Pub Date : 2023-03-02DOI: 10.1109/ICEARS56392.2023.10085475
Lakshmi Devi N, Rajasekhar Reddy Bochu, Naveen Kumar Buddha
Salt segmentation is the process of identifying whether a subsurface target is salt or not. There are several places on Earth where there are significant amounts of salt as well as oil and gas. For businesses engaged in oil and gas development, finding the exact locations of significant salt deposits is crucial. Also, lands that have been impacted by salt are not useful for farming. The absorption capacity of the plant reduces due to the presence of salt in the soil solution. So, in order to identify the land that contains salt, salt segmentation is being done. The seismic image of a particular pixel is analysed to classify it either as salt or sediment. TGS Salt Identification Challenge dataset is used which consists of 4,000 seismic image patches of size (101x101x3) and corresponding segmentation masks of size (101x101x1) in training set. 18,000 seismic image patches are present in the test set which are used for evaluation of the model. The existing models have less detection rate. So, this study has proposed two models for identifying the salt region with high detection rate. The primary model used here is a combination of UNET with ResNet-18 and ResNet-34. The secondary model achieves segmentation results by ensembling UNET with ResNet-34, VGG16 and Inceptionv3. Using these two models, the salt region can be determined from the seismic data. IoU is used as performance metric in order to evaluate the model. The outcomes demonstrate that the ensemble model outperforms individual network models and achieves better segmentation results.
{"title":"Salt Segment Identification in Seismic Images of Earth Surface using Deep Learning Techniques","authors":"Lakshmi Devi N, Rajasekhar Reddy Bochu, Naveen Kumar Buddha","doi":"10.1109/ICEARS56392.2023.10085475","DOIUrl":"https://doi.org/10.1109/ICEARS56392.2023.10085475","url":null,"abstract":"Salt segmentation is the process of identifying whether a subsurface target is salt or not. There are several places on Earth where there are significant amounts of salt as well as oil and gas. For businesses engaged in oil and gas development, finding the exact locations of significant salt deposits is crucial. Also, lands that have been impacted by salt are not useful for farming. The absorption capacity of the plant reduces due to the presence of salt in the soil solution. So, in order to identify the land that contains salt, salt segmentation is being done. The seismic image of a particular pixel is analysed to classify it either as salt or sediment. TGS Salt Identification Challenge dataset is used which consists of 4,000 seismic image patches of size (101x101x3) and corresponding segmentation masks of size (101x101x1) in training set. 18,000 seismic image patches are present in the test set which are used for evaluation of the model. The existing models have less detection rate. So, this study has proposed two models for identifying the salt region with high detection rate. The primary model used here is a combination of UNET with ResNet-18 and ResNet-34. The secondary model achieves segmentation results by ensembling UNET with ResNet-34, VGG16 and Inceptionv3. Using these two models, the salt region can be determined from the seismic data. IoU is used as performance metric in order to evaluate the model. The outcomes demonstrate that the ensemble model outperforms individual network models and achieves better segmentation results.","PeriodicalId":338611,"journal":{"name":"2023 Second International Conference on Electronics and Renewable Systems (ICEARS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134085173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-02DOI: 10.1109/ICEARS56392.2023.10085456
K. Makanyadevi, P. S, S. R, S. S
Across the world, people are growing more dietary sensitive today. An unbalanced diet can result in a variety of issues, including weight gain, obesity, diabetes, etc. As a result, many techniques were created to analyse images of food and determine factors like calories as well as nutrition content. One of the most essential needs of every living thing on earth is food. Humans demand that the food they eat be of standard quality, freshness, and purity. Food quality is taken care of by the standards set and automation implemented in the food processing business. The idea of using food as medicine has gained traction in recent years, in part due to doctors' and practitioners' increased understanding of the importance of including food in the treatment of chronic illnesses alongside drugs. Food measurement is crucial for a good healthy diet. One of the difficult tasks in maintaining diet is calorie and nutritional content measurement in daily eating. In today's technology age, the smartphone exacerbates the problem with nutritional intake. The meal image recognition algorithm for calculating the nutritional and calorie values has been established in this survey analysis. The system classifies the meal once the user takes a picture of it to determine the type of food, the portion size, and the expected number of calories. This approach uses food area, size, and volume to accurately compute calories and nutrition. Due to the difficulty in achieving accuracy to classify food images, many images have been trained to attain high accuracy.
{"title":"Survey on Customized Diet Assisted System based on Food Recognition","authors":"K. Makanyadevi, P. S, S. R, S. S","doi":"10.1109/ICEARS56392.2023.10085456","DOIUrl":"https://doi.org/10.1109/ICEARS56392.2023.10085456","url":null,"abstract":"Across the world, people are growing more dietary sensitive today. An unbalanced diet can result in a variety of issues, including weight gain, obesity, diabetes, etc. As a result, many techniques were created to analyse images of food and determine factors like calories as well as nutrition content. One of the most essential needs of every living thing on earth is food. Humans demand that the food they eat be of standard quality, freshness, and purity. Food quality is taken care of by the standards set and automation implemented in the food processing business. The idea of using food as medicine has gained traction in recent years, in part due to doctors' and practitioners' increased understanding of the importance of including food in the treatment of chronic illnesses alongside drugs. Food measurement is crucial for a good healthy diet. One of the difficult tasks in maintaining diet is calorie and nutritional content measurement in daily eating. In today's technology age, the smartphone exacerbates the problem with nutritional intake. The meal image recognition algorithm for calculating the nutritional and calorie values has been established in this survey analysis. The system classifies the meal once the user takes a picture of it to determine the type of food, the portion size, and the expected number of calories. This approach uses food area, size, and volume to accurately compute calories and nutrition. Due to the difficulty in achieving accuracy to classify food images, many images have been trained to attain high accuracy.","PeriodicalId":338611,"journal":{"name":"2023 Second International Conference on Electronics and Renewable Systems (ICEARS)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134166368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-02DOI: 10.1109/ICEARS56392.2023.10085204
A. Pugazhenthi, R. Thiyagarajan, P. Srividhya, R. Udhayasankar, S. R
A silicon carbide strengthened aluminium 6463 composite was formed by stir casting. To assess crucial process parameters, the composite was machined. At three different levels, three variables—current, pulse ON time, and feed of the wire—were incorporated in Taguchi's experimental setup. The components that impact the process were found using a statistical analysis. The ON time of the pulse of 160 s, the current of 18 A, and the feed of the wire of 2 mm/min had the highest removal rate. The pulse on-time of 100 s, the current of 12 A, and the feed of the wire rate of 2 mm/min remained the most effective factors for obtaining a good surface quality. Feed of the wire had minimal impact on output characteristics, but pulse duty cycle and current were important elements in achieving high material removal rates with acceptable surface quality. The experimental Taguchi design improved machinability characteristics while milling the synthesized composites by maintain the higher value of the ON time of the pulse and current. The artificial neural network model is developed to predict the experimental outcome and the model predicts the result with an accuracy of 100%.
{"title":"Artificial Neural Network and Process Optimization of Electrical Discharge Machining of Al 6463","authors":"A. Pugazhenthi, R. Thiyagarajan, P. Srividhya, R. Udhayasankar, S. R","doi":"10.1109/ICEARS56392.2023.10085204","DOIUrl":"https://doi.org/10.1109/ICEARS56392.2023.10085204","url":null,"abstract":"A silicon carbide strengthened aluminium 6463 composite was formed by stir casting. To assess crucial process parameters, the composite was machined. At three different levels, three variables—current, pulse ON time, and feed of the wire—were incorporated in Taguchi's experimental setup. The components that impact the process were found using a statistical analysis. The ON time of the pulse of 160 s, the current of 18 A, and the feed of the wire of 2 mm/min had the highest removal rate. The pulse on-time of 100 s, the current of 12 A, and the feed of the wire rate of 2 mm/min remained the most effective factors for obtaining a good surface quality. Feed of the wire had minimal impact on output characteristics, but pulse duty cycle and current were important elements in achieving high material removal rates with acceptable surface quality. The experimental Taguchi design improved machinability characteristics while milling the synthesized composites by maintain the higher value of the ON time of the pulse and current. The artificial neural network model is developed to predict the experimental outcome and the model predicts the result with an accuracy of 100%.","PeriodicalId":338611,"journal":{"name":"2023 Second International Conference on Electronics and Renewable Systems (ICEARS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134456323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-02DOI: 10.1109/ICEARS56392.2023.10085128
T. N. Deepthi, S. Sharmila, M. Swarna, M. Gouthami, C. Akshaya
Blood vessels in brain serve a major function in supplying the brain with nutrients and oxygen. All body parts are meant to be worked out actively. One of the deadliest diseases in the world is a brain stroke. Most strokes fall within the ischemic embolic and haemorrhagic categories. A blood clot that originates away from the patient's brain, typically in the heart, travels through the patient's bloodstream to lodge in the brain's smaller arteries to cause an ischemic stroke. The second is haemorrhagic stroke occurs when a brain artery bursts or releases blood. When a blood vessel either bursts or becomes blocked by a clot, a stroke develops. This study has collected a variety of patients' datasets. It includes a number of medical factors. There are a variety of machine learning algorithms available for making predictions, here the K-Nearest Neighbour with Random Forest algorithms are considered.
{"title":"Prediction of Brain Stroke in Human Beings using Machine Learning","authors":"T. N. Deepthi, S. Sharmila, M. Swarna, M. Gouthami, C. Akshaya","doi":"10.1109/ICEARS56392.2023.10085128","DOIUrl":"https://doi.org/10.1109/ICEARS56392.2023.10085128","url":null,"abstract":"Blood vessels in brain serve a major function in supplying the brain with nutrients and oxygen. All body parts are meant to be worked out actively. One of the deadliest diseases in the world is a brain stroke. Most strokes fall within the ischemic embolic and haemorrhagic categories. A blood clot that originates away from the patient's brain, typically in the heart, travels through the patient's bloodstream to lodge in the brain's smaller arteries to cause an ischemic stroke. The second is haemorrhagic stroke occurs when a brain artery bursts or releases blood. When a blood vessel either bursts or becomes blocked by a clot, a stroke develops. This study has collected a variety of patients' datasets. It includes a number of medical factors. There are a variety of machine learning algorithms available for making predictions, here the K-Nearest Neighbour with Random Forest algorithms are considered.","PeriodicalId":338611,"journal":{"name":"2023 Second International Conference on Electronics and Renewable Systems (ICEARS)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132951239","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-02DOI: 10.1109/ICEARS56392.2023.10084944
P. Ilampiray, A. Thilagavathy, Challa Sai Hari Uma Sahith, Penumathsa Girish Sai Varma, Bhuvanendra Chowdary V, M. Dhanush
Home Automation has become an important part nowadays. Home automation and the Internet of Things are becoming popular because automatic systems are preferred by most people. Life has become easier with automation. The emerging technologies like Machine Learning (ML) and Deep Learning (DL) play a major role in home automation. Nowadays there is a tremendous growth of mobile devices. But with machine learning systems, there is an increasing demand for smartphone applications. This paper focuses on an interactive mobile application that can control household electronic devices such as fans, AC, light, Television, etc., with the help of on-device machine learning and the Internet of Things. The proposed machine-learning algorithm automatically detects the type of device in just a photo-scan and performs the basic operations.
{"title":"An Ingenious Deep Learning Approach for Home Automation using Tensorflow Computational Framework","authors":"P. Ilampiray, A. Thilagavathy, Challa Sai Hari Uma Sahith, Penumathsa Girish Sai Varma, Bhuvanendra Chowdary V, M. Dhanush","doi":"10.1109/ICEARS56392.2023.10084944","DOIUrl":"https://doi.org/10.1109/ICEARS56392.2023.10084944","url":null,"abstract":"Home Automation has become an important part nowadays. Home automation and the Internet of Things are becoming popular because automatic systems are preferred by most people. Life has become easier with automation. The emerging technologies like Machine Learning (ML) and Deep Learning (DL) play a major role in home automation. Nowadays there is a tremendous growth of mobile devices. But with machine learning systems, there is an increasing demand for smartphone applications. This paper focuses on an interactive mobile application that can control household electronic devices such as fans, AC, light, Television, etc., with the help of on-device machine learning and the Internet of Things. The proposed machine-learning algorithm automatically detects the type of device in just a photo-scan and performs the basic operations.","PeriodicalId":338611,"journal":{"name":"2023 Second International Conference on Electronics and Renewable Systems (ICEARS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133419810","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-02DOI: 10.1109/ICEARS56392.2023.10085636
S. Sujanthi, A. S, H. K, S. S
The fourth most frequent illness-related cause of death in women is cervical malignant growth. Cervical cancer is associated with the presence of the human papillomavirus (HPV). Early detection has made cervical cancer preventable, which has decreased overall impact of the disease. Due to the high expense of routine exams, a lack of awareness, and limited access to medical facilities, women do not participate in enough screening programs in underdeveloped countries. This way, each patient is expected to be at extremely high risk. There are numerous threat factors that can lead to the growth of cervical cancer. As a result, the datasets will be checked for cervical cancer by using a variety of data analytics tools, including machine learning and deep learning algorithms. The classification of normal and abnormal cervical data is done by performing a quick overview of how cervical cancer works and is detected.
{"title":"Prediction of Cervical Cancer using Multilayer Perceptron Algorithm","authors":"S. Sujanthi, A. S, H. K, S. S","doi":"10.1109/ICEARS56392.2023.10085636","DOIUrl":"https://doi.org/10.1109/ICEARS56392.2023.10085636","url":null,"abstract":"The fourth most frequent illness-related cause of death in women is cervical malignant growth. Cervical cancer is associated with the presence of the human papillomavirus (HPV). Early detection has made cervical cancer preventable, which has decreased overall impact of the disease. Due to the high expense of routine exams, a lack of awareness, and limited access to medical facilities, women do not participate in enough screening programs in underdeveloped countries. This way, each patient is expected to be at extremely high risk. There are numerous threat factors that can lead to the growth of cervical cancer. As a result, the datasets will be checked for cervical cancer by using a variety of data analytics tools, including machine learning and deep learning algorithms. The classification of normal and abnormal cervical data is done by performing a quick overview of how cervical cancer works and is detected.","PeriodicalId":338611,"journal":{"name":"2023 Second International Conference on Electronics and Renewable Systems (ICEARS)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133421715","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-02DOI: 10.1109/ICEARS56392.2023.10085408
A. M, Thirumalai A
First, with regards to attribute-based encryption (ABE), it is an approach to access control that allows data to be encrypted and decrypted based on certain attributes, such as a user's role, location, or other characteristics. This approach provides granular control over who can access specific data, which is particularly useful for IoT applications where sensitive data is being generated by many devices. However, as I mentioned earlier, ABE can be computationally intensive, which may not be suitable for low-power IoT devices. One possible solution to this challenge is to use edge computing, where some of the computing tasks are performed at the edge of the network, closer to the devices generating the data. This can help reduce the amount of data that needs to be sent to the cloud and can improve overall system performance. Another challenge with ABE is that it does not provide protection against key sharing. If a user shares their decryption key with an unauthorized party, that party could potentially gain access to sensitive data. To address this challenge, it's important to have strong access controls in place to prevent unauthorized sharing of keys. In terms of data storage security, while outsourcing to cloud servers can certainly help with complex computing tasks, it's still important to implement sophisticated security measures. This might include encrypting the data at rest and in transit, implementing access controls, and monitoring the system for potential security breaches. Finally, it's important to follow regulations and best practices for key sharing to prevent unauthorized access to sensitive data. This might include policies around key management, user authentication, and data governance.
{"title":"Effective Management of IoT Devices that can Withstand Attacks on Cloud Data","authors":"A. M, Thirumalai A","doi":"10.1109/ICEARS56392.2023.10085408","DOIUrl":"https://doi.org/10.1109/ICEARS56392.2023.10085408","url":null,"abstract":"First, with regards to attribute-based encryption (ABE), it is an approach to access control that allows data to be encrypted and decrypted based on certain attributes, such as a user's role, location, or other characteristics. This approach provides granular control over who can access specific data, which is particularly useful for IoT applications where sensitive data is being generated by many devices. However, as I mentioned earlier, ABE can be computationally intensive, which may not be suitable for low-power IoT devices. One possible solution to this challenge is to use edge computing, where some of the computing tasks are performed at the edge of the network, closer to the devices generating the data. This can help reduce the amount of data that needs to be sent to the cloud and can improve overall system performance. Another challenge with ABE is that it does not provide protection against key sharing. If a user shares their decryption key with an unauthorized party, that party could potentially gain access to sensitive data. To address this challenge, it's important to have strong access controls in place to prevent unauthorized sharing of keys. In terms of data storage security, while outsourcing to cloud servers can certainly help with complex computing tasks, it's still important to implement sophisticated security measures. This might include encrypting the data at rest and in transit, implementing access controls, and monitoring the system for potential security breaches. Finally, it's important to follow regulations and best practices for key sharing to prevent unauthorized access to sensitive data. This might include policies around key management, user authentication, and data governance.","PeriodicalId":338611,"journal":{"name":"2023 Second International Conference on Electronics and Renewable Systems (ICEARS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122805623","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-02DOI: 10.1109/ICEARS56392.2023.10085155
Kanagaraj Venusamy, Abdul Hafeel M, K. M, Muthukkaruppan S, Chandramohan P
The limitation in the procedure of India’s postal service is that it takes additional operations and human work, making it harder and impossible to reduce costs and time. Weighing, sorting, and updating information are the laborious processes which could be more productive and cheaper when automated. A barcode scanner-based courier sorting system conveyor belt design using IoT has been proposed in this paper. Barcode scanning, weight estimation, and product tracking utilizing an IoT-powered conveyor system are the key goals of this work. This allows postal service systems to combine contemporary technology for logistics monitoring, sorting by destination and weight, shipping cost estimates, and quick information access.
{"title":"Study on Conveyor Belt System enabled with IoT in Postal and Courier Services","authors":"Kanagaraj Venusamy, Abdul Hafeel M, K. M, Muthukkaruppan S, Chandramohan P","doi":"10.1109/ICEARS56392.2023.10085155","DOIUrl":"https://doi.org/10.1109/ICEARS56392.2023.10085155","url":null,"abstract":"The limitation in the procedure of India’s postal service is that it takes additional operations and human work, making it harder and impossible to reduce costs and time. Weighing, sorting, and updating information are the laborious processes which could be more productive and cheaper when automated. A barcode scanner-based courier sorting system conveyor belt design using IoT has been proposed in this paper. Barcode scanning, weight estimation, and product tracking utilizing an IoT-powered conveyor system are the key goals of this work. This allows postal service systems to combine contemporary technology for logistics monitoring, sorting by destination and weight, shipping cost estimates, and quick information access.","PeriodicalId":338611,"journal":{"name":"2023 Second International Conference on Electronics and Renewable Systems (ICEARS)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121302823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-02DOI: 10.1109/ICEARS56392.2023.10085551
S. Sharmila, R. Bhargavi, R. Anusha, K. Anusha, B. Divya
Deep learning is a subset of artificial intelligence. It's a form of artificial intelligence and machine learning that attempts to simulate the way humans pick up specific types of information. The goal of this project is to create a deep learning model based on convolutional neural networks that can distinguish between healthy and diseased leaves. Due to its useful features in learner autonomy and extraction of features, it has drawn a great deal of attention in past years from researchers and industry professionals alike. Images of healthy and rotting leaves are included in the dataset. It is widely used in fields such as computational linguistics, voice processing, image processing, and video processing. It has also become a center for studies on agricultural plant protection, such as the detection of plant diseases and the assessment of pest ranges. This study has also discussed about some of the problems and issues that are currently being faced and need to be addressed. Library packages such as KERAS, MATPLOTLIB, NUMPY, and OPENCV have been utilized here.
{"title":"Cotton Leaf Disease Detection using Convolutional Neural Networks (CNN)","authors":"S. Sharmila, R. Bhargavi, R. Anusha, K. Anusha, B. Divya","doi":"10.1109/ICEARS56392.2023.10085551","DOIUrl":"https://doi.org/10.1109/ICEARS56392.2023.10085551","url":null,"abstract":"Deep learning is a subset of artificial intelligence. It's a form of artificial intelligence and machine learning that attempts to simulate the way humans pick up specific types of information. The goal of this project is to create a deep learning model based on convolutional neural networks that can distinguish between healthy and diseased leaves. Due to its useful features in learner autonomy and extraction of features, it has drawn a great deal of attention in past years from researchers and industry professionals alike. Images of healthy and rotting leaves are included in the dataset. It is widely used in fields such as computational linguistics, voice processing, image processing, and video processing. It has also become a center for studies on agricultural plant protection, such as the detection of plant diseases and the assessment of pest ranges. This study has also discussed about some of the problems and issues that are currently being faced and need to be addressed. Library packages such as KERAS, MATPLOTLIB, NUMPY, and OPENCV have been utilized here.","PeriodicalId":338611,"journal":{"name":"2023 Second International Conference on Electronics and Renewable Systems (ICEARS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121347911","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-02DOI: 10.1109/ICEARS56392.2023.10085491
N. Kumar, N. Sathyanarayana
Patients with diabetes are more likely to be readmitted to the hospital than those who are nondiabetic. The earlier patients with a strong probability of readmission are monitored and cared for, the better. The goal of this research is to develop a decision - making framework that can identify diabetes patients who are at risk of early readmission. Many data analysis approaches have been employed to perform this. Computer vision is used to create a novel model in this study. Individuals at high risk of complications to be readmitted are prioritized in the early stages, which in turn reduces healthcare costs and improves the reputation of the hospital, thus enhancing the health service and saving money. Predictions made using machine learning are more accurate than those made using traditional methods. In this study, patients' hospital readmissions may be predicted by utilizing a standard scaler, a decision tree, and random forests for classification, CATboost for categorical features, and XGBoost classifiers. When applied to real-world data, a machine learning method that incorporates deep learning technique has outperformed the other methods. As a response to a number of modules, including extracting features, the analysis has been enhanced and a more useful framework has been created.
{"title":"Prediction of Diabetic Patients with High Risk of Readmission using Smart Decision Support Framework","authors":"N. Kumar, N. Sathyanarayana","doi":"10.1109/ICEARS56392.2023.10085491","DOIUrl":"https://doi.org/10.1109/ICEARS56392.2023.10085491","url":null,"abstract":"Patients with diabetes are more likely to be readmitted to the hospital than those who are nondiabetic. The earlier patients with a strong probability of readmission are monitored and cared for, the better. The goal of this research is to develop a decision - making framework that can identify diabetes patients who are at risk of early readmission. Many data analysis approaches have been employed to perform this. Computer vision is used to create a novel model in this study. Individuals at high risk of complications to be readmitted are prioritized in the early stages, which in turn reduces healthcare costs and improves the reputation of the hospital, thus enhancing the health service and saving money. Predictions made using machine learning are more accurate than those made using traditional methods. In this study, patients' hospital readmissions may be predicted by utilizing a standard scaler, a decision tree, and random forests for classification, CATboost for categorical features, and XGBoost classifiers. When applied to real-world data, a machine learning method that incorporates deep learning technique has outperformed the other methods. As a response to a number of modules, including extracting features, the analysis has been enhanced and a more useful framework has been created.","PeriodicalId":338611,"journal":{"name":"2023 Second International Conference on Electronics and Renewable Systems (ICEARS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121428801","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：