Pub Date : 2021-10-01DOI: 10.1109/GCAT52182.2021.9587806
Jenish Hirpara, Mihir Shah, D. Nanda, Pratik Kanani
The lockdown imposed in many countries due to the deadly effects of COVID-19 caused a huge backlog in offices. A lot of employees have a shift in their working hours and changes in their schedule which makes the manual attendance system less efficient. Employees are preoccupied with the workload so much that it becomes difficult to maintain social distancing in the office space. During these times, where a safe and healthy work environment should be promoted, a mistake from a single person can do irreparable damage to his/her peers. In order to tackle the above problems, we have implemented an automated attendance system to record attendance via QR Scanner, a violation tracker implemented using Internet of Things and Machine Learning which tracks the total number of social distancing and mask violations, a website and an app to display the results. Our software provides a clean and easy to use user-interface which gives the ability to the user to login, view his work calendar, take a note of important announcements made at his/her workplace, keep a track of user’s attendance, and generate a QR code which is unique just to the user.
{"title":"Automated Attendance System, Mask Detection and Social Distancing Violation Tracker for Post Covid Scenarios","authors":"Jenish Hirpara, Mihir Shah, D. Nanda, Pratik Kanani","doi":"10.1109/GCAT52182.2021.9587806","DOIUrl":"https://doi.org/10.1109/GCAT52182.2021.9587806","url":null,"abstract":"The lockdown imposed in many countries due to the deadly effects of COVID-19 caused a huge backlog in offices. A lot of employees have a shift in their working hours and changes in their schedule which makes the manual attendance system less efficient. Employees are preoccupied with the workload so much that it becomes difficult to maintain social distancing in the office space. During these times, where a safe and healthy work environment should be promoted, a mistake from a single person can do irreparable damage to his/her peers. In order to tackle the above problems, we have implemented an automated attendance system to record attendance via QR Scanner, a violation tracker implemented using Internet of Things and Machine Learning which tracks the total number of social distancing and mask violations, a website and an app to display the results. Our software provides a clean and easy to use user-interface which gives the ability to the user to login, view his work calendar, take a note of important announcements made at his/her workplace, keep a track of user’s attendance, and generate a QR code which is unique just to the user.","PeriodicalId":436231,"journal":{"name":"2021 2nd Global Conference for Advancement in Technology (GCAT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130304874","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 : 2021-10-01DOI: 10.1109/GCAT52182.2021.9587850
Alankar Uniyal, Ayush Patel, Ritesh Dhanare
with the increasing integration of automobiles in our daily lives, the number of four-wheelers on the road has seen a substantial jump in the tally. Furthermore, the number of drivers has also increased. Moreover, people nowadays have a slightly higher chance to opt for a taxi for daily commute. With this statistic, a coinciding fact that the number of Parkinson’s Disease cases have also increased cannot be overlooked. Also, the advancement in the technology of machine learning has enabled us to accurately detect Parkinson’s Disease with unorthodox testing techniques like voice analysis. With these things in mind, we have attempted to use machine learning to predict whether a person has Parkinson’s disease or not using their voice samples whilst designing the model to assign higher weights to features that help accurately classify the voice sample. For Example, pitch being a critical factor to determine if the person is showing an excited emotional state. Once the model reaches the desired generalization ability, it can be integrated into the recruiting process of organizations like uber.
{"title":"Parkinson’s Disease Predictor via Voice Analysis","authors":"Alankar Uniyal, Ayush Patel, Ritesh Dhanare","doi":"10.1109/GCAT52182.2021.9587850","DOIUrl":"https://doi.org/10.1109/GCAT52182.2021.9587850","url":null,"abstract":"with the increasing integration of automobiles in our daily lives, the number of four-wheelers on the road has seen a substantial jump in the tally. Furthermore, the number of drivers has also increased. Moreover, people nowadays have a slightly higher chance to opt for a taxi for daily commute. With this statistic, a coinciding fact that the number of Parkinson’s Disease cases have also increased cannot be overlooked. Also, the advancement in the technology of machine learning has enabled us to accurately detect Parkinson’s Disease with unorthodox testing techniques like voice analysis. With these things in mind, we have attempted to use machine learning to predict whether a person has Parkinson’s disease or not using their voice samples whilst designing the model to assign higher weights to features that help accurately classify the voice sample. For Example, pitch being a critical factor to determine if the person is showing an excited emotional state. Once the model reaches the desired generalization ability, it can be integrated into the recruiting process of organizations like uber.","PeriodicalId":436231,"journal":{"name":"2021 2nd Global Conference for Advancement in Technology (GCAT)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134288480","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 : 2021-10-01DOI: 10.1109/GCAT52182.2021.9587801
I.T Shruthi, Shreelekha Panchal, Sarita Uniyal, Dr. Shashidhar Tantry
The schematic of class-AB yield stage with BJT, CMOS, BiCMOS is carried out in cadence virtuoso simulator. Every transistor size in the operational amp is designed, validated and BiCMOS operated at supply voltage of 3.3V. The proposed amplifier circuit utilizes a class-AB output stage comprising of PMOS and NMOS transistors along with NPN an PNP push pull circuit is made use. The BiCMOS circuit is made use to achieve advantage of CMOS as well as bipolar. Then, at that point Cascode amplifier stage-based op amp using CMOS Class-AB output and Cascode amplifier stage-based op amp using BiCMOS Class-AB output are compared.
{"title":"A High Gain, Low Power Operational Amplifier utilizing BiCMOS Class AB Output Stage","authors":"I.T Shruthi, Shreelekha Panchal, Sarita Uniyal, Dr. Shashidhar Tantry","doi":"10.1109/GCAT52182.2021.9587801","DOIUrl":"https://doi.org/10.1109/GCAT52182.2021.9587801","url":null,"abstract":"The schematic of class-AB yield stage with BJT, CMOS, BiCMOS is carried out in cadence virtuoso simulator. Every transistor size in the operational amp is designed, validated and BiCMOS operated at supply voltage of 3.3V. The proposed amplifier circuit utilizes a class-AB output stage comprising of PMOS and NMOS transistors along with NPN an PNP push pull circuit is made use. The BiCMOS circuit is made use to achieve advantage of CMOS as well as bipolar. Then, at that point Cascode amplifier stage-based op amp using CMOS Class-AB output and Cascode amplifier stage-based op amp using BiCMOS Class-AB output are compared.","PeriodicalId":436231,"journal":{"name":"2021 2nd Global Conference for Advancement in Technology (GCAT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134553035","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 : 2021-10-01DOI: 10.1109/GCAT52182.2021.9587498
N. Raj, M. Suri, S. K.
Electric Vehicles (EV) are gaining popularity from the transportation sector, as it causes less harm to the environment. The battery inside the EV can be refilled using battery charging or battery swapping. As battery swapping method is found to be advantageous over battery charging, Battery Swapping Stations (BSS) is presently the hot topic of research. Forecasting of EV arrivals helps in optimal planning of BSS. Back Propagation Neural Network (BPNN) is frequently used in forecasting. BPNN trained with traditional algorithms such as Levenberg Marquardt (LM) gets stuck at the local optima. This problem can be overcomed using metaheuristic algorithms such as Genetic Algorithm (GA). Thus, in this present work a comparative study on forecasting the EV arrivals at BSS is carried out using LM-BPNN and GA-BPNN. The two models have been simulated using MATLAB/Simulink environment and their performance is analysed using metrics such as Mean Square Error (MSE) and simulation time.
{"title":"Forecasting of EV Arrivals at Battery Swapping Station using GA-BPNN","authors":"N. Raj, M. Suri, S. K.","doi":"10.1109/GCAT52182.2021.9587498","DOIUrl":"https://doi.org/10.1109/GCAT52182.2021.9587498","url":null,"abstract":"Electric Vehicles (EV) are gaining popularity from the transportation sector, as it causes less harm to the environment. The battery inside the EV can be refilled using battery charging or battery swapping. As battery swapping method is found to be advantageous over battery charging, Battery Swapping Stations (BSS) is presently the hot topic of research. Forecasting of EV arrivals helps in optimal planning of BSS. Back Propagation Neural Network (BPNN) is frequently used in forecasting. BPNN trained with traditional algorithms such as Levenberg Marquardt (LM) gets stuck at the local optima. This problem can be overcomed using metaheuristic algorithms such as Genetic Algorithm (GA). Thus, in this present work a comparative study on forecasting the EV arrivals at BSS is carried out using LM-BPNN and GA-BPNN. The two models have been simulated using MATLAB/Simulink environment and their performance is analysed using metrics such as Mean Square Error (MSE) and simulation time.","PeriodicalId":436231,"journal":{"name":"2021 2nd Global Conference for Advancement in Technology (GCAT)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133224745","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 : 2021-10-01DOI: 10.1109/GCAT52182.2021.9587638
Parth Mahajan, Aniket Gupta
Recognition of human activity plays an important role in computer-human interaction, surveillance, reconnaissance, robotics for humans, and understanding interpersonal behaviour relationships. These activities can be recorded as a sequence of still images but only using vision to solve the HAR poses a major task due to problems like scale variation, wide change, in contrast, lighting, viewpoint and occlusions. Thus to address this our work is concentrated on developing and training two deep learning pipelines one Spatiotemporal based and the other being skeletal based on publicly available human activity classification datasets. Moreover, we merge the two pipelines using late fusion and provide a comparison between the three with the existing state of the art algorithms for various activities in the dataset. Finally, we present the future work for the same problem.
{"title":"Depth And Skeleton Based View-invariant Human Action Recognition","authors":"Parth Mahajan, Aniket Gupta","doi":"10.1109/GCAT52182.2021.9587638","DOIUrl":"https://doi.org/10.1109/GCAT52182.2021.9587638","url":null,"abstract":"Recognition of human activity plays an important role in computer-human interaction, surveillance, reconnaissance, robotics for humans, and understanding interpersonal behaviour relationships. These activities can be recorded as a sequence of still images but only using vision to solve the HAR poses a major task due to problems like scale variation, wide change, in contrast, lighting, viewpoint and occlusions. Thus to address this our work is concentrated on developing and training two deep learning pipelines one Spatiotemporal based and the other being skeletal based on publicly available human activity classification datasets. Moreover, we merge the two pipelines using late fusion and provide a comparison between the three with the existing state of the art algorithms for various activities in the dataset. Finally, we present the future work for the same problem.","PeriodicalId":436231,"journal":{"name":"2021 2nd Global Conference for Advancement in Technology (GCAT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133892978","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 : 2021-10-01DOI: 10.1109/GCAT52182.2021.9587478
P. Mahapatro, Jatinderkumar R. Saini
This paper presents Zika Virus Analysis. Zika virus infection during pregnancy causes neurological disorder, Guillain-Barre syndrome, and birth defects in newborns. No cure or vaccine is available. The study of genome replication will bring some insight into the Zika virus. One of the important tasks in the cell is Genome replication. The daughter cells inherit its own copy of the genome, and then the cell divides in the process of genome replication. Ori is the position in the genome where the genome replicates. Finding the position of ori is a complicated task even for biologists. This task can be performed using Genome analysis. This paper presents the Genome analysis of Zika virus using innovative programming techniques instead of using a laboratory. Identifying the position ori will help the biologist in finding the position where the genome replication occurs.
{"title":"An Innovative Computer Programming based Analysis of Zika Virus for Identification of Genome Replication Location","authors":"P. Mahapatro, Jatinderkumar R. Saini","doi":"10.1109/GCAT52182.2021.9587478","DOIUrl":"https://doi.org/10.1109/GCAT52182.2021.9587478","url":null,"abstract":"This paper presents Zika Virus Analysis. Zika virus infection during pregnancy causes neurological disorder, Guillain-Barre syndrome, and birth defects in newborns. No cure or vaccine is available. The study of genome replication will bring some insight into the Zika virus. One of the important tasks in the cell is Genome replication. The daughter cells inherit its own copy of the genome, and then the cell divides in the process of genome replication. Ori is the position in the genome where the genome replicates. Finding the position of ori is a complicated task even for biologists. This task can be performed using Genome analysis. This paper presents the Genome analysis of Zika virus using innovative programming techniques instead of using a laboratory. Identifying the position ori will help the biologist in finding the position where the genome replication occurs.","PeriodicalId":436231,"journal":{"name":"2021 2nd Global Conference for Advancement in Technology (GCAT)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120954620","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 : 2021-10-01DOI: 10.1109/GCAT52182.2021.9587659
Atharva Gondkar, Jeevan Thukrul, Raghav Bang, S. Rakshe, S. Sarode
The highly volatile nature of the stock market has made stock price prediction as challenging as weather forecasting. Consequently, as a hint of this dread, people don’t invest in the stock market. In this paper, we have discussed hybrid networks and a stacked LSTM network for stock price prediction. Additionally, it also focuses on portfolio optimization done using six different techniques, which focuses on creating best performing portfolios categorized on the basis of sectors. One hybrid neural network consists of 1D-Convolutional layers and LSTM layers, and the other is a combination of GRU and LSTM layers. The stock prices of SBI, Indian Bank, Bank of India are predicted using stacked LSTM and Hybrid Neural Networks and compared using the sliding window of time steps with variable width. The neural networks predict the following day’s closing price using a variable sliding window. The RMSE, MSE, and MAE are used to evaluate the efficiency of these neural networks. The hybrid network is proving to be more competent in various situations.
{"title":"Stock Market Prediction and Portfolio Optimization","authors":"Atharva Gondkar, Jeevan Thukrul, Raghav Bang, S. Rakshe, S. Sarode","doi":"10.1109/GCAT52182.2021.9587659","DOIUrl":"https://doi.org/10.1109/GCAT52182.2021.9587659","url":null,"abstract":"The highly volatile nature of the stock market has made stock price prediction as challenging as weather forecasting. Consequently, as a hint of this dread, people don’t invest in the stock market. In this paper, we have discussed hybrid networks and a stacked LSTM network for stock price prediction. Additionally, it also focuses on portfolio optimization done using six different techniques, which focuses on creating best performing portfolios categorized on the basis of sectors. One hybrid neural network consists of 1D-Convolutional layers and LSTM layers, and the other is a combination of GRU and LSTM layers. The stock prices of SBI, Indian Bank, Bank of India are predicted using stacked LSTM and Hybrid Neural Networks and compared using the sliding window of time steps with variable width. The neural networks predict the following day’s closing price using a variable sliding window. The RMSE, MSE, and MAE are used to evaluate the efficiency of these neural networks. The hybrid network is proving to be more competent in various situations.","PeriodicalId":436231,"journal":{"name":"2021 2nd Global Conference for Advancement in Technology (GCAT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114954747","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 : 2021-10-01DOI: 10.1109/GCAT52182.2021.9587841
Manjusha Nair, A. R, Arya C. Babu
The different mutated variants of Corona Virus (SARS-CoV-2), affected a large percentage of the world population so far. On this light, any study on understanding the virus’s immunity to vaccines and medicines has greater relevance. Studies on Angiotensin-converting enzyme 2 (ACE2), the main entry receptor for the SARS-COV-2 S protein is significantly important in understanding SARS-COV-2 infection in host cells. The functional implications of various motifs found in the spike glycoprotein and its conformational changes had been studied previously to better understand the pathogenesis. The computational study, described herein, have focused on the disease transmission mechanisms of the virus especially on the receptor recognition mechanisms during viral infection. This study used different computational techniques to identify significant motif of the SARS-CoV-2 S Glycoprotein. Different corona viral genomes were compared against the reference genome (Wuhan seafood market isolate) and the possible intermediate hosts of the virus has been proposed based on the similarity in the motifs which are critical for viral infections. Previous studies on S protein motifs of proteolytic cleavage site are revisited here using computational techniques to suggest the possible intermediate hosts of infection.
{"title":"Recognizing Significant Motifs of Corona Virus Spike Proteins using Computational Approaches","authors":"Manjusha Nair, A. R, Arya C. Babu","doi":"10.1109/GCAT52182.2021.9587841","DOIUrl":"https://doi.org/10.1109/GCAT52182.2021.9587841","url":null,"abstract":"The different mutated variants of Corona Virus (SARS-CoV-2), affected a large percentage of the world population so far. On this light, any study on understanding the virus’s immunity to vaccines and medicines has greater relevance. Studies on Angiotensin-converting enzyme 2 (ACE2), the main entry receptor for the SARS-COV-2 S protein is significantly important in understanding SARS-COV-2 infection in host cells. The functional implications of various motifs found in the spike glycoprotein and its conformational changes had been studied previously to better understand the pathogenesis. The computational study, described herein, have focused on the disease transmission mechanisms of the virus especially on the receptor recognition mechanisms during viral infection. This study used different computational techniques to identify significant motif of the SARS-CoV-2 S Glycoprotein. Different corona viral genomes were compared against the reference genome (Wuhan seafood market isolate) and the possible intermediate hosts of the virus has been proposed based on the similarity in the motifs which are critical for viral infections. Previous studies on S protein motifs of proteolytic cleavage site are revisited here using computational techniques to suggest the possible intermediate hosts of infection.","PeriodicalId":436231,"journal":{"name":"2021 2nd Global Conference for Advancement in Technology (GCAT)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116720829","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 : 2021-10-01DOI: 10.1109/GCAT52182.2021.9587709
Priyam A. Sheth, Soumya, A. Lad, Yash Solanki
The world of the Internet of Things (IoT) has exploded and expanded rapidly in recent years. IoT is made up of several connected devices and sensors that communicate by exchanging data through the internet. With exponential growth in the number of installed devices and sensors, conservation of energy is a buzzing topic in the field. IoT facilitates the conservation of energy by enabling the management of data collected from various sensors. The paper presents an implementation of Energy-aware Smart University focusing on Smart Lighting, Air-conditioning, and Ventilating system, whose scope can be expanded to any electrical appliances. This paper attempts to make a low-cost, energy-efficient system. The proposed solution uses Message Queuing Telemetry Transport (MQTT) Client protocol, an IEEE 802.3 standard Ethernet connectivity shield for internet publishing, and a set of sensors such as PIR Sensor and 5 Megapixel infrared camera supported by the raspberry pi for obtaining real-time data. The electrical appliances are turned on only when motion sensors detect movement, and the presence of humans is confirmed using image processing on pictures captured by the Pi Camera. As a result, a significant amount of energy is saved by preventing the continuous operation of the appliances. The data is stored using the MySQL database, which could be accessed using an Android application remotely, which would make this an easily accessible and operational automation system.
{"title":"Energy Aware IoT based Green Smart University with Automated Lighting and CCTV System using MQTT and MySQL","authors":"Priyam A. Sheth, Soumya, A. Lad, Yash Solanki","doi":"10.1109/GCAT52182.2021.9587709","DOIUrl":"https://doi.org/10.1109/GCAT52182.2021.9587709","url":null,"abstract":"The world of the Internet of Things (IoT) has exploded and expanded rapidly in recent years. IoT is made up of several connected devices and sensors that communicate by exchanging data through the internet. With exponential growth in the number of installed devices and sensors, conservation of energy is a buzzing topic in the field. IoT facilitates the conservation of energy by enabling the management of data collected from various sensors. The paper presents an implementation of Energy-aware Smart University focusing on Smart Lighting, Air-conditioning, and Ventilating system, whose scope can be expanded to any electrical appliances. This paper attempts to make a low-cost, energy-efficient system. The proposed solution uses Message Queuing Telemetry Transport (MQTT) Client protocol, an IEEE 802.3 standard Ethernet connectivity shield for internet publishing, and a set of sensors such as PIR Sensor and 5 Megapixel infrared camera supported by the raspberry pi for obtaining real-time data. The electrical appliances are turned on only when motion sensors detect movement, and the presence of humans is confirmed using image processing on pictures captured by the Pi Camera. As a result, a significant amount of energy is saved by preventing the continuous operation of the appliances. The data is stored using the MySQL database, which could be accessed using an Android application remotely, which would make this an easily accessible and operational automation system.","PeriodicalId":436231,"journal":{"name":"2021 2nd Global Conference for Advancement in Technology (GCAT)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117108113","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 : 2021-10-01DOI: 10.1109/GCAT52182.2021.9587740
Gauri Ramanathan, Diya Chakrabarti, Aarti Patil, Sakshi Rishipathak, S. Kharche
The dominant causes of visual impairment worldwide are Cataract, Glaucoma, and retinal diseases among patients. The alarming cases of these diseases call for an urgent intervention by early diagnosis. The proposed system is designed and developed to easily facilitate the detection of cataract, glaucoma and retinal diseases among patients. The Logistic Regression, Random Forest, Gradient Boosting and Support Vector Machine algorithms are used for detection. The proposed system will help people to get the proper treatment of the aforementioned diseases at an early stage thus reducing the percentage of blindness being caused. The proposed system evaluates the effectiveness and safety of cataract surgery in eyes with age-related degeneration along with glaucoma and retinal diseases detection. This paper shows the accuracy of algorithms and SVM classifiers based upon the glaucoma, retina, cataract and normal eye’s fundus images. The idea of classifying the images based on its fundus and extracting features is widely known now-a-days and also it plays a vital role in the final outcome. This paper talks about the multiclass built models of these classifiers and on the basis of the ROC curves plotted it predicts the output of the images. As far as the algorithms are concerned, the efficiency of algorithms helps it stand best out of many and in our case Gradient boosting proves to give best results for the eye with cataract with 90% accuracy. Then the supervised algorithms logistic regression and random forest gives the accuracy of 89% and 86% respectively.
{"title":"Eye Disease Detection Using Machine Learning","authors":"Gauri Ramanathan, Diya Chakrabarti, Aarti Patil, Sakshi Rishipathak, S. Kharche","doi":"10.1109/GCAT52182.2021.9587740","DOIUrl":"https://doi.org/10.1109/GCAT52182.2021.9587740","url":null,"abstract":"The dominant causes of visual impairment worldwide are Cataract, Glaucoma, and retinal diseases among patients. The alarming cases of these diseases call for an urgent intervention by early diagnosis. The proposed system is designed and developed to easily facilitate the detection of cataract, glaucoma and retinal diseases among patients. The Logistic Regression, Random Forest, Gradient Boosting and Support Vector Machine algorithms are used for detection. The proposed system will help people to get the proper treatment of the aforementioned diseases at an early stage thus reducing the percentage of blindness being caused. The proposed system evaluates the effectiveness and safety of cataract surgery in eyes with age-related degeneration along with glaucoma and retinal diseases detection. This paper shows the accuracy of algorithms and SVM classifiers based upon the glaucoma, retina, cataract and normal eye’s fundus images. The idea of classifying the images based on its fundus and extracting features is widely known now-a-days and also it plays a vital role in the final outcome. This paper talks about the multiclass built models of these classifiers and on the basis of the ROC curves plotted it predicts the output of the images. As far as the algorithms are concerned, the efficiency of algorithms helps it stand best out of many and in our case Gradient boosting proves to give best results for the eye with cataract with 90% accuracy. Then the supervised algorithms logistic regression and random forest gives the accuracy of 89% and 86% respectively.","PeriodicalId":436231,"journal":{"name":"2021 2nd Global Conference for Advancement in Technology (GCAT)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115623934","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：