Pub Date : 2021-12-01DOI: 10.1109/ComPE53109.2021.9751934
V. Duhoon, R. Bhardwaj
The paper deals with the objective to study the different artificial intelligence methods and compare their efficiency of forecasting the temperature, rainfall, wind speed in order to contribute in policy making and forecast upcoming disaster if any. Daily data of weather parameters such as Minimum Temperature, Maximum Temperature, Relative Humidity, Evaporation, Bright sunshine, Rainfall, Wind Speed for Delhi region from January 1, 2017 to April 15, 2018 is considered. The behaviour of the considered data set is studied for weather parameters Temperature, Rainfall and Wind Speed daily basis and prediction are made and compared for the period April 16-30, 2018 using Multilayer perceptron (MLP), Radial Basis Function(RBF) and Sequential Minimal Optimization(SMO) artificial intelligence techniques. On comparing these methods, it is observed that MLP Regression shows the least error and maximum Correlation coefficient and is concluded to be the more efficient artificial intelligence technique for forecasting weather parameters. The study will help the concerned authorities for future planning and take preventive steps for the future coming calamities if any. It will also help the government to make effective policies.
{"title":"Artificial Intelligence Technique for Weather Parameter Forecasting","authors":"V. Duhoon, R. Bhardwaj","doi":"10.1109/ComPE53109.2021.9751934","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9751934","url":null,"abstract":"The paper deals with the objective to study the different artificial intelligence methods and compare their efficiency of forecasting the temperature, rainfall, wind speed in order to contribute in policy making and forecast upcoming disaster if any. Daily data of weather parameters such as Minimum Temperature, Maximum Temperature, Relative Humidity, Evaporation, Bright sunshine, Rainfall, Wind Speed for Delhi region from January 1, 2017 to April 15, 2018 is considered. The behaviour of the considered data set is studied for weather parameters Temperature, Rainfall and Wind Speed daily basis and prediction are made and compared for the period April 16-30, 2018 using Multilayer perceptron (MLP), Radial Basis Function(RBF) and Sequential Minimal Optimization(SMO) artificial intelligence techniques. On comparing these methods, it is observed that MLP Regression shows the least error and maximum Correlation coefficient and is concluded to be the more efficient artificial intelligence technique for forecasting weather parameters. The study will help the concerned authorities for future planning and take preventive steps for the future coming calamities if any. It will also help the government to make effective policies.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133922878","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-01DOI: 10.1109/ComPE53109.2021.9752340
V. Kiruthika, G. G. R. Krishna, G. Karthik, X. B. Xavier, K. Sankaran, B. Kavitha
Movement for blind and elderly people is a challenging problem as they face many difficulties in their daily life. To overcome this problem most commonly, hand stick is used as a support system. Walking stick helps the user to know the presence of obstacle which is in close proximity but does not facilitate detection of obstacles, pits or water that is in the pathway. It does not give information about the location of the user too. Moreover, blind and elderly people are also in a need to monitor their health conditions such as blood pressure and pulse rate. An intelligent system incorporating multiple features will serve as an optimized device for the blind and elderly people. So, a new concept of smart wearable device with multiple features is proposed in this study which will help both blind and elderly people in their daily life. This device enables the movement of both blind and elder people in any environment and monitor their health conditions as well. In this device different sensors such as ultrasonic sensor, infrared sensor, water sensor, blood pressure sensor, pulse sensor, ADXL335 accelerometer sensor, and GPS/GSM technology are embedded to assist the blind and elderly at various instances. During emergencies the information can be communicated to the registered mobile number. This novel system will make the blind and elder people to move confidently and feel their environment.
{"title":"Smart Wearable Device for Blind and Elderly People","authors":"V. Kiruthika, G. G. R. Krishna, G. Karthik, X. B. Xavier, K. Sankaran, B. Kavitha","doi":"10.1109/ComPE53109.2021.9752340","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752340","url":null,"abstract":"Movement for blind and elderly people is a challenging problem as they face many difficulties in their daily life. To overcome this problem most commonly, hand stick is used as a support system. Walking stick helps the user to know the presence of obstacle which is in close proximity but does not facilitate detection of obstacles, pits or water that is in the pathway. It does not give information about the location of the user too. Moreover, blind and elderly people are also in a need to monitor their health conditions such as blood pressure and pulse rate. An intelligent system incorporating multiple features will serve as an optimized device for the blind and elderly people. So, a new concept of smart wearable device with multiple features is proposed in this study which will help both blind and elderly people in their daily life. This device enables the movement of both blind and elder people in any environment and monitor their health conditions as well. In this device different sensors such as ultrasonic sensor, infrared sensor, water sensor, blood pressure sensor, pulse sensor, ADXL335 accelerometer sensor, and GPS/GSM technology are embedded to assist the blind and elderly at various instances. During emergencies the information can be communicated to the registered mobile number. This novel system will make the blind and elder people to move confidently and feel their environment.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134576486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-01DOI: 10.1109/ComPE53109.2021.9752100
Ochin Sharma, K. Mehta, Renuka Sharma
In machine learning, association rule mining is a field with immense opportunity to explore relationships among various attributes and item-sets. However, in Association rule mining, statistically it is the interest measure which play the crucial role to decide these relationships. There exist various types of interest measures based upon the business needs and problem statements. In this paper, a novel interest measure has been proposed to decide the overall importance of an association rule. Statistical comparisons and experimental results have also been embedded to support its potential.
{"title":"Significant Support (SISU): A New Interest Measure in Association Rule Mining","authors":"Ochin Sharma, K. Mehta, Renuka Sharma","doi":"10.1109/ComPE53109.2021.9752100","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752100","url":null,"abstract":"In machine learning, association rule mining is a field with immense opportunity to explore relationships among various attributes and item-sets. However, in Association rule mining, statistically it is the interest measure which play the crucial role to decide these relationships. There exist various types of interest measures based upon the business needs and problem statements. In this paper, a novel interest measure has been proposed to decide the overall importance of an association rule. Statistical comparisons and experimental results have also been embedded to support its potential.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124704147","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-01DOI: 10.1109/ComPE53109.2021.9752278
B. B, Jeyasakthi R, J. S., Rishwana M, Swathilakshmi P R K, Reshma K K
Deep learning is important in the medical profession, and it has a wide range of applications, including diagnosis, research, and so on. In imaging technology, classifying the medical images in an automatic way is onerous. In the proposed work, the ABO blood group identification using novel deep learning approach for enhancement of bio medical automation. The ABO blood group data set is developed and classify the blood group automatically using Convolute neural network (CNN) which is capable of extracting and learning features from medical image dataset. As a result, the proposed innovative CNN framework is used in the medical field to classify human blood classes. As a result, our proposed dataset is used to train the model and test the sample in order to identify blood group in the shortest time possible with a 96.7 percent accuracy. The results of the proposed model are compared to those of existing CNN models such as Alex net and Lenet5. The findings show that the proposed method is the most appropriate for classifying human blood groups in medical applications.
{"title":"A novel approach of classifying ABO blood group image dataset using deep learning algorithm","authors":"B. B, Jeyasakthi R, J. S., Rishwana M, Swathilakshmi P R K, Reshma K K","doi":"10.1109/ComPE53109.2021.9752278","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752278","url":null,"abstract":"Deep learning is important in the medical profession, and it has a wide range of applications, including diagnosis, research, and so on. In imaging technology, classifying the medical images in an automatic way is onerous. In the proposed work, the ABO blood group identification using novel deep learning approach for enhancement of bio medical automation. The ABO blood group data set is developed and classify the blood group automatically using Convolute neural network (CNN) which is capable of extracting and learning features from medical image dataset. As a result, the proposed innovative CNN framework is used in the medical field to classify human blood classes. As a result, our proposed dataset is used to train the model and test the sample in order to identify blood group in the shortest time possible with a 96.7 percent accuracy. The results of the proposed model are compared to those of existing CNN models such as Alex net and Lenet5. The findings show that the proposed method is the most appropriate for classifying human blood groups in medical applications.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134177918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-01DOI: 10.1109/ComPE53109.2021.9752133
Abhishek Singh, A. Payal
A low-cost Obstacle Detection and Collision Avoidance (ODCA) System stimulated from Coulomb’s inverse-square law has been proposed, deployed, and tested on self-assembled multi-rotor system. The algorithm is focused to be inexpensive in terms of spacio-temporal complexities, cross platform, and able to run on low-cost, easily available hardware. It aims at protecting the drone from entering a complex situation in manual and autonomous flight modes. The ODCA system hardware design is focused to be easily integrable with various flight controllers. The hardware and communication interfacing among various modules required by the ODCA system have been briefly explained. Since, proposed ODCA system is tested on self-assembled drone, a small description about drone hardware, assembly, and communication mechanism is also provided. Furthermore, the ODCA system algorithm that processes sensor data in various stages and culminated actions are explained. Finally, the system is tested and evaluated in multi-obstacle scenario through hardware in the loop (HIL) simulation and their findings are shown.
{"title":"Development of a low-cost Collision Avoidance System based on Coulomb’s inverse-square law for Multi-rotor Drones (UAVs)","authors":"Abhishek Singh, A. Payal","doi":"10.1109/ComPE53109.2021.9752133","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752133","url":null,"abstract":"A low-cost Obstacle Detection and Collision Avoidance (ODCA) System stimulated from Coulomb’s inverse-square law has been proposed, deployed, and tested on self-assembled multi-rotor system. The algorithm is focused to be inexpensive in terms of spacio-temporal complexities, cross platform, and able to run on low-cost, easily available hardware. It aims at protecting the drone from entering a complex situation in manual and autonomous flight modes. The ODCA system hardware design is focused to be easily integrable with various flight controllers. The hardware and communication interfacing among various modules required by the ODCA system have been briefly explained. Since, proposed ODCA system is tested on self-assembled drone, a small description about drone hardware, assembly, and communication mechanism is also provided. Furthermore, the ODCA system algorithm that processes sensor data in various stages and culminated actions are explained. Finally, the system is tested and evaluated in multi-obstacle scenario through hardware in the loop (HIL) simulation and their findings are shown.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132348991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-01DOI: 10.1109/ComPE53109.2021.9751857
Anju Yadav, Rahul Saxena, B. Saini, V. K. Verma, Vibhav Srivastava
Sign language is an effective mode of conversation for persons who have difficulty speaking or hearing. There are numerous media accessible for translation or for identifying sign languages and converting those to text format, However, methods for converting text to sign language have been few and even not web-based software, owing to the scarcity of resources. The proposed web application seeks to develop a translating mechanism or automation that includes a parser element that converts the incoming speech data or English text to a phrase structure grammar representation, which is then used by another module that contains Indi Sign language grammatical format. This is accomplished through the means of removing stop-words from the reordered input format. Because Indian sign language does not provide word inflections, stemming and lemmatization are used to turn words into their root form. Following sentence filtration, all words are tested against the words in the database, which is represented as a dictionary comprising video representations of each word. If the words are missing from the database, the algorithm will then look for its related synonym and replace it with that term.In many ways, the proposed system is more innovative and efficient than existing systems, because Existing methods can only convert words directly into Indi sign language, and they were not as efficient as this system, whereas this in the actual world, the system tries to translate these phrases into Indian sign language grammatical order. Because this is a web-based programmed, it is straightforward to access and use. This technology is platform agnostic and more versatile to use, and it transforms phrases to sign language in real time.
{"title":"Audio to Sign Language Translator Web Application","authors":"Anju Yadav, Rahul Saxena, B. Saini, V. K. Verma, Vibhav Srivastava","doi":"10.1109/ComPE53109.2021.9751857","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9751857","url":null,"abstract":"Sign language is an effective mode of conversation for persons who have difficulty speaking or hearing. There are numerous media accessible for translation or for identifying sign languages and converting those to text format, However, methods for converting text to sign language have been few and even not web-based software, owing to the scarcity of resources. The proposed web application seeks to develop a translating mechanism or automation that includes a parser element that converts the incoming speech data or English text to a phrase structure grammar representation, which is then used by another module that contains Indi Sign language grammatical format. This is accomplished through the means of removing stop-words from the reordered input format. Because Indian sign language does not provide word inflections, stemming and lemmatization are used to turn words into their root form. Following sentence filtration, all words are tested against the words in the database, which is represented as a dictionary comprising video representations of each word. If the words are missing from the database, the algorithm will then look for its related synonym and replace it with that term.In many ways, the proposed system is more innovative and efficient than existing systems, because Existing methods can only convert words directly into Indi sign language, and they were not as efficient as this system, whereas this in the actual world, the system tries to translate these phrases into Indian sign language grammatical order. Because this is a web-based programmed, it is straightforward to access and use. This technology is platform agnostic and more versatile to use, and it transforms phrases to sign language in real time.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"2659 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133439928","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-01DOI: 10.1109/ComPE53109.2021.9752376
S. Sharma, Durga Prasad Sharma, M. K. Sharma, K. Gaur, Pratibha Manohar
Climate change is a crucial challenge in this century. Temperature and rainfall are two essential determinants of climate. The present study is conducted to explore changes in rainfall and temperature using time series data of Jaipur districts over a period of last 37 years. Data on minimum temperature, maximum temperature and rainfall were collected from the Agrometeorology laboratory of Sri Karan Narendra Agriculture University, Jobner (Jaipur). Trend lines were fitted for minimum temperature, maximum temperature and rainfall and their significance is tested making use of the Mann-Kendall test. The increasing but non-significant trend was observed in minimum temperature whereas maximum temperature showed a significant increase over time which was confirmed by Mann-Kendall trend test. Rainfall showed non-significant decreasing trend for the given period.
{"title":"Analysis of Temperature and Rainfall Trends for Jaipur district of Rajasthan, India","authors":"S. Sharma, Durga Prasad Sharma, M. K. Sharma, K. Gaur, Pratibha Manohar","doi":"10.1109/ComPE53109.2021.9752376","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752376","url":null,"abstract":"Climate change is a crucial challenge in this century. Temperature and rainfall are two essential determinants of climate. The present study is conducted to explore changes in rainfall and temperature using time series data of Jaipur districts over a period of last 37 years. Data on minimum temperature, maximum temperature and rainfall were collected from the Agrometeorology laboratory of Sri Karan Narendra Agriculture University, Jobner (Jaipur). Trend lines were fitted for minimum temperature, maximum temperature and rainfall and their significance is tested making use of the Mann-Kendall test. The increasing but non-significant trend was observed in minimum temperature whereas maximum temperature showed a significant increase over time which was confirmed by Mann-Kendall trend test. Rainfall showed non-significant decreasing trend for the given period.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133975750","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-01DOI: 10.1109/ComPE53109.2021.9752229
Chandrika Acharjee, Sumanta Deb
The prevalent COVID 19 pandemic is incessantly taking toll on the lives of people throughout the world. Moreover, the dearth of effectual remedies has caused an expeditious rise in the total COVID 19 cases. Though vaccines have been developed, the enormous task of vaccinating a large population is still challenging. Also, as new variants emanate, the resilience from infections conceivably decreases. Hence, it’s most unlikely that we’ll achieve herd immunity globally so soon. Thus, since the transmission of COVID causing coronavirus roots mainly to social proximity between people, it is necessary to stringently comply to the non pharmaceutical preventive measures of wearing masks and maintaining physical distancing. Howbeit, it has evidently been found that people are being lethargically ignorant to the social distancing norms with passing time. Hence, an autonomous mechanism intended at social distancing violation detection through monitoring of people is needed to be introduced at an authority level. In this paper, the implementation of YOLO Object detection transfer learning process has been used for accomplishing this aim of real time detection of social distancing violation. Our social distance prediction approach uses a pre-trained YOLOv3 object tracking algorithm for identifying people in an input video stream. A Distance estimation algorithm is further used, that works by computing euclidean distance between the centroids of each pair of detected people. This approach highlights the people violating the social distancing criteria as well as calculates the number of times social distancing gets violated as any two people get closer than a set threshold value of minimum permissible distance. A number of experiments on various pre-recorded video streams has been conducted in order to estimate the viability of this method. Through experimental outcomes, it has been found that this YOLO based object detection method with the proposed social distance prediction algorithm produces favourable results for tracking social distancing in public spaces.
{"title":"YOLOv3 based Real Time Social Distance Violation Detection in Public Places","authors":"Chandrika Acharjee, Sumanta Deb","doi":"10.1109/ComPE53109.2021.9752229","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752229","url":null,"abstract":"The prevalent COVID 19 pandemic is incessantly taking toll on the lives of people throughout the world. Moreover, the dearth of effectual remedies has caused an expeditious rise in the total COVID 19 cases. Though vaccines have been developed, the enormous task of vaccinating a large population is still challenging. Also, as new variants emanate, the resilience from infections conceivably decreases. Hence, it’s most unlikely that we’ll achieve herd immunity globally so soon. Thus, since the transmission of COVID causing coronavirus roots mainly to social proximity between people, it is necessary to stringently comply to the non pharmaceutical preventive measures of wearing masks and maintaining physical distancing. Howbeit, it has evidently been found that people are being lethargically ignorant to the social distancing norms with passing time. Hence, an autonomous mechanism intended at social distancing violation detection through monitoring of people is needed to be introduced at an authority level. In this paper, the implementation of YOLO Object detection transfer learning process has been used for accomplishing this aim of real time detection of social distancing violation. Our social distance prediction approach uses a pre-trained YOLOv3 object tracking algorithm for identifying people in an input video stream. A Distance estimation algorithm is further used, that works by computing euclidean distance between the centroids of each pair of detected people. This approach highlights the people violating the social distancing criteria as well as calculates the number of times social distancing gets violated as any two people get closer than a set threshold value of minimum permissible distance. A number of experiments on various pre-recorded video streams has been conducted in order to estimate the viability of this method. Through experimental outcomes, it has been found that this YOLO based object detection method with the proposed social distance prediction algorithm produces favourable results for tracking social distancing in public spaces.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114205054","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-01DOI: 10.1109/ComPE53109.2021.9751990
V. S., Madhusudanan Pillai V, Basil Kuraichen
Tool wear in a milling process affects the finished product's overall quality, which results in rejection. With an increase in tool wear, cutting power decreases that affects the load on the machine. This results in damage of the equipment. Conventional manufacturing system lacks the way of forecasting the tool wear and its effects. Machine Learning (ML) model-based techniques with data-driven prognostics convert conventional manufacturing systems into smart manufacturing systems. This research paper focuses on the comparison of data-driven predictive models that predict tool wear based on the analysis of various sensor signals. In this study, eight algorithms such as Linear Regression (LR), Support Vector Regression (SVR), Naïve Bayesian (NB), Gradient Boost (GB), XG Boost (XGB), CatBoost (CB), Random Forest Regression (RFR), and Artificial Neural Network (ANN) are applied and compared their performance evaluation. The comparative study of regression algorithms provides an overview of tool wear prediction. Evaluation metrics chosen show conclusive evidence that the ANN model performs better than other models. The obtained predictive performance of the ANN model outperforms the existing models reported in the literature. The proposed ANN model for tool wear prediction uses the sensor information and exposes hidden patterns that completely fit the dataset.
{"title":"Data Driven Prognostics of Milling Tool Wear :A Machine Learning Approach","authors":"V. S., Madhusudanan Pillai V, Basil Kuraichen","doi":"10.1109/ComPE53109.2021.9751990","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9751990","url":null,"abstract":"Tool wear in a milling process affects the finished product's overall quality, which results in rejection. With an increase in tool wear, cutting power decreases that affects the load on the machine. This results in damage of the equipment. Conventional manufacturing system lacks the way of forecasting the tool wear and its effects. Machine Learning (ML) model-based techniques with data-driven prognostics convert conventional manufacturing systems into smart manufacturing systems. This research paper focuses on the comparison of data-driven predictive models that predict tool wear based on the analysis of various sensor signals. In this study, eight algorithms such as Linear Regression (LR), Support Vector Regression (SVR), Naïve Bayesian (NB), Gradient Boost (GB), XG Boost (XGB), CatBoost (CB), Random Forest Regression (RFR), and Artificial Neural Network (ANN) are applied and compared their performance evaluation. The comparative study of regression algorithms provides an overview of tool wear prediction. Evaluation metrics chosen show conclusive evidence that the ANN model performs better than other models. The obtained predictive performance of the ANN model outperforms the existing models reported in the literature. The proposed ANN model for tool wear prediction uses the sensor information and exposes hidden patterns that completely fit the dataset.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120925661","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-01DOI: 10.1109/ComPE53109.2021.9751799
Tarun Agrawal, P. Choudhary
COVID-19 was previously identified as 2019-nCoV, however it was reclassified as severe acute respiratory syndrome coronavirus 2 by the International Committee on Taxonomy of Viruses (ICTV) (SARS-CoV-2). It was first discovered in Wuhan, China’s Hubei Province, and has since spread all over the world. The scientific community is working to develop COVID-19 detection technologies that are both quick and accurate. Chest x-ray imaging can aid in the early diagnosis of COVID-19 patients. In COVID-19 individuals, chest x-rays can indicate a variety of lung abnormalities, including lung consolidation, ground-glass opacity, and others. The COVID-19 biomarkers, however, must be identified by qualified and experienced radiologists. Each report must be inspected by the radiologist, which is a time-consuming procedure. The medical infrastructure is currently overburdened due to the huge volume of patients. In this study, we propose automatic COVID-19 identification in chest x-rays using a deep learning technique. COVID-19, pneumonia, and healthy x-rays are included in the dataset for the studies. The proposed model had an average accuracy and sensitivity of 97 percent. The obtained findings demonstrate that the model can compete with existing state-of-the-art models.
{"title":"Automated COVID-19 detection using Deep Convolutional Neural Network and Chest X-ray Images","authors":"Tarun Agrawal, P. Choudhary","doi":"10.1109/ComPE53109.2021.9751799","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9751799","url":null,"abstract":"COVID-19 was previously identified as 2019-nCoV, however it was reclassified as severe acute respiratory syndrome coronavirus 2 by the International Committee on Taxonomy of Viruses (ICTV) (SARS-CoV-2). It was first discovered in Wuhan, China’s Hubei Province, and has since spread all over the world. The scientific community is working to develop COVID-19 detection technologies that are both quick and accurate. Chest x-ray imaging can aid in the early diagnosis of COVID-19 patients. In COVID-19 individuals, chest x-rays can indicate a variety of lung abnormalities, including lung consolidation, ground-glass opacity, and others. The COVID-19 biomarkers, however, must be identified by qualified and experienced radiologists. Each report must be inspected by the radiologist, which is a time-consuming procedure. The medical infrastructure is currently overburdened due to the huge volume of patients. In this study, we propose automatic COVID-19 identification in chest x-rays using a deep learning technique. COVID-19, pneumonia, and healthy x-rays are included in the dataset for the studies. The proposed model had an average accuracy and sensitivity of 97 percent. The obtained findings demonstrate that the model can compete with existing state-of-the-art models.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116798569","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：