wall Carbon Nanotube (SWCNT) is used to design the patch of the antenna. Copper is used to designing the ground and FR-4 (lossy) is used in the substrate. The antenna has a total thickness of 5.5 mm where the patch thickness is 0.5 mm, the substrate thickness is 4.5 mm, and the ground thickness is 0.5 mm. The total volume (length x width x thickness) of this antenna is 80 mm x 80 mm x 5.5 mm (35200 mm3). For detecting COVID-19, designed two human lung phantom body models such as a COVID-19 affected lung model and a non-affected normal lung model. The patch antenna and all the models were designed in CST Microwave Studio. All the dielectric properties and other valuable parameters of the antenna materials and lung phantom models were collected and used for designing the antenna and phantom lung models. The antenna's return loss (S1,1) is −27.498894 dB, gain is 3.007 dB, VSWR is 1.0880641, directivity is 6.007 dB, resonant frequency is 6.296 GHz, SAR 1.19 W/Kg, bandwidth is 1.8174 GHz and the efficiency is 61% in free space. In this pandemic situation, this antenna can be given a new step for detecting COVID-19 affected lung.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"26 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":"126059967","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/icaeee54957.2022.9836432
A. Shatil, Shuvra Saha, Kazi Firoz Ahmed, A. N. M. S. Hasan, S. Rahman
Floating solar panels become a recent trend in solar energy harvesting systems. Countries like Bangladesh where land is scarce and densely populated could conduct feasibility tests about these floating panels. There are many rivers, canals, beel around Bangladesh which could be a perfect place for such kind of experiment. This paper investigates the possibility to set up floating solar panels in Chalan Beel, Natore, Rajshahi. Throughout the experimental setup, it is also observed the comparison between the ground-mounted panel and floating panel based on electrical parameters like output power along with costing. After the analysis, it is found that the energy conversion cost in the floating panel set up is 0.57 cents/kWh, which is acceptable comparably with other countries.
{"title":"Design and Comparison of Floating Solar Panel for Chalan Beel","authors":"A. Shatil, Shuvra Saha, Kazi Firoz Ahmed, A. N. M. S. Hasan, S. Rahman","doi":"10.1109/icaeee54957.2022.9836432","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836432","url":null,"abstract":"Floating solar panels become a recent trend in solar energy harvesting systems. Countries like Bangladesh where land is scarce and densely populated could conduct feasibility tests about these floating panels. There are many rivers, canals, beel around Bangladesh which could be a perfect place for such kind of experiment. This paper investigates the possibility to set up floating solar panels in Chalan Beel, Natore, Rajshahi. Throughout the experimental setup, it is also observed the comparison between the ground-mounted panel and floating panel based on electrical parameters like output power along with costing. After the analysis, it is found that the energy conversion cost in the floating panel set up is 0.57 cents/kWh, which is acceptable comparably with other countries.","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":"131546082","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/icaeee54957.2022.9836407
Manash Sarker, Md. Forhad Hossain, Fahmida Rahman Liza, S. N. Sakib, Abdullah Al Farooq
The growth of social media is causing the emergence of hate speech. Email extortion and cyberbullying are on the rise in Bangladesh, along with online sexual harassment of women. In order to prevent these crimes, studies on Bengali comments on social media have become progressively important. However, the requisite datasets are scarce for this kind of study. The motive of this research is to create a dataset of Bangla comments from social platforms and develop a classifier model as well as to detect whether the comments are social or anti-social quickly and efficiently. 2000 comments were gathered from Facebook and YouTube, two prominent platforms for social media. In our study, an artificial neural network model like Gated Recurrent Unit (GRU), and supervised machine learning classifiers like Logistic Regression (LR), Random Forest (RF), Multinomial Naive Bayes (MNB), and Support Vector Machine (SVM) were utilized in our study to distinguish between anti-social and socially acceptable comments. Finally, language models such as unigrams, bigrams, and trigrams have been implemented in our research. To the best of our knowledge, there are no studies regarding the anti-social classification in Bangla language. This work will help to prevent anti-social activities in Bangla community.
{"title":"A Machine Learning Approach to Classify Anti-social Bengali Comments on Social Media","authors":"Manash Sarker, Md. Forhad Hossain, Fahmida Rahman Liza, S. N. Sakib, Abdullah Al Farooq","doi":"10.1109/icaeee54957.2022.9836407","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836407","url":null,"abstract":"The growth of social media is causing the emergence of hate speech. Email extortion and cyberbullying are on the rise in Bangladesh, along with online sexual harassment of women. In order to prevent these crimes, studies on Bengali comments on social media have become progressively important. However, the requisite datasets are scarce for this kind of study. The motive of this research is to create a dataset of Bangla comments from social platforms and develop a classifier model as well as to detect whether the comments are social or anti-social quickly and efficiently. 2000 comments were gathered from Facebook and YouTube, two prominent platforms for social media. In our study, an artificial neural network model like Gated Recurrent Unit (GRU), and supervised machine learning classifiers like Logistic Regression (LR), Random Forest (RF), Multinomial Naive Bayes (MNB), and Support Vector Machine (SVM) were utilized in our study to distinguish between anti-social and socially acceptable comments. Finally, language models such as unigrams, bigrams, and trigrams have been implemented in our research. To the best of our knowledge, there are no studies regarding the anti-social classification in Bangla language. This work will help to prevent anti-social activities in Bangla community.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"1 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":"133194787","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/icaeee54957.2022.9836502
Sowrav Chowdhury, A. Doulah, M. Rasheduzzaman
Accurate assessment of respiratory sounds can aid the early detection of respiratory disorders such as crackles, wheezes, chronic obstructive pulmonary disease (COPD), and pneumonia. Typically, a stethoscope is used as a first aid to listen to respiratory sounds and initial diagnosis of underlying diseases. Unlike a traditional stethoscope, a digital stethoscope can offer recording of respiratory sounds and automatically diagnose abnormalities through machine learning technology. However, accurate machine learning models rely on good-quality data and features. The medical quality stethoscopes may provide high-quality data, however, are highly expensive. Alternatively, there are immense challenges in obtaining quality data from low-cost stethoscopes. The current work developed three inexpensive digital stethoscopes and compared the performance concerning six time and frequency domain features. The quality of extracted features was examined by Pearson's linear correlation coefficients. The results suggested that one of the low-cost stethoscopes exhibited 84% (5 out 6 features) highly correlated features. Based on the findings of this work, it may potentially help the researcher to carefully select low-cost stethoscopes for acquiring data.
{"title":"Quality Assessment of Respiratory Sounds Extracted from Self-Assembled Digital Stethoscopes","authors":"Sowrav Chowdhury, A. Doulah, M. Rasheduzzaman","doi":"10.1109/icaeee54957.2022.9836502","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836502","url":null,"abstract":"Accurate assessment of respiratory sounds can aid the early detection of respiratory disorders such as crackles, wheezes, chronic obstructive pulmonary disease (COPD), and pneumonia. Typically, a stethoscope is used as a first aid to listen to respiratory sounds and initial diagnosis of underlying diseases. Unlike a traditional stethoscope, a digital stethoscope can offer recording of respiratory sounds and automatically diagnose abnormalities through machine learning technology. However, accurate machine learning models rely on good-quality data and features. The medical quality stethoscopes may provide high-quality data, however, are highly expensive. Alternatively, there are immense challenges in obtaining quality data from low-cost stethoscopes. The current work developed three inexpensive digital stethoscopes and compared the performance concerning six time and frequency domain features. The quality of extracted features was examined by Pearson's linear correlation coefficients. The results suggested that one of the low-cost stethoscopes exhibited 84% (5 out 6 features) highly correlated features. Based on the findings of this work, it may potentially help the researcher to carefully select low-cost stethoscopes for acquiring data.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"22 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":"133885192","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/icaeee54957.2022.9836564
K. Shahiduzzaman, Md Salah Uddin Yusuf
Human activity recognition (HAR) is an important area for elderly care. Because with an effective HAR clinical management authorities can monitor movement, abnormality, human behavior, chronicle diseases, and suddenly fall remotely. HAR may also reduce the workload of a caregiver. Our research mainly focuses on HAR for sudden fall detection and prediction. Usually, raw signals or features extracted from raw signals are used in HAR developmental works, which can increase false alarm rates (FAR). Besides, it is hard to differentiate various human activities through the illustration of this time-series signal. If these activities can be patterned in regular shape and can be expressed with a simple mathematical equation, then the recognition algorithm can not only detect daily activities but also predict them. Therefore, we will present a new and much effective technical way by using visual-inertial odometry (VIO) for human activity recognition in this paper. We consider walking, running and jumping activities to show our claims. From the results, we can see that considered human activities are easy to differentiate. 'Goodness of fit’ of these activities will show how we could model mathematically them.
{"title":"Generating a Visual-Inertial Odometry Dataset based on a Helmet Prototype for Recognizing Human Activities","authors":"K. Shahiduzzaman, Md Salah Uddin Yusuf","doi":"10.1109/icaeee54957.2022.9836564","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836564","url":null,"abstract":"Human activity recognition (HAR) is an important area for elderly care. Because with an effective HAR clinical management authorities can monitor movement, abnormality, human behavior, chronicle diseases, and suddenly fall remotely. HAR may also reduce the workload of a caregiver. Our research mainly focuses on HAR for sudden fall detection and prediction. Usually, raw signals or features extracted from raw signals are used in HAR developmental works, which can increase false alarm rates (FAR). Besides, it is hard to differentiate various human activities through the illustration of this time-series signal. If these activities can be patterned in regular shape and can be expressed with a simple mathematical equation, then the recognition algorithm can not only detect daily activities but also predict them. Therefore, we will present a new and much effective technical way by using visual-inertial odometry (VIO) for human activity recognition in this paper. We consider walking, running and jumping activities to show our claims. From the results, we can see that considered human activities are easy to differentiate. 'Goodness of fit’ of these activities will show how we could model mathematically them.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"34 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":"116298894","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：