Pub Date : 2022-03-16DOI: 10.1109/ICEARS53579.2022.9752225
M. Jayasree, L. Rao
The current scenario expresses that deep learning is the leading technology in the field of machine learning. Deep learning is a form of artificial intelligence that effectively uses neural network concepts where the computing system is essentially a multi-layered mesh architecture, which is motivated by the human brain and nervous system. The multiple hidden layers of CNN extract higher level features from large datasets and its methodology are speedily becoming a best choice for every field. Deep learning methods have improved and are highly developed in object recognition, Natural Language Processing, classification of images, medical image analysis etc. This paper provides introduction of different deep learning architectures, algorithms and the optimization methods used to improve the accuracy and performance of the deep learning model. And also, described challenges, obstacles to be faced while training a deep learning model and introduced applications of deep learning in various fields.
{"title":"A Deep Insight into Deep Learning Architectures, Algorithms and Applications","authors":"M. Jayasree, L. Rao","doi":"10.1109/ICEARS53579.2022.9752225","DOIUrl":"https://doi.org/10.1109/ICEARS53579.2022.9752225","url":null,"abstract":"The current scenario expresses that deep learning is the leading technology in the field of machine learning. Deep learning is a form of artificial intelligence that effectively uses neural network concepts where the computing system is essentially a multi-layered mesh architecture, which is motivated by the human brain and nervous system. The multiple hidden layers of CNN extract higher level features from large datasets and its methodology are speedily becoming a best choice for every field. Deep learning methods have improved and are highly developed in object recognition, Natural Language Processing, classification of images, medical image analysis etc. This paper provides introduction of different deep learning architectures, algorithms and the optimization methods used to improve the accuracy and performance of the deep learning model. And also, described challenges, obstacles to be faced while training a deep learning model and introduced applications of deep learning in various fields.","PeriodicalId":252961,"journal":{"name":"2022 International Conference on Electronics and Renewable Systems (ICEARS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123555768","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 : 2022-03-16DOI: 10.1109/ICEARS53579.2022.9752088
G. Kannan, Manjula Pattnaik, G. Karthikeyan, B. E., P. J. Augustine, Lohith J J
Modern supply chain management relies heavily on crop processing technologies and blockchain technology. However, the majority of crop processing technology fails due to a lack of available supply chain management technologies. A supply chain management system based on crop processing is developed in this research. Digital ledger technology (blockchain) takes care of supply chains and deep learning image processing (crop processing). To process the harvested crops, the study makes use of machine learning techniques. Blockchain supply chain management technology is then used to deliver the processed crops to the shops. Consequently, the research permits the accurate and transparent distribution of crops to users in an optimal and secure manner. The full hybrid model is tested in a simulation to see if it can improve agricultural production and supply chain management. This new strategy improves agricultural processing rates, and when combined with the blockchain distributed ledger technology, this results in optimal crop management for the required users.
{"title":"Managing the Supply Chain for the Crops Directed from Agricultural Fields using Blockchains","authors":"G. Kannan, Manjula Pattnaik, G. Karthikeyan, B. E., P. J. Augustine, Lohith J J","doi":"10.1109/ICEARS53579.2022.9752088","DOIUrl":"https://doi.org/10.1109/ICEARS53579.2022.9752088","url":null,"abstract":"Modern supply chain management relies heavily on crop processing technologies and blockchain technology. However, the majority of crop processing technology fails due to a lack of available supply chain management technologies. A supply chain management system based on crop processing is developed in this research. Digital ledger technology (blockchain) takes care of supply chains and deep learning image processing (crop processing). To process the harvested crops, the study makes use of machine learning techniques. Blockchain supply chain management technology is then used to deliver the processed crops to the shops. Consequently, the research permits the accurate and transparent distribution of crops to users in an optimal and secure manner. The full hybrid model is tested in a simulation to see if it can improve agricultural production and supply chain management. This new strategy improves agricultural processing rates, and when combined with the blockchain distributed ledger technology, this results in optimal crop management for the required users.","PeriodicalId":252961,"journal":{"name":"2022 International Conference on Electronics and Renewable Systems (ICEARS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125561619","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 : 2022-03-16DOI: 10.1109/ICEARS53579.2022.9752274
S. Surana, Komal Pathak, Mehul Gagnani, Vidhan Shrivastava, Mahesh T R, Sindhu Madhuri G
Machine Learning is subset of Artificial Intelligence and there is lots of research growth across the world. It has capability to learn by its own without seeking any help from human beings or without any explicit programming based on its previous experience and knowledge. Mainly it can make its own decisions or can predict in performing certain tasks based on the res pective input dataset and its training set. Machine Learning is applicable in various real-time applications in our daily life. Text detection and text extraction is one of the important applications which contain valuable information from images captured from various sources. Text with different variations differs in their size, orientation, alignment, style, low brightness or contrast in images with complex background. Many facing issues in reading due to various variations in text on images. So, text detection and extraction is very important and challenging now a days. The objective here is to help human beings with a different language from different parts of the world so that they can easily read and understand any language written. Researchers use various machine learning algorithms and tools to recognize handwritten text and text captured from images to convert them into digital format. Optical Character Recognition (OCR) is a Machine learning technique that helps us to detect and extract text data or information of a document and turn it into editable and searchable data. This research paper mainly focusses on various machine learning algorithms that are applicable for text extraction of handwritten documents, images and detect them into digital format also translate it according to the user's requirements.
{"title":"Text Extraction and Detection from Images using Machine Learning Techniques: A Research Review","authors":"S. Surana, Komal Pathak, Mehul Gagnani, Vidhan Shrivastava, Mahesh T R, Sindhu Madhuri G","doi":"10.1109/ICEARS53579.2022.9752274","DOIUrl":"https://doi.org/10.1109/ICEARS53579.2022.9752274","url":null,"abstract":"Machine Learning is subset of Artificial Intelligence and there is lots of research growth across the world. It has capability to learn by its own without seeking any help from human beings or without any explicit programming based on its previous experience and knowledge. Mainly it can make its own decisions or can predict in performing certain tasks based on the res pective input dataset and its training set. Machine Learning is applicable in various real-time applications in our daily life. Text detection and text extraction is one of the important applications which contain valuable information from images captured from various sources. Text with different variations differs in their size, orientation, alignment, style, low brightness or contrast in images with complex background. Many facing issues in reading due to various variations in text on images. So, text detection and extraction is very important and challenging now a days. The objective here is to help human beings with a different language from different parts of the world so that they can easily read and understand any language written. Researchers use various machine learning algorithms and tools to recognize handwritten text and text captured from images to convert them into digital format. Optical Character Recognition (OCR) is a Machine learning technique that helps us to detect and extract text data or information of a document and turn it into editable and searchable data. This research paper mainly focusses on various machine learning algorithms that are applicable for text extraction of handwritten documents, images and detect them into digital format also translate it according to the user's requirements.","PeriodicalId":252961,"journal":{"name":"2022 International Conference on Electronics and Renewable Systems (ICEARS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116069417","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 : 2022-03-16DOI: 10.1109/ICEARS53579.2022.9752384
R. Seetharaman, M. Ramajayam, K. Kamalakannan, M. Vignesh, R.L. Saran, K. Anandan, S. Sreeja Mole
People with hearing and visual impairments can communicate effectively through this project. In the FPGA based Morse code, the Basys-3 board is programmed to decode a Morse code communication attempt by the impaired person. The decoded message is then displayed via a seven-segment display connected to the Basys-3 so the caretaker can understand. For individuals with physical limitations, Morse code provides a communication channel that can be used with just one or two switches. Thus, this project provides a communication tool that can be used by visually impaired individuals and those with speech impairments. In this paper, we have tried our best in making the morse code decoder system as mobile as possible considering the fact in mind that the challenged person would mostly need encoders while travelling out to meet new people and the system should be mobile and easily feasible to assemble at any location. Basys-3 being a highly effective programmable board, can effectively compile the morse inputs given, decode at a fast pace and show the output in the seven-segment display at a reasonably high speed for effective communication.
{"title":"FPGA Based Morse Code Communicator for Visual and Speech Impaired People using Basys-3","authors":"R. Seetharaman, M. Ramajayam, K. Kamalakannan, M. Vignesh, R.L. Saran, K. Anandan, S. Sreeja Mole","doi":"10.1109/ICEARS53579.2022.9752384","DOIUrl":"https://doi.org/10.1109/ICEARS53579.2022.9752384","url":null,"abstract":"People with hearing and visual impairments can communicate effectively through this project. In the FPGA based Morse code, the Basys-3 board is programmed to decode a Morse code communication attempt by the impaired person. The decoded message is then displayed via a seven-segment display connected to the Basys-3 so the caretaker can understand. For individuals with physical limitations, Morse code provides a communication channel that can be used with just one or two switches. Thus, this project provides a communication tool that can be used by visually impaired individuals and those with speech impairments. In this paper, we have tried our best in making the morse code decoder system as mobile as possible considering the fact in mind that the challenged person would mostly need encoders while travelling out to meet new people and the system should be mobile and easily feasible to assemble at any location. Basys-3 being a highly effective programmable board, can effectively compile the morse inputs given, decode at a fast pace and show the output in the seven-segment display at a reasonably high speed for effective communication.","PeriodicalId":252961,"journal":{"name":"2022 International Conference on Electronics and Renewable Systems (ICEARS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122586806","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 : 2022-03-16DOI: 10.1109/ICEARS53579.2022.9752038
P. Harshith, P. V. Naidu, C. Jahnavi, Anusha T, N. K, M. Praneetha
The Grass–Hook shaped MIMO antenna having Asymmetric coplanar strip (ACS) feeding is designed with the dimensions 50 x 50 x 1.6 mm3.The tri band characteristics of antenna are used for the applications WLAN / WiMAX / LTE / Zigbee / Wi-Fi / Bluetooth / RFID. The operating frequency ranges are 2.25–2.47 GHz, 3.42–3.60 GHz and 4.59–6.65 GHz respectively. The results of antenna obtain Correlation Coefficient (ECC) value below 0.001, Diversity Gain >9.95 and CCL lower than 0.4 bits/s/Hertz. The designed antenna is efficient in reducing coupling and correlation within the antenna elements with the isolation result of <-17dB.
{"title":"Quardport Grass-Hook Structured MIMO Antenna for Triband Frequency Applications","authors":"P. Harshith, P. V. Naidu, C. Jahnavi, Anusha T, N. K, M. Praneetha","doi":"10.1109/ICEARS53579.2022.9752038","DOIUrl":"https://doi.org/10.1109/ICEARS53579.2022.9752038","url":null,"abstract":"The Grass–Hook shaped MIMO antenna having Asymmetric coplanar strip (ACS) feeding is designed with the dimensions 50 x 50 x 1.6 mm3.The tri band characteristics of antenna are used for the applications WLAN / WiMAX / LTE / Zigbee / Wi-Fi / Bluetooth / RFID. The operating frequency ranges are 2.25–2.47 GHz, 3.42–3.60 GHz and 4.59–6.65 GHz respectively. The results of antenna obtain Correlation Coefficient (ECC) value below 0.001, Diversity Gain >9.95 and CCL lower than 0.4 bits/s/Hertz. The designed antenna is efficient in reducing coupling and correlation within the antenna elements with the isolation result of <-17dB.","PeriodicalId":252961,"journal":{"name":"2022 International Conference on Electronics and Renewable Systems (ICEARS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122726773","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 : 2022-03-16DOI: 10.1109/ICEARS53579.2022.9752157
Chuili Hu
Based on VR and 3D modeling technology, this paper studies the multi-modal identity authentication system of face recognition, and solves the problem that identity recognition is affected by distance. By analyzing the dynamic characteristics, static characteristics, and walking directions of pedestrians in a gait cycle, construct a long-distance identity authentication scheme based on gait; construct a short-distance identity authentication scheme based on multi-posture face detection and sparse representation of facial components Face recognition method. Combining gait and face recognition to realize distance-independent identity authentication, realizes the design of audio and video s system; simulation results show that the effect of this system and data model has increased by 7.2%
{"title":"VR Technology-Based Audio and Video System Design and Face Authentication Assisted Multi-Modal Data Model","authors":"Chuili Hu","doi":"10.1109/ICEARS53579.2022.9752157","DOIUrl":"https://doi.org/10.1109/ICEARS53579.2022.9752157","url":null,"abstract":"Based on VR and 3D modeling technology, this paper studies the multi-modal identity authentication system of face recognition, and solves the problem that identity recognition is affected by distance. By analyzing the dynamic characteristics, static characteristics, and walking directions of pedestrians in a gait cycle, construct a long-distance identity authentication scheme based on gait; construct a short-distance identity authentication scheme based on multi-posture face detection and sparse representation of facial components Face recognition method. Combining gait and face recognition to realize distance-independent identity authentication, realizes the design of audio and video s system; simulation results show that the effect of this system and data model has increased by 7.2%","PeriodicalId":252961,"journal":{"name":"2022 International Conference on Electronics and Renewable Systems (ICEARS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122645273","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 : 2022-03-16DOI: 10.1109/ICEARS53579.2022.9751977
Nan Ding
This article first combines the application scenarios and performance indicators of 5G with an increase of about 11.38%, and analyzes its important value in adjustable load applications. Secondly, for the typical application scenario of adjustable load, that is, demand response, it analyzed that the bandwidth and delay requirements of the 5G communication network increased by about 7.92%. Then it analyzes the adjustment potential of the typical adjustable load in the demand response service under the 5G communication network environment. Finally, the system architecture and interaction process of demand response in the 5G communication network environment are designed.
{"title":"Application Analysis of Adjustable Load in 5G Communication Network Environment","authors":"Nan Ding","doi":"10.1109/ICEARS53579.2022.9751977","DOIUrl":"https://doi.org/10.1109/ICEARS53579.2022.9751977","url":null,"abstract":"This article first combines the application scenarios and performance indicators of 5G with an increase of about 11.38%, and analyzes its important value in adjustable load applications. Secondly, for the typical application scenario of adjustable load, that is, demand response, it analyzed that the bandwidth and delay requirements of the 5G communication network increased by about 7.92%. Then it analyzes the adjustment potential of the typical adjustable load in the demand response service under the 5G communication network environment. Finally, the system architecture and interaction process of demand response in the 5G communication network environment are designed.","PeriodicalId":252961,"journal":{"name":"2022 International Conference on Electronics and Renewable Systems (ICEARS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122890804","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 : 2022-03-16DOI: 10.1109/ICEARS53579.2022.9752413
Ram Rathan K R, RanjithKumar N, Meghana T A, Shashi Raj K
An efficient approach to improve security is given by double point multiplication. The performance is further improved by replacing the Conventional Array multiplier with Vedic multiplier and replacing scalar multiplication with left shift operation. The proposed multiplier periodically processes data as 64-bit double words repeatedly. This multiplier when employed in the ECC algorithm drastically reduces the total area utilization. The shifting operation increases the security at every instant. The simulation of the proposed design is done using Xilinx 14.7 software. Experimental findings show a remarkable improvement in the speed of the process and its security.
{"title":"Rapid, Secure and Vedic Approach to Cryptography","authors":"Ram Rathan K R, RanjithKumar N, Meghana T A, Shashi Raj K","doi":"10.1109/ICEARS53579.2022.9752413","DOIUrl":"https://doi.org/10.1109/ICEARS53579.2022.9752413","url":null,"abstract":"An efficient approach to improve security is given by double point multiplication. The performance is further improved by replacing the Conventional Array multiplier with Vedic multiplier and replacing scalar multiplication with left shift operation. The proposed multiplier periodically processes data as 64-bit double words repeatedly. This multiplier when employed in the ECC algorithm drastically reduces the total area utilization. The shifting operation increases the security at every instant. The simulation of the proposed design is done using Xilinx 14.7 software. Experimental findings show a remarkable improvement in the speed of the process and its security.","PeriodicalId":252961,"journal":{"name":"2022 International Conference on Electronics and Renewable Systems (ICEARS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124212062","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 : 2022-03-16DOI: 10.1109/ICEARS53579.2022.9752349
U. Venkateshkumar, A. V., D. V., E. B.
Agriculture is one of the primary occupations that is very essential for livelihood. India has about 215.6 million acres of agricultural land, which forms about 60.4% of total land population. It contributes over 17% of India’s GDP (Gross Domestic Product), which estimates up to 4862.92 INR Billion in the year 2021. Such occupation is given very less priority and considerations. The key factors required for a farmer to do agriculture are land and the cattle. But nowadays there are many incidents of land attacks and animal theft happening. Recently in the states of Haryana and Delhi there are buffalo thefts happening, which is becoming a nightmare for the farmers. This situation leads them to end up their life or remain starving for their day-to-day needs. Only if the farmers live, people can live; keeping this in mind and as an act of lending a hand for their support, a solution which might stop these types of cruelties taking place on farm lands and making farmers sleep peacefully has been proposed. Through this device the farmer will be receiving an alert on the application installed in their mobile when someone intrudes into his/her farm. On receiving the alert, which will enable the farmer to go to his farm and check if any strange movement is happening. There will be also an alarm installed in the farmer’s land which will alert the neighboring localities/farmers. Through this any type of intrusion into his/her farm can be prevented. This system might greatly help in reducing farmer’s worries on safety of his/her farm and cattle’s.
{"title":"Farm Intrusion Detection System using IoT","authors":"U. Venkateshkumar, A. V., D. V., E. B.","doi":"10.1109/ICEARS53579.2022.9752349","DOIUrl":"https://doi.org/10.1109/ICEARS53579.2022.9752349","url":null,"abstract":"Agriculture is one of the primary occupations that is very essential for livelihood. India has about 215.6 million acres of agricultural land, which forms about 60.4% of total land population. It contributes over 17% of India’s GDP (Gross Domestic Product), which estimates up to 4862.92 INR Billion in the year 2021. Such occupation is given very less priority and considerations. The key factors required for a farmer to do agriculture are land and the cattle. But nowadays there are many incidents of land attacks and animal theft happening. Recently in the states of Haryana and Delhi there are buffalo thefts happening, which is becoming a nightmare for the farmers. This situation leads them to end up their life or remain starving for their day-to-day needs. Only if the farmers live, people can live; keeping this in mind and as an act of lending a hand for their support, a solution which might stop these types of cruelties taking place on farm lands and making farmers sleep peacefully has been proposed. Through this device the farmer will be receiving an alert on the application installed in their mobile when someone intrudes into his/her farm. On receiving the alert, which will enable the farmer to go to his farm and check if any strange movement is happening. There will be also an alarm installed in the farmer’s land which will alert the neighboring localities/farmers. Through this any type of intrusion into his/her farm can be prevented. This system might greatly help in reducing farmer’s worries on safety of his/her farm and cattle’s.","PeriodicalId":252961,"journal":{"name":"2022 International Conference on Electronics and Renewable Systems (ICEARS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114524653","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 : 2022-03-16DOI: 10.1109/ICEARS53579.2022.9752115
J. Dhanraj, K. Sangeethalakshmi, T. S. Kumar, P. Nagarajan, P. Bharathi
The gear trains have been used in devices for power transmission. The gearbox becomes defective and produces noises that cause the unit to vibrate because of the wear and tear process. The frequency of vibration and sound also increases as wear and tear increase, making the gears unsuitable for particular applications. The state of gear trains is important to know before it is replaced by the new one. This paper uses the machine learning approach to classify the status of trains by means of classification models. The research was performed on a lab setup of Triumph Herald, which collected raw vibration signals and extracted significant statistical characteristics, and selected the significant features by means of a J48 classification. The features were chosen were classified in the classification of Naïve Bayes. For the classification of the selected feature, time complexity was 0.15s and the maximum accuracy was 96.75%.
{"title":"An Assessment on Condition Monitoring of Automobile Gearbox through Naïve Bayes Approach using Statistical Features","authors":"J. Dhanraj, K. Sangeethalakshmi, T. S. Kumar, P. Nagarajan, P. Bharathi","doi":"10.1109/ICEARS53579.2022.9752115","DOIUrl":"https://doi.org/10.1109/ICEARS53579.2022.9752115","url":null,"abstract":"The gear trains have been used in devices for power transmission. The gearbox becomes defective and produces noises that cause the unit to vibrate because of the wear and tear process. The frequency of vibration and sound also increases as wear and tear increase, making the gears unsuitable for particular applications. The state of gear trains is important to know before it is replaced by the new one. This paper uses the machine learning approach to classify the status of trains by means of classification models. The research was performed on a lab setup of Triumph Herald, which collected raw vibration signals and extracted significant statistical characteristics, and selected the significant features by means of a J48 classification. The features were chosen were classified in the classification of Naïve Bayes. For the classification of the selected feature, time complexity was 0.15s and the maximum accuracy was 96.75%.","PeriodicalId":252961,"journal":{"name":"2022 International Conference on Electronics and Renewable Systems (ICEARS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114540359","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：