Pub Date : 2023-04-05DOI: 10.1109/ICNWC57852.2023.10127315
Paras Rawat, Annanya Pandey, Annapurani Panaiyappan.K
Rice is the primary food source for a significant portion of the global population and the productivity of rice crops can be severely impacted by diseases. These diseases can cause significant yield loss, which can have a major impact on food security. Accurate and timely detection of rice leaf diseases is therefore crucial for implementing effective control measures to minimize yield loss. This study aims to work towards the detection of rice leaf diseases, specifically leaf smut, brown spot, and bacterial leaf blight, using a deep learning approach. ResNet50 with an added NN architecture was trained on a dataset consisting of images of rice leaves collected from the Bahribahri rice farm in Indonesia. The dataset includes 4000 photos of each of the three diseases listed above in addition to an equal number of photographs of rice crops in good health. The dataset is used to train the model so that it can identify the presence of the diseases in new images. The results show that the use of ResNet50+NN achieved an accuracy of 99.5% in detecting the three diseases, making it a promising tool for rice leaf disease detection in a farm setting. In summary, this study provides an efficient and accurate solution for rice leaf disease detection, which is critical for maintaining rice productivity and food security.
{"title":"Rice Leaf Diseases Classification Using Deep Learning Techniques","authors":"Paras Rawat, Annanya Pandey, Annapurani Panaiyappan.K","doi":"10.1109/ICNWC57852.2023.10127315","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127315","url":null,"abstract":"Rice is the primary food source for a significant portion of the global population and the productivity of rice crops can be severely impacted by diseases. These diseases can cause significant yield loss, which can have a major impact on food security. Accurate and timely detection of rice leaf diseases is therefore crucial for implementing effective control measures to minimize yield loss. This study aims to work towards the detection of rice leaf diseases, specifically leaf smut, brown spot, and bacterial leaf blight, using a deep learning approach. ResNet50 with an added NN architecture was trained on a dataset consisting of images of rice leaves collected from the Bahribahri rice farm in Indonesia. The dataset includes 4000 photos of each of the three diseases listed above in addition to an equal number of photographs of rice crops in good health. The dataset is used to train the model so that it can identify the presence of the diseases in new images. The results show that the use of ResNet50+NN achieved an accuracy of 99.5% in detecting the three diseases, making it a promising tool for rice leaf disease detection in a farm setting. In summary, this study provides an efficient and accurate solution for rice leaf disease detection, which is critical for maintaining rice productivity and food security.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126380875","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 : 2023-04-05DOI: 10.1109/ICNWC57852.2023.10127284
Himanshu Singh, Utkarsh Tewari, S. Ushasukhanya
Agriculture struggles to cater to the rapidly increasing global population, one major cause for this are the plant diseases and pests which negatively hinder the production quantity and quality of food, fibre and biofuel crops. In some parts of the world, losses in tomato production due to pests continue to exceed a staggering 50% of attainable production. This paper aims to utilize DL algorithms such as CNN (Convolution Neural Network) to detect multiple diseases in tomato plant. One limitation of the current CNN models is that it does not perform well with small datasets and fails in cases of specimen having symptoms of multiple diseases or viruses in the same image of the dataset. This paper aims to fix that
{"title":"Tomato Crop Disease Classification using Convolution Neural Network and Transfer Learning","authors":"Himanshu Singh, Utkarsh Tewari, S. Ushasukhanya","doi":"10.1109/ICNWC57852.2023.10127284","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127284","url":null,"abstract":"Agriculture struggles to cater to the rapidly increasing global population, one major cause for this are the plant diseases and pests which negatively hinder the production quantity and quality of food, fibre and biofuel crops. In some parts of the world, losses in tomato production due to pests continue to exceed a staggering 50% of attainable production. This paper aims to utilize DL algorithms such as CNN (Convolution Neural Network) to detect multiple diseases in tomato plant. One limitation of the current CNN models is that it does not perform well with small datasets and fails in cases of specimen having symptoms of multiple diseases or viruses in the same image of the dataset. This paper aims to fix that","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125148116","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 : 2023-04-05DOI: 10.1109/ICNWC57852.2023.10127512
P. Pandian, C. Selvaraj, N. Bhalaji, K. G. Arun Depak, S. Saikrishnan
According to the Cisco’s white paper for the year 2018-2023, machine-to-machine (M2M) connections are mentioned as the first fastest growing connections, with a 2.4 fold increase between 2018 and 2023. This will possibly lead to an increase in radio spectrum utilization. The spectrum will be congested due to its limited availability, and interruption of services also occurs in high-traffic scenarios. To overcome this drawback, Cognitive Radio (CR) acts as a promising and intelligent technology that facilitates the unlicensed users (Secondary Users) to efficiently utilize the spectrum allotted to the licensed users (Primary Users) without imposing any interference to them. In order to increase the coexistence of devices without modifying anything in terms of hardware, CR has the feasibility of providing solutions to spectrum prediction for end users. Further, to improve spectrum prediction, machine learning algorithms greatly help the cognitive radio to select the appropriate spectrum based on the requirements of secondary users. In this paper, machine learning algorithms like Random forest classifier, Logistic Regression, KNN classifier, Decision Tree classifier, Artificial Neural Network (ANN), Support Vector Machine (SVM) are used to demonstrate how the proposed model can be used for making spectrum prediction based on the dataset applied to the network and predicting whether the spectrum is used for voice or data communication. The selected machine learning algorithms are implemented, and their performances are compared against a given data set consisting of transmission power, frequency, and duty cycle. The proposed model will have the capability of selecting the best suitable algorithm for the given data set. Further, the processed information can be used in cognitive radio networks for the effective utilization of channels. From simulations, it is clear that, by using appropriate ML technique, it will most probably increase the spectral prediction with the highest accuracy of 85%.
{"title":"Machine Learning based Spectrum Prediction in Cognitive Radio Networks","authors":"P. Pandian, C. Selvaraj, N. Bhalaji, K. G. Arun Depak, S. Saikrishnan","doi":"10.1109/ICNWC57852.2023.10127512","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127512","url":null,"abstract":"According to the Cisco’s white paper for the year 2018-2023, machine-to-machine (M2M) connections are mentioned as the first fastest growing connections, with a 2.4 fold increase between 2018 and 2023. This will possibly lead to an increase in radio spectrum utilization. The spectrum will be congested due to its limited availability, and interruption of services also occurs in high-traffic scenarios. To overcome this drawback, Cognitive Radio (CR) acts as a promising and intelligent technology that facilitates the unlicensed users (Secondary Users) to efficiently utilize the spectrum allotted to the licensed users (Primary Users) without imposing any interference to them. In order to increase the coexistence of devices without modifying anything in terms of hardware, CR has the feasibility of providing solutions to spectrum prediction for end users. Further, to improve spectrum prediction, machine learning algorithms greatly help the cognitive radio to select the appropriate spectrum based on the requirements of secondary users. In this paper, machine learning algorithms like Random forest classifier, Logistic Regression, KNN classifier, Decision Tree classifier, Artificial Neural Network (ANN), Support Vector Machine (SVM) are used to demonstrate how the proposed model can be used for making spectrum prediction based on the dataset applied to the network and predicting whether the spectrum is used for voice or data communication. The selected machine learning algorithms are implemented, and their performances are compared against a given data set consisting of transmission power, frequency, and duty cycle. The proposed model will have the capability of selecting the best suitable algorithm for the given data set. Further, the processed information can be used in cognitive radio networks for the effective utilization of channels. From simulations, it is clear that, by using appropriate ML technique, it will most probably increase the spectral prediction with the highest accuracy of 85%.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127046062","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 : 2023-04-05DOI: 10.1109/ICNWC57852.2023.10127298
K. Mahendran, J. Dhivya Dharshini., S. Dhivya Dharshini., A. Anitha
Predicting cardiac disease is one of the utmost challenging challenges in the medical industry today. It is hard to pick out various cardiac diseases, because of several relevant health conditions such as Hypertension, Elevated blood pressure, hyperlipidemia, and irregular pulse rate with many factors. Heart disease is one of many illnesses that can be fatal, and it has received a lot of attention in medical studies. The detection of cardiac diseases is a more difficult task, but it can provide an accurate prognosis of the patient’s heart status to help with the purification step. Typically, the patient’s symptoms and warning signs are employed to determine the presence of cardiovascular disease. Cardiovascular disease seriousness is categorized using a variety of techniques,including Logistic Regression, Decision Tree Classifier, Random Forest, Svc, Naive Bayes, and KNN. The handling of cardiac diseaseis more difficult and we handle it with care, not doing may affect theheart or cause premature death. This study examines the performance of several models based on these algorithms and methodologies for the prediction of cardiac disease.
{"title":"Comparative Analysis Of Cardiovascular Disease Using Machine Learning Techniques","authors":"K. Mahendran, J. Dhivya Dharshini., S. Dhivya Dharshini., A. Anitha","doi":"10.1109/ICNWC57852.2023.10127298","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127298","url":null,"abstract":"Predicting cardiac disease is one of the utmost challenging challenges in the medical industry today. It is hard to pick out various cardiac diseases, because of several relevant health conditions such as Hypertension, Elevated blood pressure, hyperlipidemia, and irregular pulse rate with many factors. Heart disease is one of many illnesses that can be fatal, and it has received a lot of attention in medical studies. The detection of cardiac diseases is a more difficult task, but it can provide an accurate prognosis of the patient’s heart status to help with the purification step. Typically, the patient’s symptoms and warning signs are employed to determine the presence of cardiovascular disease. Cardiovascular disease seriousness is categorized using a variety of techniques,including Logistic Regression, Decision Tree Classifier, Random Forest, Svc, Naive Bayes, and KNN. The handling of cardiac diseaseis more difficult and we handle it with care, not doing may affect theheart or cause premature death. This study examines the performance of several models based on these algorithms and methodologies for the prediction of cardiac disease.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133723581","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 : 2023-04-05DOI: 10.1109/ICNWC57852.2023.10127556
Shivam Shekhar, Reeti Jha, K. Annapurani Panaiyappan
The concept of peer learning dates back centuries, and with the increasing technology, it has become more accessible and easier for everyone to interact and learn from others. In such a situation, a common ground that brings everyone together plays a crucial role. Through sharing knowledge and experiences, people can build on the accomplishments of those who came before them and progress in various fields such as science, technology, medicine, and more. Various attempts have been made to make such a common platform, Quora and StackOverflow are two major players in this domain. Query fuel-an interactive community platform that aims to provide a similar solution with some features better than the existing solutions. The platform works on an organizational basis, where a registered user can post a query or any topic of discussion and let others participate. The organization and topic can vary from being a college to a support group where people feel safe discussing their discrete issues. Built on the MERN stack and having a custom ‘Query Searching Algorithm,’ the web application takes in the query as text input and passes through a search engine where we use the Probabilistic Ranking Algorithm and log-Linear Model Ranking Algorithm, which sets criterions for each query and rank them. This minimizes each query’s search time and enables the ‘Search as Type’ feature, which is not present in the existing systems. After thorough testing, we have come up with several metrics which prove that our solution is much more secure compared to the existing ones. Once we test the scalability with data in millions, we will be ready to ship this to the commercial market.
{"title":"Query Fuel - In-house Query Solver","authors":"Shivam Shekhar, Reeti Jha, K. Annapurani Panaiyappan","doi":"10.1109/ICNWC57852.2023.10127556","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127556","url":null,"abstract":"The concept of peer learning dates back centuries, and with the increasing technology, it has become more accessible and easier for everyone to interact and learn from others. In such a situation, a common ground that brings everyone together plays a crucial role. Through sharing knowledge and experiences, people can build on the accomplishments of those who came before them and progress in various fields such as science, technology, medicine, and more. Various attempts have been made to make such a common platform, Quora and StackOverflow are two major players in this domain. Query fuel-an interactive community platform that aims to provide a similar solution with some features better than the existing solutions. The platform works on an organizational basis, where a registered user can post a query or any topic of discussion and let others participate. The organization and topic can vary from being a college to a support group where people feel safe discussing their discrete issues. Built on the MERN stack and having a custom ‘Query Searching Algorithm,’ the web application takes in the query as text input and passes through a search engine where we use the Probabilistic Ranking Algorithm and log-Linear Model Ranking Algorithm, which sets criterions for each query and rank them. This minimizes each query’s search time and enables the ‘Search as Type’ feature, which is not present in the existing systems. After thorough testing, we have come up with several metrics which prove that our solution is much more secure compared to the existing ones. Once we test the scalability with data in millions, we will be ready to ship this to the commercial market.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":"43 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131191157","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 : 2023-04-05DOI: 10.1109/ICNWC57852.2023.10127487
T.Ganesh Kumar, Dhanya Sri Aravapalli, R. Jeya
The ability for users to collaborate, exchange ideas, and provide answers makes forums crucial in the process of knowledge generation. Online forums are a common teaching tool for undergraduate students today. They expand the learning environment beyond the classroom by providing opportunities for asynchronous peer collaboration. The results of students online posting behaviors have been linked to learning outcomes, according to earlier study. In the discussion forum, pupils might enquire about the subject matter of the course, their homework, matters pertaining to the campus, etc. or answer questions from other pupils. We may link all ranks of university associates for various types of demands by creating a conversation platform for a specific university. It will act as a focal point for all students, graduates, teachers, mentors, professional tutors, etc. to interact, ask questions, and receive responses. Additionally, it will be run by the university management, who will have complete control over the forum, preventing any chance of mistakes or incorrect information.
{"title":"Online Discussion Forum for University","authors":"T.Ganesh Kumar, Dhanya Sri Aravapalli, R. Jeya","doi":"10.1109/ICNWC57852.2023.10127487","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127487","url":null,"abstract":"The ability for users to collaborate, exchange ideas, and provide answers makes forums crucial in the process of knowledge generation. Online forums are a common teaching tool for undergraduate students today. They expand the learning environment beyond the classroom by providing opportunities for asynchronous peer collaboration. The results of students online posting behaviors have been linked to learning outcomes, according to earlier study. In the discussion forum, pupils might enquire about the subject matter of the course, their homework, matters pertaining to the campus, etc. or answer questions from other pupils. We may link all ranks of university associates for various types of demands by creating a conversation platform for a specific university. It will act as a focal point for all students, graduates, teachers, mentors, professional tutors, etc. to interact, ask questions, and receive responses. Additionally, it will be run by the university management, who will have complete control over the forum, preventing any chance of mistakes or incorrect information.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129354285","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 : 2023-04-05DOI: 10.1109/ICNWC57852.2023.10127559
A. L. Siridhara, K. Manikanta, Dugesh Yadav, Peetha Varun, Jahnavi Saragada
There is an escalate interest for the great quality food because of the expanding populace. In rural industry, the recognition of imperfections in fruits and vegetables is an imperative assignment, concerning the extraordinary interest for fruits and vegetables on the lookout. The customary manual assessment of fruits and vegetables grown from the ground is tedious process and it requires more human force. There might be some human mistakes. To reduce the human blunders and to accelerate the process a few philosophies for automation is presented. The various blemishes in the fruit’s and vegetable’s skin is more useful to investigate the imperfections in them.In this project, the defects in fruits and vegetables are detected through software simulation using some of the image processing techniques like K means clustering algorithm and Otsu’s thresholding method on the fruits and vegetable images, using MATLAB software. K-means clustering technique is an iterative process used to divide an image into k clusters. Pixels are clustered based on color intensity values and the images are generated to identify the defected part. The Otsu’s method is a global thresholding technique which uses the histogram of the image for threshold searching process. Simply we can say that this algorithm returns a single intensity threshold value which separates the pixels in the image into two classes, as foreground and background.
{"title":"Defect Detection in Fruits and Vegetables using K Means Segmentation and Otsu’s Thresholding","authors":"A. L. Siridhara, K. Manikanta, Dugesh Yadav, Peetha Varun, Jahnavi Saragada","doi":"10.1109/ICNWC57852.2023.10127559","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127559","url":null,"abstract":"There is an escalate interest for the great quality food because of the expanding populace. In rural industry, the recognition of imperfections in fruits and vegetables is an imperative assignment, concerning the extraordinary interest for fruits and vegetables on the lookout. The customary manual assessment of fruits and vegetables grown from the ground is tedious process and it requires more human force. There might be some human mistakes. To reduce the human blunders and to accelerate the process a few philosophies for automation is presented. The various blemishes in the fruit’s and vegetable’s skin is more useful to investigate the imperfections in them.In this project, the defects in fruits and vegetables are detected through software simulation using some of the image processing techniques like K means clustering algorithm and Otsu’s thresholding method on the fruits and vegetable images, using MATLAB software. K-means clustering technique is an iterative process used to divide an image into k clusters. Pixels are clustered based on color intensity values and the images are generated to identify the defected part. The Otsu’s method is a global thresholding technique which uses the histogram of the image for threshold searching process. Simply we can say that this algorithm returns a single intensity threshold value which separates the pixels in the image into two classes, as foreground and background.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130931172","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 : 2023-04-05DOI: 10.1109/ICNWC57852.2023.10127343
S. Swathi, M. Rajalakshmi, Vijayalakshmi Senniappan
Deep learning has been performing reasonably well in computer vision tasks that call for a high volume of photos, although gathering images is often expensive and challenging. Different picture augmentation techniques have been put forth as practical and efficient solutions to this problem Understanding current algorithms is critical when developing new processes or determining the best approaches for a certain task. With deep learning, some of the data pre-processing that is typically required for machine learning is avoided. Unstructured text and visual data can be handled by these algorithms, which can also automate feature extraction and lessen the need for human experts. With a brand-new taxonomy of usable data, we undertake a complete survey of picture augmentation for deep learning in this work. We discuss the difficulties in computer vision tasks and vicinity distribution to give you a fundamental understanding of why we want picture augmentation. Based on the study, we think that our survey provides a clearer knowledge that may be used to select the best techniques or create original algorithms for real-world uses.
{"title":"Deep Learning: A Detailed Analysis Of Various Image Augmentation Techniques","authors":"S. Swathi, M. Rajalakshmi, Vijayalakshmi Senniappan","doi":"10.1109/ICNWC57852.2023.10127343","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127343","url":null,"abstract":"Deep learning has been performing reasonably well in computer vision tasks that call for a high volume of photos, although gathering images is often expensive and challenging. Different picture augmentation techniques have been put forth as practical and efficient solutions to this problem Understanding current algorithms is critical when developing new processes or determining the best approaches for a certain task. With deep learning, some of the data pre-processing that is typically required for machine learning is avoided. Unstructured text and visual data can be handled by these algorithms, which can also automate feature extraction and lessen the need for human experts. With a brand-new taxonomy of usable data, we undertake a complete survey of picture augmentation for deep learning in this work. We discuss the difficulties in computer vision tasks and vicinity distribution to give you a fundamental understanding of why we want picture augmentation. Based on the study, we think that our survey provides a clearer knowledge that may be used to select the best techniques or create original algorithms for real-world uses.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116353930","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 : 2023-04-05DOI: 10.1109/ICNWC57852.2023.10127494
P. Brindha, R. Rajalaxmi
Reproduction is the process of giving birth to a child. A child may bring all the happiness inside a family. Now a days due to change in the life style and the food habits, the couples may not have a successful reproduction. Even though there are many reasons for infertility, PCO in female is one of the major cause. PCOS can be treated and there are many procedures in the medical field which should be followed to get reproduction. Among the medical procedure US scanning is done to identify the presence of PCO. Compared to other medical tests US scans are cost effective and at the same time presence of PCOS can be easily identified. Many machine learning algorithms are applied on segmentation and classification of these images. In the proposed work, a self defined CNN model is created and the performance of the model is analyzed with the eight other models. VGG16, RESNET, Transfer Learning models having ANN and SVM as classifiers for VGG16,RESNET and self defined models are taken here. Accuracy of self defined model with SVM is comparatively same as VGG16 and RESNET50 with SVM but still the F1 score of self defined is low when compared VGG16 with SVM.
{"title":"Comparative Study of CNN and Transfer Learning Techniques in the classification of PCO Ultra Sound Images","authors":"P. Brindha, R. Rajalaxmi","doi":"10.1109/ICNWC57852.2023.10127494","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127494","url":null,"abstract":"Reproduction is the process of giving birth to a child. A child may bring all the happiness inside a family. Now a days due to change in the life style and the food habits, the couples may not have a successful reproduction. Even though there are many reasons for infertility, PCO in female is one of the major cause. PCOS can be treated and there are many procedures in the medical field which should be followed to get reproduction. Among the medical procedure US scanning is done to identify the presence of PCO. Compared to other medical tests US scans are cost effective and at the same time presence of PCOS can be easily identified. Many machine learning algorithms are applied on segmentation and classification of these images. In the proposed work, a self defined CNN model is created and the performance of the model is analyzed with the eight other models. VGG16, RESNET, Transfer Learning models having ANN and SVM as classifiers for VGG16,RESNET and self defined models are taken here. Accuracy of self defined model with SVM is comparatively same as VGG16 and RESNET50 with SVM but still the F1 score of self defined is low when compared VGG16 with SVM.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122296191","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 : 2023-04-05DOI: 10.1109/ICNWC57852.2023.10127328
Swarna Sethu, S. Nathan, Dongyi Wang, D. Jayanthi, Hanseok Seo, Victoria J.Hogan
Recently, the efforts to use machine vision and artificial intelligence to evaluate the characteristics of food products has increased significantly. This is largely because, these technologies put up considerable advances in areas where the humans fail. We develop a sensory panel to study the effects of lighting conditions viz., light temperature and lighting power on the freshness of a food product. Panelists evaluated the product in terms of purchase intent (line scale from 0 to 100), overall liking (line scale from 0 to 100), and freshness (line scale from 0 to 100). Later, using machine learning models, predictive analytics is conducted to analyze the correlation among the light conditions and panliests’ gradings.
{"title":"Sensory predictive analysis of freshness of food products under different lighting conditions","authors":"Swarna Sethu, S. Nathan, Dongyi Wang, D. Jayanthi, Hanseok Seo, Victoria J.Hogan","doi":"10.1109/ICNWC57852.2023.10127328","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127328","url":null,"abstract":"Recently, the efforts to use machine vision and artificial intelligence to evaluate the characteristics of food products has increased significantly. This is largely because, these technologies put up considerable advances in areas where the humans fail. We develop a sensory panel to study the effects of lighting conditions viz., light temperature and lighting power on the freshness of a food product. Panelists evaluated the product in terms of purchase intent (line scale from 0 to 100), overall liking (line scale from 0 to 100), and freshness (line scale from 0 to 100). Later, using machine learning models, predictive analytics is conducted to analyze the correlation among the light conditions and panliests’ gradings.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":"2013 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123930266","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：