Pub Date : 2022-10-07DOI: 10.1109/GCAT55367.2022.9971940
Alka Mishra, S. Bhusnur
Heart problems are increasing day by day and Electrocardiogram (ECG) signal is extremely important to evaluate cardiac problems. A common problem in ECG interpretation is noise removal because real ECG signals are corrupted by various types of noises and artifacts with different frequencies. Among all the noises the power line interference is the most significant and can strongly affect the ECG signal. This paper presents second order FIR Notch filter to remove power line interference which is occurred with frequency of 50Hz in India, followed by a novel parametric representation of real ECG signals. First, Notch filter is designed here for two cases first one is filter with two zeros, and in second case adding two poles at different radius but in same frequency as those of zeros, but the radius is less then unity in all the cases to consider the stability of filter. The effect of poles with their variables radius (0.8o to 0.99) is also analyzed at the output with SNR and has considered best result in term of stability, magnitude and phase response. Second part includes Signal acquisition, Control point detection, and develops a spline model of real ECG signal.
{"title":"A New Adaptive Modeling and Denoising of Real ECG signal","authors":"Alka Mishra, S. Bhusnur","doi":"10.1109/GCAT55367.2022.9971940","DOIUrl":"https://doi.org/10.1109/GCAT55367.2022.9971940","url":null,"abstract":"Heart problems are increasing day by day and Electrocardiogram (ECG) signal is extremely important to evaluate cardiac problems. A common problem in ECG interpretation is noise removal because real ECG signals are corrupted by various types of noises and artifacts with different frequencies. Among all the noises the power line interference is the most significant and can strongly affect the ECG signal. This paper presents second order FIR Notch filter to remove power line interference which is occurred with frequency of 50Hz in India, followed by a novel parametric representation of real ECG signals. First, Notch filter is designed here for two cases first one is filter with two zeros, and in second case adding two poles at different radius but in same frequency as those of zeros, but the radius is less then unity in all the cases to consider the stability of filter. The effect of poles with their variables radius (0.8o to 0.99) is also analyzed at the output with SNR and has considered best result in term of stability, magnitude and phase response. Second part includes Signal acquisition, Control point detection, and develops a spline model of real ECG signal.","PeriodicalId":133597,"journal":{"name":"2022 IEEE 3rd Global Conference for Advancement in Technology (GCAT)","volume":"229 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123042078","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 : 2022-10-07DOI: 10.1109/GCAT55367.2022.9971814
N. Panda, M. Supriya
The Internet of Things (IoT) is a network of low-power, low-latency devices that are becoming smart day by day. The market sees a tremendous rise in the demand for IoT devices for various applications. The nature of the smart devices utilized for IoT is confined. As a result, Low Power Lossy Networks (LLN) is effective for extending and smoothing connection. RPL is a distance-vector IPv6 routing protocol that is used in LLN to provide compatibility. It produces a DODAG (Destination Oriented Directed Acyclic Graph) for data routing between client and server nodes within the network. Clients can provide the best path to the sink node using two Objective Functions (OFs): Objective Function Zero (OF0) and Minimum Rank Hysteresis Objective Function (MRHOF) in RPL. In this paper, blackhole attack is analysed in two different types of LLNs. The performance is examined under static and mobile environments. The objective functions is analysed w.r.t performance parameters namely Packet delivery ratio (PDR), Packet loss ratio (PLR), average latency, network overhead and total energy consumption with and without blackhole attack. A maximum PDR of 45.59% is achieved in an attack scenario. The lowest latency of 0.8 seconds is achieved under mobility and attacked network scenario. It is observed from the results that PDR is increasing with the networks and packet loss is reducing.
{"title":"Blackhole Attack Impact Analysis on Low Power Lossy Networks","authors":"N. Panda, M. Supriya","doi":"10.1109/GCAT55367.2022.9971814","DOIUrl":"https://doi.org/10.1109/GCAT55367.2022.9971814","url":null,"abstract":"The Internet of Things (IoT) is a network of low-power, low-latency devices that are becoming smart day by day. The market sees a tremendous rise in the demand for IoT devices for various applications. The nature of the smart devices utilized for IoT is confined. As a result, Low Power Lossy Networks (LLN) is effective for extending and smoothing connection. RPL is a distance-vector IPv6 routing protocol that is used in LLN to provide compatibility. It produces a DODAG (Destination Oriented Directed Acyclic Graph) for data routing between client and server nodes within the network. Clients can provide the best path to the sink node using two Objective Functions (OFs): Objective Function Zero (OF0) and Minimum Rank Hysteresis Objective Function (MRHOF) in RPL. In this paper, blackhole attack is analysed in two different types of LLNs. The performance is examined under static and mobile environments. The objective functions is analysed w.r.t performance parameters namely Packet delivery ratio (PDR), Packet loss ratio (PLR), average latency, network overhead and total energy consumption with and without blackhole attack. A maximum PDR of 45.59% is achieved in an attack scenario. The lowest latency of 0.8 seconds is achieved under mobility and attacked network scenario. It is observed from the results that PDR is increasing with the networks and packet loss is reducing.","PeriodicalId":133597,"journal":{"name":"2022 IEEE 3rd Global Conference for Advancement in Technology (GCAT)","volume":"153 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123087144","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 : 2022-10-07DOI: 10.1109/GCAT55367.2022.9971923
S. Yadav, K. Yadav
This paper concern on Firefly (FF) Algorithm for enhancing the power quality of three phase hybrid energy storage (HES) system integrated unified power quality conditioner (UPQC). Models are created for RES such PV arrays, BESS, and wind energy with the goal of supplying constant electricity. In general, the BESS can meet total load demand even when the PV array and wind turbine are not providing energy, which improves the stability of the distribution power system. The UPQC model with shunt and series active filter compensator is to reduce the grid's power quality problems and the harmonics which injected by non-linear loads. Furthermore, in the event of long voltage disruptions, PV, wind, and BESS integrated UPQC can manage power quality issues. While the load is protected from grid-related power quality problems by the series compensator, the shunt compensator of UPQC extracts power from hybrid energy systems. Therefore, the goal of this research is to create a FOPI controller with iso-damping properties in order to regulating the voltage of the DC link at the desired level. Particularly, the gain of PI controller (Kp, Ki, $lambda$) are ideally tuned by a algorithm known Firefly Algorithm. In order to analyze the performance during voltage sag/swell, concerning the total harmonic distortion, the proposed method was implemented in MATLAB/Simulink. It is capable of producing competitive and promising results.
{"title":"Firefly Algorithm in FOPI Controller for Improving Power Quality of Three-phase HES System Integrated UPQC","authors":"S. Yadav, K. Yadav","doi":"10.1109/GCAT55367.2022.9971923","DOIUrl":"https://doi.org/10.1109/GCAT55367.2022.9971923","url":null,"abstract":"This paper concern on Firefly (FF) Algorithm for enhancing the power quality of three phase hybrid energy storage (HES) system integrated unified power quality conditioner (UPQC). Models are created for RES such PV arrays, BESS, and wind energy with the goal of supplying constant electricity. In general, the BESS can meet total load demand even when the PV array and wind turbine are not providing energy, which improves the stability of the distribution power system. The UPQC model with shunt and series active filter compensator is to reduce the grid's power quality problems and the harmonics which injected by non-linear loads. Furthermore, in the event of long voltage disruptions, PV, wind, and BESS integrated UPQC can manage power quality issues. While the load is protected from grid-related power quality problems by the series compensator, the shunt compensator of UPQC extracts power from hybrid energy systems. Therefore, the goal of this research is to create a FOPI controller with iso-damping properties in order to regulating the voltage of the DC link at the desired level. Particularly, the gain of PI controller (Kp, Ki, $lambda$) are ideally tuned by a algorithm known Firefly Algorithm. In order to analyze the performance during voltage sag/swell, concerning the total harmonic distortion, the proposed method was implemented in MATLAB/Simulink. It is capable of producing competitive and promising results.","PeriodicalId":133597,"journal":{"name":"2022 IEEE 3rd Global Conference for Advancement in Technology (GCAT)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127725346","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 : 2022-10-07DOI: 10.1109/GCAT55367.2022.9971860
Arnav Agarwal, Sunakshi Singh, V. Chaurasiya
Entity resolution (ER) is the task of identifying data instances referring to the same real-word entity. In this work, we study two major works that propose a deep-learning based solution for ER, namely DeepER and DeepMatcher. We re-evaluate their published results and benchmark it with the re-evaluated results of Magellan, an end-to-end entity resolution framework that uses classical machine learning. We then try to answer some questions mentioned in the sections below with the help of these results. We also report several interesting observations noted while reproducing these works. We highlight important but missing knowledge pertaining to generation of training and test sets. This information heavily influences the quality of evaluation results and is necessary to produce accurate authentic results. We conclude by presenting a study on ease of setting-up and rebuilding these solutions as an end-user.
{"title":"Assessing Entity Resolution techniques based on deep learning","authors":"Arnav Agarwal, Sunakshi Singh, V. Chaurasiya","doi":"10.1109/GCAT55367.2022.9971860","DOIUrl":"https://doi.org/10.1109/GCAT55367.2022.9971860","url":null,"abstract":"Entity resolution (ER) is the task of identifying data instances referring to the same real-word entity. In this work, we study two major works that propose a deep-learning based solution for ER, namely DeepER and DeepMatcher. We re-evaluate their published results and benchmark it with the re-evaluated results of Magellan, an end-to-end entity resolution framework that uses classical machine learning. We then try to answer some questions mentioned in the sections below with the help of these results. We also report several interesting observations noted while reproducing these works. We highlight important but missing knowledge pertaining to generation of training and test sets. This information heavily influences the quality of evaluation results and is necessary to produce accurate authentic results. We conclude by presenting a study on ease of setting-up and rebuilding these solutions as an end-user.","PeriodicalId":133597,"journal":{"name":"2022 IEEE 3rd Global Conference for Advancement in Technology (GCAT)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121238221","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 : 2022-10-07DOI: 10.1109/GCAT55367.2022.9972020
T. Likitha, Venkatanarasimharao Medam, G. Ranjani
In the motor control unit, the precision and accuracy are everything. In this paper we propose an algorithm as a part of the implementation of field-oriented control (FOC) of the permanent magnet synchronous motor (PMSM). Though FOC is more computationally complex, it can drive more advantages like improved efficiency and full torque control. The proposed algorithm synchronizes the Analog to digital converter (ADC) and Flex timer module (FTM) such that the two-phase currents can be measured simultaneously in the middle of the Pulse-width modulator (PWM) pulse only when the bottom semiconductors of three-phase inverters are turned on. Regardless of ADC being able to measure precisely there is chance for obtaining wrong data. So, the instance for current sensing is more important. These timing implementations are supported by the micro controller peripherals. The Microcontroller (S32K144-EVB) is very versatile and supports the interconnectivity between different modules (ADC-PDB-TRGMUX-FTM). Their flexible interconnectivity helps in simplifying these complicated timing designs.
{"title":"ADC-PWM Synchronization for Motor Control Unit Development","authors":"T. Likitha, Venkatanarasimharao Medam, G. Ranjani","doi":"10.1109/GCAT55367.2022.9972020","DOIUrl":"https://doi.org/10.1109/GCAT55367.2022.9972020","url":null,"abstract":"In the motor control unit, the precision and accuracy are everything. In this paper we propose an algorithm as a part of the implementation of field-oriented control (FOC) of the permanent magnet synchronous motor (PMSM). Though FOC is more computationally complex, it can drive more advantages like improved efficiency and full torque control. The proposed algorithm synchronizes the Analog to digital converter (ADC) and Flex timer module (FTM) such that the two-phase currents can be measured simultaneously in the middle of the Pulse-width modulator (PWM) pulse only when the bottom semiconductors of three-phase inverters are turned on. Regardless of ADC being able to measure precisely there is chance for obtaining wrong data. So, the instance for current sensing is more important. These timing implementations are supported by the micro controller peripherals. The Microcontroller (S32K144-EVB) is very versatile and supports the interconnectivity between different modules (ADC-PDB-TRGMUX-FTM). Their flexible interconnectivity helps in simplifying these complicated timing designs.","PeriodicalId":133597,"journal":{"name":"2022 IEEE 3rd Global Conference for Advancement in Technology (GCAT)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121299747","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 : 2022-10-07DOI: 10.1109/GCAT55367.2022.9971999
P. Divya, Reenu Sara George, G. Madhusudhan, S. Padmasree
Endpoint Security is an important layer in cyber security and it is one of the first places organizations look to secure their enterprise network. Proactively and iteratively monitoring endpoints for threats and Indicators of Compromise (IOC), helps security analysts to detect malware/attacks and to respond to incidents quickly. An Indicator of Compromise (IOC) refers to data that indicates that a system may have been infiltrated by a cyber-threat. Cyber security agencies send regular cyber-alerts to various organizations nation-wide and provide IOC list in the form of hashes, IPs, URLs, domains, yara rules, etc. for monitoring the presence of IOCs in their respective network. Periodic auditing of endpoints for security compliance is also a challenging and time-consuming task for every organization. To overcome these challenges, a solution based on client-server architecture is proposed in organizational network using open-source tools named Osquery, Fleet, Filebeat and Graylog. Using these tools, endpoints can be monitored for IOCs on demand or on scheduled manner from a central server. Yara based scan can also be performed efficiently in endpoints to monitor for IOCs using this architecture. In addition to IOC monitoring, this paper explains verifying compliance of endpoints with the organization's security policy using the proposed setup. Impact on performance of the endpoints during query execution was also analyzed. This solution will contribute in strengthening the endpoint security which in turn enhances overall cyber-security posture of the organization.
端点安全是网络安全的重要一层，也是组织保护其企业网络安全的首要场所之一。主动和迭代地监控端点的威胁和危害指标(IOC)，有助于安全分析师检测恶意软件/攻击并快速响应事件。IOC (An Indicator of Compromise)是指表明系统可能已被网络威胁渗透的数据。网络安全机构定期向全国各组织发送网络警报，并以哈希、ip、url、域名、雅拉规则等形式提供IOC列表，监测各自网络中IOC的存在情况。对每个组织来说，定期审计端点的安全遵从性也是一项具有挑战性且耗时的任务。为了克服这些挑战，在组织网络中提出了一种基于客户端-服务器架构的解决方案，使用开源工具Osquery、Fleet、Filebeat和Graylog。使用这些工具，可以从中央服务器按需或按计划方式监视端点的ioc。基于Yara的扫描也可以在端点上有效地执行，以监视使用该体系结构的ioc。除了IOC监视之外，本文还解释了如何使用建议的设置验证端点是否符合组织的安全策略。还分析了查询执行期间端点对性能的影响。该解决方案将有助于加强端点安全性，从而提高组织的整体网络安全状况。
{"title":"Organization-wide IOC Monitoring and Security Compliance in Endpoints using Open Source Tools","authors":"P. Divya, Reenu Sara George, G. Madhusudhan, S. Padmasree","doi":"10.1109/GCAT55367.2022.9971999","DOIUrl":"https://doi.org/10.1109/GCAT55367.2022.9971999","url":null,"abstract":"Endpoint Security is an important layer in cyber security and it is one of the first places organizations look to secure their enterprise network. Proactively and iteratively monitoring endpoints for threats and Indicators of Compromise (IOC), helps security analysts to detect malware/attacks and to respond to incidents quickly. An Indicator of Compromise (IOC) refers to data that indicates that a system may have been infiltrated by a cyber-threat. Cyber security agencies send regular cyber-alerts to various organizations nation-wide and provide IOC list in the form of hashes, IPs, URLs, domains, yara rules, etc. for monitoring the presence of IOCs in their respective network. Periodic auditing of endpoints for security compliance is also a challenging and time-consuming task for every organization. To overcome these challenges, a solution based on client-server architecture is proposed in organizational network using open-source tools named Osquery, Fleet, Filebeat and Graylog. Using these tools, endpoints can be monitored for IOCs on demand or on scheduled manner from a central server. Yara based scan can also be performed efficiently in endpoints to monitor for IOCs using this architecture. In addition to IOC monitoring, this paper explains verifying compliance of endpoints with the organization's security policy using the proposed setup. Impact on performance of the endpoints during query execution was also analyzed. This solution will contribute in strengthening the endpoint security which in turn enhances overall cyber-security posture of the organization.","PeriodicalId":133597,"journal":{"name":"2022 IEEE 3rd Global Conference for Advancement in Technology (GCAT)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116412697","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 : 2022-10-07DOI: 10.1109/GCAT55367.2022.9972033
Azra Nazir, Roohie Naaz, Shaima Qureshi, Nidha Nazir
COVID-19, caused by SARS - COV 2 virus, has afflicted approximately 62.3 million people worldwide, with 1.46 million deaths around the globe by the end of November 2020. In most cases, the cause of death has been due to acute pneumonia. However, there have been cases where patients developed pulmonary arterial hypertension leading to sudden death. The virus can affect the heart in previously healthy individuals also. The severe inflammatory response in the body can affect arteries exaggerating cardiac damage. Studies recommend monitoring the cardiac conditions of POST COVID-19 patients. This paper employs a convolutional neural network (CNN) model to learn features from the standard axial slice of high-resolution chest CT. The CNN captures variation in the pulmonary artery region to determine whether a patient is at high risk of developing pulmonary arterial hypertension or not. With 86.1 % classification accuracy, the model shows a promising future for studies related to POST COVID risk analysis of heart complications.
{"title":"HRCT chest analysis for detection of pulmonary arterial hypertension in COVID-19 patients using convolutional neural networks","authors":"Azra Nazir, Roohie Naaz, Shaima Qureshi, Nidha Nazir","doi":"10.1109/GCAT55367.2022.9972033","DOIUrl":"https://doi.org/10.1109/GCAT55367.2022.9972033","url":null,"abstract":"COVID-19, caused by SARS - COV 2 virus, has afflicted approximately 62.3 million people worldwide, with 1.46 million deaths around the globe by the end of November 2020. In most cases, the cause of death has been due to acute pneumonia. However, there have been cases where patients developed pulmonary arterial hypertension leading to sudden death. The virus can affect the heart in previously healthy individuals also. The severe inflammatory response in the body can affect arteries exaggerating cardiac damage. Studies recommend monitoring the cardiac conditions of POST COVID-19 patients. This paper employs a convolutional neural network (CNN) model to learn features from the standard axial slice of high-resolution chest CT. The CNN captures variation in the pulmonary artery region to determine whether a patient is at high risk of developing pulmonary arterial hypertension or not. With 86.1 % classification accuracy, the model shows a promising future for studies related to POST COVID risk analysis of heart complications.","PeriodicalId":133597,"journal":{"name":"2022 IEEE 3rd Global Conference for Advancement in Technology (GCAT)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117175485","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 : 2022-10-07DOI: 10.1109/GCAT55367.2022.9971997
Soorya Narayanan, Rahul Krishnan
Sorting by prefix block interchange is a combina-torial optimization problem having its origin in comparative genomics. The problem is to sort a given permutation with the minimum number of prefix block interchanges. A prefix block interchange is a rearrangement operation that interchanges a block of permutation from the prefix with another disjoint block. In comparative genomics, a permutation is used to model the arrangement of genes in genomes, and a rearrangement operation like prefix block interchanges models global genomic mutations. The problem of sorting permutations by prefix block interchanges is used to compute the evolutionary distance between related species. The computational complexity of the problem is unknown and some approximation algorithms are existent. In this article, we perform an empirical study of the 2-approximation algorithm for sorting by prefix block interchange problem, designed by Antony Labarre.
{"title":"Empirical Evaluation of Approximation Algorithm for Sorting by Prefix-block Interchanges","authors":"Soorya Narayanan, Rahul Krishnan","doi":"10.1109/GCAT55367.2022.9971997","DOIUrl":"https://doi.org/10.1109/GCAT55367.2022.9971997","url":null,"abstract":"Sorting by prefix block interchange is a combina-torial optimization problem having its origin in comparative genomics. The problem is to sort a given permutation with the minimum number of prefix block interchanges. A prefix block interchange is a rearrangement operation that interchanges a block of permutation from the prefix with another disjoint block. In comparative genomics, a permutation is used to model the arrangement of genes in genomes, and a rearrangement operation like prefix block interchanges models global genomic mutations. The problem of sorting permutations by prefix block interchanges is used to compute the evolutionary distance between related species. The computational complexity of the problem is unknown and some approximation algorithms are existent. In this article, we perform an empirical study of the 2-approximation algorithm for sorting by prefix block interchange problem, designed by Antony Labarre.","PeriodicalId":133597,"journal":{"name":"2022 IEEE 3rd Global Conference for Advancement in Technology (GCAT)","volume":"3 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116664744","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 : 2022-10-07DOI: 10.1109/GCAT55367.2022.9972013
Simren Dubey, Nisarg Patil, P. Thakur, Harshil T. Kanakia
Predicting the stock market is one of the intriguing and real life problem statements. In the current virtual world, social media like Twitter is the perfect representation of public opinion. Using the information available on these platforms, we can create very genuine and helpful insights about stocks. This paper explains different methods of interactively learning the complex market and its trends. We have used three different models for this paper which are Support Vector Regression, Long Short Term Memory and Random Forest and have also performed sentiment analysis on tweets related to Apple stock and compared the final results with Amazon and Tesla results. The model with the least error is the ideal and the most preferred method for prediction. We have combined Twitter's polarity data with Yahoo Finance's stock data for an efficient input. The results have given us a clear polarity view, both a statistical, and a graphical view.
{"title":"Stock Market Prediction Using Yahoo finance and Twitter Polarity","authors":"Simren Dubey, Nisarg Patil, P. Thakur, Harshil T. Kanakia","doi":"10.1109/GCAT55367.2022.9972013","DOIUrl":"https://doi.org/10.1109/GCAT55367.2022.9972013","url":null,"abstract":"Predicting the stock market is one of the intriguing and real life problem statements. In the current virtual world, social media like Twitter is the perfect representation of public opinion. Using the information available on these platforms, we can create very genuine and helpful insights about stocks. This paper explains different methods of interactively learning the complex market and its trends. We have used three different models for this paper which are Support Vector Regression, Long Short Term Memory and Random Forest and have also performed sentiment analysis on tweets related to Apple stock and compared the final results with Amazon and Tesla results. The model with the least error is the ideal and the most preferred method for prediction. We have combined Twitter's polarity data with Yahoo Finance's stock data for an efficient input. The results have given us a clear polarity view, both a statistical, and a graphical view.","PeriodicalId":133597,"journal":{"name":"2022 IEEE 3rd Global Conference for Advancement in Technology (GCAT)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115509592","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 : 2022-10-07DOI: 10.1109/GCAT55367.2022.9971819
K. Chayashree, U. K. Harshitha, M. Sayeed, L. P. Nagaditya, Sumalatha Aradhya, K. R. S. Navada
Blinks are the movements that happen involuntarily and can be used in many applications such as wearable computing, Human-Computer interaction, etc. Blinks can be considered as one of the changes that happen visibly when there are any abnormalities in our eyes. These abnormalities of blinks can be used for the early detection of eye diseases. Here, we are considering it as one of the major parameters in the detection of dry eyes. This can be achieved using cameras and sensors. To achieve high accuracy results using a camera, the resolution must be high which results in huge amounts of data. On the other side, sensors are less expensive as well as the data generated from sensors can be easily processed. Sensors are comparatively reliable and superior to other methods.
{"title":"Early Detection of Dry Eyes Through Blink","authors":"K. Chayashree, U. K. Harshitha, M. Sayeed, L. P. Nagaditya, Sumalatha Aradhya, K. R. S. Navada","doi":"10.1109/GCAT55367.2022.9971819","DOIUrl":"https://doi.org/10.1109/GCAT55367.2022.9971819","url":null,"abstract":"Blinks are the movements that happen involuntarily and can be used in many applications such as wearable computing, Human-Computer interaction, etc. Blinks can be considered as one of the changes that happen visibly when there are any abnormalities in our eyes. These abnormalities of blinks can be used for the early detection of eye diseases. Here, we are considering it as one of the major parameters in the detection of dry eyes. This can be achieved using cameras and sensors. To achieve high accuracy results using a camera, the resolution must be high which results in huge amounts of data. On the other side, sensors are less expensive as well as the data generated from sensors can be easily processed. Sensors are comparatively reliable and superior to other methods.","PeriodicalId":133597,"journal":{"name":"2022 IEEE 3rd Global Conference for Advancement in Technology (GCAT)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125397419","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：