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/ICICCSP53532.2022.9862368
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/ICICCSP53532.2022.9862410
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}
Pub Date : 2022-07-21DOI: 10.1109/ICICCSP53532.2022.9862477
Soumik Kundu, Subhankit Prusti, S. Patnaik
Ventricular Fibrillation is a potentially fatal cardiac disorder that occurs when electrical impulses in the ventricles are disrupted, causing the heart to quiver instead of pump. In order to preserve lives during this form of arrhythmia, a strong current impulse is passed. Electrocardiograms (ECGs) record the electrical activity of the human heart, and specialists with years of experience may interpret the ECG signal to determine the heart's condition. Since it is a life-threatening disease, its earlier detection and prevention can help survive a patient's life. The fundamental idea behind tackling this challenge was to create an algorithm that could identify trends from continuous ECG readings from various individuals and identify arrhythmias early on. An efficient data was built for classification utilizing a Random Forest classifier algorithm employing signal processing tools such as Empirical Mode Decomposition (EMD) and Discrete Fourier Transform (DFT) for feature extraction. The pre-processed data when fed into the proposed machine learning method results in an accuracy of 96.58% and two classes were classified correctly with equal confidence (Specificity = 94.26% and Sensitivity = 98.97%). Furthermore, the results are compared with various other machine learning classification algorithms like Logistic Regression, Decision Tree classifier, Extra tree classifier where the accuracy was 86.49%, 91.77%, 95.84% respectively. The results obtained after experimental validation of proposed Random Forest classifier algorithm against the other machine learning achieves highest accuracy with optimal specificity and sensitivity.
{"title":"Detection of Ventricular Fibrillation by combining Signal Processing and Machine Learning approach","authors":"Soumik Kundu, Subhankit Prusti, S. Patnaik","doi":"10.1109/ICICCSP53532.2022.9862477","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862477","url":null,"abstract":"Ventricular Fibrillation is a potentially fatal cardiac disorder that occurs when electrical impulses in the ventricles are disrupted, causing the heart to quiver instead of pump. In order to preserve lives during this form of arrhythmia, a strong current impulse is passed. Electrocardiograms (ECGs) record the electrical activity of the human heart, and specialists with years of experience may interpret the ECG signal to determine the heart's condition. Since it is a life-threatening disease, its earlier detection and prevention can help survive a patient's life. The fundamental idea behind tackling this challenge was to create an algorithm that could identify trends from continuous ECG readings from various individuals and identify arrhythmias early on. An efficient data was built for classification utilizing a Random Forest classifier algorithm employing signal processing tools such as Empirical Mode Decomposition (EMD) and Discrete Fourier Transform (DFT) for feature extraction. The pre-processed data when fed into the proposed machine learning method results in an accuracy of 96.58% and two classes were classified correctly with equal confidence (Specificity = 94.26% and Sensitivity = 98.97%). Furthermore, the results are compared with various other machine learning classification algorithms like Logistic Regression, Decision Tree classifier, Extra tree classifier where the accuracy was 86.49%, 91.77%, 95.84% respectively. The results obtained after experimental validation of proposed Random Forest classifier algorithm against the other machine learning achieves highest accuracy with optimal specificity and sensitivity.","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":"14 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":"125321406","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/ICICCSP53532.2022.9862445
Sarita Samal, Roshan Kumar Soni, Sarthak Nayak, P. K. Barik, Rudranarayan Dash, Geetanjali Dei
This Paper presents the concept of a Maximum Power Point Tracking (MPPT) based Solar Charge Controllers (SCC) for charging a battery in stand-alone Solar Photo-voltaic (SPV) systems. A SCC is a battery charge regulator which is connected in between the SPV panel and the battery, the primary purpose of the SCC is to regulate the charging of the battery so that it charges correctly. PWM based SCCs may get the job done but they have very low efficiency as compared to MPPT based ones and thus waste a lot of SPV power. This fact has been analyzed in our article by executing the simulations for both the charge controller types and the efficiency of PWM was found to be only 65% whereas that of the MPPT based is 94%. Another useful feature in modern day SCCs and in our prototype is the facility to monitor the device parameters remotely on a wireless network which provides major flexibility to controllers. In this prototype model we have implemented MPPT based SCC along with one Wi-Fi module for monitoring the battery voltage, current, PWM pulses and battery status on smartphones. The user also gets notified about the battery status, whether the battery is charging or it is over charging. If the SPV voltage is more than 12V the relay disconnects the battery from the SPV cell and a notification regarding this is given to the user.
{"title":"A Smart Solar Charge Controller Based on IOT Technology with Hardware Implementation","authors":"Sarita Samal, Roshan Kumar Soni, Sarthak Nayak, P. K. Barik, Rudranarayan Dash, Geetanjali Dei","doi":"10.1109/ICICCSP53532.2022.9862445","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862445","url":null,"abstract":"This Paper presents the concept of a Maximum Power Point Tracking (MPPT) based Solar Charge Controllers (SCC) for charging a battery in stand-alone Solar Photo-voltaic (SPV) systems. A SCC is a battery charge regulator which is connected in between the SPV panel and the battery, the primary purpose of the SCC is to regulate the charging of the battery so that it charges correctly. PWM based SCCs may get the job done but they have very low efficiency as compared to MPPT based ones and thus waste a lot of SPV power. This fact has been analyzed in our article by executing the simulations for both the charge controller types and the efficiency of PWM was found to be only 65% whereas that of the MPPT based is 94%. Another useful feature in modern day SCCs and in our prototype is the facility to monitor the device parameters remotely on a wireless network which provides major flexibility to controllers. In this prototype model we have implemented MPPT based SCC along with one Wi-Fi module for monitoring the battery voltage, current, PWM pulses and battery status on smartphones. The user also gets notified about the battery status, whether the battery is charging or it is over charging. If the SPV voltage is more than 12V the relay disconnects the battery from the SPV cell and a notification regarding this is given to the user.","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":"24 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":"114043054","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/ICICCSP53532.2022.9862400
Sneha Gope, Imon Dutta, Kairab Roy, Indrayudh Chakrabarti, D. Bose, C. K. Chanda
This paper introduces a method to optimize the number of crewmen deployed at various faulty nodes within a city to boost power system resiliency to pre-calamitous values during the post-restorative period. The approach follows a case study wherein data has been created and analyzed and then predictions have been performed using a multivariate linear regression machine learning model and Artificial Neural Network (ANN). The results of both have then been tabulated and compared. The model proposed in this paper will be highly beneficial for power distribution companies because in case of future disasters power distribution companies just need to give the input parameters for the specific area and they will get the optimal number of crewmen required for the restoration of that area.
{"title":"Crewman Deployment Model for Improving the Resiliency of the Power System","authors":"Sneha Gope, Imon Dutta, Kairab Roy, Indrayudh Chakrabarti, D. Bose, C. K. Chanda","doi":"10.1109/ICICCSP53532.2022.9862400","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862400","url":null,"abstract":"This paper introduces a method to optimize the number of crewmen deployed at various faulty nodes within a city to boost power system resiliency to pre-calamitous values during the post-restorative period. The approach follows a case study wherein data has been created and analyzed and then predictions have been performed using a multivariate linear regression machine learning model and Artificial Neural Network (ANN). The results of both have then been tabulated and compared. The model proposed in this paper will be highly beneficial for power distribution companies because in case of future disasters power distribution companies just need to give the input parameters for the specific area and they will get the optimal number of crewmen required for the restoration of that area.","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":"231 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":"127649636","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/ICICCSP53532.2022.9862441
Swapna Subudhiray, H. Palo, Niva Das
In this article, the authors attempt to characterize the facial emotions utilizing a few statistically measurable elements. The objective is to demarcate the emotions based on their arousal level. Several low and high arousal emotions such as anger, surprise, sadness, happiness, fear, and disgust are investigated to segment them based on the level of arousal. Initially, the facial images are loaded and the sector of interest is extracted to assess the factual component of the face. The versatile Gabor filter is applied to each of the facial images to extract the discriminate feature vectors. Finally, several statistical parameters are computed from the Gabor feature vectors of each facial emotional expression to characterization and identification based on the level of arousal. To exhibit the stated acknowledgment strategy, JAFFE facial information base and the MATLAB 18 (b) platform are incorporated. Simulation results reveal, it is possible to demarcate the high arousal emotional states from the low arousal states graphically for the sake of identification.
{"title":"Facial Behaviour Realization using Statistical Features","authors":"Swapna Subudhiray, H. Palo, Niva Das","doi":"10.1109/ICICCSP53532.2022.9862441","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862441","url":null,"abstract":"In this article, the authors attempt to characterize the facial emotions utilizing a few statistically measurable elements. The objective is to demarcate the emotions based on their arousal level. Several low and high arousal emotions such as anger, surprise, sadness, happiness, fear, and disgust are investigated to segment them based on the level of arousal. Initially, the facial images are loaded and the sector of interest is extracted to assess the factual component of the face. The versatile Gabor filter is applied to each of the facial images to extract the discriminate feature vectors. Finally, several statistical parameters are computed from the Gabor feature vectors of each facial emotional expression to characterization and identification based on the level of arousal. To exhibit the stated acknowledgment strategy, JAFFE facial information base and the MATLAB 18 (b) platform are incorporated. Simulation results reveal, it is possible to demarcate the high arousal emotional states from the low arousal states graphically for the sake of identification.","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":"3 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":"127977861","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/ICICCSP53532.2022.9862510
S. Prasanna, Kumaresh Pal, Debesh Mandal
Solar radiation is one of the vital resources found on Earth which can be renewed and hence tested and tried to be beneficiary for humankind. Solar energy is harnessed to fulfill the basic requirements of humans i.e.; supply power to operate any kind of machine or device. The way to utilize the energy for our maximum benefit is by approximating the radiation values of Sun and this can be achieved by installing measuring equipments. The main issue arises here as the equipment's maintenance and installation cost is too high to be affordable by the general people. To overcome this inconvenience, an affordable solution was developing models and methods to calculate the radiation and find the approximate values. We focus on city, Hubli, India and estimate the monthly mean radiation received on this particular city by creating a neural network in ANN (Artificial Neural network) using MATLAB. The models are validated for 3 training functions: resilient back-propagation (RP), Scaled Conjugate Gradient (SCG) and Levenberg-Marquardt (LM). The predicted values accuracy is also tested through statistical indicators like MSE, RMSE, MBE and MAPE.
{"title":"Predicting The Monthly Average Incident Shortwave Solar Energy for Hubli, India by Using Training Functions in ANN","authors":"S. Prasanna, Kumaresh Pal, Debesh Mandal","doi":"10.1109/ICICCSP53532.2022.9862510","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862510","url":null,"abstract":"Solar radiation is one of the vital resources found on Earth which can be renewed and hence tested and tried to be beneficiary for humankind. Solar energy is harnessed to fulfill the basic requirements of humans i.e.; supply power to operate any kind of machine or device. The way to utilize the energy for our maximum benefit is by approximating the radiation values of Sun and this can be achieved by installing measuring equipments. The main issue arises here as the equipment's maintenance and installation cost is too high to be affordable by the general people. To overcome this inconvenience, an affordable solution was developing models and methods to calculate the radiation and find the approximate values. We focus on city, Hubli, India and estimate the monthly mean radiation received on this particular city by creating a neural network in ANN (Artificial Neural network) using MATLAB. The models are validated for 3 training functions: resilient back-propagation (RP), Scaled Conjugate Gradient (SCG) and Levenberg-Marquardt (LM). The predicted values accuracy is also tested through statistical indicators like MSE, RMSE, MBE and MAPE.","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":"136 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":"121380588","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：