Pub Date : 2022-07-21DOI: 10.1109/ICICCSP53532.2022.9862368
Rebba Prashanth Kumar, Sangineni Siri Vandana, Dushetti Tejaswi, K. Charan, Ravichander Janapati, Usha Desai
Brain-Computer-Interface (BCI) is an exceedingly growing field of research where individual communicates to the computer, without physical connection. The natural responses to visual stimulation at a particular frequency of EEG are characterized as Steady-State Visually Evoked Potential (SSVEP) signals. Efficient classification of EEG signals is an important phase in BCI. In this paper, a method is anticipated for classification of SSVEP signals in which the standard dataset and Neural Network (NN) classifier is applied. The improved classification accuracy of 90 % is achieved using the proposed method. This methodology is useful in BCI applications such as assisting people who are suffering from neurodegenerative problems; Amyotrophic Lateral Sclerosis (ALS) for automatic wheelchair navigation-based multimedia applications, etc.
{"title":"Classification of SSVEP Signals using Neural Networks for BCI Applications","authors":"Rebba Prashanth Kumar, Sangineni Siri Vandana, Dushetti Tejaswi, K. Charan, Ravichander Janapati, Usha Desai","doi":"10.1109/ICICCSP53532.2022.9862368","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862368","url":null,"abstract":"Brain-Computer-Interface (BCI) is an exceedingly growing field of research where individual communicates to the computer, without physical connection. The natural responses to visual stimulation at a particular frequency of EEG are characterized as Steady-State Visually Evoked Potential (SSVEP) signals. Efficient classification of EEG signals is an important phase in BCI. In this paper, a method is anticipated for classification of SSVEP signals in which the standard dataset and Neural Network (NN) classifier is applied. The improved classification accuracy of 90 % is achieved using the proposed method. This methodology is useful in BCI applications such as assisting people who are suffering from neurodegenerative problems; Amyotrophic Lateral Sclerosis (ALS) for automatic wheelchair navigation-based multimedia applications, etc.","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129807367","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-21DOI: 10.1109/ICICCSP53532.2022.9862426
Lalmalsawmi, P. Biswas
In this paper, the analysis and simulations of a Full-Bridge DC-DC Converter and a Boost DC-DC Converter with Resonant Circuit for Plug-in Hybrid Electric Vehicles (PHEVs) are presented. Simulations are carried out using MATLAB-SIMULINK software and the results show that both the converters are able to boost the input voltage of 220V to an output voltage of 440V, and 480V respectively, which is required to control the motor. The outputs of these converters are then applied to a 3-phase 180° mode voltage source inverter (VSI) fed permanent magnet synchronous motor (PMSM). The converters, which are connected to a 3-phase 180° mode VSI fed PMSM, are also simulated and presented in this paper. The input ripples of the converters are reduced by connecting the inductor in series with the input DC source. The output voltage ripples are also removed/reduced by connecting a capacitor-based filter at the output side of the converter. MATLAB 2018b is used for the simulation.
{"title":"Full-Bridge DC-DC Converter and Boost DC-DC Converter with Resonant Circuit For Plug-in Hybrid Electric Vehicles","authors":"Lalmalsawmi, P. Biswas","doi":"10.1109/ICICCSP53532.2022.9862426","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862426","url":null,"abstract":"In this paper, the analysis and simulations of a Full-Bridge DC-DC Converter and a Boost DC-DC Converter with Resonant Circuit for Plug-in Hybrid Electric Vehicles (PHEVs) are presented. Simulations are carried out using MATLAB-SIMULINK software and the results show that both the converters are able to boost the input voltage of 220V to an output voltage of 440V, and 480V respectively, which is required to control the motor. The outputs of these converters are then applied to a 3-phase 180° mode voltage source inverter (VSI) fed permanent magnet synchronous motor (PMSM). The converters, which are connected to a 3-phase 180° mode VSI fed PMSM, are also simulated and presented in this paper. The input ripples of the converters are reduced by connecting the inductor in series with the input DC source. The output voltage ripples are also removed/reduced by connecting a capacitor-based filter at the output side of the converter. MATLAB 2018b is used for the simulation.","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130007457","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-21DOI: 10.1109/ICICCSP53532.2022.9862332
B. Prusty, Kishore Bingi, Neeraj Gupta
It is challenging to approximate multimodal distributions of probabilistic load flow (PLF) result variables stemming from discrete and non-standard continuous input random variables (RVs). The Gaussian mixture model (GMM) approximates the probability distribution of the above input RVs as a “K” weighted sum of Gaussian distributions. The expectation-maximization (EM) algorithm effectively estimates the mixture component parameters. Nevertheless, knowing the true number of components a priori is vital. In pursuing a pragmatic GMM-based PLF, several approaches have been suggested in the literature to determine the true number of mixture components and parameter initialization. This paper comprehensively reviews GMM-based PLF using EM. The criteria adopted in the literature for selecting the value of “K” and the initialization strategies are given special attention. This detailed review is expected to help novice readers in the area of GMM-based PLF.
{"title":"Review of Gaussian Mixture Model-Based Probabilistic Load Flow Calculations","authors":"B. Prusty, Kishore Bingi, Neeraj Gupta","doi":"10.1109/ICICCSP53532.2022.9862332","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862332","url":null,"abstract":"It is challenging to approximate multimodal distributions of probabilistic load flow (PLF) result variables stemming from discrete and non-standard continuous input random variables (RVs). The Gaussian mixture model (GMM) approximates the probability distribution of the above input RVs as a “K” weighted sum of Gaussian distributions. The expectation-maximization (EM) algorithm effectively estimates the mixture component parameters. Nevertheless, knowing the true number of components a priori is vital. In pursuing a pragmatic GMM-based PLF, several approaches have been suggested in the literature to determine the true number of mixture components and parameter initialization. This paper comprehensively reviews GMM-based PLF using EM. The criteria adopted in the literature for selecting the value of “K” and the initialization strategies are given special attention. This detailed review is expected to help novice readers in the area of GMM-based PLF.","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128508128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-21DOI: 10.1109/ICICCSP53532.2022.9862433
Biswanath Dekaraja, L. Saikia, Satish Kumar Ramoji
This article presents a novel fractional-order (FO) cascade controller named FO tilt-derivative with filter cascaded to FO proportional-derivative with filter (CFOTDN-FOPDN) controller for unified automatic load frequency control study considering automatic voltage regulator loop. The considered system includes hydro and dish-Stirling solar thermal system in area-1 and area-2 consists of thermal and solar thermal power plant. Pertinent physical constraints are provided to the thermal and hydro units. The communication time delay (CTD) among load dispatch center and location of the power generation unit is considered. The optimization method named artificial flora algorithm is utilized to accomplish superlative solution. Investigations reveal that the proposed controller outperforms the PIDN and TIDN controllers. Analysis reflects that the higher value of CTD degrades the system performance. Moreover, the system performance improves with the higher value of the solar insolation. Lastly, the sensitivity analysis divulges the AFA optimized controller parameters are more robust against wide variations of system loading.
{"title":"Combined ALFC-AVR Control of Diverse Energy Source Based Interconnected Power System using Cascade Controller","authors":"Biswanath Dekaraja, L. Saikia, Satish Kumar Ramoji","doi":"10.1109/ICICCSP53532.2022.9862433","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862433","url":null,"abstract":"This article presents a novel fractional-order (FO) cascade controller named FO tilt-derivative with filter cascaded to FO proportional-derivative with filter (CFOTDN-FOPDN) controller for unified automatic load frequency control study considering automatic voltage regulator loop. The considered system includes hydro and dish-Stirling solar thermal system in area-1 and area-2 consists of thermal and solar thermal power plant. Pertinent physical constraints are provided to the thermal and hydro units. The communication time delay (CTD) among load dispatch center and location of the power generation unit is considered. The optimization method named artificial flora algorithm is utilized to accomplish superlative solution. Investigations reveal that the proposed controller outperforms the PIDN and TIDN controllers. Analysis reflects that the higher value of CTD degrades the system performance. Moreover, the system performance improves with the higher value of the solar insolation. Lastly, the sensitivity analysis divulges the AFA optimized controller parameters are more robust against wide variations of system loading.","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127700764","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-21DOI: 10.1109/ICICCSP53532.2022.9862331
S. Anbuselvi, R. Devi, R. Brinda
With the advancement in battery technology and power electronic converters, there is a massive increase in the use of Electric Vehicles (EV). Huge penetration of power electronic devices into the grid reduces the rotational inertia of the power system and compromise on the frequency stability. In order to reduce frequency error and the Rate of Change of Frequency (ROCOF) in low inertia power system, inertia support needs to be provided. Various methods are employed to provide grid frequency support by regulating the power exchange between the grid and grid tied inverter. In case of EV integration, virtual inertia can be obtained from two sources: one from the energy stored in dc link capacitors of the grid tied VSC and the other from the battery charging points. Coordinated control from the VSC and EV charging ports provide frequency support to the grid on an event of disturbance. This paper proposes a coordinated droop control strategy to mitigate the frequency stability issues.
{"title":"Coordinated Control of EV Charging stations for Grid Frequency Support","authors":"S. Anbuselvi, R. Devi, R. Brinda","doi":"10.1109/ICICCSP53532.2022.9862331","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862331","url":null,"abstract":"With the advancement in battery technology and power electronic converters, there is a massive increase in the use of Electric Vehicles (EV). Huge penetration of power electronic devices into the grid reduces the rotational inertia of the power system and compromise on the frequency stability. In order to reduce frequency error and the Rate of Change of Frequency (ROCOF) in low inertia power system, inertia support needs to be provided. Various methods are employed to provide grid frequency support by regulating the power exchange between the grid and grid tied inverter. In case of EV integration, virtual inertia can be obtained from two sources: one from the energy stored in dc link capacitors of the grid tied VSC and the other from the battery charging points. Coordinated control from the VSC and EV charging ports provide frequency support to the grid on an event of disturbance. This paper proposes a coordinated droop control strategy to mitigate the frequency stability issues.","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125096986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-21DOI: 10.1109/ICICCSP53532.2022.9862456
Vraj Patel, Jayant Vagajiyani, Rushikesh Nayi, Dhaval Sagar, Jay Rakholiya, Sathish Dharmalingam
The electromagnetic engine is similar to the conventional internal combustion engines that are commonly utilized to meet daily demands. With the growing population, there are many chances that non-renewable resources may be depleted in the near future. As a result, those resources have been depleted, and pollution has increased. As a result, it's critical to create an engine that can function with a different alternative or source. Internal combustion engines use fossil fuels, which are inefficient since they emit a lot of pollution and are nonrenewable energy sources. The construction of an electromagnetic engine can address all of these concerns. The magnetic qualities of repulsion and attraction are used to operate the electromagnetic engine. The connecting rod, piston, crankshaft, and other components of a classic internal combustion engine are included in this system. This project's purpose is to develop and build an electromagnetic engine that can power an unmanned aerial vehicle's propeller. The engine has been tested for voltage ranges from 12 V to 24 V. Force, torque, and efficiency have been calculated. Airspeed behind the propeller and RPM have been measured using a pitot-static probe and a tachometer, respectively.
{"title":"Development and Testing of V-8 Electromagnetic Engine","authors":"Vraj Patel, Jayant Vagajiyani, Rushikesh Nayi, Dhaval Sagar, Jay Rakholiya, Sathish Dharmalingam","doi":"10.1109/ICICCSP53532.2022.9862456","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862456","url":null,"abstract":"The electromagnetic engine is similar to the conventional internal combustion engines that are commonly utilized to meet daily demands. With the growing population, there are many chances that non-renewable resources may be depleted in the near future. As a result, those resources have been depleted, and pollution has increased. As a result, it's critical to create an engine that can function with a different alternative or source. Internal combustion engines use fossil fuels, which are inefficient since they emit a lot of pollution and are nonrenewable energy sources. The construction of an electromagnetic engine can address all of these concerns. The magnetic qualities of repulsion and attraction are used to operate the electromagnetic engine. The connecting rod, piston, crankshaft, and other components of a classic internal combustion engine are included in this system. This project's purpose is to develop and build an electromagnetic engine that can power an unmanned aerial vehicle's propeller. The engine has been tested for voltage ranges from 12 V to 24 V. Force, torque, and efficiency have been calculated. Airspeed behind the propeller and RPM have been measured using a pitot-static probe and a tachometer, respectively.","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121522430","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-21DOI: 10.1109/ICICCSP53532.2022.9862425
A. K. Singh, Joyjit Patra, Monalisa Chakraborty, Subir Gupta
An investment is capturing money to profit from it. Investing has become a buzzword among middle-class households. People can invest their money in a variety of ways. Land, gold, jewels, cash, mutual funds, and the stock market may all make investments. We all know how volatile the stock market is. But why is it beneficial to middle-class families? For example, a man from a middle-class family may want to buy land, but it may be too expensive. However, it is possible to obtain a share for a pittance. The disparity between investment and result is apparent here. Forecasting is challenging due to the volatility and non-linearity of financial stock markets. Artificial intelligence and increased computing power have enhanced accuracy in stock price prediction programs. In this paper, we consider Bharat Petroleum Corporation Limited (BPCL), Hindustan Petroleum Corporation Limited (HPCL), and Indian Oil Corporation (I.O.C.) to be the government oil corporations with the most significant stake in the Indian petroleum industry. This paper enhances the prediction of effect by combining a hybridized model of Machine Learning with a Data Science model. Machine Learning-based Hyper Parameter Tuning of Neural Network LSTM has been used to estimate the following day closing price for three equity from Indian government oil industries. The open and close stock prices are considered when creating new model input variables. This project's accuracy is around 99 percent.
{"title":"Prediction of Indian government stakeholder oil stock prices using hyper parameterized LSTM models","authors":"A. K. Singh, Joyjit Patra, Monalisa Chakraborty, Subir Gupta","doi":"10.1109/ICICCSP53532.2022.9862425","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862425","url":null,"abstract":"An investment is capturing money to profit from it. Investing has become a buzzword among middle-class households. People can invest their money in a variety of ways. Land, gold, jewels, cash, mutual funds, and the stock market may all make investments. We all know how volatile the stock market is. But why is it beneficial to middle-class families? For example, a man from a middle-class family may want to buy land, but it may be too expensive. However, it is possible to obtain a share for a pittance. The disparity between investment and result is apparent here. Forecasting is challenging due to the volatility and non-linearity of financial stock markets. Artificial intelligence and increased computing power have enhanced accuracy in stock price prediction programs. In this paper, we consider Bharat Petroleum Corporation Limited (BPCL), Hindustan Petroleum Corporation Limited (HPCL), and Indian Oil Corporation (I.O.C.) to be the government oil corporations with the most significant stake in the Indian petroleum industry. This paper enhances the prediction of effect by combining a hybridized model of Machine Learning with a Data Science model. Machine Learning-based Hyper Parameter Tuning of Neural Network LSTM has been used to estimate the following day closing price for three equity from Indian government oil industries. The open and close stock prices are considered when creating new model input variables. This project's accuracy is around 99 percent.","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132601089","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-21DOI: 10.1109/ICICCSP53532.2022.9862402
Snehashis Ghoshal, Sumit Banerjee, Sweta, Rakesh Maji, Nehal Akhter, C. K. Chanda
Minimizing the emission of greenhouse gases attained significant concern during last century. Eco-friendly energy extraction has been a matter of great concern due to the finite and polluting nature of fossil fuel-based resources. In view of this, fuel cell possesses an important part. A fuel cell generally converts chemical energy embedded within fuel into electricity without any combustion as well as through more efficient way. With the advancement in polymer technology, different fuel cells have been fabricated and proton exchange membrane fuel cell (PEMFC) has found efficient in most of the applications now-a-days. In this study, the objective was to analyze the performance of a PEM fuel cell in small scale DC system using a boost converter. The converter is actuated by a Fuzzy logic controller (FLC). The simulation was done in MATLAB/Simulink environment. Such a system can be used to implement small DC charging stations in view of charging electric vehicles.
{"title":"Modeling and Performance Analysis of a Closed Loop PEMFC in Small Scale Stand Alone DC System","authors":"Snehashis Ghoshal, Sumit Banerjee, Sweta, Rakesh Maji, Nehal Akhter, C. K. Chanda","doi":"10.1109/ICICCSP53532.2022.9862402","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862402","url":null,"abstract":"Minimizing the emission of greenhouse gases attained significant concern during last century. Eco-friendly energy extraction has been a matter of great concern due to the finite and polluting nature of fossil fuel-based resources. In view of this, fuel cell possesses an important part. A fuel cell generally converts chemical energy embedded within fuel into electricity without any combustion as well as through more efficient way. With the advancement in polymer technology, different fuel cells have been fabricated and proton exchange membrane fuel cell (PEMFC) has found efficient in most of the applications now-a-days. In this study, the objective was to analyze the performance of a PEM fuel cell in small scale DC system using a boost converter. The converter is actuated by a Fuzzy logic controller (FLC). The simulation was done in MATLAB/Simulink environment. Such a system can be used to implement small DC charging stations in view of charging electric vehicles.","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133544825","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-21DOI: 10.1109/ICICCSP53532.2022.9862438
Shiv Kumar, Sandeep Kumar Singh
In this paper, we put forward the notion of an approach centered on single object tracking. The single object tracker is going to find one object, and then it is going to track that object over the whole frame of the video. The basic elements of this methodology are images, groundtruths, neural network, and detector which are used to make a single object tracker. The neural network used for this tracking method is RESNET-101. Other trackers are also efficient in tracking the object, but still not getting accurate predicted bounding boxes on the selected object, this field gives other people a chance to make different trackers that can do perfect tracking. The datasets used in this paper are the Online object tracking benchmark(OOTB) and Unmanned Aerial Vehicle(UAV).
{"title":"Deep Neural Network-based Single Object Tracking","authors":"Shiv Kumar, Sandeep Kumar Singh","doi":"10.1109/ICICCSP53532.2022.9862438","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862438","url":null,"abstract":"In this paper, we put forward the notion of an approach centered on single object tracking. The single object tracker is going to find one object, and then it is going to track that object over the whole frame of the video. The basic elements of this methodology are images, groundtruths, neural network, and detector which are used to make a single object tracker. The neural network used for this tracking method is RESNET-101. Other trackers are also efficient in tracking the object, but still not getting accurate predicted bounding boxes on the selected object, this field gives other people a chance to make different trackers that can do perfect tracking. The datasets used in this paper are the Online object tracking benchmark(OOTB) and Unmanned Aerial Vehicle(UAV).","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131169749","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-21DOI: 10.1109/ICICCSP53532.2022.9862410
Vrushali Pagire, A. Phadke
The researchers face a difficult problem in detecting and identifying underwater fish species. Marine researchers and ecologists must evaluate the comparative profusion of fish species in their environments on a regular basis and track population trends. Researchers have presented a number of underwater computer vision, machine learning-based automatic systems for fish detection and classification. However, due of the changing undersea environment, it is extremely challenging to find the ideal system for detecting and classifying fish. Because light has such a strong influence in the aqueous medium, conducting research in this environment is difficult. The MobileNet model is utilised to detect and recognise the fish breed in the proposed work. The dataset is preprocessed before the model is implemented in order to obtain appropriate performance metrics. The work is based on the Kaggle dataset, which has nine different fish breeds in total. With a 99.74 percent accuracy, the model can detect and recognise nine different breeds. In comparison to other state of art methods, the model exhibits promising results.
{"title":"Underwater Fish Detection and Classification using Deep Learning","authors":"Vrushali Pagire, A. Phadke","doi":"10.1109/ICICCSP53532.2022.9862410","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862410","url":null,"abstract":"The researchers face a difficult problem in detecting and identifying underwater fish species. Marine researchers and ecologists must evaluate the comparative profusion of fish species in their environments on a regular basis and track population trends. Researchers have presented a number of underwater computer vision, machine learning-based automatic systems for fish detection and classification. However, due of the changing undersea environment, it is extremely challenging to find the ideal system for detecting and classifying fish. Because light has such a strong influence in the aqueous medium, conducting research in this environment is difficult. The MobileNet model is utilised to detect and recognise the fish breed in the proposed work. The dataset is preprocessed before the model is implemented in order to obtain appropriate performance metrics. The work is based on the Kaggle dataset, which has nine different fish breeds in total. With a 99.74 percent accuracy, the model can detect and recognise nine different breeds. In comparison to other state of art methods, the model exhibits promising results.","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128321016","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：