Pub Date : 2023-06-09DOI: 10.1109/APSIT58554.2023.10201753
M. Narasimharao, B. Swain, P. Nayak, S. Bhuyan
Diabetes is a major global health issue that affects multiple bodily components and contributes to millions of deaths each year. Traditional approaches to diabetes diagnosis and treatment are often limited by their lack of accuracy, transparency, and efficiency. This study aims to develop and evaluate a novel machine learning-based diagnosis system for diabetes mellitus using interpretable supervised and neural network techniques. The study used a dataset of 9 features listed in 2000 patient information from The Frankfurt Hospital, Germany, and trained and tested several ML algorithms including logistic regression, gradient boosting, naive Bayes classifier, random forest classifier, and artificial neural network (ANN). The performance of each algorithm was evaluated using precision, recall, and F1-score, and the findings indicate that the ANN model performs best with a larger number of features, achieving 100% accuracy. Interpretable techniques were used to facilitate understanding of the ML model decision-making process. The suggested system offers several implications and potential impacts on healthcare practice, including improved diagnosis accuracy, automation of diabetes testing and referral algorithms, and reduced time, work, and labor in medical services. These findings highlight the potential of machine learning to address the limitations of traditional diabetes diagnosis and treatment, and contribute to better patient outcomes.
{"title":"Developing and Evaluating a Machine Learning Based Diagnosis System for Diabetes Mellitus using Interpretable Techniques","authors":"M. Narasimharao, B. Swain, P. Nayak, S. Bhuyan","doi":"10.1109/APSIT58554.2023.10201753","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201753","url":null,"abstract":"Diabetes is a major global health issue that affects multiple bodily components and contributes to millions of deaths each year. Traditional approaches to diabetes diagnosis and treatment are often limited by their lack of accuracy, transparency, and efficiency. This study aims to develop and evaluate a novel machine learning-based diagnosis system for diabetes mellitus using interpretable supervised and neural network techniques. The study used a dataset of 9 features listed in 2000 patient information from The Frankfurt Hospital, Germany, and trained and tested several ML algorithms including logistic regression, gradient boosting, naive Bayes classifier, random forest classifier, and artificial neural network (ANN). The performance of each algorithm was evaluated using precision, recall, and F1-score, and the findings indicate that the ANN model performs best with a larger number of features, achieving 100% accuracy. Interpretable techniques were used to facilitate understanding of the ML model decision-making process. The suggested system offers several implications and potential impacts on healthcare practice, including improved diagnosis accuracy, automation of diabetes testing and referral algorithms, and reduced time, work, and labor in medical services. These findings highlight the potential of machine learning to address the limitations of traditional diabetes diagnosis and treatment, and contribute to better patient outcomes.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121496602","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 : 2023-06-09DOI: 10.1109/APSIT58554.2023.10201794
Anubhav Shukla, D. Arora
Everyday, many individuals face online trolling and receive hate on different social media platforms like Twitter, Instagram to name a few. Often these comments involving racial abuse, hate based on religion, caste are made by anonymous people over the internet, and it is quite a task to keep these comments under control. So, the objective was to develop a Machine Learning Model to help identify these comments. A Deep Learning Model (a sequential model) was made and it was trained to identify and classify a comment based on whether it is an apt comment or not. LSTM (Long Short-Term Memory) is a type of recurrent neural network (RNN) that is particularly well-suited for modeling sequential data, such as text. LSTMs are capable of modeling long-term dependencies in sequential data. In the case of text classification, this means that LSTMs can take into account the context of a word or phrase within a sentence, paragraph, or even an entire document. LSTMs can learn to selectively forget or remember information from the past, which is useful for filtering out noise or irrelevant information in text. LSTMs are well-established in the field of natural language processing (NLP) and have been shown to be effective for various NLP tasks, including sentiment analysis and text classification. Binary cross-entropy is a commonly used loss function in deep learning models for binary classification problems, such as predicting whether a comment is toxic or not. Binary cross-entropy is designed to optimize the model's predictions based on the binary nature of the classification task. It penalizes the model for assigning a low probability to the correct class and rewards it for assigning a high probability to the correct class. The loss function is differentiable, which allows gradient-based optimization methods to be used during training to minimize the loss and improve the model's performance. Binary cross-entropy is a well-established loss function that has been extensively used in the field of deep learning, and there are many tools and frameworks that support it, making it easy to implement in practice. Binary cross-entropy also has a probabilistic interpretation, which can be useful in some applications. For example, it can be used to estimate the probability that a given comment is toxic. Hence, Binary Cross Entropy has been chosen as the loss function for the Deep Learning model.
{"title":"Deep Learning Model for Identification and Classification of Web based Toxic Comments","authors":"Anubhav Shukla, D. Arora","doi":"10.1109/APSIT58554.2023.10201794","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201794","url":null,"abstract":"Everyday, many individuals face online trolling and receive hate on different social media platforms like Twitter, Instagram to name a few. Often these comments involving racial abuse, hate based on religion, caste are made by anonymous people over the internet, and it is quite a task to keep these comments under control. So, the objective was to develop a Machine Learning Model to help identify these comments. A Deep Learning Model (a sequential model) was made and it was trained to identify and classify a comment based on whether it is an apt comment or not. LSTM (Long Short-Term Memory) is a type of recurrent neural network (RNN) that is particularly well-suited for modeling sequential data, such as text. LSTMs are capable of modeling long-term dependencies in sequential data. In the case of text classification, this means that LSTMs can take into account the context of a word or phrase within a sentence, paragraph, or even an entire document. LSTMs can learn to selectively forget or remember information from the past, which is useful for filtering out noise or irrelevant information in text. LSTMs are well-established in the field of natural language processing (NLP) and have been shown to be effective for various NLP tasks, including sentiment analysis and text classification. Binary cross-entropy is a commonly used loss function in deep learning models for binary classification problems, such as predicting whether a comment is toxic or not. Binary cross-entropy is designed to optimize the model's predictions based on the binary nature of the classification task. It penalizes the model for assigning a low probability to the correct class and rewards it for assigning a high probability to the correct class. The loss function is differentiable, which allows gradient-based optimization methods to be used during training to minimize the loss and improve the model's performance. Binary cross-entropy is a well-established loss function that has been extensively used in the field of deep learning, and there are many tools and frameworks that support it, making it easy to implement in practice. Binary cross-entropy also has a probabilistic interpretation, which can be useful in some applications. For example, it can be used to estimate the probability that a given comment is toxic. Hence, Binary Cross Entropy has been chosen as the loss function for the Deep Learning model.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123240703","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}
The proposed research provides an essential set of requirements for battery charging systems in Electric Vehicle (EV) applications. Because of their superior power output, low cost, and environmental flexibility, EVs have become a viable alternative to IC-based engines. The battery and charger designs are discussed in this study. The battery charger's contribution to harmonic distortion on the grid is one of the main challenges of the application.
{"title":"A case studies on various Charging Methodology in EVs","authors":"S. Mishra, Sudheshna G, RUDRANARAYAN SENAPATI, Priyanka D, Lokeswar Rao K, Adilakshmi K, Manoina Ch","doi":"10.1109/APSIT58554.2023.10201676","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201676","url":null,"abstract":"The proposed research provides an essential set of requirements for battery charging systems in Electric Vehicle (EV) applications. Because of their superior power output, low cost, and environmental flexibility, EVs have become a viable alternative to IC-based engines. The battery and charger designs are discussed in this study. The battery charger's contribution to harmonic distortion on the grid is one of the main challenges of the application.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123596972","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 : 2023-06-09DOI: 10.1109/APSIT58554.2023.10201790
N. Nayak, Anshuman Sathpathy
The rapid growth in power demand increased the per capita consumption of power. In this scenario, the nonconventional energy sources play a significant role in a power system. Solar power is one of the renewable sources RES, popularly used to meet energy demand. The increase in the PV integration into the main grid makes the solar power prediction an essential aspect as it helps in the reduction of different power quality issues and thus enhancing the system reliability. The nonlinear nature of solar power makes the prediction difficult hence a precise prediction technique is required for an accurate result. This paper proposes a hybrid technique is proposed for 5min- ahead solar power prediction. The hybrid model comprises EMD, VMD, and ELM optimized by phase angle particle swarm optimization (PA-PSO). To validate the accuracy and effectiveness of the proposed model a solar power data series is considered. 5min solar power data from New Jersey, is considered as interpretive examples for evaluating the model efficiency. The experimental result shows that the proposed model outperforms other techniques considered over the different prediction horizon.
{"title":"Short Term Solar Power Prediction Using Hybrid Two Layered Decomposition Technique Based Optimized ELM","authors":"N. Nayak, Anshuman Sathpathy","doi":"10.1109/APSIT58554.2023.10201790","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201790","url":null,"abstract":"The rapid growth in power demand increased the per capita consumption of power. In this scenario, the nonconventional energy sources play a significant role in a power system. Solar power is one of the renewable sources RES, popularly used to meet energy demand. The increase in the PV integration into the main grid makes the solar power prediction an essential aspect as it helps in the reduction of different power quality issues and thus enhancing the system reliability. The nonlinear nature of solar power makes the prediction difficult hence a precise prediction technique is required for an accurate result. This paper proposes a hybrid technique is proposed for 5min- ahead solar power prediction. The hybrid model comprises EMD, VMD, and ELM optimized by phase angle particle swarm optimization (PA-PSO). To validate the accuracy and effectiveness of the proposed model a solar power data series is considered. 5min solar power data from New Jersey, is considered as interpretive examples for evaluating the model efficiency. The experimental result shows that the proposed model outperforms other techniques considered over the different prediction horizon.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121375243","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 : 2023-06-09DOI: 10.1109/APSIT58554.2023.10201757
R. R. Ali, Mohamed Ayad Alkhafaji, M. Guneser, F. Al-dolaimy, A. Alsalamy, Sameer Alani, F. Abbas, A. Alkhayyat, S. Mahmood
A Vehicular Adhoc Network (VANET) is used in maximum of the applications of intelligent transportation system (ITS). It is one among the high-speed communication networks as the results it undergone few of the drawbacks such as congestion occurrence, computation delay and overhead occurrence and so on. It is essential to monitor the network periodically and complicated to monitor the VANETs. In this paper, a Trust based Data dissemination and Queue management for VANETs (TDQ-VANETs) are introduced. At the initial stage, before the data transmission direct trust, indirect trust and total trust values of each vehicle are measured and it gets updated periodically. At the time of data transmission queue management is performed using dual queue model that employs both CSMA and TDMA models to transfer the data. The simulation of the proposed TDQ-VANETs approach is performed in NS2 and SUMO. The packet delivery rate, computational delay, computational overhead and throughput are the parameters used for performance analysis. The results compared with the earlier approaches such as AJ-MOFA and RO-DLAA. The results show that the TDQ-VANETs approach achieved superior performance in terms of packet delivery ratio and throughput.
{"title":"Trust based Data Dissemination and Queue Management for Vehicular Communication Networks","authors":"R. R. Ali, Mohamed Ayad Alkhafaji, M. Guneser, F. Al-dolaimy, A. Alsalamy, Sameer Alani, F. Abbas, A. Alkhayyat, S. Mahmood","doi":"10.1109/APSIT58554.2023.10201757","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201757","url":null,"abstract":"A Vehicular Adhoc Network (VANET) is used in maximum of the applications of intelligent transportation system (ITS). It is one among the high-speed communication networks as the results it undergone few of the drawbacks such as congestion occurrence, computation delay and overhead occurrence and so on. It is essential to monitor the network periodically and complicated to monitor the VANETs. In this paper, a Trust based Data dissemination and Queue management for VANETs (TDQ-VANETs) are introduced. At the initial stage, before the data transmission direct trust, indirect trust and total trust values of each vehicle are measured and it gets updated periodically. At the time of data transmission queue management is performed using dual queue model that employs both CSMA and TDMA models to transfer the data. The simulation of the proposed TDQ-VANETs approach is performed in NS2 and SUMO. The packet delivery rate, computational delay, computational overhead and throughput are the parameters used for performance analysis. The results compared with the earlier approaches such as AJ-MOFA and RO-DLAA. The results show that the TDQ-VANETs approach achieved superior performance in terms of packet delivery ratio and throughput.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126762214","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 : 2023-06-09DOI: 10.1109/APSIT58554.2023.10201656
Ashutosh Kumar Singh, S. K. Rajput, Amaresh Gantayet
The rooftop PV installation is one of the most significant solutions for producing electrical energy without creating any pollution. PV plants need a significant initial investment, and they also provide energy assistance to grid and users. There is an urgent need to create a straightforward and error-free economic analysis methodology to attract consumers from commercial buildings (such as institutional buildings). The presented study covers a time-value of money based economic analysis for a 100 kWp PV plant at a composite climate in Gwalior, India. The study is performed through real-time data collection and analysis. The results show that there is 127020 kWh electricity generation in the first year, which declined to 104828.34 kWh in the last year (of PV plant life) due to the degradation of the PV array. By considering the uniform cash flow and discount rate of 8.6%, the average annual benefit is Rs. 904374.88. The simple and discounted paybacks of the case study are 7 and 12 years, respectively, whereas the net present value and benefit-to-cost ratio of the plant are Rs. 4679070 and 2.04, respectively.
{"title":"Grid Connected Rooftop PV Plant Economic Analysis Using Present Time Frame Methodology","authors":"Ashutosh Kumar Singh, S. K. Rajput, Amaresh Gantayet","doi":"10.1109/APSIT58554.2023.10201656","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201656","url":null,"abstract":"The rooftop PV installation is one of the most significant solutions for producing electrical energy without creating any pollution. PV plants need a significant initial investment, and they also provide energy assistance to grid and users. There is an urgent need to create a straightforward and error-free economic analysis methodology to attract consumers from commercial buildings (such as institutional buildings). The presented study covers a time-value of money based economic analysis for a 100 kWp PV plant at a composite climate in Gwalior, India. The study is performed through real-time data collection and analysis. The results show that there is 127020 kWh electricity generation in the first year, which declined to 104828.34 kWh in the last year (of PV plant life) due to the degradation of the PV array. By considering the uniform cash flow and discount rate of 8.6%, the average annual benefit is Rs. 904374.88. The simple and discounted paybacks of the case study are 7 and 12 years, respectively, whereas the net present value and benefit-to-cost ratio of the plant are Rs. 4679070 and 2.04, respectively.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126065077","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 : 2023-06-09DOI: 10.1109/APSIT58554.2023.10201717
P. Sahu, Anjali Routray, Smitasree Jena, S. Panda, R. Prusty, B. K. Sahu
This paper addresses the importance of flexible AC transmission devices for frequency and tie-line power stability improvement of two area power system. The research work has implemented two FACTS devices such as SMES (super magnetic energy storing devices) & IPFC (Interline power flow controller) to improve frequency profile of a non-linear power system. The load dynamic is the main source to create frequency instability issues in the power system. Besides FACTS devices, the paper has also employed a type-2 fuzzy control approach to develop secondary loop in the system. In validity concern, the activity of the suggested type-2 fuzzy controller is compared with type-1 fuzzy controller and PID control approach. The controller parameters are tuned with suggesting a quassi oppositional path finder algorithm (QO-PFA) in different situations. The result and outcomes are obtained through various dynamic responses and numeric values. Finally, it is concluded from the outcomes that FACTS devices having huge effect to improve dynamic performance of the system in different conditions.
{"title":"Role of IPFC and SMES for Stability improvement of a Power system with type-2 fuzzy controller","authors":"P. Sahu, Anjali Routray, Smitasree Jena, S. Panda, R. Prusty, B. K. Sahu","doi":"10.1109/APSIT58554.2023.10201717","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201717","url":null,"abstract":"This paper addresses the importance of flexible AC transmission devices for frequency and tie-line power stability improvement of two area power system. The research work has implemented two FACTS devices such as SMES (super magnetic energy storing devices) & IPFC (Interline power flow controller) to improve frequency profile of a non-linear power system. The load dynamic is the main source to create frequency instability issues in the power system. Besides FACTS devices, the paper has also employed a type-2 fuzzy control approach to develop secondary loop in the system. In validity concern, the activity of the suggested type-2 fuzzy controller is compared with type-1 fuzzy controller and PID control approach. The controller parameters are tuned with suggesting a quassi oppositional path finder algorithm (QO-PFA) in different situations. The result and outcomes are obtained through various dynamic responses and numeric values. Finally, it is concluded from the outcomes that FACTS devices having huge effect to improve dynamic performance of the system in different conditions.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"47 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127475791","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 : 2023-06-09DOI: 10.1109/APSIT58554.2023.10201661
K. Anjaiah, P. K. Dash, Lsm Ieee, Snehamoy Dhar, R. Bisoi
In DC microgrids, quick fault detection and isolation is still a key challenge in microgrid protection. This paper proposes a new approach using a modified change detection filter (M-CDF) to detect and isolate faults in multiple photovoltaic-based DC microgrids. The proposed microgrid is subjected to various faults, and corresponding data is collected from the DC bus. The voltage signal is then processed through the M-CDF, which uses a reference window to compare with other windows in a sliding pattern to detect sudden changes or faults based on the detection threshold. Simultaneously, it also isolates the fault section from the healthy section by sending a trip signal to the circuit breaker. To obtain remarkable results in terms of detection for both low and high-magnitude faults, M-CDF is further subjected to Teager energy (TE) and it is named TE-CDF. As a result, it accurately detects the faults even when low-magnitude faults occur by exhibiting large magnitudes. Further, to evidence the superiority, applicability, and simplicity of the proposed approach (i.e., TE-CDF) is validated on a hardware test bench through dSPACE DS 1104 embedded processor, and obtained results are compared over benchmark techniques.
{"title":"Real-Time Fault Diagnosis in Photovoltaic Based DC Microgrids Using Modified Change Detection Filter","authors":"K. Anjaiah, P. K. Dash, Lsm Ieee, Snehamoy Dhar, R. Bisoi","doi":"10.1109/APSIT58554.2023.10201661","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201661","url":null,"abstract":"In DC microgrids, quick fault detection and isolation is still a key challenge in microgrid protection. This paper proposes a new approach using a modified change detection filter (M-CDF) to detect and isolate faults in multiple photovoltaic-based DC microgrids. The proposed microgrid is subjected to various faults, and corresponding data is collected from the DC bus. The voltage signal is then processed through the M-CDF, which uses a reference window to compare with other windows in a sliding pattern to detect sudden changes or faults based on the detection threshold. Simultaneously, it also isolates the fault section from the healthy section by sending a trip signal to the circuit breaker. To obtain remarkable results in terms of detection for both low and high-magnitude faults, M-CDF is further subjected to Teager energy (TE) and it is named TE-CDF. As a result, it accurately detects the faults even when low-magnitude faults occur by exhibiting large magnitudes. Further, to evidence the superiority, applicability, and simplicity of the proposed approach (i.e., TE-CDF) is validated on a hardware test bench through dSPACE DS 1104 embedded processor, and obtained results are compared over benchmark techniques.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130592884","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 : 2023-06-09DOI: 10.1109/APSIT58554.2023.10201727
P. Nayak, Nityananda Giri, Rakesh Rosan Prusty, R. Mallick, A. K. Sahoo, Subham Kumar
Accurate fault detection and classification is a measure issue in a microgrid (MG). The MG often experiences shunt faults inside or outside of it, the circuit breaker connected between the utility grid and MG must immediately respond and open the circuit. If the fault is not detected accurately, it hampers the system's reliability and load performances also increase faulty line restoration costs. This research proposes a robust fault detection and classification technique based on Empirical Mode Decomposition (EMD) and Extreme Learning Machine (ELM). Energy of Decomposed current signals are used for unbiased feature extraction in presence of noise. whereas ELM is used for accurate fault detection and classification. The proposed EMD-ELM technique is validated in standard test system and found to be performing better as compared to other competitive techniques.
{"title":"Fault Detection and Classification of Microgrid Based on Mode Decomposition and Extreme Learning Machine","authors":"P. Nayak, Nityananda Giri, Rakesh Rosan Prusty, R. Mallick, A. K. Sahoo, Subham Kumar","doi":"10.1109/APSIT58554.2023.10201727","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201727","url":null,"abstract":"Accurate fault detection and classification is a measure issue in a microgrid (MG). The MG often experiences shunt faults inside or outside of it, the circuit breaker connected between the utility grid and MG must immediately respond and open the circuit. If the fault is not detected accurately, it hampers the system's reliability and load performances also increase faulty line restoration costs. This research proposes a robust fault detection and classification technique based on Empirical Mode Decomposition (EMD) and Extreme Learning Machine (ELM). Energy of Decomposed current signals are used for unbiased feature extraction in presence of noise. whereas ELM is used for accurate fault detection and classification. The proposed EMD-ELM technique is validated in standard test system and found to be performing better as compared to other competitive techniques.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"179 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132181442","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 : 2023-06-09DOI: 10.1109/APSIT58554.2023.10201709
Mahesh Kumar Pal, P. M. Pradhan
The synthetic satellite images can be generated by various methodologies using available Landsat images and the MODIS composite. This paper uses a hybrid methodology combining regression analysis, Kalman filtering, and smoothing. It combines the forward recursion Kalman filter with the backward recursion Kalman filter, which is named a combined mode Kalman filter. This improved hybrid technique provides more accurate synthetic satellite images than those provided by the other blending algorithms like STARFM, ESTARFM, SPSTFM, and KFRFM. Residuals are lower for the combined recursion for the generated synthetic NDVI image generated by the forward or backward recursion filter.
{"title":"Generation of NDVI Time Series using a Hybrid Regression Kalman Filter based Approach","authors":"Mahesh Kumar Pal, P. M. Pradhan","doi":"10.1109/APSIT58554.2023.10201709","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201709","url":null,"abstract":"The synthetic satellite images can be generated by various methodologies using available Landsat images and the MODIS composite. This paper uses a hybrid methodology combining regression analysis, Kalman filtering, and smoothing. It combines the forward recursion Kalman filter with the backward recursion Kalman filter, which is named a combined mode Kalman filter. This improved hybrid technique provides more accurate synthetic satellite images than those provided by the other blending algorithms like STARFM, ESTARFM, SPSTFM, and KFRFM. Residuals are lower for the combined recursion for the generated synthetic NDVI image generated by the forward or backward recursion filter.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134430672","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：