Pub Date : 2023-06-09DOI: 10.1109/APSIT58554.2023.10201754
Ashok Kumar Mohapatra, P. Sahu, Srikanta Mohapatra, Sunil Kumar Bhatta, M. Debnath
The microgrids are most reliable and digital grid which offers power at good frequency and voltage level. The grid is normally located at the distribution level and able to generate electrical energy with penetrating different renewable source based generating units. The renewable energies such as wind power, solar energy, tidal power, geothermal power are now most convenient source to produce electricity. The limitations of renewable power generating plants are uncertainty in wind velocity and variation in the solar radiation power. These uncertainties produces abnormal in the microgrid frequency and also in voltage. This article has employed a noble fuzzy PID approach to manipulate frequency oscillation issues under such uncertainties. The controller is also implemented to maintain standard frequency environment under frequency load dynamic issues. Further, the controllability in this proposed fuzzy techniques is evaluated on few standard methods like PID & PID approaches by different results and responses. The research has also applied an advanced whale optimization algorithm (A-WOA) to get most fit parameters of the controller. Finally, the effective action of the suggested A-WOA technique over PSO and GA has been synthesized to validate superiority of the proposed algorithm.
{"title":"Artificial Intelligence technique governed robust fuzzy controller for microgrid frequency control","authors":"Ashok Kumar Mohapatra, P. Sahu, Srikanta Mohapatra, Sunil Kumar Bhatta, M. Debnath","doi":"10.1109/APSIT58554.2023.10201754","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201754","url":null,"abstract":"The microgrids are most reliable and digital grid which offers power at good frequency and voltage level. The grid is normally located at the distribution level and able to generate electrical energy with penetrating different renewable source based generating units. The renewable energies such as wind power, solar energy, tidal power, geothermal power are now most convenient source to produce electricity. The limitations of renewable power generating plants are uncertainty in wind velocity and variation in the solar radiation power. These uncertainties produces abnormal in the microgrid frequency and also in voltage. This article has employed a noble fuzzy PID approach to manipulate frequency oscillation issues under such uncertainties. The controller is also implemented to maintain standard frequency environment under frequency load dynamic issues. Further, the controllability in this proposed fuzzy techniques is evaluated on few standard methods like PID & PID approaches by different results and responses. The research has also applied an advanced whale optimization algorithm (A-WOA) to get most fit parameters of the controller. Finally, the effective action of the suggested A-WOA technique over PSO and GA has been synthesized to validate superiority of the proposed algorithm.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"41 2 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":"129139597","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/APSIT58554.2023.10201747
Sreelekha Panda, Satyasis Mishra, M. Mohanty, Sunita Satapathy
Epileptic seizure leads to the unconsciousness of the brain due to the lack of sleep, toxic consumption mainly. Now a days the death rate becomes high due to the negligence of the people who suffered from the seizure. The diagnosis of epileptic seizure at the early stage is essential. The manual diagnosis of detection and classification of seizure is difficult for radiologists. Several researchers have proposed automatic detection and classification of seizure, but somehow failed in detecting and classifying seizures related the computational time and accuracy. We are proposing a novel hybrid using Adaptive Sine cosine Algorithm-Whale Optimization Algorithm optimized Extreme Learning Machine (ASCA-WOA-ELM) model for classification of epileptic seizure. The hybrid ASCA-WOA technique is proposed to optimize the weights of the ELM model to improve the performance of the conventional ELM model. The EEG signals from University of Bonn dataset are considered for the research. First, the statistical features are extracted from the EEG signals using wavelet transform. The ASCA-WOA-ELM is fed with features for classification. The proposed ASCA-WOA method's uniqueness is shown by optimizing benchmark functions. The performance measure parameters such sensitivity, specificity and accuracy are evaluated from the proposed ASCA-WOA-ELM model. The ASCA-WOA-ELM model achieved 99.42% accuracy, 99.47% specificity, and 99.53% sensitivity. Further, the computational time of 21.2841 seconds achieved by the proposed ASCA-WOA-ELM model. The comparison results with other optimized models such as SCA-ELM, WOA-ELM, ASCA-ELM, WOA-ELM, along with the proposed ASCA-WOA-ELM model are presented
{"title":"Epileptic Seizure Classification Using Adaptive Sine Cosine Algorithm-Whale Optimization Algorithm Optimized Learning Machine Model","authors":"Sreelekha Panda, Satyasis Mishra, M. Mohanty, Sunita Satapathy","doi":"10.1109/APSIT58554.2023.10201747","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201747","url":null,"abstract":"Epileptic seizure leads to the unconsciousness of the brain due to the lack of sleep, toxic consumption mainly. Now a days the death rate becomes high due to the negligence of the people who suffered from the seizure. The diagnosis of epileptic seizure at the early stage is essential. The manual diagnosis of detection and classification of seizure is difficult for radiologists. Several researchers have proposed automatic detection and classification of seizure, but somehow failed in detecting and classifying seizures related the computational time and accuracy. We are proposing a novel hybrid using Adaptive Sine cosine Algorithm-Whale Optimization Algorithm optimized Extreme Learning Machine (ASCA-WOA-ELM) model for classification of epileptic seizure. The hybrid ASCA-WOA technique is proposed to optimize the weights of the ELM model to improve the performance of the conventional ELM model. The EEG signals from University of Bonn dataset are considered for the research. First, the statistical features are extracted from the EEG signals using wavelet transform. The ASCA-WOA-ELM is fed with features for classification. The proposed ASCA-WOA method's uniqueness is shown by optimizing benchmark functions. The performance measure parameters such sensitivity, specificity and accuracy are evaluated from the proposed ASCA-WOA-ELM model. The ASCA-WOA-ELM model achieved 99.42% accuracy, 99.47% specificity, and 99.53% sensitivity. Further, the computational time of 21.2841 seconds achieved by the proposed ASCA-WOA-ELM model. The comparison results with other optimized models such as SCA-ELM, WOA-ELM, ASCA-ELM, WOA-ELM, along with the proposed ASCA-WOA-ELM model are presented","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"50 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":"127581088","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/APSIT58554.2023.10201798
S. Mohanty, Sikha Mishra, G. P. Mishra
In this work, a dielectrically modulated tri-material hetero stack gate (DM-TMHSG) MOSFET biosensor is designed for biosensing application to improve the sensitivity of the device. So, here the device is developed for the recognition of analytes such as Uricase, Ferro-cytochrome-C, Streptavidin, and Protein to assess the features of the biosensor. The various performance constraints like threshold voltage, threshold voltage sensitivity, current, current sensitivity, Subthreshold swing (SS), and SS sensitivity are investigated in the presence of only neutral biomolecules. All the constraints are simulated using the 2D TCAD platform. Simulation results showed that protein biomolecules offer better sensitivity as compared to other biomolecules in terms of current, threshold voltage, and subthreshold swing.
{"title":"Sensitivity Assessment of Dielectrically Modulated Tri-Material Hetero Stack Gate MOSFET biosensor","authors":"S. Mohanty, Sikha Mishra, G. P. Mishra","doi":"10.1109/APSIT58554.2023.10201798","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201798","url":null,"abstract":"In this work, a dielectrically modulated tri-material hetero stack gate (DM-TMHSG) MOSFET biosensor is designed for biosensing application to improve the sensitivity of the device. So, here the device is developed for the recognition of analytes such as Uricase, Ferro-cytochrome-C, Streptavidin, and Protein to assess the features of the biosensor. The various performance constraints like threshold voltage, threshold voltage sensitivity, current, current sensitivity, Subthreshold swing (SS), and SS sensitivity are investigated in the presence of only neutral biomolecules. All the constraints are simulated using the 2D TCAD platform. Simulation results showed that protein biomolecules offer better sensitivity as compared to other biomolecules in terms of current, threshold voltage, and subthreshold swing.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"13 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":"123002080","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/APSIT58554.2023.10201683
Tariq Mousa Alar, Mohammed Shuaib, Ibrahim Mohsen Khormi, Shadab Alam, Ibrahim Aqeel, Sadaf Ahmad
Academic record-keeping and verification systems face several challenges related to data security, privacy, and fraud prevention. Blockchain technology has been proposed as a potential solution to these challenges, as it offers a more secure and transparent system that can enhance the credibility and integrity of academic records. However, the implementation of self-sovereign identity (SSI) principles can further enhance the user-centric and decentralized nature of the platform. This paper proposes a blockchain-based education portal that leverages the power of blockchain technology and SSI to provide a more secure, efficient, and user-centric system for academic record-keeping and verification. The proposed system aims to comply with SSI principles, ensuring the privacy and security of student data while enabling students to control and share their academic records. By providing a decentralized, tamper-proof system for academic record-keeping and verification, the proposed system can enhance the trust and transparency of academic records, thereby enabling faster and more efficient verification processes. This investigation can provide insights into the potential benefits of SSI compliance in education record-keeping and verification and help to advance the adoption of SSI principles in other domains.
{"title":"Enhancing the Trust and Transparency of Academic Records with Blockchain-Based Systems","authors":"Tariq Mousa Alar, Mohammed Shuaib, Ibrahim Mohsen Khormi, Shadab Alam, Ibrahim Aqeel, Sadaf Ahmad","doi":"10.1109/APSIT58554.2023.10201683","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201683","url":null,"abstract":"Academic record-keeping and verification systems face several challenges related to data security, privacy, and fraud prevention. Blockchain technology has been proposed as a potential solution to these challenges, as it offers a more secure and transparent system that can enhance the credibility and integrity of academic records. However, the implementation of self-sovereign identity (SSI) principles can further enhance the user-centric and decentralized nature of the platform. This paper proposes a blockchain-based education portal that leverages the power of blockchain technology and SSI to provide a more secure, efficient, and user-centric system for academic record-keeping and verification. The proposed system aims to comply with SSI principles, ensuring the privacy and security of student data while enabling students to control and share their academic records. By providing a decentralized, tamper-proof system for academic record-keeping and verification, the proposed system can enhance the trust and transparency of academic records, thereby enabling faster and more efficient verification processes. This investigation can provide insights into the potential benefits of SSI compliance in education record-keeping and verification and help to advance the adoption of SSI principles in other domains.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"222 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":"115529974","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/APSIT58554.2023.10201752
S. Sahoo, N. Jena, Aditya Anurag, A. Naik, B. K. Sahu, P. Sahu
Now-a-days, the microgrids become more popular and the alternative for the conventional grid. Since microgrid consists number of renewable sources, its frequency regulation is a challengeable task for the operation personnel. In this article, adaptive fuzzy logic controller is designed by tuning input and output scaling factors through another fuzzy logic unit. The developed controller is used as the secondary controller to improve the dynamic stability of the microgrid. The results obtained by using the designed controller is compared with that of normal Fuzzy-logic based PI controller and the robust PID controller. The gain parameters of the above controllers are selected through Wild-Goat Algorithm (WGA).
{"title":"Frequency Regulation of Microgrid using Fuzzy-logic based controllers","authors":"S. Sahoo, N. Jena, Aditya Anurag, A. Naik, B. K. Sahu, P. Sahu","doi":"10.1109/APSIT58554.2023.10201752","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201752","url":null,"abstract":"Now-a-days, the microgrids become more popular and the alternative for the conventional grid. Since microgrid consists number of renewable sources, its frequency regulation is a challengeable task for the operation personnel. In this article, adaptive fuzzy logic controller is designed by tuning input and output scaling factors through another fuzzy logic unit. The developed controller is used as the secondary controller to improve the dynamic stability of the microgrid. The results obtained by using the designed controller is compared with that of normal Fuzzy-logic based PI controller and the robust PID controller. The gain parameters of the above controllers are selected through Wild-Goat Algorithm (WGA).","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":"132409218","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/APSIT58554.2023.10201658
Jayson A. Sabejon, Jeyhozaphat B. Rejas, Gernel S. Lumacad, Reymund L. Zarate, Edwin Anthony D. Mendez, Frances Marie Lynn O. Tinoy
Diabetes is a metabolic condition caused by either a lack of insulin production from the pancreas or insufficient utilization of insulin by the body. It is among the most prevalent diseases without a known cure, however, survival can be increased with timely detection. This study discussed the utilization of an ensemble learning method called extreme gradient boosting (XGBoost) algorithm for analyzing the early-stage diabetes risk dataset. First, a predictive model is formulated using the XGBoost algorithm in classifying a positive or negative diabetes case. Second, a feature importance analysis is implemented to measure the relative importance of each input feature in the dataset. Lastly, an XGBoost decision tree structure is generated illustrating set conditions of a negative or positive diabetes case. Experimental result showed that the formulated predictive model (accuracy = 0.9903, kappa coefficient = 0.9797, f-score = 0.990) outperformed the methods discussed in previous literatures. The feature importance analysis revealed that the ‘age’ variable has the highest relative score for early-stage diabetes risk prediction. This result confirms previous findings that age often does influence diabetes, since increased insulin resistance and impaired pancreatic islet function is associated with aging. In the latter part of this paper, the XGBoost decision tree model provided 13 different decision rules for early-stage diabetes risk prediction.
{"title":"XGBoost–Based Analysis of the Early–Stage Diabetes Risk Dataset","authors":"Jayson A. Sabejon, Jeyhozaphat B. Rejas, Gernel S. Lumacad, Reymund L. Zarate, Edwin Anthony D. Mendez, Frances Marie Lynn O. Tinoy","doi":"10.1109/APSIT58554.2023.10201658","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201658","url":null,"abstract":"Diabetes is a metabolic condition caused by either a lack of insulin production from the pancreas or insufficient utilization of insulin by the body. It is among the most prevalent diseases without a known cure, however, survival can be increased with timely detection. This study discussed the utilization of an ensemble learning method called extreme gradient boosting (XGBoost) algorithm for analyzing the early-stage diabetes risk dataset. First, a predictive model is formulated using the XGBoost algorithm in classifying a positive or negative diabetes case. Second, a feature importance analysis is implemented to measure the relative importance of each input feature in the dataset. Lastly, an XGBoost decision tree structure is generated illustrating set conditions of a negative or positive diabetes case. Experimental result showed that the formulated predictive model (accuracy = 0.9903, kappa coefficient = 0.9797, f-score = 0.990) outperformed the methods discussed in previous literatures. The feature importance analysis revealed that the ‘age’ variable has the highest relative score for early-stage diabetes risk prediction. This result confirms previous findings that age often does influence diabetes, since increased insulin resistance and impaired pancreatic islet function is associated with aging. In the latter part of this paper, the XGBoost decision tree model provided 13 different decision rules for early-stage diabetes risk prediction.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"97 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":"126324122","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/APSIT58554.2023.10201758
Manohar Mishra, Chinmoy Kumar Patra, Pratyush Kumar Muni, D. A. Gadanayak, Tanmoy Parida
This paper presents an islanding detection approach for integrated distribution systems that incorporate distributed energy resources (DERs). The approach utilizes the S-transform and an ensemble K-Nearest Neighbor model (KNN). Initially, the S-transform is employed to extract the characteristic features of the system signals, effectively capturing the transient power variations that occur during islanding events. Subsequently, a KNN model is developed to classify the system states as either islanding or non-islanding. To achieve high accuracy and generalization performance, the KNN model is optimized using a Bayesian optimization algorithm. The proposed approach is evaluated on a simulated DER-integrated distribution system, considering various scenarios, and the results demonstrate its effectiveness in accurately detecting islanding events. This approach provides a reliable and efficient solution for islanding detection in integrated distribution systems (IDS), playing a crucial role in ensuring the stability and reliability of power systems. The modeling and simulation are conducted using MATLAB software.
{"title":"Islanding detection in distributed generation system based on optimized KNN utilizing S-transform based features","authors":"Manohar Mishra, Chinmoy Kumar Patra, Pratyush Kumar Muni, D. A. Gadanayak, Tanmoy Parida","doi":"10.1109/APSIT58554.2023.10201758","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201758","url":null,"abstract":"This paper presents an islanding detection approach for integrated distribution systems that incorporate distributed energy resources (DERs). The approach utilizes the S-transform and an ensemble K-Nearest Neighbor model (KNN). Initially, the S-transform is employed to extract the characteristic features of the system signals, effectively capturing the transient power variations that occur during islanding events. Subsequently, a KNN model is developed to classify the system states as either islanding or non-islanding. To achieve high accuracy and generalization performance, the KNN model is optimized using a Bayesian optimization algorithm. The proposed approach is evaluated on a simulated DER-integrated distribution system, considering various scenarios, and the results demonstrate its effectiveness in accurately detecting islanding events. This approach provides a reliable and efficient solution for islanding detection in integrated distribution systems (IDS), playing a crucial role in ensuring the stability and reliability of power systems. The modeling and simulation are conducted using MATLAB software.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"103 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":"126371174","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/APSIT58554.2023.10201723
M. Bilal, Imdadullah, S. Hameed
The conventional grid has significant transmission losses. Power generation using conventional sources causes environmental degradation. Renewable energy-based distributed generators form microgrids (MGs). The MGs are environmentally friendly, cost-effective, reliable, and secure solutions for community loads. A residential load of Aligarh Muslim University (AMU) is considered in this study. The resource availability is taken using NASA surface metrology based on the location. An MG is designed using HOMER, taking solar, wind, battery, and converter components. The optimization results for MG architecture are obtained from simulation, taking NPC and COE as a constraint. Moreover, the optimized cost is calculated for the best proposed MG architecture. There is an annual net sale of 2,851,796 kWh of energy. The share of renewable energy for the most efficient planned microgrid is 84.6%. The energy used throughout a year is shown in the time series plot.
{"title":"Design of a Microgrid for Residential Application Using HOMER Software","authors":"M. Bilal, Imdadullah, S. Hameed","doi":"10.1109/APSIT58554.2023.10201723","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201723","url":null,"abstract":"The conventional grid has significant transmission losses. Power generation using conventional sources causes environmental degradation. Renewable energy-based distributed generators form microgrids (MGs). The MGs are environmentally friendly, cost-effective, reliable, and secure solutions for community loads. A residential load of Aligarh Muslim University (AMU) is considered in this study. The resource availability is taken using NASA surface metrology based on the location. An MG is designed using HOMER, taking solar, wind, battery, and converter components. The optimization results for MG architecture are obtained from simulation, taking NPC and COE as a constraint. Moreover, the optimized cost is calculated for the best proposed MG architecture. There is an annual net sale of 2,851,796 kWh of energy. The share of renewable energy for the most efficient planned microgrid is 84.6%. The energy used throughout a year is shown in the time series plot.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"32 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":"125251242","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/APSIT58554.2023.10201774
Sourav Bera, Anukampa Behera
For countries where primary sector of economy is agriculture, the claim for insurance based on crop damage is a common phenomenon. To make the related processes like claim assessment, faster disbursement etc. more effective and faster, it is essential to have a proper damage assessment of the crop fields. KishanRakshak is a transfer learning approach based Convolutional Neural Network(CNN) model which when applied and fine-tuned on a custom made dataset classified the percentage of damage that has occurred in the field. These classifications are adhering to the government rules. Instead of making use of drones to capture the images of damaged crops which is rather a costly process, images are obtained through smartphones' cameras at certain angles making it much cost effective. On experimentation conducted over available as well as custom made datasets the proposed model has achieved a classification accuracy of 94.67 %. KishaRakshak, is a novel and productive approach to facilitate farmers in India with easier insurance claim assessment as well as disbursement.
{"title":"KishanRakshak : A Transfer Learning Approach to Classification and Prediction of Rice Crop Damage Estimation in India for Effective Insurance Claims","authors":"Sourav Bera, Anukampa Behera","doi":"10.1109/APSIT58554.2023.10201774","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201774","url":null,"abstract":"For countries where primary sector of economy is agriculture, the claim for insurance based on crop damage is a common phenomenon. To make the related processes like claim assessment, faster disbursement etc. more effective and faster, it is essential to have a proper damage assessment of the crop fields. KishanRakshak is a transfer learning approach based Convolutional Neural Network(CNN) model which when applied and fine-tuned on a custom made dataset classified the percentage of damage that has occurred in the field. These classifications are adhering to the government rules. Instead of making use of drones to capture the images of damaged crops which is rather a costly process, images are obtained through smartphones' cameras at certain angles making it much cost effective. On experimentation conducted over available as well as custom made datasets the proposed model has achieved a classification accuracy of 94.67 %. KishaRakshak, is a novel and productive approach to facilitate farmers in India with easier insurance claim assessment as well as disbursement.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"20 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":"114483202","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}
Reversible data hiding (RDH) is an undetectable communication technology that enables restoration of the original cover image after extracting the hidden secret data from the image. It's being widely used in sevaral fields such as military, medical, etc,. Till date, various RDH have been developed to increase the amount of hidden data while maintaining their quality. However, the problem of traditional trade-off between the embedding capacity (EC) and image quality still persists. For this, we propose a new RDH method for color images based on skewed histograms and cross-channel correlation. The skewed histogram is generated with the help of extreme predictors, aids in achieving less distortion by only incorporating pixels from the peak and short tail. Further, the proposed method splits the secret data (or payload) based on each channel's characteristics so that the most smooth channel can be exploited for embedding to further benefit in reducing the caused distortion and increasing the EC. Moreover, embedding in the complex regions of images is done with the help of more comprehensive predictor which also takes into account various possible edges. Thus, the proposed method achieves greater EC with better quality stego-images than the related and existing RDH methods for color images.
{"title":"Reversible Data Hiding scheme for color images based on skewed histograms and cross-channel correlation","authors":"Priyansh Bhatnagar, Prateek Tomar, Rishabh Naagar, Raj Kumar","doi":"10.1109/APSIT58554.2023.10201792","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201792","url":null,"abstract":"Reversible data hiding (RDH) is an undetectable communication technology that enables restoration of the original cover image after extracting the hidden secret data from the image. It's being widely used in sevaral fields such as military, medical, etc,. Till date, various RDH have been developed to increase the amount of hidden data while maintaining their quality. However, the problem of traditional trade-off between the embedding capacity (EC) and image quality still persists. For this, we propose a new RDH method for color images based on skewed histograms and cross-channel correlation. The skewed histogram is generated with the help of extreme predictors, aids in achieving less distortion by only incorporating pixels from the peak and short tail. Further, the proposed method splits the secret data (or payload) based on each channel's characteristics so that the most smooth channel can be exploited for embedding to further benefit in reducing the caused distortion and increasing the EC. Moreover, embedding in the complex regions of images is done with the help of more comprehensive predictor which also takes into account various possible edges. Thus, the proposed method achieves greater EC with better quality stego-images than the related and existing RDH methods for color images.","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":"114726765","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：