Pub Date : 2021-10-21DOI: 10.1109/ICACC-202152719.2021.9708150
S. Liji, P. Muhamed Ilyas
Covid-19 is a global pandemic, has affected millions of people physically and mentally. The dynamic and rapidly growing situation with COVID-19 made it more difficult to discourse accurate and authoritative information about the disease, in most of the Indian local languages like Malayalam. To resolve this issue, here we propose a semantic Malayalam Dialogue System for COVID-19 related Question Answering. This is a user-friendly knowledge system to automatically deliver relevant answers to COVID-19 related queries in the Malayalam language. The proposed system proceeds in three stages; Document pre-processing, Semantic modelling using word embedding and Answer Retrieval. The NLP techniques are used for document processing, word embedding - CBOW and Skip Gram methods, Neural Network models are used for Semantic Modelling and finally, a cosine similarity measure is used to map and retrieve the answers for the user's queries. The experiment was conducted with our own Malayalam dataset; and compared the performance of two Word2Vec algorithms - CBOW and Skip Gram. The result, with our data set, shows that Skip-Gram is more efficient than CBOW and CBOW is faster than the Skip Gram model.
{"title":"Semantic Malayalam Dialogue System For Covid-19 Question Answering Using Word Embedding And Cosine Similarity","authors":"S. Liji, P. Muhamed Ilyas","doi":"10.1109/ICACC-202152719.2021.9708150","DOIUrl":"https://doi.org/10.1109/ICACC-202152719.2021.9708150","url":null,"abstract":"Covid-19 is a global pandemic, has affected millions of people physically and mentally. The dynamic and rapidly growing situation with COVID-19 made it more difficult to discourse accurate and authoritative information about the disease, in most of the Indian local languages like Malayalam. To resolve this issue, here we propose a semantic Malayalam Dialogue System for COVID-19 related Question Answering. This is a user-friendly knowledge system to automatically deliver relevant answers to COVID-19 related queries in the Malayalam language. The proposed system proceeds in three stages; Document pre-processing, Semantic modelling using word embedding and Answer Retrieval. The NLP techniques are used for document processing, word embedding - CBOW and Skip Gram methods, Neural Network models are used for Semantic Modelling and finally, a cosine similarity measure is used to map and retrieve the answers for the user's queries. The experiment was conducted with our own Malayalam dataset; and compared the performance of two Word2Vec algorithms - CBOW and Skip Gram. The result, with our data set, shows that Skip-Gram is more efficient than CBOW and CBOW is faster than the Skip Gram model.","PeriodicalId":198810,"journal":{"name":"2021 International Conference on Advances in Computing and Communications (ICACC)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133478523","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 : 2021-10-21DOI: 10.1109/ICACC-202152719.2021.9708244
M. Sabeena, L. Abraham, P. Sreelekshmi
Fake news, frequently making use of tampered photos, has currently emerged as a global epidemic, mainly due to the widespread use of social media as a present alternative to traditional news outlets. This development is often due to the swiftly declining price of advanced cameras and phones, which prompts the simple making of computerized pictures. The accessibility and usability of picture-altering softwares make picture-altering or controlling processes significantly simple, regardless of whether it is for the blameless or malicious plan. Various investigations have been utilized around to distinguish this sort of controlled media to deal with this issue. This paper proposes an efficient technique of copy-move forgery detection using the deep learning method. Two deep learning models such as Buster Net and VGG with FPN are used here to detect copy move forgery in digital images. The two models' performance is evaluated using the CoMoFoD dataset. The experimental result shows that VGG with FPN outperforms the Buster Net model for detecting forgery in images with an accuracy of 99.8% whereas the accuracy for the Buster Net model is 96.9%.
{"title":"Copy-move Image Forgery Localization Using Deep Feature Pyramidal Network","authors":"M. Sabeena, L. Abraham, P. Sreelekshmi","doi":"10.1109/ICACC-202152719.2021.9708244","DOIUrl":"https://doi.org/10.1109/ICACC-202152719.2021.9708244","url":null,"abstract":"Fake news, frequently making use of tampered photos, has currently emerged as a global epidemic, mainly due to the widespread use of social media as a present alternative to traditional news outlets. This development is often due to the swiftly declining price of advanced cameras and phones, which prompts the simple making of computerized pictures. The accessibility and usability of picture-altering softwares make picture-altering or controlling processes significantly simple, regardless of whether it is for the blameless or malicious plan. Various investigations have been utilized around to distinguish this sort of controlled media to deal with this issue. This paper proposes an efficient technique of copy-move forgery detection using the deep learning method. Two deep learning models such as Buster Net and VGG with FPN are used here to detect copy move forgery in digital images. The two models' performance is evaluated using the CoMoFoD dataset. The experimental result shows that VGG with FPN outperforms the Buster Net model for detecting forgery in images with an accuracy of 99.8% whereas the accuracy for the Buster Net model is 96.9%.","PeriodicalId":198810,"journal":{"name":"2021 International Conference on Advances in Computing and Communications (ICACC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117222344","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 : 2021-10-21DOI: 10.1109/ICACC-202152719.2021.9708193
Neenu Johnson, M. B. Santosh Kumar, T. Dhannia
Deep learning has emerged as a precise tool for image and non-image-based data analytics in various domains. Smart farming is a major domain where deep learning approaches have been effectively applied for crop data analytics. Crop monitoring is a significant task in smart farming to enhance agricultural productivity. Accurate prediction of crop yield with limited availability of information related to environmental parameters is the main challenge. Crop diseases are often the major reason for yield loss. In developing countries, rural farmers are not equipped with modern techniques for real-time crop disease detection and thus fail to implement corrective actions. Recently, deep learning approaches have proven to be more effective in generating more accurate results in crop data analytics. In this study, research works pertaining to deep learning-based models applied in crop yield estimation and crop disease detection are reviewed.
{"title":"A survey on Deep Learning Architectures for effective Crop Data Analytics","authors":"Neenu Johnson, M. B. Santosh Kumar, T. Dhannia","doi":"10.1109/ICACC-202152719.2021.9708193","DOIUrl":"https://doi.org/10.1109/ICACC-202152719.2021.9708193","url":null,"abstract":"Deep learning has emerged as a precise tool for image and non-image-based data analytics in various domains. Smart farming is a major domain where deep learning approaches have been effectively applied for crop data analytics. Crop monitoring is a significant task in smart farming to enhance agricultural productivity. Accurate prediction of crop yield with limited availability of information related to environmental parameters is the main challenge. Crop diseases are often the major reason for yield loss. In developing countries, rural farmers are not equipped with modern techniques for real-time crop disease detection and thus fail to implement corrective actions. Recently, deep learning approaches have proven to be more effective in generating more accurate results in crop data analytics. In this study, research works pertaining to deep learning-based models applied in crop yield estimation and crop disease detection are reviewed.","PeriodicalId":198810,"journal":{"name":"2021 International Conference on Advances in Computing and Communications (ICACC)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117234732","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 : 2021-10-21DOI: 10.1109/ICACC-202152719.2021.9708189
D. Pradeep, A. Harsha, J. Jacob
The superior breadth of data transmission through the internet is rapidly increasing in the current scenario. The information in the form of images is really critical in the fields of Banking, Military, Medicine, etc, especially, in the medical field as people are unable to travel to different locations, they rely on telemedicine facilities available. All these fields are equally vulnerable to intruders. So, to prevent such an act, encryption of these data in the form of images can be done using chaos encryption. Chaos Encryption has its long way in the field of Secure Communication. Their Unique features offer much more security than any conventional algorithms. There are many simple chaotic maps that could be used for encryption. In this paper, at first Henon chaotic maps is used for the encryption purpose. The comparison of the algorithm with conventional algorithms is also done. Finally, a security analysis for proving the robustness of the algorithm is carried out. Also, different existing and some new versions are compared so as to check whether a new combination could produce a better result. The simulation results show that the proposed algorithm is robust and simple to be used for this application. Also, found a new combination of the map to be used for the application.
{"title":"Image Encryption Using Chaotic Map And Related Analysis","authors":"D. Pradeep, A. Harsha, J. Jacob","doi":"10.1109/ICACC-202152719.2021.9708189","DOIUrl":"https://doi.org/10.1109/ICACC-202152719.2021.9708189","url":null,"abstract":"The superior breadth of data transmission through the internet is rapidly increasing in the current scenario. The information in the form of images is really critical in the fields of Banking, Military, Medicine, etc, especially, in the medical field as people are unable to travel to different locations, they rely on telemedicine facilities available. All these fields are equally vulnerable to intruders. So, to prevent such an act, encryption of these data in the form of images can be done using chaos encryption. Chaos Encryption has its long way in the field of Secure Communication. Their Unique features offer much more security than any conventional algorithms. There are many simple chaotic maps that could be used for encryption. In this paper, at first Henon chaotic maps is used for the encryption purpose. The comparison of the algorithm with conventional algorithms is also done. Finally, a security analysis for proving the robustness of the algorithm is carried out. Also, different existing and some new versions are compared so as to check whether a new combination could produce a better result. The simulation results show that the proposed algorithm is robust and simple to be used for this application. Also, found a new combination of the map to be used for the application.","PeriodicalId":198810,"journal":{"name":"2021 International Conference on Advances in Computing and Communications (ICACC)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123166779","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 : 2021-10-21DOI: 10.1109/ICACC-202152719.2021.9708136
R. Sreemol, M. B. Santosh Kumar, A. Sreekumar
Numerous prevalent techniques build a Multi-Modal Biometric (MMB) system that struggles in offering security and also revocability onto the templates. This work proffered a MMB system centred on the Modulus Fuzzy Vault (MFV) aimed at resolving these issues. The methodology proposed includes Fingerprint (FP), Palmprint (PP), Ear and also Retina images. Utilizing the Boosted Double Plateau Histogram Equalization (BDPHE) technique, all images are improved. Aimed at removing the unnecessary things as of the ear and the blood vessels are segmented as of the retina images utilizing the Modified Balanced Iterative Reducing and Clustering using Hierarchy (MBIRCH) technique. Next, the input traits features are extracted; then the essential features are chosen as of the features extracted utilizing the Bidirectional Deer Hunting optimization Algorithm (BDHOA). The features chosen are merged utilizing the Normalized Feature Level and Score Level (NFLSL) fusion. The features fused are saved securely utilizing Modulus Fuzzy Vault. Upto fusion, the procedure is repeated aimed at the query image template. Next, the de-Fuzzy Vault procedure is executed aimed at the query template, and then the key is detached by matching the query template’s and input biometric template features. The key separated is analogized with the threshold that categorizes the user as genuine or else imposter. The proposed BDPHE and also MFV techniques function efficiently than the existent techniques.
{"title":"Improvement of Security in Multi-Biometric Cryptosystem by Modulus Fuzzy Vault Algorithm","authors":"R. Sreemol, M. B. Santosh Kumar, A. Sreekumar","doi":"10.1109/ICACC-202152719.2021.9708136","DOIUrl":"https://doi.org/10.1109/ICACC-202152719.2021.9708136","url":null,"abstract":"Numerous prevalent techniques build a Multi-Modal Biometric (MMB) system that struggles in offering security and also revocability onto the templates. This work proffered a MMB system centred on the Modulus Fuzzy Vault (MFV) aimed at resolving these issues. The methodology proposed includes Fingerprint (FP), Palmprint (PP), Ear and also Retina images. Utilizing the Boosted Double Plateau Histogram Equalization (BDPHE) technique, all images are improved. Aimed at removing the unnecessary things as of the ear and the blood vessels are segmented as of the retina images utilizing the Modified Balanced Iterative Reducing and Clustering using Hierarchy (MBIRCH) technique. Next, the input traits features are extracted; then the essential features are chosen as of the features extracted utilizing the Bidirectional Deer Hunting optimization Algorithm (BDHOA). The features chosen are merged utilizing the Normalized Feature Level and Score Level (NFLSL) fusion. The features fused are saved securely utilizing Modulus Fuzzy Vault. Upto fusion, the procedure is repeated aimed at the query image template. Next, the de-Fuzzy Vault procedure is executed aimed at the query template, and then the key is detached by matching the query template’s and input biometric template features. The key separated is analogized with the threshold that categorizes the user as genuine or else imposter. The proposed BDPHE and also MFV techniques function efficiently than the existent techniques.","PeriodicalId":198810,"journal":{"name":"2021 International Conference on Advances in Computing and Communications (ICACC)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133893083","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 : 2021-10-21DOI: 10.1109/ICACC-202152719.2021.9708352
Keziah Elizabeth George, Angel Mary, A. M. Varghese, M. Sivadas, Ambili Mohan, Akhil Santhosh
A launch vehicle(LV) or carrier rocket is a rocket-driven vehicle used to move a payload from the surface of the Earth to space. A typical LV consists of lateral and longitudinal dynamics. This paper addresses the control of a LV’s longitudinal dynamics. The control strategy focuses predominantly on the control of pitch angle. Only the rigid body dynamics of a launch vehicle system is considered. Here, an H Infinity (H∞) control method is developed for governing the pitch angle. MATLAB software is used for the simulation of the controller. The desired specifications are chosen for the nominal plant and the controller is designed by appropriate weight selection process. Later, robustness and disturbance checks were analyzed. The result of the simulation shows that the designed controller is robust and is able to handle perturbations.
{"title":"Robust Attitude Control Of Launch Vehicle Using H∞ Controller","authors":"Keziah Elizabeth George, Angel Mary, A. M. Varghese, M. Sivadas, Ambili Mohan, Akhil Santhosh","doi":"10.1109/ICACC-202152719.2021.9708352","DOIUrl":"https://doi.org/10.1109/ICACC-202152719.2021.9708352","url":null,"abstract":"A launch vehicle(LV) or carrier rocket is a rocket-driven vehicle used to move a payload from the surface of the Earth to space. A typical LV consists of lateral and longitudinal dynamics. This paper addresses the control of a LV’s longitudinal dynamics. The control strategy focuses predominantly on the control of pitch angle. Only the rigid body dynamics of a launch vehicle system is considered. Here, an H Infinity (H∞) control method is developed for governing the pitch angle. MATLAB software is used for the simulation of the controller. The desired specifications are chosen for the nominal plant and the controller is designed by appropriate weight selection process. Later, robustness and disturbance checks were analyzed. The result of the simulation shows that the designed controller is robust and is able to handle perturbations.","PeriodicalId":198810,"journal":{"name":"2021 International Conference on Advances in Computing and Communications (ICACC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133247797","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 : 2021-10-21DOI: 10.1109/ICACC-202152719.2021.9708141
Riyad Bin Rafiq, S. Hakim, Thasina Tabashum
Sign Language is an essential means of communication for people with speech and hearing impairment. In spite of this, there are no effective tools to assist the social interaction between Bangla sign language speakers and non-sign language speakers. Our main objective is to implement an automated translation system that is capable of translating Bangla sign language to Bangla text using common computing environments such as a computer and a generic webcam. The dataset has been created for this project with 1500 images for 10 signs. A seven-layered custom sequential CNN model has been trained and validated with the processed dataset. For real-time detection, we have extracted the region of interest and then detected the specified sign. The system runs in real-time and can provide output from a video feed with a time delay of 120.6 ms. Our system has been tested for an accuracy of 97.0%.
{"title":"Real-time Vision-based Bangla Sign Language Detection using Convolutional Neural Network","authors":"Riyad Bin Rafiq, S. Hakim, Thasina Tabashum","doi":"10.1109/ICACC-202152719.2021.9708141","DOIUrl":"https://doi.org/10.1109/ICACC-202152719.2021.9708141","url":null,"abstract":"Sign Language is an essential means of communication for people with speech and hearing impairment. In spite of this, there are no effective tools to assist the social interaction between Bangla sign language speakers and non-sign language speakers. Our main objective is to implement an automated translation system that is capable of translating Bangla sign language to Bangla text using common computing environments such as a computer and a generic webcam. The dataset has been created for this project with 1500 images for 10 signs. A seven-layered custom sequential CNN model has been trained and validated with the processed dataset. For real-time detection, we have extracted the region of interest and then detected the specified sign. The system runs in real-time and can provide output from a video feed with a time delay of 120.6 ms. Our system has been tested for an accuracy of 97.0%.","PeriodicalId":198810,"journal":{"name":"2021 International Conference on Advances in Computing and Communications (ICACC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131349449","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 : 2021-10-21DOI: 10.1109/ICACC-202152719.2021.9708344
Mohit Taneja, S. Bhiwapurkar, N. Mohanty, B. Bhattacharyya
With the world rapidly shifting towards digital and wireless technology, visibility and vulnerability are to be taken into consideration in order to avoid conflict and protect one’s data since security is a major concern to be addressed. The proposed system tests wireless networks through a programmed Unmanned Aircraft System (UAS) which detects and helps analyze datasets obtained such as locations of Access Points, Media Access Control (MAC) addresses, authentication, power, privacy, and cipher settings, which are then filtered and sorted to be represented visually in the form of heatmap and bar charts. The latter working of the model involves various attacks like Deauthentication attack, Beacon attack, Probe attack and Rogue Access Points which contribute to communication jamming, Denial of Service (DoS), replication of Access Points and logging data of the same; These showcase strength of security and can be developed to contribute in defense purposes and threat analysis.
{"title":"Vulnerability Analysis and Testing of Wireless Networks through Warstorming","authors":"Mohit Taneja, S. Bhiwapurkar, N. Mohanty, B. Bhattacharyya","doi":"10.1109/ICACC-202152719.2021.9708344","DOIUrl":"https://doi.org/10.1109/ICACC-202152719.2021.9708344","url":null,"abstract":"With the world rapidly shifting towards digital and wireless technology, visibility and vulnerability are to be taken into consideration in order to avoid conflict and protect one’s data since security is a major concern to be addressed. The proposed system tests wireless networks through a programmed Unmanned Aircraft System (UAS) which detects and helps analyze datasets obtained such as locations of Access Points, Media Access Control (MAC) addresses, authentication, power, privacy, and cipher settings, which are then filtered and sorted to be represented visually in the form of heatmap and bar charts. The latter working of the model involves various attacks like Deauthentication attack, Beacon attack, Probe attack and Rogue Access Points which contribute to communication jamming, Denial of Service (DoS), replication of Access Points and logging data of the same; These showcase strength of security and can be developed to contribute in defense purposes and threat analysis.","PeriodicalId":198810,"journal":{"name":"2021 International Conference on Advances in Computing and Communications (ICACC)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132817263","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 : 2021-10-21DOI: 10.1109/ICACC-202152719.2021.9708114
Smaranika Mishra, S. Swain, Rajat Kumar Samantaray
Presently electric vehicles (EVs) are considered as most propitious solution for the replacement of internal combustion (IC) engine-based vehicle. The development of EV technologies is growing rapidly and the battery technology is an important concept for development of the electric vehicles. The EV performance mainly relies on the battery performance and battery management system (BMS). Recently, the Lithium-ion (Li-ion) battery is mainly used as a battery in EVs due to smaller weight, high energy density and capability of fast charging and discharging. Considering the dynamic performance, economy, safety friendliness to the environment of the EVs, the BMS is designed such a way to meet the challenges like the energy management of battery, reduction of heating-time at low temperature and enhancing remaining-useful life (RUL) with accuracy of prediction. The battery is managed and controlled by BMS and it is mainly focused to maintain the reliability and safety. The state estimation of the battery is essential for vehicle control and management of energy. The paper gives review on the strategies like battery modeling, state estimation and prediction. The state estimation for State of charge (SOC), State of power (SOP), State of health (SOH) and prediction of RUL are overviewed.
{"title":"A Review on Battery Management system and its Application in Electric vehicle","authors":"Smaranika Mishra, S. Swain, Rajat Kumar Samantaray","doi":"10.1109/ICACC-202152719.2021.9708114","DOIUrl":"https://doi.org/10.1109/ICACC-202152719.2021.9708114","url":null,"abstract":"Presently electric vehicles (EVs) are considered as most propitious solution for the replacement of internal combustion (IC) engine-based vehicle. The development of EV technologies is growing rapidly and the battery technology is an important concept for development of the electric vehicles. The EV performance mainly relies on the battery performance and battery management system (BMS). Recently, the Lithium-ion (Li-ion) battery is mainly used as a battery in EVs due to smaller weight, high energy density and capability of fast charging and discharging. Considering the dynamic performance, economy, safety friendliness to the environment of the EVs, the BMS is designed such a way to meet the challenges like the energy management of battery, reduction of heating-time at low temperature and enhancing remaining-useful life (RUL) with accuracy of prediction. The battery is managed and controlled by BMS and it is mainly focused to maintain the reliability and safety. The state estimation of the battery is essential for vehicle control and management of energy. The paper gives review on the strategies like battery modeling, state estimation and prediction. The state estimation for State of charge (SOC), State of power (SOP), State of health (SOH) and prediction of RUL are overviewed.","PeriodicalId":198810,"journal":{"name":"2021 International Conference on Advances in Computing and Communications (ICACC)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132875805","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 : 2021-10-21DOI: 10.1109/ICACC-202152719.2021.9708373
G. Divyabarathi, S. Shailesh, M. V. Judy
Advancements in machine learning and deep learning avails the opportunity to enhance our customisation to crucial problems widely in any domain. Object detection in underwater sonar is evolving and deep learning provides reliable techniques. In our experiments we approached the sonar object classification with transfer learning and ensemble approach which produced better results than single machine learning and deep learning algorithms for the task. The preliminary step of feature extraction preserves complex and significant structures from the image data and improves classification performance. Also experiment model overcomes the scarce training data with predefined model, ResNet50. Optimized classification results achieved with ensemble classifiers for the sonar objects.
{"title":"Object Classification in Underwater SONAR Images using Transfer Learning Based Ensemble Model","authors":"G. Divyabarathi, S. Shailesh, M. V. Judy","doi":"10.1109/ICACC-202152719.2021.9708373","DOIUrl":"https://doi.org/10.1109/ICACC-202152719.2021.9708373","url":null,"abstract":"Advancements in machine learning and deep learning avails the opportunity to enhance our customisation to crucial problems widely in any domain. Object detection in underwater sonar is evolving and deep learning provides reliable techniques. In our experiments we approached the sonar object classification with transfer learning and ensemble approach which produced better results than single machine learning and deep learning algorithms for the task. The preliminary step of feature extraction preserves complex and significant structures from the image data and improves classification performance. Also experiment model overcomes the scarce training data with predefined model, ResNet50. Optimized classification results achieved with ensemble classifiers for the sonar objects.","PeriodicalId":198810,"journal":{"name":"2021 International Conference on Advances in Computing and Communications (ICACC)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124645392","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：