Pub Date : 2023-03-01DOI: 10.1109/ESCI56872.2023.10099730
Mohammed Rafi Rehman Shaikh
Due to the exponential increase in data volume, network complexity necessitated the requirement of software defined networks (SDN). But with SDN, network and service expansion significantly affect resource management. An efficient resource allocation method is mandatory to account for the random nature of network traffic and the load management across several controllers. However, due to the imprecise and dynamic relationships between resources, reinforcement learning has not been well-served in the context of real-time load in SDN. This paper presents deep reinforcement learning (DRL) technique to a Bayesian network to provide a smart optimization framework for SDN resource management. The Bayesian network use a reinforcement learning method, self-adjusting parameter weight, and automatic parameter weight adjustment to regulate the controller load congestion and anticipate the level of load congestion necessary to achieve load balance. By utilizing the prediction results from reinforcement learning, this algorithm selects the best possible next step. Theoretical analysis of the proper load balancing strategy for SDN is supported by a concurrent examination of existing datasets.
{"title":"Bayesian Network based Optimal Load Balancing in Software Defined Networks","authors":"Mohammed Rafi Rehman Shaikh","doi":"10.1109/ESCI56872.2023.10099730","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10099730","url":null,"abstract":"Due to the exponential increase in data volume, network complexity necessitated the requirement of software defined networks (SDN). But with SDN, network and service expansion significantly affect resource management. An efficient resource allocation method is mandatory to account for the random nature of network traffic and the load management across several controllers. However, due to the imprecise and dynamic relationships between resources, reinforcement learning has not been well-served in the context of real-time load in SDN. This paper presents deep reinforcement learning (DRL) technique to a Bayesian network to provide a smart optimization framework for SDN resource management. The Bayesian network use a reinforcement learning method, self-adjusting parameter weight, and automatic parameter weight adjustment to regulate the controller load congestion and anticipate the level of load congestion necessary to achieve load balance. By utilizing the prediction results from reinforcement learning, this algorithm selects the best possible next step. Theoretical analysis of the proper load balancing strategy for SDN is supported by a concurrent examination of existing datasets.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123033786","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 : 2023-03-01DOI: 10.1109/ESCI56872.2023.10100030
Ishu Sharma, Vanshika Pahuja
Vulnerability depicts the weakness in the system and it leads to risk in the extended form. Network security professionals targets to work on vulnerabilities of the network for securing information from intruder attacks. The network administrators of any organization are required to continuously take action against the vulnerabilities in the network. There is a requirement of detecting these vulnerabilities and many tools can fulfil this task. In this research paper, we presented a detailed comparative analysis of open-source vulnerability tools available in the market. This experimental study also presents a case study of campus area network scanning using the open-source innovative tool Zenmap. The results prove that the remote devices present in network infrastructure can be scanned using Zenmap without any special privilege and can provide detailed insights into the network to administrators so that they can form policies in the campus area network for threat assessment.
{"title":"Comparative Analysis of Open-Source Vulnerability Assessment Tools for Campus Area Network","authors":"Ishu Sharma, Vanshika Pahuja","doi":"10.1109/ESCI56872.2023.10100030","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10100030","url":null,"abstract":"Vulnerability depicts the weakness in the system and it leads to risk in the extended form. Network security professionals targets to work on vulnerabilities of the network for securing information from intruder attacks. The network administrators of any organization are required to continuously take action against the vulnerabilities in the network. There is a requirement of detecting these vulnerabilities and many tools can fulfil this task. In this research paper, we presented a detailed comparative analysis of open-source vulnerability tools available in the market. This experimental study also presents a case study of campus area network scanning using the open-source innovative tool Zenmap. The results prove that the remote devices present in network infrastructure can be scanned using Zenmap without any special privilege and can provide detailed insights into the network to administrators so that they can form policies in the campus area network for threat assessment.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123177967","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 : 2023-03-01DOI: 10.1109/ESCI56872.2023.10099940
Shreejeet Sahay, Pranav Pawar
One of the biggest challenges faced by humanity today is climate change. Governmental Organisations and Au-thorities all across the world, are now taking important steps to tackle this hazard, which if not dealt with, has potential of causing severe catastrophical damage, including the extinction of entire human species. One of the major contributors to this phenomenon is emissions from transport or vehicular emissions, which contribute significantly to the atmospheric concentration of CO2 or carbon dioxide, a greenhouse gas majorly responsible for climate change. The use of expensive and specialized sensors to monitor CO2 emissions in vehicles can be done, but it is neither scalable nor effective. In the proposed work, we suggest a feasible, efficient and scalable system to monitor these emissions, wherein the system proposed could be deployed on cloud, and receive the input sensor readings via IoT based dongles installed at the vehicular end, and predict the CO2 emissions. A 2-layer Long Short Term Memory (LSTM) network has been used in the proposed model, which is trained and tested on publicly available On-Board Diagnostics-II (OBD-II) data, and is compared with existing state-of-the-art model.
{"title":"An Optimal Approach to Vehicular CO2 Emissions Prediction using Deep Learning","authors":"Shreejeet Sahay, Pranav Pawar","doi":"10.1109/ESCI56872.2023.10099940","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10099940","url":null,"abstract":"One of the biggest challenges faced by humanity today is climate change. Governmental Organisations and Au-thorities all across the world, are now taking important steps to tackle this hazard, which if not dealt with, has potential of causing severe catastrophical damage, including the extinction of entire human species. One of the major contributors to this phenomenon is emissions from transport or vehicular emissions, which contribute significantly to the atmospheric concentration of CO2 or carbon dioxide, a greenhouse gas majorly responsible for climate change. The use of expensive and specialized sensors to monitor CO2 emissions in vehicles can be done, but it is neither scalable nor effective. In the proposed work, we suggest a feasible, efficient and scalable system to monitor these emissions, wherein the system proposed could be deployed on cloud, and receive the input sensor readings via IoT based dongles installed at the vehicular end, and predict the CO2 emissions. A 2-layer Long Short Term Memory (LSTM) network has been used in the proposed model, which is trained and tested on publicly available On-Board Diagnostics-II (OBD-II) data, and is compared with existing state-of-the-art model.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115355381","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 : 2023-03-01DOI: 10.1109/ESCI56872.2023.10099804
Maya Shelke, Aman Shaikh, Satayush Rai, Md Sami Mujawar, Dastagir Mulani
With the rapid development of modern society and the gradual improvement of people's living standards, the society and individuals have put forward higher requirements for safety and reliability of power supply. Therefore, the development of power distribution automation system as one of the important ways to improve the safety and reliability of power supply, when the fault occurs, the feeder terminal can report the fault information to the master station; then the master station, according to the corresponding information reported, uses the corresponding algorithm to detect the fault location quickly and accurately, and isolate it. For the non-fault power outage area, power supply is restored to reduce the loss of production and life. Therefore, studying the fault location and isolation technology for distribution network is very important to improve the reliability of distribution network. At present, the research on the fault location of smart grid has made some progress, and many scholars have proposed different programs respectively. In a published research, the developed software system can realize the information interaction among Energy Management System (EMS), Supervisory Control and Data Acquisition (SCADA) and Fault Information System (FIS); when complicated and rare faults occur, it can support operators to determine and change the fault component rapidly, so as to shorten the handling time of accidents and improve the efficiency of accident handling. In another study, the researchers improved particle swarm optimization for wavelet neural networks, and used the improved method for distribution network fault location, providing an important reference for the design and research of practical fault location system.
{"title":"An Enhanced Intelligent Algorithm on Fault Location System","authors":"Maya Shelke, Aman Shaikh, Satayush Rai, Md Sami Mujawar, Dastagir Mulani","doi":"10.1109/ESCI56872.2023.10099804","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10099804","url":null,"abstract":"With the rapid development of modern society and the gradual improvement of people's living standards, the society and individuals have put forward higher requirements for safety and reliability of power supply. Therefore, the development of power distribution automation system as one of the important ways to improve the safety and reliability of power supply, when the fault occurs, the feeder terminal can report the fault information to the master station; then the master station, according to the corresponding information reported, uses the corresponding algorithm to detect the fault location quickly and accurately, and isolate it. For the non-fault power outage area, power supply is restored to reduce the loss of production and life. Therefore, studying the fault location and isolation technology for distribution network is very important to improve the reliability of distribution network. At present, the research on the fault location of smart grid has made some progress, and many scholars have proposed different programs respectively. In a published research, the developed software system can realize the information interaction among Energy Management System (EMS), Supervisory Control and Data Acquisition (SCADA) and Fault Information System (FIS); when complicated and rare faults occur, it can support operators to determine and change the fault component rapidly, so as to shorten the handling time of accidents and improve the efficiency of accident handling. In another study, the researchers improved particle swarm optimization for wavelet neural networks, and used the improved method for distribution network fault location, providing an important reference for the design and research of practical fault location system.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125092768","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 : 2023-03-01DOI: 10.1109/ESCI56872.2023.10100172
K. Swamy, S. T. Ahmed, B. Obulesu, K. Tarun, T. H. V. Reddy, G. Deepak, B. U. Kumar, S. Kabeer
NavIC (Navigation with Indian Constellation) is an essential and indigenous positioning system developed by ISRO (Indian Space Research Organization) for all the location and navigation requirements in India. Before the deployment of NavIC in navigation and communication devices, it requires measuring and analyzing the residual bias remains in pseudorange and carrier phase observations when removing the atmospheric errors, satellite and receiver based errors. In this article we analyze the bias in NavIC pseudorange measurements on L5 band (1176.45 MHz) by using Double Difference (DD) method with different base lengths viz. zero base length, 1 meter base length, 3.56 meter base length, 5 meter base length, 7 meter base length and 9 meter base length. For all baseline lengths, the experiments were carried out in static position by using two multi-GNSS receivers at Kurnool (15. 79°N, 78.07°E), India. The pseudorange bias results were presented for a Geostationary orbit(GEO) satellite, IRNSS-1G (I07) and a Geosynchronous orbit (GSO) satellite, IRNSS-1D (I04). The satellite IRNSS-1C (I03) was considered as a reference in DD computation because of its highest elevation angle. The outcome of this research work shows that the pseudorange bias on L5 is in the range of - 0.606 m to 7.169 m and -0.019 m to 4.331 m for I04 satellite and for I07 satellite. Further the pseudo range bias increases significantly as the baseline length increases for both I04 satellite and I07.
{"title":"NavIC Pseudorange Bias Estimation and Analysis Using Double Difference Method with Different Baseline Lengths","authors":"K. Swamy, S. T. Ahmed, B. Obulesu, K. Tarun, T. H. V. Reddy, G. Deepak, B. U. Kumar, S. Kabeer","doi":"10.1109/ESCI56872.2023.10100172","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10100172","url":null,"abstract":"NavIC (Navigation with Indian Constellation) is an essential and indigenous positioning system developed by ISRO (Indian Space Research Organization) for all the location and navigation requirements in India. Before the deployment of NavIC in navigation and communication devices, it requires measuring and analyzing the residual bias remains in pseudorange and carrier phase observations when removing the atmospheric errors, satellite and receiver based errors. In this article we analyze the bias in NavIC pseudorange measurements on L5 band (1176.45 MHz) by using Double Difference (DD) method with different base lengths viz. zero base length, 1 meter base length, 3.56 meter base length, 5 meter base length, 7 meter base length and 9 meter base length. For all baseline lengths, the experiments were carried out in static position by using two multi-GNSS receivers at Kurnool (15. 79°N, 78.07°E), India. The pseudorange bias results were presented for a Geostationary orbit(GEO) satellite, IRNSS-1G (I07) and a Geosynchronous orbit (GSO) satellite, IRNSS-1D (I04). The satellite IRNSS-1C (I03) was considered as a reference in DD computation because of its highest elevation angle. The outcome of this research work shows that the pseudorange bias on L5 is in the range of - 0.606 m to 7.169 m and -0.019 m to 4.331 m for I04 satellite and for I07 satellite. Further the pseudo range bias increases significantly as the baseline length increases for both I04 satellite and I07.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130069808","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 : 2023-03-01DOI: 10.1109/ESCI56872.2023.10100292
P. K. Sahoo, Goraknath Kashyap Modali
Nowaday's most of the people are suffering from kidney diseases due to poor quality of food and water and also because of modern life style. There are so many kidney problems like Kidney Infection, Kidney Stones and Polycystic Kidney Disease. Chronic Kidney Disease is the major type of kidney disease where it is most urgent to identify CKD at the very initial stage so that it can be cured otherwise it poses a serious threat to life. Predicting CKD is a very challenging research problem as most of the research fails to produce accurate results. There were many kidney disease prediction systems that were developed by many researches which use classification & prediction algorithms but each of the algorithms has its own limitations. The main objective of this paper is to overcome the existing limitations and to predict the possibility of CKD disease accurately. The CKD dataset is being taken from UCI Repository and has 25 attributes is used for implementation. This work is implemented using the algorithms Random Forest, Decision Tree, SVM & KNN.
{"title":"An Effective Way to Identify Chronic Kidney Disease Using Machine Learning","authors":"P. K. Sahoo, Goraknath Kashyap Modali","doi":"10.1109/ESCI56872.2023.10100292","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10100292","url":null,"abstract":"Nowaday's most of the people are suffering from kidney diseases due to poor quality of food and water and also because of modern life style. There are so many kidney problems like Kidney Infection, Kidney Stones and Polycystic Kidney Disease. Chronic Kidney Disease is the major type of kidney disease where it is most urgent to identify CKD at the very initial stage so that it can be cured otherwise it poses a serious threat to life. Predicting CKD is a very challenging research problem as most of the research fails to produce accurate results. There were many kidney disease prediction systems that were developed by many researches which use classification & prediction algorithms but each of the algorithms has its own limitations. The main objective of this paper is to overcome the existing limitations and to predict the possibility of CKD disease accurately. The CKD dataset is being taken from UCI Repository and has 25 attributes is used for implementation. This work is implemented using the algorithms Random Forest, Decision Tree, SVM & KNN.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125280358","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 : 2023-03-01DOI: 10.1109/ESCI56872.2023.10099913
B. Chaudhari, Durwa Patil, Hemant A. Patil, Rupal Patil, Jui Gawali
The consumption of fruits is in high demand due to their nutritional value. Most of the fruits available in the market are processed through chemical practices hampering their quality. Exposure to fruit preservatives and carbides enhances its life and ripens it faster. However, eating such fruit results in poor health and increases the probability of getting infected by various threatening diseases such as cancer, tuberculosis, etc. Organic farming is practiced in some areas of India to achieve fruit quality, but its inadequate to fulfill the demand. To overcome the issues mentioned, a model based on IoT is proposed in this research. A system to separate quality fruits from a basket is presented in this article. The classification will be done using a deep learning technology, Convolutional Neural Network (CNN) which uses a database consisting of pictures of three fruits particularly, apples, oranges, and bananas are used in the experiment. The input from the alcohol (MQ3) sensor and methane (MQ4) sensor are fed forward to node MCU. The input in turn is provided to Arduino UNO for comparison with preprocessed audit set. The inception V3 algorithm is used for classification purposes. This research proposes a cost-effective and near-to-accurate solution to issues in automated fruit quality identification.
{"title":"Fruit Defect Inspection System Using Image Processing and IoT Framework","authors":"B. Chaudhari, Durwa Patil, Hemant A. Patil, Rupal Patil, Jui Gawali","doi":"10.1109/ESCI56872.2023.10099913","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10099913","url":null,"abstract":"The consumption of fruits is in high demand due to their nutritional value. Most of the fruits available in the market are processed through chemical practices hampering their quality. Exposure to fruit preservatives and carbides enhances its life and ripens it faster. However, eating such fruit results in poor health and increases the probability of getting infected by various threatening diseases such as cancer, tuberculosis, etc. Organic farming is practiced in some areas of India to achieve fruit quality, but its inadequate to fulfill the demand. To overcome the issues mentioned, a model based on IoT is proposed in this research. A system to separate quality fruits from a basket is presented in this article. The classification will be done using a deep learning technology, Convolutional Neural Network (CNN) which uses a database consisting of pictures of three fruits particularly, apples, oranges, and bananas are used in the experiment. The input from the alcohol (MQ3) sensor and methane (MQ4) sensor are fed forward to node MCU. The input in turn is provided to Arduino UNO for comparison with preprocessed audit set. The inception V3 algorithm is used for classification purposes. This research proposes a cost-effective and near-to-accurate solution to issues in automated fruit quality identification.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129033993","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 : 2023-03-01DOI: 10.1109/ESCI56872.2023.10099768
Swati V. Jadhav, A. J. Vyavahare
One of the main objectives of computational biology is protein structure prediction. This is important for the development of novel enzymes in biotechnology and medicine. Each protein has a certain shape and structure and our life is supported by the complex and coordinated interaction of proteins. Hence identifying the protein structure possesses various challenges and various researches are performed relying upon various classifiers. In this research a fused pipit adapted deep convolutional neural network classifier (CNN) is used for the detection of the PSS with higher accuracy. The feature extraction is made using the fused Natural language processing (NLP) based pretrained models that efficiently extracted the features and is developed using the pretrained models T5XLuniref and XLnet model. The pretrained and the deep CNN classifier is optimized effectively using the pipit optimization that mimics the foraging and the safeguarding behavior of the pipits. The enabled optimization aids in the tuning of the fusion parameters and the hyper parameters of the classifier. By measuring the improvement, the model's dominance is demonstrated, and suggested method attained an progress of 1.77 %for accuracy, 1.01 % for sensitivity and 6.90 % for specificity, which proves the efficacy of the model.
{"title":"Novel Protein Structure Prediction Model Using Fused Pipit Adapted Deep Convolutional Neural Network Classifier","authors":"Swati V. Jadhav, A. J. Vyavahare","doi":"10.1109/ESCI56872.2023.10099768","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10099768","url":null,"abstract":"One of the main objectives of computational biology is protein structure prediction. This is important for the development of novel enzymes in biotechnology and medicine. Each protein has a certain shape and structure and our life is supported by the complex and coordinated interaction of proteins. Hence identifying the protein structure possesses various challenges and various researches are performed relying upon various classifiers. In this research a fused pipit adapted deep convolutional neural network classifier (CNN) is used for the detection of the PSS with higher accuracy. The feature extraction is made using the fused Natural language processing (NLP) based pretrained models that efficiently extracted the features and is developed using the pretrained models T5XLuniref and XLnet model. The pretrained and the deep CNN classifier is optimized effectively using the pipit optimization that mimics the foraging and the safeguarding behavior of the pipits. The enabled optimization aids in the tuning of the fusion parameters and the hyper parameters of the classifier. By measuring the improvement, the model's dominance is demonstrated, and suggested method attained an progress of 1.77 %for accuracy, 1.01 % for sensitivity and 6.90 % for specificity, which proves the efficacy of the model.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120960315","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 : 2023-03-01DOI: 10.1109/ESCI56872.2023.10100330
Priyanka S. Tondewad, M. Dale
Noise is unwanted signal present in the image. Speckle noise is usually present in Synthetic Aperture Radar (SAR), ultrasound or any active radar sensor images. This noise limits the information interpretation. The proposed novel method is realized by first applying frequency domain methods for high frequency noise removal and then applying spatial domain filters. We have demonstrated various transform-based methods. Frequency domain methods gives ease to use separate bands for processing. Stationary Wavelet transform based method proves to be more efficient. Visual quality is improved as compared to the traditional speckle noise removal filters also the qualitative parameters like Peak Signal-to-Noise Ratio (PSNR), Equivalent Number of Looks (ENL), Similarity Index Measure (SSIM) and Speckle Suppression Index (SSI) and Structural are improved.
{"title":"Denoising of SAR Images using Wavelet Transforms and Wiener Filter","authors":"Priyanka S. Tondewad, M. Dale","doi":"10.1109/ESCI56872.2023.10100330","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10100330","url":null,"abstract":"Noise is unwanted signal present in the image. Speckle noise is usually present in Synthetic Aperture Radar (SAR), ultrasound or any active radar sensor images. This noise limits the information interpretation. The proposed novel method is realized by first applying frequency domain methods for high frequency noise removal and then applying spatial domain filters. We have demonstrated various transform-based methods. Frequency domain methods gives ease to use separate bands for processing. Stationary Wavelet transform based method proves to be more efficient. Visual quality is improved as compared to the traditional speckle noise removal filters also the qualitative parameters like Peak Signal-to-Noise Ratio (PSNR), Equivalent Number of Looks (ENL), Similarity Index Measure (SSIM) and Speckle Suppression Index (SSI) and Structural are improved.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116691774","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 : 2023-03-01DOI: 10.1109/ESCI56872.2023.10099548
P. Ghadekar, Aashay Bongulwar, Aayush Jadhav, Rishikesh Ahire, Amogh Dumbre, Sumaan Ali
Two of the most essential physiological signals obtained during patient care are the photoplethysmogram (PPG) and electrocardiogram (ECG). Due to recent technological advancements the correlation between the two has come to light. The significance of each signal warrants a solution to predict one when the other is absent. Also, the inexpensive and non-invasive approach of PPG provides a cheaper and comfortable way of monitoring instead of installing ECG. Thus, This study proposes a Bi-LSTM model to predict the two physiological signals. The model was successful in predicting long term data after filtering and aligning the signals efficiently with an MSE value of 0.092 and 0.065 for ECG and PPG respectively.
{"title":"Bi-LSTM based Interdependent Prediction of Physiological Signals","authors":"P. Ghadekar, Aashay Bongulwar, Aayush Jadhav, Rishikesh Ahire, Amogh Dumbre, Sumaan Ali","doi":"10.1109/ESCI56872.2023.10099548","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10099548","url":null,"abstract":"Two of the most essential physiological signals obtained during patient care are the photoplethysmogram (PPG) and electrocardiogram (ECG). Due to recent technological advancements the correlation between the two has come to light. The significance of each signal warrants a solution to predict one when the other is absent. Also, the inexpensive and non-invasive approach of PPG provides a cheaper and comfortable way of monitoring instead of installing ECG. Thus, This study proposes a Bi-LSTM model to predict the two physiological signals. The model was successful in predicting long term data after filtering and aligning the signals efficiently with an MSE value of 0.092 and 0.065 for ECG and PPG respectively.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116431751","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：