Pub Date : 2022-07-08DOI: 10.1109/CONECCT55679.2022.9865785
Arvind Cs, A. K, Keerthan Hs, Mohammed Farhan, Asha Kn, S. Patil
In recent years, fruit sellers, consumers, and mid-lower income farmers have faced difficulty grading the fruits as it is laborious and needs massive investment. Artificial intelligence and vision sensors on mobile devices have led to non-invasive ways to grade the fruits. Hence, using deep learning, fruit grading applications with recommendation features were developed to handle multiple fruits. YoloV3 will detect the fruit type, followed by sub-categories classification using inceptionNet V3 and MobileNet V2 classifiers. Finally, Neural network classifier will predict the fruit grade based on handcrafted features. Deep neural network models were trained using two different data sets (i) fruit360 and (ii) our own (custom fruit dataset) in a transfer learning approach. The proposed application has client interface was developed using the angular framework, which communicates with the server using flask microservices. Where end-users can upload fruit images via mobile phones or web browsers to obtain (i) Fruit Sub Categories, and it grades with user recommendations such as (i) finding the nearest fruit shop (ii) Present retail market price of the fruit (iii) Recipe recommendation. The developed mobile application will remove bias and improve the perception of non-invasive fruit grading.
{"title":"Non-Invasive Multistage Fruit Grading Application with User Recommendation system","authors":"Arvind Cs, A. K, Keerthan Hs, Mohammed Farhan, Asha Kn, S. Patil","doi":"10.1109/CONECCT55679.2022.9865785","DOIUrl":"https://doi.org/10.1109/CONECCT55679.2022.9865785","url":null,"abstract":"In recent years, fruit sellers, consumers, and mid-lower income farmers have faced difficulty grading the fruits as it is laborious and needs massive investment. Artificial intelligence and vision sensors on mobile devices have led to non-invasive ways to grade the fruits. Hence, using deep learning, fruit grading applications with recommendation features were developed to handle multiple fruits. YoloV3 will detect the fruit type, followed by sub-categories classification using inceptionNet V3 and MobileNet V2 classifiers. Finally, Neural network classifier will predict the fruit grade based on handcrafted features. Deep neural network models were trained using two different data sets (i) fruit360 and (ii) our own (custom fruit dataset) in a transfer learning approach. The proposed application has client interface was developed using the angular framework, which communicates with the server using flask microservices. Where end-users can upload fruit images via mobile phones or web browsers to obtain (i) Fruit Sub Categories, and it grades with user recommendations such as (i) finding the nearest fruit shop (ii) Present retail market price of the fruit (iii) Recipe recommendation. The developed mobile application will remove bias and improve the perception of non-invasive fruit grading.","PeriodicalId":380005,"journal":{"name":"2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128859365","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-08DOI: 10.1109/CONECCT55679.2022.9865730
Nibras Ahmed Nizar, Krishna Raj P. M., V. Bp
This paper explores unsupervised machine learning methods for anomaly detection in telemetry datasets by reviewing and identifying best-automated detection algorithms and methodologies for anomaly detection. There have been various research to identify an effective model to detect anomalies for telemetry data to reduce response time so as to mitigate risks and avoid failures. Traditional algorithms for anomaly detection have trouble identifying attacks throughout the data analysis task. Machine learning approaches, such as supervised, and unsupervised methods for grouping, classification, and regression, appear to be very useful tools for analyzing anomalous behavior. These techniques can identify any anomalous behavior in telemetry data and allow room for research into the real-time analysis. The principal aim of this research is to answer the question "How can we improve on the current machine learning models for anomaly detection in telemetry datasets?". The dataset consists of five Time-Series datasets and is representative of the data with which we are concerned. Five algorithms are applied to these datasets and examined in depth. Then, three unsupervised anomaly definitions are examined.
{"title":"Anomaly Detection In Telemetry Data Using Ensemble Machine Learning","authors":"Nibras Ahmed Nizar, Krishna Raj P. M., V. Bp","doi":"10.1109/CONECCT55679.2022.9865730","DOIUrl":"https://doi.org/10.1109/CONECCT55679.2022.9865730","url":null,"abstract":"This paper explores unsupervised machine learning methods for anomaly detection in telemetry datasets by reviewing and identifying best-automated detection algorithms and methodologies for anomaly detection. There have been various research to identify an effective model to detect anomalies for telemetry data to reduce response time so as to mitigate risks and avoid failures. Traditional algorithms for anomaly detection have trouble identifying attacks throughout the data analysis task. Machine learning approaches, such as supervised, and unsupervised methods for grouping, classification, and regression, appear to be very useful tools for analyzing anomalous behavior. These techniques can identify any anomalous behavior in telemetry data and allow room for research into the real-time analysis. The principal aim of this research is to answer the question \"How can we improve on the current machine learning models for anomaly detection in telemetry datasets?\". The dataset consists of five Time-Series datasets and is representative of the data with which we are concerned. Five algorithms are applied to these datasets and examined in depth. Then, three unsupervised anomaly definitions are examined.","PeriodicalId":380005,"journal":{"name":"2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132774545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-08DOI: 10.1109/CONECCT55679.2022.9865748
Yuganshu Wadhwa, A. Rani
During pandemics, Intensive care units (ICUs) play a major role in providing necessary medical treatment to the patients and stabilizing dire situations. Mechanical ventilation systems are an integral part of ICUs in every medical facility. A Mechanical Ventilation system must provide accurate and fast tracking of a pre-set pressure profile. Therefore various controller designs are tested and analyzed in the presented paper for a blower-hose-patient mechanical ventilation system. The basic framework for the control problem, and necessary mathematical and simulation background is presented along with a comparative analysis of the designed control schemes. An attempt is also made to find an optimal controller design providing the desired system output with minimal trade-offs.
{"title":"Controller Design For Respiratory Systems Used During The Covid-19 Pandemic","authors":"Yuganshu Wadhwa, A. Rani","doi":"10.1109/CONECCT55679.2022.9865748","DOIUrl":"https://doi.org/10.1109/CONECCT55679.2022.9865748","url":null,"abstract":"During pandemics, Intensive care units (ICUs) play a major role in providing necessary medical treatment to the patients and stabilizing dire situations. Mechanical ventilation systems are an integral part of ICUs in every medical facility. A Mechanical Ventilation system must provide accurate and fast tracking of a pre-set pressure profile. Therefore various controller designs are tested and analyzed in the presented paper for a blower-hose-patient mechanical ventilation system. The basic framework for the control problem, and necessary mathematical and simulation background is presented along with a comparative analysis of the designed control schemes. An attempt is also made to find an optimal controller design providing the desired system output with minimal trade-offs.","PeriodicalId":380005,"journal":{"name":"2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130984249","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}
Image Pyramids i.e. set of down-sampled images from high-resolution input is used in computer vision processing pipe to account for unknown distance of objects from Camera. The image pyramid can be set of Octave (down-sampling by 2) and/or Generic scaling (arbitrary downscaling ratio). The prior literature addresses generating all down-scaled images using either input or previous output as an overall scaling architecture and consists of "N" set of independent scalers, which are separately tuned to Octave and generic scaling. The disadvantage of the above approach is higher silicon area and DRAM Bandwidth proportional to number of independent scalars. The paper proposes a novel solution on top of traditional poly-phase filtering which consists of new concepts e.g. Re-scale from previous octave scale architecture, Multi-thread processing with flexible mapping of shared Scalers, Unconventional processing order for 2D scaling without line buffers, shared coefficients and flexible Region of Interest (ROI). The proposed solution is implemented as HW IP with 0.2 mm2 in 16nm process node with 720 Mpix/sec throughput, which is 3.5X lower in the area and 40% lower DRAM bandwidth compared to prior literature.
{"title":"High Throughput VLSI Architecture for Image Pyramid Generation in Computer Vision","authors":"Mihir Mody, Rajshekar Allu, Niraj Nandan, Hetual Sanghavi, Ankur Baranwal","doi":"10.1109/CONECCT55679.2022.9865803","DOIUrl":"https://doi.org/10.1109/CONECCT55679.2022.9865803","url":null,"abstract":"Image Pyramids i.e. set of down-sampled images from high-resolution input is used in computer vision processing pipe to account for unknown distance of objects from Camera. The image pyramid can be set of Octave (down-sampling by 2) and/or Generic scaling (arbitrary downscaling ratio). The prior literature addresses generating all down-scaled images using either input or previous output as an overall scaling architecture and consists of \"N\" set of independent scalers, which are separately tuned to Octave and generic scaling. The disadvantage of the above approach is higher silicon area and DRAM Bandwidth proportional to number of independent scalars. The paper proposes a novel solution on top of traditional poly-phase filtering which consists of new concepts e.g. Re-scale from previous octave scale architecture, Multi-thread processing with flexible mapping of shared Scalers, Unconventional processing order for 2D scaling without line buffers, shared coefficients and flexible Region of Interest (ROI). The proposed solution is implemented as HW IP with 0.2 mm2 in 16nm process node with 720 Mpix/sec throughput, which is 3.5X lower in the area and 40% lower DRAM bandwidth compared to prior literature.","PeriodicalId":380005,"journal":{"name":"2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115182669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-08DOI: 10.1109/CONECCT55679.2022.9865726
Maneesh Kumar, K. Shanmugam, Kaustove Pradeep, Matteo Filippone
Energy storage systems (ESS) provide numerous benefits like smart energy consumption, better grid management, cost-cutting, resilience, resource-saving, grid stability, etc. In this paper, various ESS techniques are compared in terms of the parameters such as capacity, cost of energy, energy density, round trip efficiency, response time, lifetime, etc. Among all the ESS, Li-ion Battery energy storage system (BESS) is found to be optimum for power applications due to research & technical advancements in power electronics & battery technologies. With a wide range of power and storage capacity, BESSs are designed for small-sized household applications to large scale systems used for utilities, industrial, commercial, defense, hospital applications. In this paper, a secondary distributed control technique is developed for BESS farms utility grid BESS plant along with a centralized plant controller at the PCC level. While designing these control algorithms care is taken to make the plant compliant with all grid codes, provide additional support to grid during contingencies, and also able to be operative in both grid connected and standalone modes. The BESS farm is modelled with three BESS units connected to the grid using IEC61131-PLC programming language, the operation is validated & analyzed under different operating conditions while considering the grid transitions, as well as the grid management during contingencies by providing voltage frequency support, reactive power control at PCC by controlling the power factor as per the IEEE1547-2018 reactive power control methodologies.
{"title":"Grid integration and application of Battery Energy Storage Systems","authors":"Maneesh Kumar, K. Shanmugam, Kaustove Pradeep, Matteo Filippone","doi":"10.1109/CONECCT55679.2022.9865726","DOIUrl":"https://doi.org/10.1109/CONECCT55679.2022.9865726","url":null,"abstract":"Energy storage systems (ESS) provide numerous benefits like smart energy consumption, better grid management, cost-cutting, resilience, resource-saving, grid stability, etc. In this paper, various ESS techniques are compared in terms of the parameters such as capacity, cost of energy, energy density, round trip efficiency, response time, lifetime, etc. Among all the ESS, Li-ion Battery energy storage system (BESS) is found to be optimum for power applications due to research & technical advancements in power electronics & battery technologies. With a wide range of power and storage capacity, BESSs are designed for small-sized household applications to large scale systems used for utilities, industrial, commercial, defense, hospital applications. In this paper, a secondary distributed control technique is developed for BESS farms utility grid BESS plant along with a centralized plant controller at the PCC level. While designing these control algorithms care is taken to make the plant compliant with all grid codes, provide additional support to grid during contingencies, and also able to be operative in both grid connected and standalone modes. The BESS farm is modelled with three BESS units connected to the grid using IEC61131-PLC programming language, the operation is validated & analyzed under different operating conditions while considering the grid transitions, as well as the grid management during contingencies by providing voltage frequency support, reactive power control at PCC by controlling the power factor as per the IEEE1547-2018 reactive power control methodologies.","PeriodicalId":380005,"journal":{"name":"2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116753737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-08DOI: 10.1109/CONECCT55679.2022.9865762
Md. Arafat Bin Zafar, Md. Sajjad-Ul Islam, Md. Rashidul Islam, M. Shafiullah
For the growth and improvement of human life in the modern world, access to energy is one of the most crucial requirements. Due to a lack of resources, it is difficult to increase the capacity of traditional energy generation in Bangladesh. The nation should thus look for alternate solutions while taking climate change and fuel shortage into consideration because traditional generation capacity cannot meet the demand for power. Integrating renewable energy sources into the process of producing electricity is one strategy to alleviate the present power supply shortage in Bangladesh. This article considers a hybrid energy generating system for a small region, Halishahar in Chattogram, Bangladesh, that consists of a waste-to-energy (WtE) plant, solar system, wind turbine, a diesel generator as the backup power source, batteries, and converters. The article suggests a setup for the system that meets load demands while not incurring additional costs. Using a system model created by the HOMER program, the optimal combination of renewable energy sources is chosen. Results demonstrated support the effectiveness of the suggested model setup.
{"title":"Optimized Waste to Energy Technology Combined with PV-Wind-Diesel for Halishahar in Chattogram","authors":"Md. Arafat Bin Zafar, Md. Sajjad-Ul Islam, Md. Rashidul Islam, M. Shafiullah","doi":"10.1109/CONECCT55679.2022.9865762","DOIUrl":"https://doi.org/10.1109/CONECCT55679.2022.9865762","url":null,"abstract":"For the growth and improvement of human life in the modern world, access to energy is one of the most crucial requirements. Due to a lack of resources, it is difficult to increase the capacity of traditional energy generation in Bangladesh. The nation should thus look for alternate solutions while taking climate change and fuel shortage into consideration because traditional generation capacity cannot meet the demand for power. Integrating renewable energy sources into the process of producing electricity is one strategy to alleviate the present power supply shortage in Bangladesh. This article considers a hybrid energy generating system for a small region, Halishahar in Chattogram, Bangladesh, that consists of a waste-to-energy (WtE) plant, solar system, wind turbine, a diesel generator as the backup power source, batteries, and converters. The article suggests a setup for the system that meets load demands while not incurring additional costs. Using a system model created by the HOMER program, the optimal combination of renewable energy sources is chosen. Results demonstrated support the effectiveness of the suggested model setup.","PeriodicalId":380005,"journal":{"name":"2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132116673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-08DOI: 10.1109/CONECCT55679.2022.9865724
K. Shruthi, C. Kavitha
Underwater acoustic sensor networks find their applications in many areas including Environmental monitoring, Undersea explorations, Disaster prevention, Seismic monitoring, Assisted navigation, Mine reconnaissance, and many more. Many of the issues are addressed and resolved in underwater applications. One of the important issues to be addressed is routing. Routing is an essential task in all the networks. Finding the best path to send packets to the destination is of utmost importance. Routing in underwater networks is a difficult task due to invariant conditions of the underwater environment. Many of the algorithms have been designed to find the best path to the destination. In this paper, we propose a Reinforcement learning-based approach to establish the best path to the destination by considering the energy of the nodes and underwater environment. In RL based approach, a neighbor node is selected based on the underwater environment and the remaining energy of the nodes. The algorithm calculates the reward for every action and the best path is established based on total reward. Packets are then routed using the best path to the sink. The authors conclude RL based approach provides a better path to a destination by taking into consideration the energy of the nodes.
{"title":"Reinforcement learning-based approach for establishing energy-efficient routes in underwater sensor networks","authors":"K. Shruthi, C. Kavitha","doi":"10.1109/CONECCT55679.2022.9865724","DOIUrl":"https://doi.org/10.1109/CONECCT55679.2022.9865724","url":null,"abstract":"Underwater acoustic sensor networks find their applications in many areas including Environmental monitoring, Undersea explorations, Disaster prevention, Seismic monitoring, Assisted navigation, Mine reconnaissance, and many more. Many of the issues are addressed and resolved in underwater applications. One of the important issues to be addressed is routing. Routing is an essential task in all the networks. Finding the best path to send packets to the destination is of utmost importance. Routing in underwater networks is a difficult task due to invariant conditions of the underwater environment. Many of the algorithms have been designed to find the best path to the destination. In this paper, we propose a Reinforcement learning-based approach to establish the best path to the destination by considering the energy of the nodes and underwater environment. In RL based approach, a neighbor node is selected based on the underwater environment and the remaining energy of the nodes. The algorithm calculates the reward for every action and the best path is established based on total reward. Packets are then routed using the best path to the sink. The authors conclude RL based approach provides a better path to a destination by taking into consideration the energy of the nodes.","PeriodicalId":380005,"journal":{"name":"2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128271434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-08DOI: 10.1109/CONECCT55679.2022.9865746
M. M., S. Shivakumar, T. J, V. R.
In the recent years online reviews are prevalent. Over the years people have started giving feedback about a restaurant by posting images as part of a review where the sentiment polarity is classified based on the facial expressions or the foods. Even more to it is a piece of text along with the image that gives more clear understanding about the picture. As there is tremendous work carried over on text sentiment analysis(SA), in this paper we are focusing on visual analysis to identify whether a given image expresses positive or negative sentiment. In this paper, an image sentiment prediction model is built using Convolutional Neural Networks(CNN). The objective of this work is to perform sentiment classification efficiently and enhance the accuracy of restaurant image dataset posted on social media. The results show that the proposed model achieves better performance on analysis of opinions from images compared to naive bayes which is a machine learning technique.
{"title":"Visual Sentiment Classification of Restaurant Review Images using Deep Convolutional Neural Networks","authors":"M. M., S. Shivakumar, T. J, V. R.","doi":"10.1109/CONECCT55679.2022.9865746","DOIUrl":"https://doi.org/10.1109/CONECCT55679.2022.9865746","url":null,"abstract":"In the recent years online reviews are prevalent. Over the years people have started giving feedback about a restaurant by posting images as part of a review where the sentiment polarity is classified based on the facial expressions or the foods. Even more to it is a piece of text along with the image that gives more clear understanding about the picture. As there is tremendous work carried over on text sentiment analysis(SA), in this paper we are focusing on visual analysis to identify whether a given image expresses positive or negative sentiment. In this paper, an image sentiment prediction model is built using Convolutional Neural Networks(CNN). The objective of this work is to perform sentiment classification efficiently and enhance the accuracy of restaurant image dataset posted on social media. The results show that the proposed model achieves better performance on analysis of opinions from images compared to naive bayes which is a machine learning technique.","PeriodicalId":380005,"journal":{"name":"2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134490287","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-08DOI: 10.1109/CONECCT55679.2022.9865758
Utkrisht Singh, Mahendra Kumar Gourisaria, B. K. Mishra
Hepatitis C (HCV) is a micro-contagion that leads to liver inflammation, sometimes affecting the liver to a serious extent. In any medical therapy, proper diagnosis of treatment response is critical for decreasing the effects of the disease. It is assessed that three to four million new cases come every year for Hepatitis C, which is a public health issue that should be solved with treatment policies and recognition. The principal motive of this paper is to implement a twofold dataset approach for the finding of Hepatitis C Virus in the general population. Popular supervised learning models like Decision tree (DT), Logistic regression (LR), K-Nearest Neighbor (KNN), Extreme gradient boosting (XGB), Ada boost (AB), Gradient Boosting Machine, Gaussian Naive Bayes, Random Forest (RF), Gradient Boosting (GB), Support Vector Machine and its variations were instigated on the classification dataset, furthermore, some unsupervised learning models like K-means, Hierarchical clustering, DBMSCN, and Gaussian Mixture algorithms were applied on the HCV clustering dataset. It was concluded that Logistic Regression and K-Means were the superlative models
{"title":"A Dual Dataset approach for the diagnosis of Hepatitis C Virus using Machine Learning","authors":"Utkrisht Singh, Mahendra Kumar Gourisaria, B. K. Mishra","doi":"10.1109/CONECCT55679.2022.9865758","DOIUrl":"https://doi.org/10.1109/CONECCT55679.2022.9865758","url":null,"abstract":"Hepatitis C (HCV) is a micro-contagion that leads to liver inflammation, sometimes affecting the liver to a serious extent. In any medical therapy, proper diagnosis of treatment response is critical for decreasing the effects of the disease. It is assessed that three to four million new cases come every year for Hepatitis C, which is a public health issue that should be solved with treatment policies and recognition. The principal motive of this paper is to implement a twofold dataset approach for the finding of Hepatitis C Virus in the general population. Popular supervised learning models like Decision tree (DT), Logistic regression (LR), K-Nearest Neighbor (KNN), Extreme gradient boosting (XGB), Ada boost (AB), Gradient Boosting Machine, Gaussian Naive Bayes, Random Forest (RF), Gradient Boosting (GB), Support Vector Machine and its variations were instigated on the classification dataset, furthermore, some unsupervised learning models like K-means, Hierarchical clustering, DBMSCN, and Gaussian Mixture algorithms were applied on the HCV clustering dataset. It was concluded that Logistic Regression and K-Means were the superlative models","PeriodicalId":380005,"journal":{"name":"2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134552124","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-08DOI: 10.1109/CONECCT55679.2022.9865694
S. Akshay, P. Vasanth
As the widespread Internet connection is expanding, the transition from traditional classroom learning to virtual learning is now easier than ever. Online education has developed all over and replacing traditional learning. The ability to precisely monitor user behavior and understand where the pain spots are in the learning process is one of the benefits of the change to online learning. Therefore, this research will provide a benefit to Online learning education. Here, Fixation recognizable proof, which involves confining and identifying Fixation and saccades in eye-tracking conventions, is a vital piece of eye movement information handling that can altogether affect more elevated level examinations. Fixation distinguishing proof techniques, then again, are normally talked about casually and seldom analyzed. The work specified gives a scientific classification of fixation distinguishing proof calculations that groups calculations as per how they utilize spatial and fleeting data in eye-following conventions. Utilizing this scientific categorization, the Adaptive algorithm that is suggestive of one-of-a-kind classes in the scientific classification and is based on regularly utilized strategies. Then, at that point, utilizing a bunch of subjective rules, we investigate and look at this algorithm. Here, CNN has been utilized for face information registering and Adaptive calculation for eye fixation. The after effects of these correlations have interesting ramifications for how algorithms will be utilized later on. Providing an expected results on adapting for eye contact lenses and kajal strengthens the research work. An alert and email system that notifies the participant if there is a lack in focus during the online class is proposed.
{"title":"A CNN based model for Identification of the Level of Participation in Virtual Classrooms using Eye Movement Features","authors":"S. Akshay, P. Vasanth","doi":"10.1109/CONECCT55679.2022.9865694","DOIUrl":"https://doi.org/10.1109/CONECCT55679.2022.9865694","url":null,"abstract":"As the widespread Internet connection is expanding, the transition from traditional classroom learning to virtual learning is now easier than ever. Online education has developed all over and replacing traditional learning. The ability to precisely monitor user behavior and understand where the pain spots are in the learning process is one of the benefits of the change to online learning. Therefore, this research will provide a benefit to Online learning education. Here, Fixation recognizable proof, which involves confining and identifying Fixation and saccades in eye-tracking conventions, is a vital piece of eye movement information handling that can altogether affect more elevated level examinations. Fixation distinguishing proof techniques, then again, are normally talked about casually and seldom analyzed. The work specified gives a scientific classification of fixation distinguishing proof calculations that groups calculations as per how they utilize spatial and fleeting data in eye-following conventions. Utilizing this scientific categorization, the Adaptive algorithm that is suggestive of one-of-a-kind classes in the scientific classification and is based on regularly utilized strategies. Then, at that point, utilizing a bunch of subjective rules, we investigate and look at this algorithm. Here, CNN has been utilized for face information registering and Adaptive calculation for eye fixation. The after effects of these correlations have interesting ramifications for how algorithms will be utilized later on. Providing an expected results on adapting for eye contact lenses and kajal strengthens the research work. An alert and email system that notifies the participant if there is a lack in focus during the online class is proposed.","PeriodicalId":380005,"journal":{"name":"2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133731503","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：