Pub Date : 2021-09-24DOI: 10.1109/ICSES52305.2021.9633854
M. L. Jatav, A. Datar, L. Malviya
The process of resource optimization enhances the capacity of device-to-device communication. The utility and diversity of device-to-device communication influence next-generation wireless communication. The sharing of resources in wireless combination treats as assets of communication. The limitation of assets is spectrum allocation and energy efficiency. The allocation process faces a problem of interference in different variants such as cochannel interference, intercell interference and some others. This paper proposed the constraints-based function for the optimization of energy and resource sharing. The proposed methods focus on the total users of a single-cell network and utilize all resources in the best selection mode. The pairing factors of D2D users and CU users satisfy the defined constraints and got optimal resources of energy and spectrum. The proposed algorithm simulated in MATLAB environments and set different parameters for the validation. The proposed optimization algorithm compares with two algorithms, particle swarm optimization and ant colony optimization.
{"title":"Optimization of Resource and Energy for D2D enable Communication System using Constraint's- based Function","authors":"M. L. Jatav, A. Datar, L. Malviya","doi":"10.1109/ICSES52305.2021.9633854","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633854","url":null,"abstract":"The process of resource optimization enhances the capacity of device-to-device communication. The utility and diversity of device-to-device communication influence next-generation wireless communication. The sharing of resources in wireless combination treats as assets of communication. The limitation of assets is spectrum allocation and energy efficiency. The allocation process faces a problem of interference in different variants such as cochannel interference, intercell interference and some others. This paper proposed the constraints-based function for the optimization of energy and resource sharing. The proposed methods focus on the total users of a single-cell network and utilize all resources in the best selection mode. The pairing factors of D2D users and CU users satisfy the defined constraints and got optimal resources of energy and spectrum. The proposed algorithm simulated in MATLAB environments and set different parameters for the validation. The proposed optimization algorithm compares with two algorithms, particle swarm optimization and ant colony optimization.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"46 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":"77326357","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/ICSES52305.2021.9633879
M. Bhagwat, G. Gupta, Asha Ambhaikar
Segmentation of images is a pre-requisite for all modern high efficiency image processing system. In order to perform this task, various application specific algorithms are designed and deployed by image processing experts. These systems work on a context-specific mode, wherein all segmentation outputs are restricted by context of images for which the system is trained. In order to deploy these systems to other domains, complex tuning and optimization operations are needed. This reduces applicability of these system models for real time use cases, where general purpose segmentation methods are needed. These use cases include but are not limited to, scene classification, satellite image classification, yield prediction, traffic detection, etc. Moreover, general purpose image segmentation models work effectively only under a pre-set types of application scenarios, and need to be constantly trained in order to improve their applicability. Retraining these systems increases computational costs, and requires large training and testing delays. In order to remove these drawbacks, in this text an incremental feedback learning mechanism with feature coupling is proposed. The proposed model uses a wide variety of image segmentation methods that analyze colour, texture & shape information; and map it with relevant image features. These features are traced along with segmentation quality metrics like peak signal to noise ratio (PSNR), figure of merit (FOM), minimum mean squared error (MMSE), and probabilistic random index (PRI) in order to evaluate the best segmentation algorithm. These features are classified using an ensemble classification model for selection of the most efficient segmentation method that maximizes PSNR, & PRI while minimizing MMSE. Parametric evaluation suggests that the proposed model is able to improve segmentation accuracy by 8%, and reduce false alarm rate by 15% when compared with standard automatic segmentation models.
{"title":"Incremental feedback learning mechanism for highly efficient automatic image segmentation with feature coupling","authors":"M. Bhagwat, G. Gupta, Asha Ambhaikar","doi":"10.1109/ICSES52305.2021.9633879","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633879","url":null,"abstract":"Segmentation of images is a pre-requisite for all modern high efficiency image processing system. In order to perform this task, various application specific algorithms are designed and deployed by image processing experts. These systems work on a context-specific mode, wherein all segmentation outputs are restricted by context of images for which the system is trained. In order to deploy these systems to other domains, complex tuning and optimization operations are needed. This reduces applicability of these system models for real time use cases, where general purpose segmentation methods are needed. These use cases include but are not limited to, scene classification, satellite image classification, yield prediction, traffic detection, etc. Moreover, general purpose image segmentation models work effectively only under a pre-set types of application scenarios, and need to be constantly trained in order to improve their applicability. Retraining these systems increases computational costs, and requires large training and testing delays. In order to remove these drawbacks, in this text an incremental feedback learning mechanism with feature coupling is proposed. The proposed model uses a wide variety of image segmentation methods that analyze colour, texture & shape information; and map it with relevant image features. These features are traced along with segmentation quality metrics like peak signal to noise ratio (PSNR), figure of merit (FOM), minimum mean squared error (MMSE), and probabilistic random index (PRI) in order to evaluate the best segmentation algorithm. These features are classified using an ensemble classification model for selection of the most efficient segmentation method that maximizes PSNR, & PRI while minimizing MMSE. Parametric evaluation suggests that the proposed model is able to improve segmentation accuracy by 8%, and reduce false alarm rate by 15% when compared with standard automatic segmentation models.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"121 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":"78431833","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/ICSES52305.2021.9633907
Mikhili Murali Krishna, M. Vadivel
The modern world is digitally advancing rapidly. However, the real world is analog which requires an adequate converter. The analysis of Such an Analog-to-digital modulator is designed and presented in this paper. The ΣΔ-modulator inherits an OTAas the main block. Where the modulator is a discrete-time switched capacitor integrator, Discrete-time low pass integrator and a double tail comparator as 1-bit ADC/quantizer obtain a first-order noise shaping modulator. The modulator implemented at 0.13um CMOS technology using 1.3v supply voltage. That obtained the SFDR of 72.58dB, THD of 0.489 and overall power dissipation (excluding D-flip flips) of the modulator is 1.147mw.
{"title":"Design and Analysis of First Order Sigma-Delta Modulator Based on Switched Capacitor Integrator (130nm)","authors":"Mikhili Murali Krishna, M. Vadivel","doi":"10.1109/ICSES52305.2021.9633907","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633907","url":null,"abstract":"The modern world is digitally advancing rapidly. However, the real world is analog which requires an adequate converter. The analysis of Such an Analog-to-digital modulator is designed and presented in this paper. The ΣΔ-modulator inherits an OTAas the main block. Where the modulator is a discrete-time switched capacitor integrator, Discrete-time low pass integrator and a double tail comparator as 1-bit ADC/quantizer obtain a first-order noise shaping modulator. The modulator implemented at 0.13um CMOS technology using 1.3v supply voltage. That obtained the SFDR of 72.58dB, THD of 0.489 and overall power dissipation (excluding D-flip flips) of the modulator is 1.147mw.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"75 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":"83806526","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/ICSES52305.2021.9633786
Sonal Shukla, Anand Sharma
In modern digital era, as the technological advancements are touching the new heights over internet, so is the crimes related to it. Education industry is no exception. Education sector is facing many cyber threats like application security, patching cadence and point to point security. It is important to understand the need of cyber security and what is at risk. In this paper, we bring light on existing scenario of cyber security in Education including the challenges and how we can make it as a priority, by implementing cyber security through machine learning techniques. Machine learning, subsets of artificial intelligence, for security in cyber world has become an avenger, due to its effectiveness. It provides great help to detect any threats in security, far better than any other software oriented ways, which is a great helps to security analysts.
{"title":"Cyber security using Machine Learning in Digital Education industry","authors":"Sonal Shukla, Anand Sharma","doi":"10.1109/ICSES52305.2021.9633786","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633786","url":null,"abstract":"In modern digital era, as the technological advancements are touching the new heights over internet, so is the crimes related to it. Education industry is no exception. Education sector is facing many cyber threats like application security, patching cadence and point to point security. It is important to understand the need of cyber security and what is at risk. In this paper, we bring light on existing scenario of cyber security in Education including the challenges and how we can make it as a priority, by implementing cyber security through machine learning techniques. Machine learning, subsets of artificial intelligence, for security in cyber world has become an avenger, due to its effectiveness. It provides great help to detect any threats in security, far better than any other software oriented ways, which is a great helps to security analysts.","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":"88398259","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/ICSES52305.2021.9633913
Ashutosh Kumar Singh, Sachin Sharma, K. Purohit, K. Nithin Kumar
The rapid growth of innovations in all fields of science has made our lives easier, but the increase in traffic accidents on roads over the years has cost many lives. Local governments are unable to control the global economic growth that is accompanied by an increase in the number of automobiles on the road. Controlling traffic has been a problem for more than a decade and will continue to be a major concern in the near future. Despite the fact that numerous researchers presented their research findings, the problem remains unresolved. This work focuses on a novel approach to automated real-time traffic control based on artificial intelligence concepts. The videos were shot at a four-lane traffic signal in Dehradun and are being tested for various models capable of detecting and counting all types of vehicles. This research focuses on the development of a model that can automatically control traffic based on the YOLO model and DMM to control the traffic light. The YOLO model is integrated in such a way that traffic-related obstacles are minimized. The videos are taken with a 13mega pixel Camera in three places: morning, afternoon and evening. The gray-scale image subtraction system is used. The highest accuracy of the vehicle count is at a mean visibility of 96.15% in the morning, while the lowest accuracy of the fog/low visibility in the night is 66.66% It is also used to control traffic light automatically with the intelligence transportation system.
{"title":"Artificial Intelligence based Framework for Effective Performance of Traffic Light Control System","authors":"Ashutosh Kumar Singh, Sachin Sharma, K. Purohit, K. Nithin Kumar","doi":"10.1109/ICSES52305.2021.9633913","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633913","url":null,"abstract":"The rapid growth of innovations in all fields of science has made our lives easier, but the increase in traffic accidents on roads over the years has cost many lives. Local governments are unable to control the global economic growth that is accompanied by an increase in the number of automobiles on the road. Controlling traffic has been a problem for more than a decade and will continue to be a major concern in the near future. Despite the fact that numerous researchers presented their research findings, the problem remains unresolved. This work focuses on a novel approach to automated real-time traffic control based on artificial intelligence concepts. The videos were shot at a four-lane traffic signal in Dehradun and are being tested for various models capable of detecting and counting all types of vehicles. This research focuses on the development of a model that can automatically control traffic based on the YOLO model and DMM to control the traffic light. The YOLO model is integrated in such a way that traffic-related obstacles are minimized. The videos are taken with a 13mega pixel Camera in three places: morning, afternoon and evening. The gray-scale image subtraction system is used. The highest accuracy of the vehicle count is at a mean visibility of 96.15% in the morning, while the lowest accuracy of the fog/low visibility in the night is 66.66% It is also used to control traffic light automatically with the intelligence transportation system.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"40 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":"86995914","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/ICSES52305.2021.9633958
D. Sudha, G. Amarnath, V. A
This manuscript presents an artificial-neural-network based programmable-neuron for implementation of analog circuits with multi-layer-perceptron. The proposed programmable-neuron can estimate linear, hyperbolic, tangent and sigmoid functions which are used to activate the analog circuits. With this, a neural-network-designer can utilize maximum number of controller-bits to select an activation-function kind with no actual change. For this neuron, 0.18-µm CMOS-technology is used for simulations and demonstrates a good estimation in peak error with ideal sigmoid and hyperbolic tangent function by 7.3% and 29.34% respectively. To assess the usefulness of the neuron, a Multi-Layer-Perceptron-neural-network (MLP-NN) is used. The MLP-NN is trained to carry out XOR-logic gate for handling signals in frequency-range from 3mHz to 60MHz. The correctness of the proposed-neuron is over 99.9%. These results shows that there is a decrease of 49% in power consumption with related to previous works.
{"title":"Utilizing Analog Circuits by Neural-Network based Multi-Layer-Perceptron","authors":"D. Sudha, G. Amarnath, V. A","doi":"10.1109/ICSES52305.2021.9633958","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633958","url":null,"abstract":"This manuscript presents an artificial-neural-network based programmable-neuron for implementation of analog circuits with multi-layer-perceptron. The proposed programmable-neuron can estimate linear, hyperbolic, tangent and sigmoid functions which are used to activate the analog circuits. With this, a neural-network-designer can utilize maximum number of controller-bits to select an activation-function kind with no actual change. For this neuron, 0.18-µm CMOS-technology is used for simulations and demonstrates a good estimation in peak error with ideal sigmoid and hyperbolic tangent function by 7.3% and 29.34% respectively. To assess the usefulness of the neuron, a Multi-Layer-Perceptron-neural-network (MLP-NN) is used. The MLP-NN is trained to carry out XOR-logic gate for handling signals in frequency-range from 3mHz to 60MHz. The correctness of the proposed-neuron is over 99.9%. These results shows that there is a decrease of 49% in power consumption with related to previous works.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"1 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":"77726859","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}
COVID-19 outbreak compelled people to stay at home due to complete lockdown in all the working areas. Immense use of World Wide Web and social media to exchange and share opinions, generated enormous web data to be utilized in the research work of the Natural Language Processing (NLP) field. Being a dominant side of NLP, Sentiment Analysis uses numerous tools to classify human sentiments as Positive (1), Negative (-1) and Neutral (0) so as to reach various conclusions. This research work focused on sentiment analysis of four datasets, web scraped from four different sources namely: Twitter, Facebook, Economic Times Headlines and news articles keyed by stock market. Seven contemporary and tremendously used sentiment analysis tools: Stanford, SVC, TextBlob, Henry, Loughran-McDonald, Logistic Regression and VADER are considered here to process four scraped datasets individually and analyses result in two ways: Facebook scraped data generates maximum overall positive sentiment score as 38.17% and VADER tool performs best among seven tools. VADER calculates overall positive sentiment score as 56.63%
{"title":"A Comparative Study of Sentiment Analysis Tools","authors":"Nabanita Das, Saloni Gupta, Srinjoy Das, Shuvam Yadav, Trishika Subramanian, Nairita Sarkar","doi":"10.1109/ICSES52305.2021.9633905","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633905","url":null,"abstract":"COVID-19 outbreak compelled people to stay at home due to complete lockdown in all the working areas. Immense use of World Wide Web and social media to exchange and share opinions, generated enormous web data to be utilized in the research work of the Natural Language Processing (NLP) field. Being a dominant side of NLP, Sentiment Analysis uses numerous tools to classify human sentiments as Positive (1), Negative (-1) and Neutral (0) so as to reach various conclusions. This research work focused on sentiment analysis of four datasets, web scraped from four different sources namely: Twitter, Facebook, Economic Times Headlines and news articles keyed by stock market. Seven contemporary and tremendously used sentiment analysis tools: Stanford, SVC, TextBlob, Henry, Loughran-McDonald, Logistic Regression and VADER are considered here to process four scraped datasets individually and analyses result in two ways: Facebook scraped data generates maximum overall positive sentiment score as 38.17% and VADER tool performs best among seven tools. VADER calculates overall positive sentiment score as 56.63%","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"37 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":"74180273","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/ICSES52305.2021.9633969
D. Shubhangi, Preeti
Nowadays the widening of illegal activity in the social media, intelligent machinery to detect harmful web pages is required. URL analysis is the best method for detecting phishing and other assaults. Venomous internet robots create fraud posts and start the communication by impersonating a follower or generating several fraud social accounts that are used for venomous purposes. Furthermore, hostile internet robots use shortened harmful URLs in tweets to send queries from online social networking users to venomous servers. As a result, distinguishing harmful internet robots from legitimate users is one of the Twitter network's and instagram's utmost critical responsibilities. To identify harmful internet robots, hyperlink-based data (such as Hyperlink redirect, number of shared hyperlinks, and garbage material in URLs) takes small amount of duration to extract than social chart-based factors (which repeat on the social communication of peoples). A Learning Automata algorithm is used to find the real users of the social media network.
{"title":"Learning Automata with Hyperlink Features for Detecting Venomous Social Trolls on the Social Media Platform","authors":"D. Shubhangi, Preeti","doi":"10.1109/ICSES52305.2021.9633969","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633969","url":null,"abstract":"Nowadays the widening of illegal activity in the social media, intelligent machinery to detect harmful web pages is required. URL analysis is the best method for detecting phishing and other assaults. Venomous internet robots create fraud posts and start the communication by impersonating a follower or generating several fraud social accounts that are used for venomous purposes. Furthermore, hostile internet robots use shortened harmful URLs in tweets to send queries from online social networking users to venomous servers. As a result, distinguishing harmful internet robots from legitimate users is one of the Twitter network's and instagram's utmost critical responsibilities. To identify harmful internet robots, hyperlink-based data (such as Hyperlink redirect, number of shared hyperlinks, and garbage material in URLs) takes small amount of duration to extract than social chart-based factors (which repeat on the social communication of peoples). A Learning Automata algorithm is used to find the real users of the social media network.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"40 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":"78811205","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/ICSES52305.2021.9633787
Monish Murale, N. Devi, AR Guru Gokul, P. Leela Rani, S. NavishVardanaa
The major purpose of the study topic is to use data science to anticipate the future effect of COVID-19 using existing data. The goal of this research is to use data science and analytics to generate precise forecasts of the number of substantiations and deaths. LSTM, GRUs, and Prophet are the major models created and tested for the solution. An LSTM model is a type of Recurrent Neural Network that is used to forecast datasets with increasingly changing patterns. Gated recurrent units only has two gateways: reboot and update. The prophet is best suited for forecasting assignments involving observation swith at least a year of history. The various models discussed above were used to the covid-19 data set to forecast the number of positive cases, active cases, and deaths associated with covid-19. We trained the model using data from April and May 2021 to demonstrate a comparison between the observed and expected number of positive events. To assume the future happing of COVID-19 by applying models which are in use, so that we will be able to calculate the impact of the disease's potential spread throughout the human being, preparing our selves to make proper planning and idea to prevent further transmission and equip health systems to manage the disease properly and battle the worldwide pandemic.
{"title":"Forecasting the potential influence of Covid-19 using Data Science and Analytics","authors":"Monish Murale, N. Devi, AR Guru Gokul, P. Leela Rani, S. NavishVardanaa","doi":"10.1109/ICSES52305.2021.9633787","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633787","url":null,"abstract":"The major purpose of the study topic is to use data science to anticipate the future effect of COVID-19 using existing data. The goal of this research is to use data science and analytics to generate precise forecasts of the number of substantiations and deaths. LSTM, GRUs, and Prophet are the major models created and tested for the solution. An LSTM model is a type of Recurrent Neural Network that is used to forecast datasets with increasingly changing patterns. Gated recurrent units only has two gateways: reboot and update. The prophet is best suited for forecasting assignments involving observation swith at least a year of history. The various models discussed above were used to the covid-19 data set to forecast the number of positive cases, active cases, and deaths associated with covid-19. We trained the model using data from April and May 2021 to demonstrate a comparison between the observed and expected number of positive events. To assume the future happing of COVID-19 by applying models which are in use, so that we will be able to calculate the impact of the disease's potential spread throughout the human being, preparing our selves to make proper planning and idea to prevent further transmission and equip health systems to manage the disease properly and battle the worldwide pandemic.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"23 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":"73145180","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/ICSES52305.2021.9633866
P. Sivagami, D. Jamunarani, P. Abirami, R. Harikrishnan, M. Pushpavalli, V. Geetha
In power generation the main source which disports a key role is the fossil fuel. The preeminent composition of it is carbon. It requires millions of years to form and it cannot form in short duration. That is, they are non-renewable, once exhausted it cannot be retrieved back. In order to supplant the place of conventional energy sources the world looks for other resources such as renewable energy. Renewable energy sources help in meeting the energy requirement of the growing population along with depleting sources. There are numerous inexhaustible resources available. Among them PV, Wind is gaining importance and its yield helps in satisfying the needs of energy requirement of growing population and industries. Renewable energy power production relies on the substantial factor such as temperature, wind speed, intensity of light etc. These factors affect the performance of energy conversion in renewable energy sources. In Solar photovoltaic panel, soiling decreases the quantum rays reaching the panel. It affects the power yield from PV. Soiling- the accumulation of dust over the PV panels influenced by factors such as orientation, tilt angle, wind velocity, ambient temperature, site characteristics, the texture of the PV panel surface. This paper deliberates about soiling factor influencing performance of the Photovoltaic panel and the methodologies to reduce the effect of soiling.
{"title":"Review on Soiling Implications and Cleaning Methodology for Photovoltaic Panels","authors":"P. Sivagami, D. Jamunarani, P. Abirami, R. Harikrishnan, M. Pushpavalli, V. Geetha","doi":"10.1109/ICSES52305.2021.9633866","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633866","url":null,"abstract":"In power generation the main source which disports a key role is the fossil fuel. The preeminent composition of it is carbon. It requires millions of years to form and it cannot form in short duration. That is, they are non-renewable, once exhausted it cannot be retrieved back. In order to supplant the place of conventional energy sources the world looks for other resources such as renewable energy. Renewable energy sources help in meeting the energy requirement of the growing population along with depleting sources. There are numerous inexhaustible resources available. Among them PV, Wind is gaining importance and its yield helps in satisfying the needs of energy requirement of growing population and industries. Renewable energy power production relies on the substantial factor such as temperature, wind speed, intensity of light etc. These factors affect the performance of energy conversion in renewable energy sources. In Solar photovoltaic panel, soiling decreases the quantum rays reaching the panel. It affects the power yield from PV. Soiling- the accumulation of dust over the PV panels influenced by factors such as orientation, tilt angle, wind velocity, ambient temperature, site characteristics, the texture of the PV panel surface. This paper deliberates about soiling factor influencing performance of the Photovoltaic panel and the methodologies to reduce the effect of soiling.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"29 1","pages":"1-10"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75356384","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：