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":null,"pages":null},"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}
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":null,"pages":null},"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/ICNWC57852.2023.10127269
G. Pradeep, T. D. V. Rayen, A. Pushpalatha, P. K. Rani
Crop production forecasting is a huge challenge nowadays, resulting in inaccurate results such as food shortages, economic instability, inefficient resource allocation, environmental impact, and lower farmer profitability. Our proposed machine-learning algorithm forecasting yield can help address these difficulties and enhance agricultural outcomes. Crop yield prediction is used to estimate the potential harvest of crops, providing valuable information to farmers, policymakers, and agribusinesses for planning, resource management, and making informed crop production decisions. It helps to improve food security, reduce food waste, and increase the efficiency of food production. Gradient Boosting Agricultural Yield Prediction is a machine learning approach that employs decision trees and gradient descent optimization to create accurate crop yield predictions. This approach and strategy are useful in predicting crop yields. They can assist farmers and agricultural organizations in making better-educated planting, harvesting, and resource allocation decisions. The results of crop yield prediction based on gradient boosting with an accuracy rate of 87.2%, precision of0.84, recall ofO.90, and F1-Score of0.87 indicate that the model is making accurate predictions about crop yields with a good balance of precision and recall. Our work suggests that the model performs efficiently and makes accurate predictions for crop yields. It increases crop production prediction, which improves decision-making, increases efficiency, effectively allocates resources, supports planning, and reduces agriculture’s environmental impact. It has a tremendous impact on the agriculture sector because it promotes sustainability, reduces waste, and improves overall performance.
{"title":"Effective Crop Yield Prediction Using Gradient Boosting To Improve Agricultural Outcomes","authors":"G. Pradeep, T. D. V. Rayen, A. Pushpalatha, P. K. Rani","doi":"10.1109/ICNWC57852.2023.10127269","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127269","url":null,"abstract":"Crop production forecasting is a huge challenge nowadays, resulting in inaccurate results such as food shortages, economic instability, inefficient resource allocation, environmental impact, and lower farmer profitability. Our proposed machine-learning algorithm forecasting yield can help address these difficulties and enhance agricultural outcomes. Crop yield prediction is used to estimate the potential harvest of crops, providing valuable information to farmers, policymakers, and agribusinesses for planning, resource management, and making informed crop production decisions. It helps to improve food security, reduce food waste, and increase the efficiency of food production. Gradient Boosting Agricultural Yield Prediction is a machine learning approach that employs decision trees and gradient descent optimization to create accurate crop yield predictions. This approach and strategy are useful in predicting crop yields. They can assist farmers and agricultural organizations in making better-educated planting, harvesting, and resource allocation decisions. The results of crop yield prediction based on gradient boosting with an accuracy rate of 87.2%, precision of0.84, recall ofO.90, and F1-Score of0.87 indicate that the model is making accurate predictions about crop yields with a good balance of precision and recall. Our work suggests that the model performs efficiently and makes accurate predictions for crop yields. It increases crop production prediction, which improves decision-making, increases efficiency, effectively allocates resources, supports planning, and reduces agriculture’s environmental impact. It has a tremendous impact on the agriculture sector because it promotes sustainability, reduces waste, and improves overall performance.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124839526","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/ICNWC57852.2023.10127467
Ranjith, V. M, Berin Shalu S
In India, the sewage system is the most serious issue. Since the drainage system isn•t properly maintained, drainage water periodically mixes with drinking water, putting people•s health in peril. We suggest the use of a smart drainage monitoring system to solve this issue. The proposed device would keep an eye on water levels in the sewage system as well as the movement of water and potentially harmful gasses. The value set will be stored in the cloud and later reviewed. The Blynk server will send an SMS with the drainage status to a point close to the corporate office. The officials of the company will then take the necessary steps.
{"title":"System for Monitoring and Controlling Drainage using Internet of Things","authors":"Ranjith, V. M, Berin Shalu S","doi":"10.1109/ICNWC57852.2023.10127467","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127467","url":null,"abstract":"In India, the sewage system is the most serious issue. Since the drainage system isn•t properly maintained, drainage water periodically mixes with drinking water, putting people•s health in peril. We suggest the use of a smart drainage monitoring system to solve this issue. The proposed device would keep an eye on water levels in the sewage system as well as the movement of water and potentially harmful gasses. The value set will be stored in the cloud and later reviewed. The Blynk server will send an SMS with the drainage status to a point close to the corporate office. The officials of the company will then take the necessary steps.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128692235","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/ICNWC57852.2023.10127264
Venkata Sai P Bhamidipati, Ishi Saxena, D. Saisanthiya, Mervin Retnadhas
Robust Intelligent Posture Estimation is an important aspect of an AI Gym Trainer that can help fitness enthusiasts improve their workout technique and prevent injuries. This research presents an approach to achieve accurate posture estimation using Mediapipe and OpenCV. Mediapipe is a machine learning framework that provides pre-trained models for human posture estimation, while OpenCV is a popular computer vision library that offers a range of functions for image and video processing. The proposed solution integrates the strengths of both tools to develop a robust posture estimation system. The system first captures the user’s video feed and passes it through MediaPipe to detect the human body landmarks, then, OpenCV is used to calculate the angles between the detected landmarks in order to analyze the posture. The system provides real-time feedback to the user on their posture and suggests reparative measures. The use case that has been used for this research was repetitions for bicep curls. The proposed system can be tested on various exercises, such as squats, push-ups, and lunges. It can accurately estimate the posture of the user in different lighting conditions and is robust to occlusions and background clutter. The system can be deployed as an AI Gym Trainer and can help fitness enthusiasts improve their form and technique while reducing the risk of injury.
{"title":"Robust Intelligent Posture Estimation for an AI Gym Trainer using Mediapipe and OpenCV","authors":"Venkata Sai P Bhamidipati, Ishi Saxena, D. Saisanthiya, Mervin Retnadhas","doi":"10.1109/ICNWC57852.2023.10127264","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127264","url":null,"abstract":"Robust Intelligent Posture Estimation is an important aspect of an AI Gym Trainer that can help fitness enthusiasts improve their workout technique and prevent injuries. This research presents an approach to achieve accurate posture estimation using Mediapipe and OpenCV. Mediapipe is a machine learning framework that provides pre-trained models for human posture estimation, while OpenCV is a popular computer vision library that offers a range of functions for image and video processing. The proposed solution integrates the strengths of both tools to develop a robust posture estimation system. The system first captures the user’s video feed and passes it through MediaPipe to detect the human body landmarks, then, OpenCV is used to calculate the angles between the detected landmarks in order to analyze the posture. The system provides real-time feedback to the user on their posture and suggests reparative measures. The use case that has been used for this research was repetitions for bicep curls. The proposed system can be tested on various exercises, such as squats, push-ups, and lunges. It can accurately estimate the posture of the user in different lighting conditions and is robust to occlusions and background clutter. The system can be deployed as an AI Gym Trainer and can help fitness enthusiasts improve their form and technique while reducing the risk of injury.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125369279","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}
Augmented Reality (AR) technology has the potential to revolutionize education by providing a new way for students to visualize and interact with complex concepts. In this project, a system is proposed to develop an AR smartphone application that allows students to visualize objects and scenarios that the teacher is teaching in real-time. The application will employ the smartphone’s camera and sensors to materialize a user-friendly and easy-to-use dynamic AR experience, with the teacher allowing the students to simply access their smartphone to project 3D models of objects or scenarios onto a flat surface. Students will be able to view these models from any angle and interact with them in a variety of ways, such as by rotating them or zooming in on specific details. In addition to enhancing student’s understanding of the material being taught, the AR application will also provide an engaging and immersive learning experience. The distinguishing factor is the storage of the 3D assets on the cloud that will equip the educator with the option of pre-planning and customizing their entire lesson as well as storing any number of models. This can help to increase student engagement and motivation, leading to better retention of the material being taught. Overall, the proposed AR smartphone application has the potential to significantly improve the way students learn and understand complex concepts, making education more effective and enjoyable for all.
{"title":"Augmented Reality For Education Based On Markerless Dynamic Rendering","authors":"Soumik Rakshit, Aarthi Iyer, Sunil Retmin Raj.C, Shiloah Elizabeth.D, Aditya Vaidyanathan","doi":"10.1109/ICNWC57852.2023.10127337","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127337","url":null,"abstract":"Augmented Reality (AR) technology has the potential to revolutionize education by providing a new way for students to visualize and interact with complex concepts. In this project, a system is proposed to develop an AR smartphone application that allows students to visualize objects and scenarios that the teacher is teaching in real-time. The application will employ the smartphone’s camera and sensors to materialize a user-friendly and easy-to-use dynamic AR experience, with the teacher allowing the students to simply access their smartphone to project 3D models of objects or scenarios onto a flat surface. Students will be able to view these models from any angle and interact with them in a variety of ways, such as by rotating them or zooming in on specific details. In addition to enhancing student’s understanding of the material being taught, the AR application will also provide an engaging and immersive learning experience. The distinguishing factor is the storage of the 3D assets on the cloud that will equip the educator with the option of pre-planning and customizing their entire lesson as well as storing any number of models. This can help to increase student engagement and motivation, leading to better retention of the material being taught. Overall, the proposed AR smartphone application has the potential to significantly improve the way students learn and understand complex concepts, making education more effective and enjoyable for all.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125841240","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/ICNWC57852.2023.10127403
Jeelakarra Teja, K. Thilak, K. P. Reddy
The introduction of invasive species, often referred to as foreign species, to the native species occurs frequently through a variety of channels, including the air, birds, and insects. This might harm the environment in the area. Invasive plants can have a negative impact on natural ecosystems by reducing native biodiversity, altering species composition, removing habitat from native and dependent species, changing biogeochemical cycling, and changing disturbance regimes. There are a few ideas that have been made in earlier studies to prevent this, but in this study, we approach to solving this issue by combining artificial intelligence with an anomaly detection technique and image processing. We compile sample photos of each species of flower in the ecosystem and create a dataset of all local flower species. In order to create a dataset of all native flower species, we first collect sample pictures of each flower species in the environment. Analyse the image dataset quantitatively and programme a machine learning model to identify the species. In order for a qualified botanist to examine the plant and decide whether it is hazardous to the park’s ecology, it is important to identify any outlier or anomalous flower species that are found. Finding flowers in pictures is one of CNNs’ most well-known applications. For instance, a producer of sunglasses employed CNNs to recognise floral images in advertising photos. The training set in this instance included thousands of photographs of actual flowers. The photos were then appropriately recognised as flowers by the network. This is a great example of how effective CNNs can be when used properly. The user so they can look into the image’s origin.
{"title":"Detection And Alert System Of Invasive Flower Species Using Cnn","authors":"Jeelakarra Teja, K. Thilak, K. P. Reddy","doi":"10.1109/ICNWC57852.2023.10127403","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127403","url":null,"abstract":"The introduction of invasive species, often referred to as foreign species, to the native species occurs frequently through a variety of channels, including the air, birds, and insects. This might harm the environment in the area. Invasive plants can have a negative impact on natural ecosystems by reducing native biodiversity, altering species composition, removing habitat from native and dependent species, changing biogeochemical cycling, and changing disturbance regimes. There are a few ideas that have been made in earlier studies to prevent this, but in this study, we approach to solving this issue by combining artificial intelligence with an anomaly detection technique and image processing. We compile sample photos of each species of flower in the ecosystem and create a dataset of all local flower species. In order to create a dataset of all native flower species, we first collect sample pictures of each flower species in the environment. Analyse the image dataset quantitatively and programme a machine learning model to identify the species. In order for a qualified botanist to examine the plant and decide whether it is hazardous to the park’s ecology, it is important to identify any outlier or anomalous flower species that are found. Finding flowers in pictures is one of CNNs’ most well-known applications. For instance, a producer of sunglasses employed CNNs to recognise floral images in advertising photos. The training set in this instance included thousands of photographs of actual flowers. The photos were then appropriately recognised as flowers by the network. This is a great example of how effective CNNs can be when used properly. The user so they can look into the image’s origin.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126108940","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/ICNWC57852.2023.10127351
Snehal Sameer Patil, Vaishnavi Moorthy
Artificial Intelligence in the healthcare sector is becoming increasingly essential to extract huge texts for decision-making. Extraction of clinical data is a fundamental task in Medical Natural language processing. This process is still challenging through deep learning due to critical medical data, lack of interpretability, and limited availability. Text extraction from Electronic Healthcare records is crucial for improving patient care and understanding clinical decision-making. It also supports analysing the patients’ feedback and physician notes to identify areas for improvement in patients’ satisfaction and care quality. This helps in drug discovery and development through clinical data patterns. The proposed research focuses on implementing Natural language processing methods for data processing like classification and prediction, Word Sense Disambiguation, Segmentation, and word Embedding. These methods can process vast amounts of medical text data for decision support, research, and drug discovery. It can increase the possibility of identifying the patients who may at risk for certain conditions and diseases related to cancer and comparing it with their medical history. The chief aim is to provide improvised data analyses that could further improve their treatment.
{"title":"Extraction of Unstructured Electronic Healthcare Records using Natural Language Processing","authors":"Snehal Sameer Patil, Vaishnavi Moorthy","doi":"10.1109/ICNWC57852.2023.10127351","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127351","url":null,"abstract":"Artificial Intelligence in the healthcare sector is becoming increasingly essential to extract huge texts for decision-making. Extraction of clinical data is a fundamental task in Medical Natural language processing. This process is still challenging through deep learning due to critical medical data, lack of interpretability, and limited availability. Text extraction from Electronic Healthcare records is crucial for improving patient care and understanding clinical decision-making. It also supports analysing the patients’ feedback and physician notes to identify areas for improvement in patients’ satisfaction and care quality. This helps in drug discovery and development through clinical data patterns. The proposed research focuses on implementing Natural language processing methods for data processing like classification and prediction, Word Sense Disambiguation, Segmentation, and word Embedding. These methods can process vast amounts of medical text data for decision support, research, and drug discovery. It can increase the possibility of identifying the patients who may at risk for certain conditions and diseases related to cancer and comparing it with their medical history. The chief aim is to provide improvised data analyses that could further improve their treatment.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130828653","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":null,"pages":null},"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/ICNWC57852.2023.10127447
Rishit Nagar, Nitish Chaturvedi, J. Prabakaran
Every well-known business has scammers who sell counterfeit goods at reduced prices. Due to a lack of transparency, supply chain management has frequently encountered issues such as service redundancy, poor departmental collaboration, and a compromise of standards. Counterfeiters in the market generate major challenges for legitimate businesses. Still, a significant number of individuals are unaware of the greatest extent of the harm that these products have on brands. As a result, it is essential to have a system that allows the end user to verify all details about the products purchased for the customer to determine the product’s authenticity. Combining these features with blockchain-based technology can create a coherent, effective counterfeit-reduction strategy.
{"title":"Product Authentication System using Blockchain*","authors":"Rishit Nagar, Nitish Chaturvedi, J. Prabakaran","doi":"10.1109/ICNWC57852.2023.10127447","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127447","url":null,"abstract":"Every well-known business has scammers who sell counterfeit goods at reduced prices. Due to a lack of transparency, supply chain management has frequently encountered issues such as service redundancy, poor departmental collaboration, and a compromise of standards. Counterfeiters in the market generate major challenges for legitimate businesses. Still, a significant number of individuals are unaware of the greatest extent of the harm that these products have on brands. As a result, it is essential to have a system that allows the end user to verify all details about the products purchased for the customer to determine the product’s authenticity. Combining these features with blockchain-based technology can create a coherent, effective counterfeit-reduction strategy.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125682045","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：