Pub Date : 2021-09-24DOI: 10.1109/ICSES52305.2021.9633889
A. Lakshmanarao, M. Babu, M. M. Bala Krishna
A URL created to attack with spam or fraud is known as a malicious/phishing URL. Viruses are downloaded into the system if the user clicks such URLs. Malicious URLs can lead to phishing and spam. With phishing, user credentials, valuable information is compromised. So, it is important to identify safe links and malicious links. Cyber-attacks are attempting with the origin of malicious URLs Phishers are manipulating their cyber attacking techniques rapidly. Machine Learning is a field of study where a system learns from previous experience and reacts to future events. Machine Learning methods are useful for resolving security applications. In this paper, authors proposed machine learning oriented solution for detecting malicious websites. For experiments, a Kaggle dataset with a large number of URLs (above 5, 00000 URLs) is used. We applied three techniques for text feature extraction count vectorizer, hashing vectorizer-IDF vectorizer, and later build a phishing website detection model with four ML classifiers Logistic Regression, K-NN, Decision Tree, Random Forest. The ML model with hash vectorizer and random forest achieved 97.5% accuracy. We also created a web app using Flask for detecting the entered URL is malicious or not.
{"title":"Malicious URL Detection using NLP, Machine Learning and FLASK","authors":"A. Lakshmanarao, M. Babu, M. M. Bala Krishna","doi":"10.1109/ICSES52305.2021.9633889","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633889","url":null,"abstract":"A URL created to attack with spam or fraud is known as a malicious/phishing URL. Viruses are downloaded into the system if the user clicks such URLs. Malicious URLs can lead to phishing and spam. With phishing, user credentials, valuable information is compromised. So, it is important to identify safe links and malicious links. Cyber-attacks are attempting with the origin of malicious URLs Phishers are manipulating their cyber attacking techniques rapidly. Machine Learning is a field of study where a system learns from previous experience and reacts to future events. Machine Learning methods are useful for resolving security applications. In this paper, authors proposed machine learning oriented solution for detecting malicious websites. For experiments, a Kaggle dataset with a large number of URLs (above 5, 00000 URLs) is used. We applied three techniques for text feature extraction count vectorizer, hashing vectorizer-IDF vectorizer, and later build a phishing website detection model with four ML classifiers Logistic Regression, K-NN, Decision Tree, Random Forest. The ML model with hash vectorizer and random forest achieved 97.5% accuracy. We also created a web app using Flask for detecting the entered URL is malicious or not.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"7 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78695148","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 : 2021-09-24DOI: 10.1109/ICSES52305.2021.9633869
P. Jain, P. Chawla
COVID-19 might be devastatingly affecting our enterprises, public activities and individual prepping norms and principles but it has also sparked a digital revolution of innovation in different fields. The objective of this paper is to understand the in-depth role of the Internet of Things (IoT) in eHealth to mitigate the impact of COVID-19. This paper covers numerous applications of IoT in healthcare starting from research, telemedicine, teleconsultation via chatbots and virtual assistants providing instantaneous medical help online. Telemedicine and remote patient monitoring is the need of the hour to avoid direct contact with the patients which have been made possible via IoT and its associated tools like Artificial Intelligence, Machine Learning, Blockchain technology and Cloud Computing. With such high volumes and diversity of data being generated from IoT there is a strong need for connectivity and streaming analytics thus 5G technology and its applications have been discussed like smart 5G connected ambulances and smart 5G based hospitals. Long Range Radio is another promising technology which due to its low power operation and long-distance data transmission at higher speeds is turning out to be the defacto technology for IoT networks across the globe especially in areas with poor network coverage. Seeing the demand for both ventilators and skilled medical professionals due to lack of proper medical infrastructure worldwide, a review of IoT -based smart ventilators has also been carried out. The paper concludes with possible solutions to IoT challenges in healthcare by proposing a smart healthcare model design. Moreover keeping in mind the situation of Covid-19 Pandemic the module also comprises a UVC Disinfection box that would help in eliminating the risk of the virus entering our homes.
{"title":"A Novel Smart Healthcare System Design for Internet of Health Things","authors":"P. Jain, P. Chawla","doi":"10.1109/ICSES52305.2021.9633869","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633869","url":null,"abstract":"COVID-19 might be devastatingly affecting our enterprises, public activities and individual prepping norms and principles but it has also sparked a digital revolution of innovation in different fields. The objective of this paper is to understand the in-depth role of the Internet of Things (IoT) in eHealth to mitigate the impact of COVID-19. This paper covers numerous applications of IoT in healthcare starting from research, telemedicine, teleconsultation via chatbots and virtual assistants providing instantaneous medical help online. Telemedicine and remote patient monitoring is the need of the hour to avoid direct contact with the patients which have been made possible via IoT and its associated tools like Artificial Intelligence, Machine Learning, Blockchain technology and Cloud Computing. With such high volumes and diversity of data being generated from IoT there is a strong need for connectivity and streaming analytics thus 5G technology and its applications have been discussed like smart 5G connected ambulances and smart 5G based hospitals. Long Range Radio is another promising technology which due to its low power operation and long-distance data transmission at higher speeds is turning out to be the defacto technology for IoT networks across the globe especially in areas with poor network coverage. Seeing the demand for both ventilators and skilled medical professionals due to lack of proper medical infrastructure worldwide, a review of IoT -based smart ventilators has also been carried out. The paper concludes with possible solutions to IoT challenges in healthcare by proposing a smart healthcare model design. Moreover keeping in mind the situation of Covid-19 Pandemic the module also comprises a UVC Disinfection box that would help in eliminating the risk of the virus entering our homes.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"29 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84911328","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 : 2021-09-24DOI: 10.1109/ICSES52305.2021.9633964
D. Patil, K. Deepa
Complexity in distributed generation and transmission of electricity is increased in this era, as electrical vehicles are newer electric load introduced into the grid. For Vehicle to Grid or Grid to Vehicle, Voltage Source Converters are used. Switching of semiconductor switches in converters causes' harmonic in voltage and current waveforms, which drastically reduces the performance of the grid. In order to mitigate the harmonics in the grid, harmonic filters are introduced into the system. In this paper, harmonic analysis with L, LC and LCL filter design for two electric vehicles and home load appliances connected to grid is presented. L and LC filters were most widely used filters, but increasing demand of the grid creates more challenges in power superiority, subsequently the value of L increases that makes the system bulky and less cost-effective. LCL filter offers striking replacement for the configuration of L and LC filters. This approach is designed under MATLAB / Simulink software and the current and voltage waveform are presented for comparison.
{"title":"Harmonic Analysis of Grid Connected Electric Vehicles with Residential Load for Different Filters","authors":"D. Patil, K. Deepa","doi":"10.1109/ICSES52305.2021.9633964","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633964","url":null,"abstract":"Complexity in distributed generation and transmission of electricity is increased in this era, as electrical vehicles are newer electric load introduced into the grid. For Vehicle to Grid or Grid to Vehicle, Voltage Source Converters are used. Switching of semiconductor switches in converters causes' harmonic in voltage and current waveforms, which drastically reduces the performance of the grid. In order to mitigate the harmonics in the grid, harmonic filters are introduced into the system. In this paper, harmonic analysis with L, LC and LCL filter design for two electric vehicles and home load appliances connected to grid is presented. L and LC filters were most widely used filters, but increasing demand of the grid creates more challenges in power superiority, subsequently the value of L increases that makes the system bulky and less cost-effective. LCL filter offers striking replacement for the configuration of L and LC filters. This approach is designed under MATLAB / Simulink software and the current and voltage waveform are presented for comparison.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"192 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85007081","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 : 2021-09-24DOI: 10.1109/ICSES52305.2021.9633825
P. Juyal, Sachin Sharma
Demand for agricultural produce has drastically increased in recent years. Meeting these demands require expansion of agricultural area and organic farming. Lack of monitoring arises in such expansive areas. Which can lead to overlooking infected plants. Failing in spotting these infected plants can lead to irreversible damage to the plant and this leading to yield loss. Unmanned aerial vehicles (UAV's)are actively being used to tackle large scale agricultural problems. In this paper, we are equipping UAV's with system that not only identifies the healthy strawberry plants and infected strawberry plants but also indicates the possible disease the strawberry plants might have. With this proposed methodology, farmer can efficiently locate and handle the treatment of the infected strawberry plants
{"title":"Strawberry Plant's Health Detection for Organic Farming Using Unmanned Aerial Vehicle","authors":"P. Juyal, Sachin Sharma","doi":"10.1109/ICSES52305.2021.9633825","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633825","url":null,"abstract":"Demand for agricultural produce has drastically increased in recent years. Meeting these demands require expansion of agricultural area and organic farming. Lack of monitoring arises in such expansive areas. Which can lead to overlooking infected plants. Failing in spotting these infected plants can lead to irreversible damage to the plant and this leading to yield loss. Unmanned aerial vehicles (UAV's)are actively being used to tackle large scale agricultural problems. In this paper, we are equipping UAV's with system that not only identifies the healthy strawberry plants and infected strawberry plants but also indicates the possible disease the strawberry plants might have. With this proposed methodology, farmer can efficiently locate and handle the treatment of the infected strawberry plants","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"36 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85142768","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 : 2021-09-24DOI: 10.1109/ICSES52305.2021.9633873
Madhuri Ninganolla, K. Vasanth
A smart container which automatically monitors and controls environmental conditions, pest formation and mildew formation is proposed. We can also know the quantity of grains present in the container via SMS. This smart container consists of different types of sensors. It also consists of other devices like ultrasonic pest repeller and load cell. This smart container works in five different modes of operation. The sensors obtain data from container and send to controller to compare them with standard values. Accordingly, the parameters are monitored and controlled in different modes. An exhaust fan is placed in the container which controls the temperature, humidity and moisture by switching the exhaust on and off automatically. The data can be reviewed by user in the form of SMS. The experiment was conducted and results obtained are very effective and proves that proposed system can store raw grains in organic manner and protect them from pests and mildew. By using this smart container we can avoid usage of chemicals and preserve the grains from germination and maintain quality of grains.
{"title":"Monitoring of Food grains on a Smart Container using Internet of Things","authors":"Madhuri Ninganolla, K. Vasanth","doi":"10.1109/ICSES52305.2021.9633873","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633873","url":null,"abstract":"A smart container which automatically monitors and controls environmental conditions, pest formation and mildew formation is proposed. We can also know the quantity of grains present in the container via SMS. This smart container consists of different types of sensors. It also consists of other devices like ultrasonic pest repeller and load cell. This smart container works in five different modes of operation. The sensors obtain data from container and send to controller to compare them with standard values. Accordingly, the parameters are monitored and controlled in different modes. An exhaust fan is placed in the container which controls the temperature, humidity and moisture by switching the exhaust on and off automatically. The data can be reviewed by user in the form of SMS. The experiment was conducted and results obtained are very effective and proves that proposed system can store raw grains in organic manner and protect them from pests and mildew. By using this smart container we can avoid usage of chemicals and preserve the grains from germination and maintain quality of grains.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"70 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76256392","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 : 2021-09-24DOI: 10.1109/ICSES52305.2021.9633849
Giridhar Vadicharla, pushpanth Sharma, S. Gupta, D. Saraf
History matching, Reservoir modeling, and production projection help with effective petroleum exploration management. These reservoirs are nonlinear and heterogeneous in nature. Obtaining credible calculates of the spatial distribution of the parameters of the reservoir and related production profiles is frequently challenging. The goal of this research is to use Non-dominated Sorting Genetic Algorithm-II (NSGA-II) and Sequential Gaussian Simulation (SGSIM) to history-match an oil reservoir. The normalized sum-of-square errors for history matching is taken as objective function. A case study is chosen and the defined objective function is used to optimize the parameters. This article analyzes the application of NSGA-II, with larger number of variables, and NSGA-II coupled with Sequential Gaussian Simulation (SGSIM), in which number of variables is drastically reduced, for the same case study.
历史匹配、油藏建模和产量预测有助于有效的石油勘探管理。这些储层具有非线性和非均质性质。获得可靠的储层参数空间分布和相关生产剖面的计算常常是一项挑战。本研究的目标是使用非支配排序遗传算法- ii (NSGA-II)和顺序高斯模拟(SGSIM)对油藏进行历史匹配。将历史匹配的归一化平方和误差作为目标函数。选取一个实例，利用定义的目标函数对参数进行优化。本文分析了变量数量较大的NSGA-II的应用，以及NSGA-II与变量数量大幅减少的顺序高斯模拟(Sequential Gaussian Simulation, SGSIM)相结合的应用。
{"title":"History matching of an Oil Reservoir using Non-dominated Sorting Genetic Algorithm-II coupled with Sequential Gaussian Simulation","authors":"Giridhar Vadicharla, pushpanth Sharma, S. Gupta, D. Saraf","doi":"10.1109/ICSES52305.2021.9633849","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633849","url":null,"abstract":"History matching, Reservoir modeling, and production projection help with effective petroleum exploration management. These reservoirs are nonlinear and heterogeneous in nature. Obtaining credible calculates of the spatial distribution of the parameters of the reservoir and related production profiles is frequently challenging. The goal of this research is to use Non-dominated Sorting Genetic Algorithm-II (NSGA-II) and Sequential Gaussian Simulation (SGSIM) to history-match an oil reservoir. The normalized sum-of-square errors for history matching is taken as objective function. A case study is chosen and the defined objective function is used to optimize the parameters. This article analyzes the application of NSGA-II, with larger number of variables, and NSGA-II coupled with Sequential Gaussian Simulation (SGSIM), in which number of variables is drastically reduced, for the same case study.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"38 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83002275","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 : 2021-09-24DOI: 10.1109/ICSES52305.2021.9633870
ParizatBinta Kabir, Sharmin Akter
Heart disease has evolved to become the most deadly ailment on the earth, and it has been the top reason for mortality worldwide. As a result, a dependable, efficient, and practical method for diagnosing and treating such disorders promptly is required. This study examines and compares several Machine Learning (ML) algorithms and approaches. Six ML classifiers are tested to see which one's the most successful at diagnosing heart disease. Tree-based techniques are among the most basic and extensively used ensemble learning approaches. According to the analysis, tree-based models such as Decision Tree (DT) and Random Forest (RF) deliver actionable insights with high efficacy, uniformity, and applicability. Relevant features are identified by using the Feature Selection (FS) process, and the output of classifiers is calculated based on these features. FS removes irrelevant features without impacting learning output. Our research intends to improve the system's efficiency. The goal of this research is to combine FS with tree-based algorithms to improve the accuracy of heart disease prediction.
{"title":"Emphasised Research on Heart Disease Divination Applying Tree Based Algorithms and Feature Selection","authors":"ParizatBinta Kabir, Sharmin Akter","doi":"10.1109/ICSES52305.2021.9633870","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633870","url":null,"abstract":"Heart disease has evolved to become the most deadly ailment on the earth, and it has been the top reason for mortality worldwide. As a result, a dependable, efficient, and practical method for diagnosing and treating such disorders promptly is required. This study examines and compares several Machine Learning (ML) algorithms and approaches. Six ML classifiers are tested to see which one's the most successful at diagnosing heart disease. Tree-based techniques are among the most basic and extensively used ensemble learning approaches. According to the analysis, tree-based models such as Decision Tree (DT) and Random Forest (RF) deliver actionable insights with high efficacy, uniformity, and applicability. Relevant features are identified by using the Feature Selection (FS) process, and the output of classifiers is calculated based on these features. FS removes irrelevant features without impacting learning output. Our research intends to improve the system's efficiency. The goal of this research is to combine FS with tree-based algorithms to improve the accuracy of heart disease prediction.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"210 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87006619","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 : 2021-09-24DOI: 10.1109/ICSES52305.2021.9633804
Ambreen Sabha, A. Selwal
In computer vision, video summarization is a critical research problem as it is related to a more condensed and engaging portrayal of the video's original content. Deep learning models have lately been employed for various approaches to human action recognition. In this paper, we examine the most up-to-date methodologies for summarizing human behaviors in videos, as well as numerous deep learning and hybrid algorithms. We provide an in-depth analysis of the many forms of human activities, including gesture-based, interaction-based, human action-based, and group activity-based activities. Our study goes over the most recent benchmark datasets for recognizing human motion in video sequences. It also discusses the strengths and limitations of the existing methods, open research issues, and future directions for human action-based video summarization (HAVS). This work clearly reveals that majority of HAVS approaches rely upon key-frames selection using Convolution neural network (CNN), which direct research community to explore sequence learning such as Long short-term neural network (LSTM). Furthermore, inadequate datasets for learning HAVS models are an additional challenge. An improvement in existing deep learning models for HAVS may be oriented towards the notion of transfer learning, which results in lower training overhead and higher accuracy.
{"title":"HAVS: Human action-based video summarization, Taxonomy, Challenges, and Future Perspectives","authors":"Ambreen Sabha, A. Selwal","doi":"10.1109/ICSES52305.2021.9633804","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633804","url":null,"abstract":"In computer vision, video summarization is a critical research problem as it is related to a more condensed and engaging portrayal of the video's original content. Deep learning models have lately been employed for various approaches to human action recognition. In this paper, we examine the most up-to-date methodologies for summarizing human behaviors in videos, as well as numerous deep learning and hybrid algorithms. We provide an in-depth analysis of the many forms of human activities, including gesture-based, interaction-based, human action-based, and group activity-based activities. Our study goes over the most recent benchmark datasets for recognizing human motion in video sequences. It also discusses the strengths and limitations of the existing methods, open research issues, and future directions for human action-based video summarization (HAVS). This work clearly reveals that majority of HAVS approaches rely upon key-frames selection using Convolution neural network (CNN), which direct research community to explore sequence learning such as Long short-term neural network (LSTM). Furthermore, inadequate datasets for learning HAVS models are an additional challenge. An improvement in existing deep learning models for HAVS may be oriented towards the notion of transfer learning, which results in lower training overhead and higher accuracy.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"108 1","pages":"1-9"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86392664","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 : 2021-09-24DOI: 10.1109/ICSES52305.2021.9633872
Nusrat Jahan, Arifatun Nesa, Md. Abu Layek
Nowadays the most common and incurable neurological disorder disease is Parkinson's disease (PD). This incurable disease is growing terribly. This study determines PD patients on the basis of fine motor symptoms using sketching. We proposed a system where we use spiral and wave sketching that can identify either the sketch is from a PD patient or not. Our experiment was done on a dataset consisting PD patient and Healthy (without PD) control group. We applied a deep learning approach Convolutional Neural Network (CNN) to determine PD infected patients and healthy (without PD) control group. We experimented on two CNN models - Inception v3 and ResNet50, with transfer learning method. The proposed system achieved 96.67% accuracy on the Inception-v3 model with spiral sketching.
{"title":"Parkinson's Disease Detection Using CNN Architectures withTransfer Learning","authors":"Nusrat Jahan, Arifatun Nesa, Md. Abu Layek","doi":"10.1109/ICSES52305.2021.9633872","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633872","url":null,"abstract":"Nowadays the most common and incurable neurological disorder disease is Parkinson's disease (PD). This incurable disease is growing terribly. This study determines PD patients on the basis of fine motor symptoms using sketching. We proposed a system where we use spiral and wave sketching that can identify either the sketch is from a PD patient or not. Our experiment was done on a dataset consisting PD patient and Healthy (without PD) control group. We applied a deep learning approach Convolutional Neural Network (CNN) to determine PD infected patients and healthy (without PD) control group. We experimented on two CNN models - Inception v3 and ResNet50, with transfer learning method. The proposed system achieved 96.67% accuracy on the Inception-v3 model with spiral sketching.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"68 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83870093","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 : 2021-09-24DOI: 10.1109/ICSES52305.2021.9633959
Amit Juyal, Sachin Sharma, Priya Matta
Autonomous vehicle is an emerging topic for both researchers and the automobile industry as companies are still struggling to make fully functional autonomous vehicles. Driving a safe vehicle in a real world depends on different conditions, such as distance from other vehicles, pedestrians, animals, speed-breakers, traffic signals and other unpredictable dynamic environments. Autonomous vehicle can decrease vehicle crashes because software installed in the vehicle instructs the control system of the autonomous vehicle rather than human, and Software makes less error compare to human beings. Automated Traffic Sign Detection and Recognition (ATSDR) is an important task for a safe driving by an autonomous vehicle. Many researchers have used various deep learning-based models for in real-time ATSDR. Here in the present review, we have studied various deep learning models used for in real-time ATSDR. Our study suggested that YOLO and SSD can detect the traffic sign in real time and are superior models for ATSDR as compared to other deep learning methods as CNN, R-CNN, Fast R-CNN and Faster RCNN.
{"title":"Traffic Sign Detection using Deep Learning Techniques in Autonomous Vehicles","authors":"Amit Juyal, Sachin Sharma, Priya Matta","doi":"10.1109/ICSES52305.2021.9633959","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633959","url":null,"abstract":"Autonomous vehicle is an emerging topic for both researchers and the automobile industry as companies are still struggling to make fully functional autonomous vehicles. Driving a safe vehicle in a real world depends on different conditions, such as distance from other vehicles, pedestrians, animals, speed-breakers, traffic signals and other unpredictable dynamic environments. Autonomous vehicle can decrease vehicle crashes because software installed in the vehicle instructs the control system of the autonomous vehicle rather than human, and Software makes less error compare to human beings. Automated Traffic Sign Detection and Recognition (ATSDR) is an important task for a safe driving by an autonomous vehicle. Many researchers have used various deep learning-based models for in real-time ATSDR. Here in the present review, we have studied various deep learning models used for in real-time ATSDR. Our study suggested that YOLO and SSD can detect the traffic sign in real time and are superior models for ATSDR as compared to other deep learning methods as CNN, R-CNN, Fast R-CNN and Faster RCNN.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"14 1","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89320206","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：