Pub Date : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987381
Wang Yachen
Therefore, in the teaching process of developing PHP business website development courses, students are gradually guided to use PHP language to complete an online examination system with relatively complete functions. By analyzing the current situation and existing problems of teachers' quality in higher normal schools, it is necessary to further recognize and cultivate innovative talents in the 21st century. The requirements of talents for the quality of teachers in higher normal schools, and recognize the very urgent practical problem of improving their own quality of teachers in higher normal schools, combine traditional teaching evaluation methods with modern educational technology, and use existing 1T technology to design a comprehensive teaching ability based on B/S model. The evaluation system changes the traditional manual evaluation into a paperless and networked process.
{"title":"Application of AI-Enhanced Analytic Hierarchy Process in the Online PHP System","authors":"Wang Yachen","doi":"10.1109/I-SMAC55078.2022.9987381","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987381","url":null,"abstract":"Therefore, in the teaching process of developing PHP business website development courses, students are gradually guided to use PHP language to complete an online examination system with relatively complete functions. By analyzing the current situation and existing problems of teachers' quality in higher normal schools, it is necessary to further recognize and cultivate innovative talents in the 21st century. The requirements of talents for the quality of teachers in higher normal schools, and recognize the very urgent practical problem of improving their own quality of teachers in higher normal schools, combine traditional teaching evaluation methods with modern educational technology, and use existing 1T technology to design a comprehensive teaching ability based on B/S model. The evaluation system changes the traditional manual evaluation into a paperless and networked process.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133078296","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987431
S. Saradha, J. Asha, J. Sreemathy
Through the use of livestock, information sharing is becoming increasingly popular around the world. This study aims to see biometric face analysis be used on sheep recognition to improve sheep monitoring in the centralized database. Anchor-free region convolutional neural networks were used to detect sheep identities (AF-RCNN). Face recognition’s effectiveness as a biometric-based identification for sheep was studied utilizing reviews of face images using the deep earing approach. The method is standalone on a set of standardized facial photos from 50 sheep, using an augmentation strategy to expand the number of sheep images. The proposed method outperforms earlier methods for sheep recognition with high accuracy.
{"title":"A Deep Learning-based Framework for Sheep Identification System based on Facial Bio-Metrics Analysis","authors":"S. Saradha, J. Asha, J. Sreemathy","doi":"10.1109/I-SMAC55078.2022.9987431","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987431","url":null,"abstract":"Through the use of livestock, information sharing is becoming increasingly popular around the world. This study aims to see biometric face analysis be used on sheep recognition to improve sheep monitoring in the centralized database. Anchor-free region convolutional neural networks were used to detect sheep identities (AF-RCNN). Face recognition’s effectiveness as a biometric-based identification for sheep was studied utilizing reviews of face images using the deep earing approach. The method is standalone on a set of standardized facial photos from 50 sheep, using an augmentation strategy to expand the number of sheep images. The proposed method outperforms earlier methods for sheep recognition with high accuracy.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122133136","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987345
S. Sruthi, S. Sridhar
Main goal of the research is to employ Music genre prediction-based classification of audio files with low level feature of frequency domain and time domain using K-Means Clustering (K-Means) and Support Vector Machine (SVM). Materials and Methods: SVM and K-Means are implemented in this research work. Sample size is calculated using G power software and determined as 10 per group with pretest power 80%, threshold 0.05% and CI 95%. Result: SVM provides a higher of 95.35% compared to K-Means algorithm with 75.20% in predicting classification of Audio files with low level feature of frequency domain. There is a noteworthy difference between two groups with a significance value of 0.28 (p>0.05). Conclusion: NovelSupport Vector Machine algorithm predicts audio files with low level frequency better than K-Means algorithm.
{"title":"Music Genre Predictor based Classification of Audio Files with Low Level Feature of Frequency and Time Domain using Support Vector Machine Over K-Means Clustering Algorithm","authors":"S. Sruthi, S. Sridhar","doi":"10.1109/I-SMAC55078.2022.9987345","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987345","url":null,"abstract":"Main goal of the research is to employ Music genre prediction-based classification of audio files with low level feature of frequency domain and time domain using K-Means Clustering (K-Means) and Support Vector Machine (SVM). Materials and Methods: SVM and K-Means are implemented in this research work. Sample size is calculated using G power software and determined as 10 per group with pretest power 80%, threshold 0.05% and CI 95%. Result: SVM provides a higher of 95.35% compared to K-Means algorithm with 75.20% in predicting classification of Audio files with low level feature of frequency domain. There is a noteworthy difference between two groups with a significance value of 0.28 (p>0.05). Conclusion: NovelSupport Vector Machine algorithm predicts audio files with low level frequency better than K-Means algorithm.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"75 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134254989","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987378
C. Latha, S. Bhuvaneswari, K. Soujanya
Forecasting is still a potential area of research, particularly in the stock market. Any forecasting model must overcome the subjective nature of the factors that affect market oscillation. Current fuzzy models have made an effort throughout the years to improve financial market forecasting accuracy. The fuzzy returns of the phenomena under study contribute to reducing the subjective nature of the financial market, particularly with respect to the effect of human emotions. These are based on large part on fuzzy sets. Fuzzy sets, on the other hand, may not fully satisfy or characterize the ambiguity of the data since they are unable to depict the level of neutrality of time series. Existing fuzzy inference systems’ reliance on a univariate framework is another important and crucial shortcoming. However, the time series that are part of a prediction problem frequently interact with one another. Given these factors, it is important to create a hybrid fuzzy system for a time series prediction issue that is built on fresh fuzzy sets and a collection of fuzzy logic relations. In this context, this research suggests a hybrid fuzzy time-series forecasting model (HFTSF) on the Standard & Poor Bombay Stock Exchange Information Technology (S& P BSE IT) index, for the prediction of time-series data. This model boosts the chances of getting better forecasts. The validation techniques such as root mean square error, mean square error, and mean absolute error were used in terms of validating the predicting outcomes.
{"title":"Stock Price Prediction using HFTSF Algorithm","authors":"C. Latha, S. Bhuvaneswari, K. Soujanya","doi":"10.1109/I-SMAC55078.2022.9987378","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987378","url":null,"abstract":"Forecasting is still a potential area of research, particularly in the stock market. Any forecasting model must overcome the subjective nature of the factors that affect market oscillation. Current fuzzy models have made an effort throughout the years to improve financial market forecasting accuracy. The fuzzy returns of the phenomena under study contribute to reducing the subjective nature of the financial market, particularly with respect to the effect of human emotions. These are based on large part on fuzzy sets. Fuzzy sets, on the other hand, may not fully satisfy or characterize the ambiguity of the data since they are unable to depict the level of neutrality of time series. Existing fuzzy inference systems’ reliance on a univariate framework is another important and crucial shortcoming. However, the time series that are part of a prediction problem frequently interact with one another. Given these factors, it is important to create a hybrid fuzzy system for a time series prediction issue that is built on fresh fuzzy sets and a collection of fuzzy logic relations. In this context, this research suggests a hybrid fuzzy time-series forecasting model (HFTSF) on the Standard & Poor Bombay Stock Exchange Information Technology (S& P BSE IT) index, for the prediction of time-series data. This model boosts the chances of getting better forecasts. The validation techniques such as root mean square error, mean square error, and mean absolute error were used in terms of validating the predicting outcomes.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131594874","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987321
S. Sivasubramanian, N. K. Sundaram, S. Padhi, Dipesh Uike, B. Maheswari, V. Banupriya
An automatic vending machine is designed to supply people with a variety of items, such as snacks, beverages, newspapers, and tickets without any human intervention. According to the money that is deposited into a vending machine as well as the product that has been selected by the user, the machine will determine the item and will distribute it to the user. In the proposed work, the vending machine has been designed to distribute fruits to the user as per their requirement. Classification algorithms have been used to predict the type of fruits required by the user with the help of the input provided by camera. The load cell is used to measure the kilogram or the quantity of the fruits as per the requirement by using some input peripherals like keyboard. The proposed system is also a user interactive based once. Here, there is a display device that has interfaced with the system and the display device will provide information such as the fruit which has been chosen and the quantity of the fruit that the user has entered and also shares the information on the status of the requirements. So, it will be useful for the user to know the process going in the vending machine. The raspberry pi microprocessor has employed here as a processor along the required input and output peripherals like LCD, Keypad, Load cell, camera, and motors. The machine learning algorithm like a support vector machine has been employed to predict the type of fruit as per the requirements of the user. The insertion of intelligence like machine learning algorithms in the vending machine is comparatively providing better performance. The long-term objective is to equip a vending machine solution that is both affordable and efficient, therefore boosting the shopping experience of customers and increasing the need for widespread deployment of intelligence in smart vending machines.
{"title":"Next generation Fruit Vending Machine using Artificial Intelligence","authors":"S. Sivasubramanian, N. K. Sundaram, S. Padhi, Dipesh Uike, B. Maheswari, V. Banupriya","doi":"10.1109/I-SMAC55078.2022.9987321","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987321","url":null,"abstract":"An automatic vending machine is designed to supply people with a variety of items, such as snacks, beverages, newspapers, and tickets without any human intervention. According to the money that is deposited into a vending machine as well as the product that has been selected by the user, the machine will determine the item and will distribute it to the user. In the proposed work, the vending machine has been designed to distribute fruits to the user as per their requirement. Classification algorithms have been used to predict the type of fruits required by the user with the help of the input provided by camera. The load cell is used to measure the kilogram or the quantity of the fruits as per the requirement by using some input peripherals like keyboard. The proposed system is also a user interactive based once. Here, there is a display device that has interfaced with the system and the display device will provide information such as the fruit which has been chosen and the quantity of the fruit that the user has entered and also shares the information on the status of the requirements. So, it will be useful for the user to know the process going in the vending machine. The raspberry pi microprocessor has employed here as a processor along the required input and output peripherals like LCD, Keypad, Load cell, camera, and motors. The machine learning algorithm like a support vector machine has been employed to predict the type of fruit as per the requirements of the user. The insertion of intelligence like machine learning algorithms in the vending machine is comparatively providing better performance. The long-term objective is to equip a vending machine solution that is both affordable and efficient, therefore boosting the shopping experience of customers and increasing the need for widespread deployment of intelligence in smart vending machines.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133713862","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9986503
K. Sarmila, S. Manisekaran
Extensive development in networking and data communication among IoT devices has involved cloud computing in IoT environments to handle the ongoing data processing demands. The accelerated growth and integration of IoT and Cloud computing led to parallel expansion in the requirement of security and privacy of data at various levels of communication. Through communication with each other, these technologies aim at simplifying human life but are more vulnerable to different types of attacks. This paper focuses on building a knowledge base on various attacks on the IoT environment and highlights the importance of implementing data protection methodologies. Awareness of various threats is the initial step in providing sufficient protection to data. This paper recognizes research directions and challenges to integrate possible techniques and protective solutions to overcome malicious attacks in IoT and Cloud.
{"title":"Certain Investigation of Various Attacks and Vulnerabilites in IoT and Cloud Environment","authors":"K. Sarmila, S. Manisekaran","doi":"10.1109/I-SMAC55078.2022.9986503","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9986503","url":null,"abstract":"Extensive development in networking and data communication among IoT devices has involved cloud computing in IoT environments to handle the ongoing data processing demands. The accelerated growth and integration of IoT and Cloud computing led to parallel expansion in the requirement of security and privacy of data at various levels of communication. Through communication with each other, these technologies aim at simplifying human life but are more vulnerable to different types of attacks. This paper focuses on building a knowledge base on various attacks on the IoT environment and highlights the importance of implementing data protection methodologies. Awareness of various threats is the initial step in providing sufficient protection to data. This paper recognizes research directions and challenges to integrate possible techniques and protective solutions to overcome malicious attacks in IoT and Cloud.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117316285","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987418
Yi-Heng Mao, Man Zhang
The image recognition rate is reduced. Based on the monochromatic atmospheric scattering model and the prior law of dark primary colors, a new algorithm for the saturation of the HS I color model for visual perception is proposed to achieve image dehazing. For the minimum pixel point of the dehazed image, the maximum value and the minimum value are used. Estimate. It is conduded that “high efficiency, energy saving, green low carbon, clean and environmental protection” is the inevitable direction of the future development of DC welding power sources. Using the good 3D image generation function of the OpenGL graphics standard, the special finite element simulation system for the steel pipe tension reduction process developed by Yanshan University is based on the SketchUp platform. where the target is.
{"title":"Application of Image Saturation Enhancement Algorithm based on OpenGL Aided Design System","authors":"Yi-Heng Mao, Man Zhang","doi":"10.1109/I-SMAC55078.2022.9987418","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987418","url":null,"abstract":"The image recognition rate is reduced. Based on the monochromatic atmospheric scattering model and the prior law of dark primary colors, a new algorithm for the saturation of the HS I color model for visual perception is proposed to achieve image dehazing. For the minimum pixel point of the dehazed image, the maximum value and the minimum value are used. Estimate. It is conduded that “high efficiency, energy saving, green low carbon, clean and environmental protection” is the inevitable direction of the future development of DC welding power sources. Using the good 3D image generation function of the OpenGL graphics standard, the special finite element simulation system for the steel pipe tension reduction process developed by Yanshan University is based on the SketchUp platform. where the target is.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120994916","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987284
S. Banu, Syeeda Ayesha Mohmudiya, Noor Rahiba, Saniya Anmol
Because health and wellbeing are so important to human society, they should be among the first to benefit from emerging technologies like IoT. Dementia affects the elderly and persons with chronic diseases who must take their medications on time and without fail. In light of this, to track patients’ day-to-day activities, several Internet of Medical Things (IoMT) systems are connected to IoT networks. To overcome this, a smart medicine box has been developed for those people, who regularly take medicines and the prescription of their medicine is very long as it is hard to remember. This medicine box contains three sub pill boxes. Caregiver can setup time for these three sub pill boxes. Pill boxes are pre-loaded in the system which patient needs to take at given time which reduces caregiver’s responsibility towards giving the correct and timely consumption of medicines. When time of pill is set, pillbox will remind to take pill at a particular time and the pills required to take at that time comes out to the user to avoid confusion among medicines.
{"title":"IoT Enabled Patient Medicine Intake Tracking System-MEDIKIT","authors":"S. Banu, Syeeda Ayesha Mohmudiya, Noor Rahiba, Saniya Anmol","doi":"10.1109/I-SMAC55078.2022.9987284","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987284","url":null,"abstract":"Because health and wellbeing are so important to human society, they should be among the first to benefit from emerging technologies like IoT. Dementia affects the elderly and persons with chronic diseases who must take their medications on time and without fail. In light of this, to track patients’ day-to-day activities, several Internet of Medical Things (IoMT) systems are connected to IoT networks. To overcome this, a smart medicine box has been developed for those people, who regularly take medicines and the prescription of their medicine is very long as it is hard to remember. This medicine box contains three sub pill boxes. Caregiver can setup time for these three sub pill boxes. Pill boxes are pre-loaded in the system which patient needs to take at given time which reduces caregiver’s responsibility towards giving the correct and timely consumption of medicines. When time of pill is set, pillbox will remind to take pill at a particular time and the pills required to take at that time comes out to the user to avoid confusion among medicines.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115533851","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987302
M. P. Varghese, T. Muthumanickam
Due to the vast amount of data collected and the very high level of complexity in VLSI design and manufacturing, the implementation using machine learning can be used in physical design has increased significantly. ML can be used to increase the abstraction level that is obtained from complex simulations based on physics models and provide results that represent a significant level of quality. Computer science techniques such as pattern matching and machine learning can reduce the design time of VLSI circuits by working with large datasets.
{"title":"Machine Learning Approaches for Electronic Design Automation in IC Design Flow","authors":"M. P. Varghese, T. Muthumanickam","doi":"10.1109/I-SMAC55078.2022.9987302","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987302","url":null,"abstract":"Due to the vast amount of data collected and the very high level of complexity in VLSI design and manufacturing, the implementation using machine learning can be used in physical design has increased significantly. ML can be used to increase the abstraction level that is obtained from complex simulations based on physics models and provide results that represent a significant level of quality. Computer science techniques such as pattern matching and machine learning can reduce the design time of VLSI circuits by working with large datasets.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115993576","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987398
D. J. N. Kumar, V. K, S. Sagar Imambi, P. V. Pramila, Ashok Kumar, Vijayabhaskar V
Rheumatoid arthritis, often known as rheumatoid, is an inflammatory condition brought on by the immune system’s malfunction.Various preliminary tests were proposed to predict this chronic illness. This study proposes a deep learning model which can detect the presence of rheumatoid by analyzing the thermal images of a person. For this purpose, the palms of the rheumatoid patients and the control group were scanned to produce a sample of thermal pictures of human hands. The efficiency of this training is then improved by preprocessing the thermal pictures. The CNN-LS TM approach is used to build a deep learning model. Then, to accurately forecast the presence of rheumatoid, this model is trained using thermal pictures. The training’s outcomes are noted and reviewed. Validation comes after training, and the outcomes of the validation are also tabulated. For simpler analysis, the findings are also plotted as graphs. The results show that as the number of epochs rises, accuracy, precision, and recall value all significantly increase. As the number of epochs rises, the loss value also falls. The model is then tested to determine the final values for each parameter after training and validation. The final accuracy score of the model is 92.78, while the loss score is 3.78, which is so minuscule as to occasionally be ignored. The model’s precision is 95.4%, and its recall value is 93.7%. This deep learning model can be utilized as a screening tool for rheumatoidbecause of its improved accuracy and precision values.
{"title":"DL-based Rheumatoid Arthritis Prediction using Thermal Images","authors":"D. J. N. Kumar, V. K, S. Sagar Imambi, P. V. Pramila, Ashok Kumar, Vijayabhaskar V","doi":"10.1109/I-SMAC55078.2022.9987398","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987398","url":null,"abstract":"Rheumatoid arthritis, often known as rheumatoid, is an inflammatory condition brought on by the immune system’s malfunction.Various preliminary tests were proposed to predict this chronic illness. This study proposes a deep learning model which can detect the presence of rheumatoid by analyzing the thermal images of a person. For this purpose, the palms of the rheumatoid patients and the control group were scanned to produce a sample of thermal pictures of human hands. The efficiency of this training is then improved by preprocessing the thermal pictures. The CNN-LS TM approach is used to build a deep learning model. Then, to accurately forecast the presence of rheumatoid, this model is trained using thermal pictures. The training’s outcomes are noted and reviewed. Validation comes after training, and the outcomes of the validation are also tabulated. For simpler analysis, the findings are also plotted as graphs. The results show that as the number of epochs rises, accuracy, precision, and recall value all significantly increase. As the number of epochs rises, the loss value also falls. The model is then tested to determine the final values for each parameter after training and validation. The final accuracy score of the model is 92.78, while the loss score is 3.78, which is so minuscule as to occasionally be ignored. The model’s precision is 95.4%, and its recall value is 93.7%. This deep learning model can be utilized as a screening tool for rheumatoidbecause of its improved accuracy and precision values.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123631515","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：