Pub Date : 2020-11-05DOI: 10.1109/ICECA49313.2020.9297603
R. Mahalakshmi, K. Reddy, M. Gautam
Electrical energy extraction from non-conventional energy sources such as solar, wind, etc., is very essential nowadays due to the huge electricity demand. The integration of these sources into the grid/electrical loads face many technical challenges like grid synchronization, power oscillations, etc., The modern wind power plants use Doubly Fed Induction Generator (DFIG) based WTGs as it has embedded Rotor Side Converter (RSC) and Stator Side Converter (SSC). This paper focuses on the performance analysis of standalone Doubly Fed Induction Generator (DFIG) based Wind Turbine using a new control strategy at RSC side. The RSC control is developed with the use of a linear regression algorithm under the Machine Learning (ML) technique. The effectiveness of the controller is validated using MATLAB/Simulink for the different operating conditions such as varying wind speed and load variations etc., The experimental setup of RSC is implemented in hardware and the results are discussed.
{"title":"Control of Standalone DFIG based Wind Turbine Generator using Machine Learning Algorithm","authors":"R. Mahalakshmi, K. Reddy, M. Gautam","doi":"10.1109/ICECA49313.2020.9297603","DOIUrl":"https://doi.org/10.1109/ICECA49313.2020.9297603","url":null,"abstract":"Electrical energy extraction from non-conventional energy sources such as solar, wind, etc., is very essential nowadays due to the huge electricity demand. The integration of these sources into the grid/electrical loads face many technical challenges like grid synchronization, power oscillations, etc., The modern wind power plants use Doubly Fed Induction Generator (DFIG) based WTGs as it has embedded Rotor Side Converter (RSC) and Stator Side Converter (SSC). This paper focuses on the performance analysis of standalone Doubly Fed Induction Generator (DFIG) based Wind Turbine using a new control strategy at RSC side. The RSC control is developed with the use of a linear regression algorithm under the Machine Learning (ML) technique. The effectiveness of the controller is validated using MATLAB/Simulink for the different operating conditions such as varying wind speed and load variations etc., The experimental setup of RSC is implemented in hardware and the results are discussed.","PeriodicalId":297285,"journal":{"name":"2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124180652","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 : 2020-11-05DOI: 10.1109/ICECA49313.2020.9297566
Shikhar
Universal Asynchronous Receiver Transmitter (UART) is a communication protocol used for sending and receiving the serial data. It offers short distance communication and it is reliable as well. This paper presents the application of UART module for creating Multiple Pulse Width Modulation (PWM) channels having different duty cycles using serial terminal on Field Programmable Gate Arrays (FPGA). The user can control the duty cycle of the PWM signals through serial terminal. UART module designed for this application features technique for baud rate detection. The design has been synthesized using Verilog Hardware Description Language (HDL) on Lattice Mach XO2 FPGA over a Tiny FPGA A2 module using Lattice Diamond Design software. A Printed Circuit Board (PCB) has been designed to observe the effects of PWM signals with different duty cycles over multiple Light Emitting Diodes (LEDs). The design is verified through simulations and logic analyzer tool. Effects of PWM signals is also observed through the intensity of Multiple LEDs. Maximum frequency that can be obtained on Lattice Mach XO2 FPGA is 133 MHz. The design uses 12.08 MHz frequency for the system clock.
{"title":"Design and Implementation of Multiple PWM Channels using Universal Asynchronous Receiver Transmitter","authors":"Shikhar","doi":"10.1109/ICECA49313.2020.9297566","DOIUrl":"https://doi.org/10.1109/ICECA49313.2020.9297566","url":null,"abstract":"Universal Asynchronous Receiver Transmitter (UART) is a communication protocol used for sending and receiving the serial data. It offers short distance communication and it is reliable as well. This paper presents the application of UART module for creating Multiple Pulse Width Modulation (PWM) channels having different duty cycles using serial terminal on Field Programmable Gate Arrays (FPGA). The user can control the duty cycle of the PWM signals through serial terminal. UART module designed for this application features technique for baud rate detection. The design has been synthesized using Verilog Hardware Description Language (HDL) on Lattice Mach XO2 FPGA over a Tiny FPGA A2 module using Lattice Diamond Design software. A Printed Circuit Board (PCB) has been designed to observe the effects of PWM signals with different duty cycles over multiple Light Emitting Diodes (LEDs). The design is verified through simulations and logic analyzer tool. Effects of PWM signals is also observed through the intensity of Multiple LEDs. Maximum frequency that can be obtained on Lattice Mach XO2 FPGA is 133 MHz. The design uses 12.08 MHz frequency for the system clock.","PeriodicalId":297285,"journal":{"name":"2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123546416","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 : 2020-11-05DOI: 10.1109/ICECA49313.2020.9297562
Aseel Hussein Zahi, Dr. Saad Talib Hasson
In this article, a model is developed to improve trust value in the relations that represents social networks by utilizing centrality measures interred with all participants in network-based and recommendations, both on connection or trust. Various central metrics were discussed and implemented to intend to trust. Algorithms are provided to facilitate their calculations. The referral neighbor that has a guaranteed trust boundary is chosen. Trust Value based on Interaction and Recommendations using Centrality Metric (TVIRCM) method is proposed and implemented in this study to improve trust value in the social network when the link between any two nodes represent the unique indication about trust whereas, there are no other standards for maintaining trust. Trust based on interaction refers to trust calculations based on real links observations and exploits the centrality metric. Trust based on recommendation refers to trust calculation based on trust participants of a remote neighbor about other participants.The developed approach is utilized in a trust observation phase as a trust-based interaction (i.e. assigned high and low centrality metrics), then the next phase is based on the proposed recommendation (i.e. the remote neighbor may have certain trust value) and the last phase is the trust calculation phase which based on combining direct and indirect trust.
{"title":"Improved Trust Model based on Centrality Measures and Recommendation in Social Network","authors":"Aseel Hussein Zahi, Dr. Saad Talib Hasson","doi":"10.1109/ICECA49313.2020.9297562","DOIUrl":"https://doi.org/10.1109/ICECA49313.2020.9297562","url":null,"abstract":"In this article, a model is developed to improve trust value in the relations that represents social networks by utilizing centrality measures interred with all participants in network-based and recommendations, both on connection or trust. Various central metrics were discussed and implemented to intend to trust. Algorithms are provided to facilitate their calculations. The referral neighbor that has a guaranteed trust boundary is chosen. Trust Value based on Interaction and Recommendations using Centrality Metric (TVIRCM) method is proposed and implemented in this study to improve trust value in the social network when the link between any two nodes represent the unique indication about trust whereas, there are no other standards for maintaining trust. Trust based on interaction refers to trust calculations based on real links observations and exploits the centrality metric. Trust based on recommendation refers to trust calculation based on trust participants of a remote neighbor about other participants.The developed approach is utilized in a trust observation phase as a trust-based interaction (i.e. assigned high and low centrality metrics), then the next phase is based on the proposed recommendation (i.e. the remote neighbor may have certain trust value) and the last phase is the trust calculation phase which based on combining direct and indirect trust.","PeriodicalId":297285,"journal":{"name":"2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124939796","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 : 2020-11-05DOI: 10.1109/ICECA49313.2020.9297543
P. Patel, D. K. Meda
In this proposed work, an improvised analysis in the parameter of a conventional Microstrip Patch Antenna for 5G is reviwed. In this design of the antenna is modified for the better gain and return loss with the best possible result using simulation software (HFSS-19.2). The performance of the antenna has been measured and compared to analyze in terms of gain, the return loss, radiation pattern and bandwidth at 28 GHz operating frequency.
{"title":"An Improvised Analysis in the Parameter of a Conventional Microstrip Patch Antenna for 5G Communication","authors":"P. Patel, D. K. Meda","doi":"10.1109/ICECA49313.2020.9297543","DOIUrl":"https://doi.org/10.1109/ICECA49313.2020.9297543","url":null,"abstract":"In this proposed work, an improvised analysis in the parameter of a conventional Microstrip Patch Antenna for 5G is reviwed. In this design of the antenna is modified for the better gain and return loss with the best possible result using simulation software (HFSS-19.2). The performance of the antenna has been measured and compared to analyze in terms of gain, the return loss, radiation pattern and bandwidth at 28 GHz operating frequency.","PeriodicalId":297285,"journal":{"name":"2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124018349","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 : 2020-11-05DOI: 10.1109/ICECA49313.2020.9297478
K. Malathi, R. Kavitha, M. Liza
Normally, the encryption and decryption is done only to convert the text into an encrypted form (i.e.) the confused form of text. In this type of method a hacker may easily hack the text using the public key or private key. So in this paper a new technique called Text to image encryption has been proposed. This will convert the plain text or information into an image format. That image will hide the encrypted text. If the user wants to view the text, first the image is divided into blocks. Each color component will be modified using the secret key. It will be difficult to the hackers to hack the information. This method can be used for large set of databases.
{"title":"Pixel based method for Text to Image Encryption","authors":"K. Malathi, R. Kavitha, M. Liza","doi":"10.1109/ICECA49313.2020.9297478","DOIUrl":"https://doi.org/10.1109/ICECA49313.2020.9297478","url":null,"abstract":"Normally, the encryption and decryption is done only to convert the text into an encrypted form (i.e.) the confused form of text. In this type of method a hacker may easily hack the text using the public key or private key. So in this paper a new technique called Text to image encryption has been proposed. This will convert the plain text or information into an image format. That image will hide the encrypted text. If the user wants to view the text, first the image is divided into blocks. Each color component will be modified using the secret key. It will be difficult to the hackers to hack the information. This method can be used for large set of databases.","PeriodicalId":297285,"journal":{"name":"2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128911339","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 : 2020-11-05DOI: 10.1109/ICECA49313.2020.9297496
K. Sultan
In this paper, a cooperative spectrum sharing scheme is proposed for NOMA based cognitive radio networks comprising of primary and secondary networks. The primary network consists of a primary transmitter PT communicating with a primary receiver PU, whereas the secondary network consists of a NOMA based secondary transmitter ST communicating with L secondary users SUs. The primary terminals are separated far apart therefore ST provides assistance as a relay in order to enable their end-to-end communication. Each terminal is equipped with a single antenna therefore end-to-end communication is accomplished in two time-slots. In first timeslot, PT transmits its signal to ST and at the same time one best SU retransmits the primary signal of the last frame to PU. In second time-slot, ST transmits the superimposed signals of primary and secondary networks. In this scenario, sum rate of SUs is maximized while ensuring to guarantee the QoS of PU. Artificial Bee Colony (ABC) global optimization algorithm is employed to solve this transmit power allocation problem which quickly converged to the best solution.
{"title":"Artificial Bee Colony assisted Spectrum Sharing Scheme for NOMA based Cognitive Radio Networks","authors":"K. Sultan","doi":"10.1109/ICECA49313.2020.9297496","DOIUrl":"https://doi.org/10.1109/ICECA49313.2020.9297496","url":null,"abstract":"In this paper, a cooperative spectrum sharing scheme is proposed for NOMA based cognitive radio networks comprising of primary and secondary networks. The primary network consists of a primary transmitter PT communicating with a primary receiver PU, whereas the secondary network consists of a NOMA based secondary transmitter ST communicating with L secondary users SUs. The primary terminals are separated far apart therefore ST provides assistance as a relay in order to enable their end-to-end communication. Each terminal is equipped with a single antenna therefore end-to-end communication is accomplished in two time-slots. In first timeslot, PT transmits its signal to ST and at the same time one best SU retransmits the primary signal of the last frame to PU. In second time-slot, ST transmits the superimposed signals of primary and secondary networks. In this scenario, sum rate of SUs is maximized while ensuring to guarantee the QoS of PU. Artificial Bee Colony (ABC) global optimization algorithm is employed to solve this transmit power allocation problem which quickly converged to the best solution.","PeriodicalId":297285,"journal":{"name":"2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA)","volume":"127 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128024353","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 : 2020-11-05DOI: 10.1109/ICECA49313.2020.9297467
A. Gowtham, L. Anirudh, B. Sreeja, BA Aakash, S. Adittya
If there is an availability of technological medical electronic devices to classify heart disease, it would absolutely change the future in terms of making it more economical and qualitative for all the people suffering from heart-related ailments. With the increasing medical expenses and non-affordability of the poor families, it becomes logical to design a system that can detect heart disease in particular Arrhythmia, without higher expense. Recently, the Cardiovascular systems are evaluated more reliably by using Electrocardiogram (ECG) waves. This project in particular is designed to check for any irregularities in heart beats, which is represented in the variations of an ECG wave, and then compared it with normal beats to detect Arrhythmia. The electronics behind this project is Raspberry Pi and ADS1115, an ADC, which converts the real-time, analog ECG wave signal into a digital wave with the help of heart rate sensor-AD8232, and a three-lead system. A normalized wave is fed into the deep convolutional neural network to predict the output into one of the 5 different categories. Furthermore, the ADASYN – Adaptive Synthetic Sampling - algorithm is used to effectively classify the disease in accordance with the MIT-BIH dataset.
{"title":"Detection of Arrhythmia using ECG waves with Deep Convolutional Neural Networks","authors":"A. Gowtham, L. Anirudh, B. Sreeja, BA Aakash, S. Adittya","doi":"10.1109/ICECA49313.2020.9297467","DOIUrl":"https://doi.org/10.1109/ICECA49313.2020.9297467","url":null,"abstract":"If there is an availability of technological medical electronic devices to classify heart disease, it would absolutely change the future in terms of making it more economical and qualitative for all the people suffering from heart-related ailments. With the increasing medical expenses and non-affordability of the poor families, it becomes logical to design a system that can detect heart disease in particular Arrhythmia, without higher expense. Recently, the Cardiovascular systems are evaluated more reliably by using Electrocardiogram (ECG) waves. This project in particular is designed to check for any irregularities in heart beats, which is represented in the variations of an ECG wave, and then compared it with normal beats to detect Arrhythmia. The electronics behind this project is Raspberry Pi and ADS1115, an ADC, which converts the real-time, analog ECG wave signal into a digital wave with the help of heart rate sensor-AD8232, and a three-lead system. A normalized wave is fed into the deep convolutional neural network to predict the output into one of the 5 different categories. Furthermore, the ADASYN – Adaptive Synthetic Sampling - algorithm is used to effectively classify the disease in accordance with the MIT-BIH dataset.","PeriodicalId":297285,"journal":{"name":"2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129016170","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 : 2020-11-05DOI: 10.1109/ICECA49313.2020.9297473
Harshita kushwah, R. Gamad, R. Gurjar
Low power and high-speed comparator design are presented in this article. Design is intended for the implementation of SAR ADC. The advantage of the proposed design can minimize power dissipation and maximize speed in SAR ADC. Simulation results are obtained in 0.18um Technology in the cadence tool. This design exhibit improved accuracy and less power consumption about 129.8$mu mathrm{W}$ with sampling frequency 100MHz and 1.8V supply. Prior work done is compared with simulated results and progress is also marked in present work.
{"title":"Design of Low Power & High Speed Comparator of SAR ADC using 180nm Technology","authors":"Harshita kushwah, R. Gamad, R. Gurjar","doi":"10.1109/ICECA49313.2020.9297473","DOIUrl":"https://doi.org/10.1109/ICECA49313.2020.9297473","url":null,"abstract":"Low power and high-speed comparator design are presented in this article. Design is intended for the implementation of SAR ADC. The advantage of the proposed design can minimize power dissipation and maximize speed in SAR ADC. Simulation results are obtained in 0.18um Technology in the cadence tool. This design exhibit improved accuracy and less power consumption about 129.8$mu mathrm{W}$ with sampling frequency 100MHz and 1.8V supply. Prior work done is compared with simulated results and progress is also marked in present work.","PeriodicalId":297285,"journal":{"name":"2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130517678","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 : 2020-11-05DOI: 10.1109/ICECA49313.2020.9297469
V. Kaleeswaran, S. Dhamodharavadhani, R. Rathipriya
The proposed study in this paper provides long-term crop prediction for Tamilnadu, India. Nonlinear Autoregressive (NAR) Neural Network (NN) with different parameter settings has been used to facilitate the correct quality and quantity of crop production. At the core of this study is to compare the effect of training algorithms (such as trainlm, trainbr, trainscg, traincgf, trainbfg, traincgf) and activation functions (such as tansig, elliotsig, logsig and purelin) in the performance of the crop yield forecasting model. This study showed that activation functions elliotsig and tansig with the training algorithm trainbr of NARNN delivered the most promising results based on the smallest error between actual and predicted value compared to the other activation and training functions of NARNN.
{"title":"A Comparative Study of Activation Functions and Training Algorithm of NAR Neural Network for Crop Prediction","authors":"V. Kaleeswaran, S. Dhamodharavadhani, R. Rathipriya","doi":"10.1109/ICECA49313.2020.9297469","DOIUrl":"https://doi.org/10.1109/ICECA49313.2020.9297469","url":null,"abstract":"The proposed study in this paper provides long-term crop prediction for Tamilnadu, India. Nonlinear Autoregressive (NAR) Neural Network (NN) with different parameter settings has been used to facilitate the correct quality and quantity of crop production. At the core of this study is to compare the effect of training algorithms (such as trainlm, trainbr, trainscg, traincgf, trainbfg, traincgf) and activation functions (such as tansig, elliotsig, logsig and purelin) in the performance of the crop yield forecasting model. This study showed that activation functions elliotsig and tansig with the training algorithm trainbr of NARNN delivered the most promising results based on the smallest error between actual and predicted value compared to the other activation and training functions of NARNN.","PeriodicalId":297285,"journal":{"name":"2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129323605","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}
Depression is a prevalent illness in todays society. It changes and influences our entire method of thought and our emotional, cognitive, and everyday behavioral behaviors. It affected over 264 million people, and the proportion increases every day. Mainly when it lasts for a prolonged time, it becomes a severe issue or health topic. It leads the trustworthy person to also malfunction, and that person commits suicide in his final position. There are several causes for depression, though social networking like Facebook, Twitter, and other networking plays a critical role in getting us more depressed. Most people in Asia use Facebook, Twitter, and various chat applications, and there they express their emotions. That is why our research initiative picks social media. Some work has been done on depression but depression detection on the Bengali community is done very rarely. So it has become a strong demand for today. The social media has intialted a study based on depression, tweets, and numerous chat app responses, and gathered Bengali data and projected depression posts and commentaries. Diverse approaches of machine learning have been used to evaluate these data and forecast depression and for algorithm purpose Support vector machine, Random Forest, Decision Tree, K-Nearest Neighbors, Naive Bayes (Multinomial Naive Bayes), Logistic Regression has been used. The desired results can be obtained by adding those algorithms. Moreover, different algorithms send us different results as trends were common, but ultimately the precision was the same for all algorithms applied to our dataset.
{"title":"Machine Learning Techniques for Depression Analysis on Social Media- Case Study on Bengali Community","authors":"Debasish Bhattacharjee Victor, Jamil Kawsher, Md Shad Labib, Subhenur Latif","doi":"10.1109/ICECA49313.2020.9297436","DOIUrl":"https://doi.org/10.1109/ICECA49313.2020.9297436","url":null,"abstract":"Depression is a prevalent illness in todays society. It changes and influences our entire method of thought and our emotional, cognitive, and everyday behavioral behaviors. It affected over 264 million people, and the proportion increases every day. Mainly when it lasts for a prolonged time, it becomes a severe issue or health topic. It leads the trustworthy person to also malfunction, and that person commits suicide in his final position. There are several causes for depression, though social networking like Facebook, Twitter, and other networking plays a critical role in getting us more depressed. Most people in Asia use Facebook, Twitter, and various chat applications, and there they express their emotions. That is why our research initiative picks social media. Some work has been done on depression but depression detection on the Bengali community is done very rarely. So it has become a strong demand for today. The social media has intialted a study based on depression, tweets, and numerous chat app responses, and gathered Bengali data and projected depression posts and commentaries. Diverse approaches of machine learning have been used to evaluate these data and forecast depression and for algorithm purpose Support vector machine, Random Forest, Decision Tree, K-Nearest Neighbors, Naive Bayes (Multinomial Naive Bayes), Logistic Regression has been used. The desired results can be obtained by adding those algorithms. Moreover, different algorithms send us different results as trends were common, but ultimately the precision was the same for all algorithms applied to our dataset.","PeriodicalId":297285,"journal":{"name":"2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128863839","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：