Pub Date : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101568
Nishan Das, M. S. Mia, Mohammad Tausiful Islam, A. Mostafa, Koli Dhar, R. Azim
This paper illustrates a dual-band MIMO antenna for WiFi/WiMAX/ WLAN/Bluetooth/C-band communication/ mid-5G applications. The single antenna element exhibits dual resonant modes at around 5.50 GHz and 8.02 GHz and achieved two working bands of 4.27 - 6.34 GHz and 6.59 - 10.05 GHz. The MIMO comprises four fork-shaped radiators orthogonally positioned on 1.6 mm wide FR4 material of size 35 mm ˟ 35 mm. The patches of the MIMO are modified to have an impedance band of 3.78 - 6.47 GHz and 6.47 - 9.5 GHz, which resonates at 4.68, 6.13, and 7.35 GHz. The planned MIMO antenna achieves more than -23 dB (maximum -45 dB) isolation throughout the working bands. The considered MIMO antenna also has a low ECC (around 0.04), high diversity gain (around 10 dB), an ultimate gain of 3.78 dBi, and a maximum efficiency of 81.8%. These advantages and features make the anticipated antenna appropriate for WLAN/Bluetooth/WiMAX/WiFi/C-band/5G sub-6 GHz bands.
{"title":"A Dual-band MIMO Antenna for 5G sub-6 GHz/WiFi/WiMAX/WLAN/Bluetooth/C-band Applications","authors":"Nishan Das, M. S. Mia, Mohammad Tausiful Islam, A. Mostafa, Koli Dhar, R. Azim","doi":"10.1109/ECCE57851.2023.10101568","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101568","url":null,"abstract":"This paper illustrates a dual-band MIMO antenna for WiFi/WiMAX/ WLAN/Bluetooth/C-band communication/ mid-5G applications. The single antenna element exhibits dual resonant modes at around 5.50 GHz and 8.02 GHz and achieved two working bands of 4.27 - 6.34 GHz and 6.59 - 10.05 GHz. The MIMO comprises four fork-shaped radiators orthogonally positioned on 1.6 mm wide FR4 material of size 35 mm ˟ 35 mm. The patches of the MIMO are modified to have an impedance band of 3.78 - 6.47 GHz and 6.47 - 9.5 GHz, which resonates at 4.68, 6.13, and 7.35 GHz. The planned MIMO antenna achieves more than -23 dB (maximum -45 dB) isolation throughout the working bands. The considered MIMO antenna also has a low ECC (around 0.04), high diversity gain (around 10 dB), an ultimate gain of 3.78 dBi, and a maximum efficiency of 81.8%. These advantages and features make the anticipated antenna appropriate for WLAN/Bluetooth/WiMAX/WiFi/C-band/5G sub-6 GHz bands.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"114 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":"122056664","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/ECCE57851.2023.10101496
N. Jahan, Saha Reno, Mamun Ahmed
To travel globally, a passport is the only official travel document that authenticates the holder's identity and citizenship which is provided by the government. Digital passports provide adamant verification through documentation that tangibly marks the passport owner using biometric techniques because it holds an electronic chip into the passport, also known as an e-passport. The biometric method uses a combination of RFID and fingerprint scanning technology. Notwithstanding, RFID chips have numerous security threats as the information confidentiality can easily be hacked and it is not entirely hassle-free. To get rid of these challenges as a potential remedy, in this paper we propose Hyperledger to secure e-passport management, which in contrast to the public blockchain, is an open-source private blockchain with strong security. When compared to the standard blockchain development framework, the legitimacy of transactions in a private blockchain powered by Hyperledger is substantially distinct, which is enable more effective and quicker transactions while maintaining essential security features. The InterPlanetary File System (IPFS), which has diverse security measures like access control features, non-modifiable data, and immutable history records, and this private ledger have both been used to safeguard private passport information and biometric data.
{"title":"Securing E-Passport Management Using Private-Permissioned Blockchain and IPFS","authors":"N. Jahan, Saha Reno, Mamun Ahmed","doi":"10.1109/ECCE57851.2023.10101496","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101496","url":null,"abstract":"To travel globally, a passport is the only official travel document that authenticates the holder's identity and citizenship which is provided by the government. Digital passports provide adamant verification through documentation that tangibly marks the passport owner using biometric techniques because it holds an electronic chip into the passport, also known as an e-passport. The biometric method uses a combination of RFID and fingerprint scanning technology. Notwithstanding, RFID chips have numerous security threats as the information confidentiality can easily be hacked and it is not entirely hassle-free. To get rid of these challenges as a potential remedy, in this paper we propose Hyperledger to secure e-passport management, which in contrast to the public blockchain, is an open-source private blockchain with strong security. When compared to the standard blockchain development framework, the legitimacy of transactions in a private blockchain powered by Hyperledger is substantially distinct, which is enable more effective and quicker transactions while maintaining essential security features. The InterPlanetary File System (IPFS), which has diverse security measures like access control features, non-modifiable data, and immutable history records, and this private ledger have both been used to safeguard private passport information and biometric data.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"22 7 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":"126125182","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/ECCE57851.2023.10101628
Md. Shamsul Alam, M. Alim, A. Rezazadeh
In this paper, GaAs-based nano-pHEMT has been measured and modeled using small signal and large signal analysis. Three distinct simulation methods have been used for DC characterization, and the results have been compared with measurements. Two separate simulation methods have been used for RF characterization, and the results have been verified with measurements. It is shown that the simulated findings accurately reflect the measured values. Additionally, it was found that both the large and small signal models-are agreed with the measured data up to 22 GHz at the same biasing point. The simulation and measurement findings are differed with less than 10%, demonstrating that the modeling procedures were accurate.
{"title":"Measurement and Modeling of GaAs Based Nano-pHEMT: Small Signal to Large Signal Analysis","authors":"Md. Shamsul Alam, M. Alim, A. Rezazadeh","doi":"10.1109/ECCE57851.2023.10101628","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101628","url":null,"abstract":"In this paper, GaAs-based nano-pHEMT has been measured and modeled using small signal and large signal analysis. Three distinct simulation methods have been used for DC characterization, and the results have been compared with measurements. Two separate simulation methods have been used for RF characterization, and the results have been verified with measurements. It is shown that the simulated findings accurately reflect the measured values. Additionally, it was found that both the large and small signal models-are agreed with the measured data up to 22 GHz at the same biasing point. The simulation and measurement findings are differed with less than 10%, demonstrating that the modeling procedures were accurate.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"132 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":"121249888","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}
Residents of the remote areas live in clusters and some of those areas are situated far from the national grid line. Supplying power to all those clustered houses from the national gridline is difficult and also not economically feasible. Therefore, supplying power from an efficient locally generated power system might be a suitable solution. In this research, a local hybrid power generation and distribution model from a diesel generator, along with hydro, wind, and solar systems are studied for Keokradong, which is one of the most visited remote tourist spots in Bangladesh. Multiple hybrid energy system models are analyzed for optimization using the HOMER software. In addition to hybrid systems connected to the grid, only renewable-based hybrid systems have been examined. Traditional fossil fuel-based energy sources and electricity output per unit cost are compared in a cost per kilowatt-hour comparison. The proposed method can be utilized for powering off-grid clustered areas of hilly and remote regions around the world in a cost-effective and environment-friendly manner.
{"title":"Design and Optimization of a Locally Generated Hybrid Energy System for Powering the Off-grid Clustered Houses of Chattogram Hill Tracts","authors":"Md. Aminul Islam, Adreeta Jami Disha, K.M. Ilham-Ar-Raiyan, Mooaj Sadaqat Chowdhury","doi":"10.1109/ECCE57851.2023.10101587","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101587","url":null,"abstract":"Residents of the remote areas live in clusters and some of those areas are situated far from the national grid line. Supplying power to all those clustered houses from the national gridline is difficult and also not economically feasible. Therefore, supplying power from an efficient locally generated power system might be a suitable solution. In this research, a local hybrid power generation and distribution model from a diesel generator, along with hydro, wind, and solar systems are studied for Keokradong, which is one of the most visited remote tourist spots in Bangladesh. Multiple hybrid energy system models are analyzed for optimization using the HOMER software. In addition to hybrid systems connected to the grid, only renewable-based hybrid systems have been examined. Traditional fossil fuel-based energy sources and electricity output per unit cost are compared in a cost per kilowatt-hour comparison. The proposed method can be utilized for powering off-grid clustered areas of hilly and remote regions around the world in a cost-effective and environment-friendly manner.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"3 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":"127863983","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/ECCE57851.2023.10101616
Avishek Gupta, Md. Mynul Islam, Md. Rafiqul Islam, Zafar Sadek, Tarik Reza Toha, Anupom Mondol, Shaikh Mohammad Mominul Alam
In our country, a great number of industries especially textile industries consume a large amount of water at different textile processes, and at the same time, contaminated water is discharged into the environment at high volume because of a lack of proper monitoring and controlling system. There is a significant number of research works about water quality monitoring and controlling system, which are not automated and also have no notification system for abnormal situations. We propose an IoT-based automatic system with a water quality monitoring device and a pH-controlling device that provides water quality information and transmits data through Wi-Fi and Bluetooth for both online and offline conditions. The monitoring device can detect several important water quality parameters like DO, ORP, TDS, Temperature, EC, and pH. Our device can detect the abnormal value of the water and alarm the users through SMS and Email. The pH controlling device can control pH automatically and dose chemicals at required quantities adaptively in need to neutralize. To improve the sensor value, we calibrated pH, TDS, and EC sensors by developing equations from regression analysis. Between different regressions, we choose polynomial regression (order 2) as it shows the highest coefficient of determination value, which is 0.97655, 0.999, and 0.9999 for pH, TDS, and EC sensors, respectively. We implement our monitoring device in four textile industries and measure the quality parameters of the inlet and outlet points of the effluent treatment plant of each factory. Our monitoring device can detect water quality parameters and can identify between less and well-treated water. This monitoring device can be used at any water treatment plant and the pH controlling device can control the pH of any process, especially a wastewater treatment plant.
{"title":"Devising an IoT-Based Water Quality Monitoring and pH Controlling System for Textile ETP","authors":"Avishek Gupta, Md. Mynul Islam, Md. Rafiqul Islam, Zafar Sadek, Tarik Reza Toha, Anupom Mondol, Shaikh Mohammad Mominul Alam","doi":"10.1109/ECCE57851.2023.10101616","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101616","url":null,"abstract":"In our country, a great number of industries especially textile industries consume a large amount of water at different textile processes, and at the same time, contaminated water is discharged into the environment at high volume because of a lack of proper monitoring and controlling system. There is a significant number of research works about water quality monitoring and controlling system, which are not automated and also have no notification system for abnormal situations. We propose an IoT-based automatic system with a water quality monitoring device and a pH-controlling device that provides water quality information and transmits data through Wi-Fi and Bluetooth for both online and offline conditions. The monitoring device can detect several important water quality parameters like DO, ORP, TDS, Temperature, EC, and pH. Our device can detect the abnormal value of the water and alarm the users through SMS and Email. The pH controlling device can control pH automatically and dose chemicals at required quantities adaptively in need to neutralize. To improve the sensor value, we calibrated pH, TDS, and EC sensors by developing equations from regression analysis. Between different regressions, we choose polynomial regression (order 2) as it shows the highest coefficient of determination value, which is 0.97655, 0.999, and 0.9999 for pH, TDS, and EC sensors, respectively. We implement our monitoring device in four textile industries and measure the quality parameters of the inlet and outlet points of the effluent treatment plant of each factory. Our monitoring device can detect water quality parameters and can identify between less and well-treated water. This monitoring device can be used at any water treatment plant and the pH controlling device can control the pH of any process, especially a wastewater treatment plant.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"39 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":"134502547","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/ECCE57851.2023.10101638
M. Alam, Nurul Bashar, Susmita Sarker, Sumiya Alam Lopa, Tofayel Ahmed
This research compares the output voltage and harmonics of open-loop and closed-loop PID-controlled boost converters. Open-loop systems produce output based on their input voltage. The output voltage's THD & the capacitor's and inductor's input and output currents' THD don't change much with voltage. Using the same circuit and setting the reference voltage at half the open loop output voltage, the closed-loop system's output voltage remains almost constant for input voltages below the reference value. If the input voltage crosses the reference voltage, the output voltage jumps up somewhat. The closed-loop method is less effective than the open-loop method since the output voltage THD and the input and output current THD of the inductor and capacitor are higher and vary more with voltage. Open loop output voltage THD was 375.06% and closed loop THD was 1742.84% for a 17-volt input.
{"title":"Comparative Study of the Open-loop Boost Converter and the Closed-loop PID Controlled Boost Converters","authors":"M. Alam, Nurul Bashar, Susmita Sarker, Sumiya Alam Lopa, Tofayel Ahmed","doi":"10.1109/ECCE57851.2023.10101638","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101638","url":null,"abstract":"This research compares the output voltage and harmonics of open-loop and closed-loop PID-controlled boost converters. Open-loop systems produce output based on their input voltage. The output voltage's THD & the capacitor's and inductor's input and output currents' THD don't change much with voltage. Using the same circuit and setting the reference voltage at half the open loop output voltage, the closed-loop system's output voltage remains almost constant for input voltages below the reference value. If the input voltage crosses the reference voltage, the output voltage jumps up somewhat. The closed-loop method is less effective than the open-loop method since the output voltage THD and the input and output current THD of the inductor and capacitor are higher and vary more with voltage. Open loop output voltage THD was 375.06% and closed loop THD was 1742.84% for a 17-volt input.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"2 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":"124012646","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/ECCE57851.2023.10101565
M. Hemel, K. Minhad, K. Ooi, M. Reaz, M. S. Amin, M. Bhuiyan
Healthcare professionals are quite concerned with constantly monitoring their patients. An Internet of Things (IoT) based wireless health monitoring station can be a viable option to reduce human labor. The design study of a single-ended ring oscillator-based voltage-controlled oscillator (RO-VCO) optimized for implementation in an IoT-based wireless health monitoring system is presented in this paper. The schematic was created using a 50 nm CMOS process. By varying the control voltage from 0.9 V to 1.5 V the voltage-controlled oscillator can operate at 1.67 to 3.13 GHz. A supply voltage of 1 V was used to achieve the oscillation frequency of 2.4 GHz. Such a VCO will be an essential module for the proposed IoT-based patient monitoring station and other ISM band applications.
{"title":"Ring Oscillator Based Voltage Controlled Oscillator Design for IoT Based Wireless Patient Monitoring Station in 50 nm CMOS Process","authors":"M. Hemel, K. Minhad, K. Ooi, M. Reaz, M. S. Amin, M. Bhuiyan","doi":"10.1109/ECCE57851.2023.10101565","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101565","url":null,"abstract":"Healthcare professionals are quite concerned with constantly monitoring their patients. An Internet of Things (IoT) based wireless health monitoring station can be a viable option to reduce human labor. The design study of a single-ended ring oscillator-based voltage-controlled oscillator (RO-VCO) optimized for implementation in an IoT-based wireless health monitoring system is presented in this paper. The schematic was created using a 50 nm CMOS process. By varying the control voltage from 0.9 V to 1.5 V the voltage-controlled oscillator can operate at 1.67 to 3.13 GHz. A supply voltage of 1 V was used to achieve the oscillation frequency of 2.4 GHz. Such a VCO will be an essential module for the proposed IoT-based patient monitoring station and other ISM band applications.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"73 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":"116063869","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/ECCE57851.2023.10101607
Md. Abu Dayan Siddik, Mohammad Shahidur Rahman
Drowsiness has severe effects on the safety of human life. The worldwide death rate due to drowsy driving is quite alarming. As the implementation of artificial intelligence (AI) is growing faster, this paper describes an attempt to implement machine learning (ML) to detect drowsiness. 120 videos of 60 participants are collected from the Real-Life Drowsiness Video Dataset made by a research team of the Vision-Learning-Mining Lab from the University of Texas at Arlington. Then Eye Aspect Ratio, Mouth Aspect Ratio, Pupil Circularity, and Mouth Aspect Ratio Over Eye Aspect Ratio, Nose Length, Chin Length, Nose Length Over Chin Length Ratio are extracted as features of each participant using the 3D Face-Mesh 468 facial landmarks system from those videos. After that, each feature is normalized by its mean and standard deviation. Then the CSV dataset is generated using seven initial and seven normalized features. A total of 30000 instances are there in the dataset. A total of eight classification algorithms are implemented to build the model. The dataset is split such that the individual in the train set will not be in the test set to test the proposed model's ability to predict drowsiness for new faces. 5-fold cross-validation is implemented to measure performance for each algorithm. Convolutional Neural Network (CNN) yields maximum accuracy (91.63%). The state of any individual's eye closing, rapid eye blinking, yawning, putting a hand on the mouth during yawning, and head posing too much up or down can be detected as drowsiness by the proposed model.
{"title":"Drowsiness and Lethargy Detection Using Machine Learning Techniques","authors":"Md. Abu Dayan Siddik, Mohammad Shahidur Rahman","doi":"10.1109/ECCE57851.2023.10101607","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101607","url":null,"abstract":"Drowsiness has severe effects on the safety of human life. The worldwide death rate due to drowsy driving is quite alarming. As the implementation of artificial intelligence (AI) is growing faster, this paper describes an attempt to implement machine learning (ML) to detect drowsiness. 120 videos of 60 participants are collected from the Real-Life Drowsiness Video Dataset made by a research team of the Vision-Learning-Mining Lab from the University of Texas at Arlington. Then Eye Aspect Ratio, Mouth Aspect Ratio, Pupil Circularity, and Mouth Aspect Ratio Over Eye Aspect Ratio, Nose Length, Chin Length, Nose Length Over Chin Length Ratio are extracted as features of each participant using the 3D Face-Mesh 468 facial landmarks system from those videos. After that, each feature is normalized by its mean and standard deviation. Then the CSV dataset is generated using seven initial and seven normalized features. A total of 30000 instances are there in the dataset. A total of eight classification algorithms are implemented to build the model. The dataset is split such that the individual in the train set will not be in the test set to test the proposed model's ability to predict drowsiness for new faces. 5-fold cross-validation is implemented to measure performance for each algorithm. Convolutional Neural Network (CNN) yields maximum accuracy (91.63%). The state of any individual's eye closing, rapid eye blinking, yawning, putting a hand on the mouth during yawning, and head posing too much up or down can be detected as drowsiness by the proposed model.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"9 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":"128065537","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/ECCE57851.2023.10101658
Nahiyan Bin Noor, Ishraq Ahmed
It is widely accepted that music is humanity's universal language since it can spread happiness and excitement throughout people's lives. Music is a form of art that is highly regarded worldwide. There are many ways that music lyrics affect our daily lives. In the music industry, it is crucial to prevent the reproduction of songs whose lyrics are toxic or unsuitable for children. Our mood might be impacted by listening to particularly toxic or non-toxic music. The listener's experience might be enhanced if the recommendation method eliminates toxicity. In this study, we use machine learning (ML) algorithms to classify lyrics from various musical genres and performers as toxic or non-toxic. Utilizing the Detoxify model, the toxicity score was generated and labelled the songs as toxic and non-toxic based on the scores. The study demonstrates that the configuration using the lyric data set along with TF-IDF vectorization and Ensemble of Logistic Regression, Support Vector Machine and Decision Tree as an algorithm surpasses all other designs with 94% accuracy. This classification will help the authority and policymakers of music industries to categorize the song based on the label and mention in the song description which is not appropriate for the children and set guidelines to prevent toxicity via songs.
{"title":"An Efficient Technique of Predicting Toxicity on Music Lyrics Machine Learning","authors":"Nahiyan Bin Noor, Ishraq Ahmed","doi":"10.1109/ECCE57851.2023.10101658","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101658","url":null,"abstract":"It is widely accepted that music is humanity's universal language since it can spread happiness and excitement throughout people's lives. Music is a form of art that is highly regarded worldwide. There are many ways that music lyrics affect our daily lives. In the music industry, it is crucial to prevent the reproduction of songs whose lyrics are toxic or unsuitable for children. Our mood might be impacted by listening to particularly toxic or non-toxic music. The listener's experience might be enhanced if the recommendation method eliminates toxicity. In this study, we use machine learning (ML) algorithms to classify lyrics from various musical genres and performers as toxic or non-toxic. Utilizing the Detoxify model, the toxicity score was generated and labelled the songs as toxic and non-toxic based on the scores. The study demonstrates that the configuration using the lyric data set along with TF-IDF vectorization and Ensemble of Logistic Regression, Support Vector Machine and Decision Tree as an algorithm surpasses all other designs with 94% accuracy. This classification will help the authority and policymakers of music industries to categorize the song based on the label and mention in the song description which is not appropriate for the children and set guidelines to prevent toxicity via songs.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"48 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":"121549497","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/ECCE57851.2023.10101594
Maodudul Hasan, Htet Wai Htun, E. Nishiyama, I. Toyoda
This manuscript proposes a single-feed quad-polarized antenna for 5.8-G Hz band applications. The antenna contains a switchable feed network, a single microstrip antenna and PIN diodes. The antenna also employs a short-ended microstrip-line perturbation for achieving circular polarization. The switchable feed network employs two PIN diodes to control its two branch to achieve two linear (LP) modes switching. A third diode is integrated between the perturbation segment and upper corner of the patch element. By activating the perturbation to function together with the radiating patch element, the same antenna can generate two circular polarization (CP) modes. The concept is examined through simulation. The impedance bandwidth for LP and CP conditions are about 1.6% and 2.6%, respectively. Around 0.7% 3-dB axial ratio bandwidth is observed within the range of interest.
本文提出了一种用于5.8 g Hz频段应用的单馈四极化天线。该天线包含一个可切换馈电网络，一个单微带天线和PIN二极管。该天线还采用短端微带线微扰实现圆极化。可切换馈电网络采用两个PIN二极管控制其两个分支，实现两种线性(LP)模式切换。第三二极管集成在微扰段和贴片元件的上角之间。通过激活微扰与辐射贴片元件共同作用，同一天线可以产生两种圆极化模式。通过仿真验证了这一概念。低电压和高电压条件下的阻抗带宽分别约为1.6%和2.6%。在感兴趣的范围内观察到约0.7% 3 db轴比带宽。
{"title":"Proposal of Single-Feed Microstrip Antenna for Quad-Polarization Agility With Short-Ended Microstrip- Line Perturbation","authors":"Maodudul Hasan, Htet Wai Htun, E. Nishiyama, I. Toyoda","doi":"10.1109/ECCE57851.2023.10101594","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101594","url":null,"abstract":"This manuscript proposes a single-feed quad-polarized antenna for 5.8-G Hz band applications. The antenna contains a switchable feed network, a single microstrip antenna and PIN diodes. The antenna also employs a short-ended microstrip-line perturbation for achieving circular polarization. The switchable feed network employs two PIN diodes to control its two branch to achieve two linear (LP) modes switching. A third diode is integrated between the perturbation segment and upper corner of the patch element. By activating the perturbation to function together with the radiating patch element, the same antenna can generate two circular polarization (CP) modes. The concept is examined through simulation. The impedance bandwidth for LP and CP conditions are about 1.6% and 2.6%, respectively. Around 0.7% 3-dB axial ratio bandwidth is observed within the range of interest.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"41 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":"121710889","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：