Pub Date : 2022-12-08DOI: 10.1109/IBSSC56953.2022.10037430
Wilfred Almeida
With the rise of technology, Server requirements have grown at an overwhelming pace. Accessing these servers and performing administrative tasks on them remotely has always been a great challenge. A popular utility used for this is the Secure Shell (SSH) which is being used extensively to get shell access on servers. SSH is however prone to vulnerabilities like Dictionary Attacks and Man-In-The-Middle (MITM) attacks. Further on, accessing servers from mobile devices is not yet feasible, SSH remains the de facto choice for it however SSH via third-party applications from mobile devices poses a security risk. In this paper, I've proposed an alternative system for accessing servers from mobile devices from operating systems Android and iOS. The main idea here is to keep commands pre-defined on servers and facilitate their execution from mobile applications securely.
{"title":"SC Connect: Secure Server Access from Mobile Device","authors":"Wilfred Almeida","doi":"10.1109/IBSSC56953.2022.10037430","DOIUrl":"https://doi.org/10.1109/IBSSC56953.2022.10037430","url":null,"abstract":"With the rise of technology, Server requirements have grown at an overwhelming pace. Accessing these servers and performing administrative tasks on them remotely has always been a great challenge. A popular utility used for this is the Secure Shell (SSH) which is being used extensively to get shell access on servers. SSH is however prone to vulnerabilities like Dictionary Attacks and Man-In-The-Middle (MITM) attacks. Further on, accessing servers from mobile devices is not yet feasible, SSH remains the de facto choice for it however SSH via third-party applications from mobile devices poses a security risk. In this paper, I've proposed an alternative system for accessing servers from mobile devices from operating systems Android and iOS. The main idea here is to keep commands pre-defined on servers and facilitate their execution from mobile applications securely.","PeriodicalId":426897,"journal":{"name":"2022 IEEE Bombay Section Signature Conference (IBSSC)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116945878","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-08DOI: 10.1109/IBSSC56953.2022.10037344
Abhishek Doshi, Abhinav Venkatadri, Sayali Kulkarni, Vedant Athavale, Akhila Jagarlapudi, Shraddha Suratkar, F. Kazi
Practically, Deepfake technology has given people access to generate fake videos that look like real content using neural networks, and can further create misconceptions and deceit about the innocuous elements of society. This technology can prove fatal not only to national security but on an international level. Existing methodologies that apply deep learning to automatically extract salient and discriminative features to detect Deepfakes based on typical CNN-LSTM models tend to have their shortcomings. Having said that, we propose a system that extracts Spatio-Temporal features and achieves Real-Time Deepfake detection using Transformers. For the end user, a web application was developed, which with utmost simplicity allows the uploading of a video that will be further authenticated within the application and, at the same time, features the authentication of live meetings.
{"title":"Realtime Deepfake Detection using Video Vision Transformer","authors":"Abhishek Doshi, Abhinav Venkatadri, Sayali Kulkarni, Vedant Athavale, Akhila Jagarlapudi, Shraddha Suratkar, F. Kazi","doi":"10.1109/IBSSC56953.2022.10037344","DOIUrl":"https://doi.org/10.1109/IBSSC56953.2022.10037344","url":null,"abstract":"Practically, Deepfake technology has given people access to generate fake videos that look like real content using neural networks, and can further create misconceptions and deceit about the innocuous elements of society. This technology can prove fatal not only to national security but on an international level. Existing methodologies that apply deep learning to automatically extract salient and discriminative features to detect Deepfakes based on typical CNN-LSTM models tend to have their shortcomings. Having said that, we propose a system that extracts Spatio-Temporal features and achieves Real-Time Deepfake detection using Transformers. For the end user, a web application was developed, which with utmost simplicity allows the uploading of a video that will be further authenticated within the application and, at the same time, features the authentication of live meetings.","PeriodicalId":426897,"journal":{"name":"2022 IEEE Bombay Section Signature Conference (IBSSC)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134642735","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-08DOI: 10.1109/IBSSC56953.2022.10037428
Subha Sreekumar, Lijiya A
Developmental Dyslexia, one of the learning disabilities is a topic of scientific interest in a variety of disciplines such as psychology, speech and language therapy, data science, etc. While the reason for Dyslexia and its symptoms are still being researched by psychologists, data science is providing ways to intervene and detect them with the aid of technological advancements. Dyslexia is a neurological condition that impairs reading comprehension and has long-lasting impacts. But timely detection and intervention programs can alleviate its effects to a certain extent. This study aims to classify images of handwritten English characters into three classes namely: normal, corrected, and reversed, where normal class refers to normal handwriting, and corrected or reversed constitutes handwriting of children with Dyslexia. The dataset used for the study is available publicly on Kaggle. The building of an efficient CNN (Convolutional Neural Network) model for classifying dyslexic handwriting is the major emphasis of this work. This is accomplished by comparing several CNN models and evaluating how well they detect Dyslexia on the same dataset. The proposed CNN approach has demonstrated a sizable improvement in reliably classifying dyslexic handwritten images.
{"title":"Comparative Study of CNN Models on the Classification of Dyslexic Handwriting","authors":"Subha Sreekumar, Lijiya A","doi":"10.1109/IBSSC56953.2022.10037428","DOIUrl":"https://doi.org/10.1109/IBSSC56953.2022.10037428","url":null,"abstract":"Developmental Dyslexia, one of the learning disabilities is a topic of scientific interest in a variety of disciplines such as psychology, speech and language therapy, data science, etc. While the reason for Dyslexia and its symptoms are still being researched by psychologists, data science is providing ways to intervene and detect them with the aid of technological advancements. Dyslexia is a neurological condition that impairs reading comprehension and has long-lasting impacts. But timely detection and intervention programs can alleviate its effects to a certain extent. This study aims to classify images of handwritten English characters into three classes namely: normal, corrected, and reversed, where normal class refers to normal handwriting, and corrected or reversed constitutes handwriting of children with Dyslexia. The dataset used for the study is available publicly on Kaggle. The building of an efficient CNN (Convolutional Neural Network) model for classifying dyslexic handwriting is the major emphasis of this work. This is accomplished by comparing several CNN models and evaluating how well they detect Dyslexia on the same dataset. The proposed CNN approach has demonstrated a sizable improvement in reliably classifying dyslexic handwritten images.","PeriodicalId":426897,"journal":{"name":"2022 IEEE Bombay Section Signature Conference (IBSSC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123658897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-08DOI: 10.1109/IBSSC56953.2022.10037326
Mohd. Aquib Ansari, D. Singh
These days, there has been a rapid increase in cases of abnormal human behavior at megastores/shops, where people commit theft by stealing, consuming, or unwrapping packets when no one is seeing and then leaving the place without paying. Such unusual actions cause huge losses in business. Therefore, there is an urgent need to attract the research community's attention to detect abnormal events at megastores. To address this issue, we have designed an advanced three-dimensional convolutional neural architecture to identify abnormal activities at megastores. The proposed network is 15 layers deep, takes a video stream of resolution 120× 120 as input, and produces classification results as output. It extracts fine-tuned as well as general details from the video feed using small and large-sized 3D convolutional filters and categorizes them into respective classes. The proposed architecture is trained and tested on a synthesized action dataset that consists of human actions distributed into five classes: normal, stealing, eating, drinking, and damaging acts. Experimental results show that our model outperforms other state-of-the-art approaches with an accuracy of 88.88%.
{"title":"Deep-3DConvNet: A Network to Detect Abnormal Activities at Megastores","authors":"Mohd. Aquib Ansari, D. Singh","doi":"10.1109/IBSSC56953.2022.10037326","DOIUrl":"https://doi.org/10.1109/IBSSC56953.2022.10037326","url":null,"abstract":"These days, there has been a rapid increase in cases of abnormal human behavior at megastores/shops, where people commit theft by stealing, consuming, or unwrapping packets when no one is seeing and then leaving the place without paying. Such unusual actions cause huge losses in business. Therefore, there is an urgent need to attract the research community's attention to detect abnormal events at megastores. To address this issue, we have designed an advanced three-dimensional convolutional neural architecture to identify abnormal activities at megastores. The proposed network is 15 layers deep, takes a video stream of resolution 120× 120 as input, and produces classification results as output. It extracts fine-tuned as well as general details from the video feed using small and large-sized 3D convolutional filters and categorizes them into respective classes. The proposed architecture is trained and tested on a synthesized action dataset that consists of human actions distributed into five classes: normal, stealing, eating, drinking, and damaging acts. Experimental results show that our model outperforms other state-of-the-art approaches with an accuracy of 88.88%.","PeriodicalId":426897,"journal":{"name":"2022 IEEE Bombay Section Signature Conference (IBSSC)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121527475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-08DOI: 10.1109/IBSSC56953.2022.10037572
Kuni Naik, D. Kumari, M. Tahiliani
Standard Ethernet networks cannot provide solutions to handle latency sensitive applications efficiently. The packet scheduling algorithms like First In First Out (FIFO), Class Based Queueing (CBQ), and others do not provide efficient solutions to Quality of Service (QoS) parameters like end-toend delay, packet loss, and jitter. Time Sensitive Networking (TSN) can be used as a solution to provide QoS to time sensitive applications. TSN has emerged as a future of realtime communication. The main advantage of TSN is that it enables determinism by supporting time critical traffic while the best effort traffic is also present in the network. This paper explores two of the most popular and widespread traffic shaping mechanisms in TSN: Time Aware Shaper (TAS) and Credit Based Shaper (CBS). IEEE 802.1Qbv is used for delivering time assurance using TAS. CBS is a key traffic shaping algorithm to provide bandwidth assurance to the time critical and real time traffic, such as the audio traffic. This paper evaluates TAS and CBS using TSN enabled Network Interface Cards (NIC) with time synchronization, real time kernel and real traffic, which includes time sensitive traffic and elastic background traffic.
{"title":"Empirical Evaluation of Traffic Shaping Algorithms for Time Sensitive Networking","authors":"Kuni Naik, D. Kumari, M. Tahiliani","doi":"10.1109/IBSSC56953.2022.10037572","DOIUrl":"https://doi.org/10.1109/IBSSC56953.2022.10037572","url":null,"abstract":"Standard Ethernet networks cannot provide solutions to handle latency sensitive applications efficiently. The packet scheduling algorithms like First In First Out (FIFO), Class Based Queueing (CBQ), and others do not provide efficient solutions to Quality of Service (QoS) parameters like end-toend delay, packet loss, and jitter. Time Sensitive Networking (TSN) can be used as a solution to provide QoS to time sensitive applications. TSN has emerged as a future of realtime communication. The main advantage of TSN is that it enables determinism by supporting time critical traffic while the best effort traffic is also present in the network. This paper explores two of the most popular and widespread traffic shaping mechanisms in TSN: Time Aware Shaper (TAS) and Credit Based Shaper (CBS). IEEE 802.1Qbv is used for delivering time assurance using TAS. CBS is a key traffic shaping algorithm to provide bandwidth assurance to the time critical and real time traffic, such as the audio traffic. This paper evaluates TAS and CBS using TSN enabled Network Interface Cards (NIC) with time synchronization, real time kernel and real traffic, which includes time sensitive traffic and elastic background traffic.","PeriodicalId":426897,"journal":{"name":"2022 IEEE Bombay Section Signature Conference (IBSSC)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116572119","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-08DOI: 10.1109/IBSSC56953.2022.10037463
A. Shaikh, M. Joshi
This paper gives an overview of various types of antennas used in airborne applications such as delivery using UAVs, defence, disaster management. Antenna characteristics are very sensitive and must be used before implementing in airborne applications. Because of different nature of aerial body on which antennas are mounted, different antenna positions will result in variations in the radiation pattern. In recent studies, researcher considers antenna positioning with respect to azimuth and elevation angles. Effect of aerial body on antenna, its signal strength and radiation pattern is observable. Cross polarization discrimination occurs due to polarization mixing of communicating channels.
{"title":"Antennas in Airborne Applications","authors":"A. Shaikh, M. Joshi","doi":"10.1109/IBSSC56953.2022.10037463","DOIUrl":"https://doi.org/10.1109/IBSSC56953.2022.10037463","url":null,"abstract":"This paper gives an overview of various types of antennas used in airborne applications such as delivery using UAVs, defence, disaster management. Antenna characteristics are very sensitive and must be used before implementing in airborne applications. Because of different nature of aerial body on which antennas are mounted, different antenna positions will result in variations in the radiation pattern. In recent studies, researcher considers antenna positioning with respect to azimuth and elevation angles. Effect of aerial body on antenna, its signal strength and radiation pattern is observable. Cross polarization discrimination occurs due to polarization mixing of communicating channels.","PeriodicalId":426897,"journal":{"name":"2022 IEEE Bombay Section Signature Conference (IBSSC)","volume":"240 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121122632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-08DOI: 10.1109/IBSSC56953.2022.10037561
Malik Obaid Ul Islam, S. A. Parah, B. A. Malik
Medical images play a vital role in disease diagnosis. When the medical images are communicated through an insecure transmission channel, their chances of being accessed by an unauthorized user increase resulting in the loss of patients' sensitive personal data. Thus, providing security to such image data while transmitting it over an insecure communication network becomes crucial. This work presents a computationally efficient cryptosystem for encrypting medical images. The encryption process consists of multiple phases. In the first phase the control parameters and initial values for the various chaotic maps used, are evaluated. This phase is followed by encryption in which these evaluated values are used to obtain the chaotic sequences for encryption. In the subsequent phases, we make use of a new approach of selective, pixel-dependent diffusion to obtain the cipher image. The effectiveness of our cryptosystem is evaluated using security analysis and execution time analysis. The obtained outcome shows a high-security level compared to already existing state-of-the-art techniques. In addition, the computational complexity of our scheme is very small (0.1sec for encrypting a 256×256 image) making it suitable for real-time smart health applications.
{"title":"Computationally efficient image encryption technique based on selective pixel diffusion","authors":"Malik Obaid Ul Islam, S. A. Parah, B. A. Malik","doi":"10.1109/IBSSC56953.2022.10037561","DOIUrl":"https://doi.org/10.1109/IBSSC56953.2022.10037561","url":null,"abstract":"Medical images play a vital role in disease diagnosis. When the medical images are communicated through an insecure transmission channel, their chances of being accessed by an unauthorized user increase resulting in the loss of patients' sensitive personal data. Thus, providing security to such image data while transmitting it over an insecure communication network becomes crucial. This work presents a computationally efficient cryptosystem for encrypting medical images. The encryption process consists of multiple phases. In the first phase the control parameters and initial values for the various chaotic maps used, are evaluated. This phase is followed by encryption in which these evaluated values are used to obtain the chaotic sequences for encryption. In the subsequent phases, we make use of a new approach of selective, pixel-dependent diffusion to obtain the cipher image. The effectiveness of our cryptosystem is evaluated using security analysis and execution time analysis. The obtained outcome shows a high-security level compared to already existing state-of-the-art techniques. In addition, the computational complexity of our scheme is very small (0.1sec for encrypting a 256×256 image) making it suitable for real-time smart health applications.","PeriodicalId":426897,"journal":{"name":"2022 IEEE Bombay Section Signature Conference (IBSSC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116913667","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}
In contemporary times it is observed that the climatic and weather conditions have become skeptical and unpredictable. To confound this unreliable nature and variability of weather conditions, we present an experimental setup of loT-based local weather stations. This paper presents the design and implementation details of the experimental setup, ESP8266-based Wi-fi module NodeMCU (12E) is the brain of the prototype. Two sensors are connected to the NodeMCU, namely a temperature and humidity sensor (DHT11), and an Air quality gas sensor (MQ135). Additionally, to display the results, we present VIT Weather Station’ - A local weather station app which can keep people updated regarding the environmental conditions utilizing live data collection and display. The device will monitor the temperature, humidity, and air quality index. This application is supported on Android as well as IOS systems. Local users can also view the monitored data from Twitter for easier convenience.
{"title":"Design and Implementation of IoT Based Local Weather Station - An Experimental Setup","authors":"Nikuni Tandan, Anup Kanse, Oj Uparkar, Riya Modi, Harish Karnam, Saurabh Mehta, Akshaj Raut, Sonali Bedade","doi":"10.1109/IBSSC56953.2022.10037309","DOIUrl":"https://doi.org/10.1109/IBSSC56953.2022.10037309","url":null,"abstract":"In contemporary times it is observed that the climatic and weather conditions have become skeptical and unpredictable. To confound this unreliable nature and variability of weather conditions, we present an experimental setup of loT-based local weather stations. This paper presents the design and implementation details of the experimental setup, ESP8266-based Wi-fi module NodeMCU (12E) is the brain of the prototype. Two sensors are connected to the NodeMCU, namely a temperature and humidity sensor (DHT11), and an Air quality gas sensor (MQ135). Additionally, to display the results, we present VIT Weather Station’ - A local weather station app which can keep people updated regarding the environmental conditions utilizing live data collection and display. The device will monitor the temperature, humidity, and air quality index. This application is supported on Android as well as IOS systems. Local users can also view the monitored data from Twitter for easier convenience.","PeriodicalId":426897,"journal":{"name":"2022 IEEE Bombay Section Signature Conference (IBSSC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130227185","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-08DOI: 10.1109/IBSSC56953.2022.10037274
S. Ghosal, Amit Jain, D. Tayal
With the rapid growth of social media text, millions of negative comments are flowing on social webs and social networking sites. Abusive content is harmful to people and societies that can provoke various criminal offenses like hate crimes. Hate speech is also a form of abusive content. An automatic and improved detection system for hate speech can help to reduce this problem. Implicit abusive content requires contextual semantic and syntactical analysis. We propose a novel abusive text detection model with the word2vec model and compositional vector model to analyze text more semantically and syntactically. The proposed model considers the English language dataset for abusive text. The abusive content detection model exhibits achievable performance compare to various deep learning and machine learning classifiers. Among all models, Multilayer Perceptron classifier achieves 86% accuracy compared to other models.
{"title":"An approach to detect abusive content incorporating Word2Vec and Multilayer Perceptron","authors":"S. Ghosal, Amit Jain, D. Tayal","doi":"10.1109/IBSSC56953.2022.10037274","DOIUrl":"https://doi.org/10.1109/IBSSC56953.2022.10037274","url":null,"abstract":"With the rapid growth of social media text, millions of negative comments are flowing on social webs and social networking sites. Abusive content is harmful to people and societies that can provoke various criminal offenses like hate crimes. Hate speech is also a form of abusive content. An automatic and improved detection system for hate speech can help to reduce this problem. Implicit abusive content requires contextual semantic and syntactical analysis. We propose a novel abusive text detection model with the word2vec model and compositional vector model to analyze text more semantically and syntactically. The proposed model considers the English language dataset for abusive text. The abusive content detection model exhibits achievable performance compare to various deep learning and machine learning classifiers. Among all models, Multilayer Perceptron classifier achieves 86% accuracy compared to other models.","PeriodicalId":426897,"journal":{"name":"2022 IEEE Bombay Section Signature Conference (IBSSC)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121985403","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-08DOI: 10.1109/IBSSC56953.2022.10037453
Bed Prakash Das, K. D. Sharma, A. Chatterjee, J. Bera
An adaptive filtering approach is proposed in this paper to address the thermal state estimation methodology along with the model parameters jointly for an indoor thermodynamic resistance capacitance model with uncertain stochastic heating inputs. The adaptive dynamics of the state of the model is combined with a particle swarm optimization (PSO) based metaheuristic approach to feed the knowledge of measurement noise statistics and the initial estimation error covariance along with forgetting factor for implementation of fading memory Kalman filter (FMKF). This study has been carried out with the variation of uncertain influential input information to enhance the estimation efficiency with the proposed PSO adaptive FMKF (PSO-AdFMKF) strategy for a real life the test thermodynamic environment scenario inside the building space. Potential observations demonstrate that the proposed estimation algorithm performs encouragingly, with a satisfactory improvement of estimation performance in terms of evaluating error metrics.
{"title":"PSO Adaptive Fading Memory Kalman Filter Based State Estimation of Indoor Thermal Model with Unknown Inputs","authors":"Bed Prakash Das, K. D. Sharma, A. Chatterjee, J. Bera","doi":"10.1109/IBSSC56953.2022.10037453","DOIUrl":"https://doi.org/10.1109/IBSSC56953.2022.10037453","url":null,"abstract":"An adaptive filtering approach is proposed in this paper to address the thermal state estimation methodology along with the model parameters jointly for an indoor thermodynamic resistance capacitance model with uncertain stochastic heating inputs. The adaptive dynamics of the state of the model is combined with a particle swarm optimization (PSO) based metaheuristic approach to feed the knowledge of measurement noise statistics and the initial estimation error covariance along with forgetting factor for implementation of fading memory Kalman filter (FMKF). This study has been carried out with the variation of uncertain influential input information to enhance the estimation efficiency with the proposed PSO adaptive FMKF (PSO-AdFMKF) strategy for a real life the test thermodynamic environment scenario inside the building space. Potential observations demonstrate that the proposed estimation algorithm performs encouragingly, with a satisfactory improvement of estimation performance in terms of evaluating error metrics.","PeriodicalId":426897,"journal":{"name":"2022 IEEE Bombay Section Signature Conference (IBSSC)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125745114","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：