Pub Date : 2023-04-05DOI: 10.1109/ICNWC57852.2023.10127440
S. Jeevidha, S. Saraswathi, D. Vishnuprasad.
With the increase in the number of crimes in the city, we are in need of a Smart surveillance camera that detects anomalies in advance. In real-world object detection identity switching and object interactions are difficult and retain identities. Due to a lack of situational awareness real-time object detection and tracking lack semantic information. Surveillance cameras are installed everywhere, and we can’t identify peoples who might be a potential threat to security, Surveillance camera needs to be monitored all the time. Existing algorithm concentrate on feature aggregation at the pixel level. A novel method is proposed to track human different movements and positions encompassing deep and detailed features. The main goal of this paper is to propose a feature aggregation at a semantic level that will prevent threats in advance by introducing a deep learning technique with Contextual inference-based object detection using the Bayesian Rule which incorporates semantic relations between classes to recognize the location. It also integrates the relationship between the object in unseen classes which helps to identify located instances and predicts the location and extracts context features for superclass prediction.
{"title":"Contextual learning in Video Analytics for Human pose Detection using Bayesian Learning and LSTM","authors":"S. Jeevidha, S. Saraswathi, D. Vishnuprasad.","doi":"10.1109/ICNWC57852.2023.10127440","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127440","url":null,"abstract":"With the increase in the number of crimes in the city, we are in need of a Smart surveillance camera that detects anomalies in advance. In real-world object detection identity switching and object interactions are difficult and retain identities. Due to a lack of situational awareness real-time object detection and tracking lack semantic information. Surveillance cameras are installed everywhere, and we can’t identify peoples who might be a potential threat to security, Surveillance camera needs to be monitored all the time. Existing algorithm concentrate on feature aggregation at the pixel level. A novel method is proposed to track human different movements and positions encompassing deep and detailed features. The main goal of this paper is to propose a feature aggregation at a semantic level that will prevent threats in advance by introducing a deep learning technique with Contextual inference-based object detection using the Bayesian Rule which incorporates semantic relations between classes to recognize the location. It also integrates the relationship between the object in unseen classes which helps to identify located instances and predicts the location and extracts context features for superclass prediction.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116304121","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 : 2023-04-05DOI: 10.1109/ICNWC57852.2023.10127495
C. Priya, J. Thangakumar, M. Sambath
In the field of Renewable energy, data processing is occurring in the photovoltaic plant using the IoT data logger. A data logger is a piece of technology that records and stores data over time, where SCADA systems are also indulged in data transfer and monitoring. Using these systems, we are transferring data from the data logger to cloud where a cloud-based platform is allowed users to manage and monitors the data loggers and as the result of analysis of various plants, the issues will be reported in the ticketing system and the further storage will be done in another cloud. This will result a cloud-cloud data flow where we are concentrating in ensuring the security of the data logger, Ethernet, WIFI, router connectivity, external web pages where data is viewed should be protected and the data backup, storage should be a secured area. RS485/RS422 bus provides the highest data transmission rate in data logger. Data encryption technique that involves Internet-cloud data transfers. This project mainly focus on introducing some new technologies in MaaS, where MaaS is a collection of tools and apps used to monitor a specific aspect of an application, server, system, or IT component. In the solar industry, this implies combining hardware, software, and services to monitor, evaluate, and troubleshoot solar plant faults throughout the solar array’s lifetime, where we can monitor the amount of energy and control it securely. And this will help to introduce a secure wide range of global monitoring and reporting techniques in the renewable energy sector where data and data loggers are rising along with the risks. Cyber threats have a significant impact on smart grid performance due to the fast proliferation of real system in power electronic systems for connecting renewable energy sources with cyber frameworks. These electrical equipment in systems are linked by communication networks, which may be vulnerable to major cyber-attacks by malicious attackers. We have shown the development of solid mitigation and response strategies in the proposed system.
{"title":"A Secure Remote Monitoring as a Service (MaaS) for Solar Power Plant","authors":"C. Priya, J. Thangakumar, M. Sambath","doi":"10.1109/ICNWC57852.2023.10127495","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127495","url":null,"abstract":"In the field of Renewable energy, data processing is occurring in the photovoltaic plant using the IoT data logger. A data logger is a piece of technology that records and stores data over time, where SCADA systems are also indulged in data transfer and monitoring. Using these systems, we are transferring data from the data logger to cloud where a cloud-based platform is allowed users to manage and monitors the data loggers and as the result of analysis of various plants, the issues will be reported in the ticketing system and the further storage will be done in another cloud. This will result a cloud-cloud data flow where we are concentrating in ensuring the security of the data logger, Ethernet, WIFI, router connectivity, external web pages where data is viewed should be protected and the data backup, storage should be a secured area. RS485/RS422 bus provides the highest data transmission rate in data logger. Data encryption technique that involves Internet-cloud data transfers. This project mainly focus on introducing some new technologies in MaaS, where MaaS is a collection of tools and apps used to monitor a specific aspect of an application, server, system, or IT component. In the solar industry, this implies combining hardware, software, and services to monitor, evaluate, and troubleshoot solar plant faults throughout the solar array’s lifetime, where we can monitor the amount of energy and control it securely. And this will help to introduce a secure wide range of global monitoring and reporting techniques in the renewable energy sector where data and data loggers are rising along with the risks. Cyber threats have a significant impact on smart grid performance due to the fast proliferation of real system in power electronic systems for connecting renewable energy sources with cyber frameworks. These electrical equipment in systems are linked by communication networks, which may be vulnerable to major cyber-attacks by malicious attackers. We have shown the development of solid mitigation and response strategies in the proposed system.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127216012","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 : 2023-04-05DOI: 10.1109/ICNWC57852.2023.10127429
RajKumar V, P. G
At its core, quantum computing is a fastdeveloping technology that has the potential to process massive volumes of data at high speeds. Some factoring issues may be difficult for the classical computer to solve because of the nature of the factoring. Quantum computing data connections are carried out using optical fiber at a distance as short as possible. While using the E91 protocol for quantum key distribution in a wireless network communication channel, we may extend the distance over which keys are sent. How to design a wireless communication channel for use in quantum computing applications. Using this technology, we are now investigating the development of a broadcast channel that will enhance the data transmission range while maintaining high security and minimizing time consumption. In our technique, we employed polarization multiplexing to communicate across a broadcast channel satellite connection, which allowed us to share data between the transmitter and receiver at the same time. The transfer key is protected by the use of polarization multiplexing and the E91 protocol, both of which are implemented. In a security network, it is used to create an extended communication channel distance between two nodes. In the end, we can meet our goal in this study by comparing the existing method to the performance analysis shown in a graph.
{"title":"Securely Transmit Data Over Long Distances Using Quantum Key Distribution Based On E91 Protocol","authors":"RajKumar V, P. G","doi":"10.1109/ICNWC57852.2023.10127429","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127429","url":null,"abstract":"At its core, quantum computing is a fastdeveloping technology that has the potential to process massive volumes of data at high speeds. Some factoring issues may be difficult for the classical computer to solve because of the nature of the factoring. Quantum computing data connections are carried out using optical fiber at a distance as short as possible. While using the E91 protocol for quantum key distribution in a wireless network communication channel, we may extend the distance over which keys are sent. How to design a wireless communication channel for use in quantum computing applications. Using this technology, we are now investigating the development of a broadcast channel that will enhance the data transmission range while maintaining high security and minimizing time consumption. In our technique, we employed polarization multiplexing to communicate across a broadcast channel satellite connection, which allowed us to share data between the transmitter and receiver at the same time. The transfer key is protected by the use of polarization multiplexing and the E91 protocol, both of which are implemented. In a security network, it is used to create an extended communication channel distance between two nodes. In the end, we can meet our goal in this study by comparing the existing method to the performance analysis shown in a graph.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124455580","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 : 2023-04-05DOI: 10.1109/ICNWC57852.2023.10127367
R. Dhanalakshmi, M. Thenmozhi, Swati Saxena, Hemalatha Mahalingam
Osteoporosis is a bone ailment which takes place because of minimum bone physique, damaging of micro-structure of bone, more over an excessive vulnerability to breakage. The main fitness difficulty throughout the globe is Osteoporosis, particularly in aged people. It may create spinal or hip breakages which can result in morbidity and burden. Hence the diagnosis of Osteoporosis at early stages and forecasting the existence of the fracture is highly essential. However automated analysis and diagnosis of osteoporosis from virtual radiographs could be very difficult as they have little variations. The proposed approach in this work uses high-dimensional textured function representations calculated from radiography pictures to distinguish healthy from osteoporotic issues. CNN helps to identify osteoporosis using structural MRI measurements of bone with high accuracy
{"title":"Convolutional Neural Network Model based Deep Learning Approach for Osteoporosis Fracture Detection","authors":"R. Dhanalakshmi, M. Thenmozhi, Swati Saxena, Hemalatha Mahalingam","doi":"10.1109/ICNWC57852.2023.10127367","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127367","url":null,"abstract":"Osteoporosis is a bone ailment which takes place because of minimum bone physique, damaging of micro-structure of bone, more over an excessive vulnerability to breakage. The main fitness difficulty throughout the globe is Osteoporosis, particularly in aged people. It may create spinal or hip breakages which can result in morbidity and burden. Hence the diagnosis of Osteoporosis at early stages and forecasting the existence of the fracture is highly essential. However automated analysis and diagnosis of osteoporosis from virtual radiographs could be very difficult as they have little variations. The proposed approach in this work uses high-dimensional textured function representations calculated from radiography pictures to distinguish healthy from osteoporotic issues. CNN helps to identify osteoporosis using structural MRI measurements of bone with high accuracy","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122217407","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 : 2023-04-05DOI: 10.1109/ICNWC57852.2023.10127406
J. Jayasree, Angaluri Venu Madhavi, G. Geetha
The one of the main problems in multi-label aerial image classification is remote sensing (RS) or aerial images understanding it increases interest in some of the research domains. Individuals can efficiently perform it by inspecting the human visual objects contained in the scene and the spatiotopological relationships of these visual objects. Although most of the existing models are pre-trained on different datasets, those existing models present some difficulties. Nowadays, Convolutional Neural Networks (CNN) have proposed a feasible approach for Aerial image Classification. With this consideration, in this work, a Deep Learning model is provided namely a convolutional neural network (CNN). In particular, CNN is employed to produce high-level appearance features and learn how visual aspects of the picture can be perceived. Our proposed models i.e., EfficeintNetB7, MobileNetV2 and ResNet50 are tested on thoroughly used datasets, and the results obtained from our proposed models show better accuracy, precision, and recall compared to the other models. Keywords - Aerial Image Classification, Convolutional Neural Network(CNN), Deep Learning, Multi-label Remote Sensing, Spatio-topological relationships.
{"title":"Multi-Label Classification On Aerial Images Using Deep Learning Techniques","authors":"J. Jayasree, Angaluri Venu Madhavi, G. Geetha","doi":"10.1109/ICNWC57852.2023.10127406","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127406","url":null,"abstract":"The one of the main problems in multi-label aerial image classification is remote sensing (RS) or aerial images understanding it increases interest in some of the research domains. Individuals can efficiently perform it by inspecting the human visual objects contained in the scene and the spatiotopological relationships of these visual objects. Although most of the existing models are pre-trained on different datasets, those existing models present some difficulties. Nowadays, Convolutional Neural Networks (CNN) have proposed a feasible approach for Aerial image Classification. With this consideration, in this work, a Deep Learning model is provided namely a convolutional neural network (CNN). In particular, CNN is employed to produce high-level appearance features and learn how visual aspects of the picture can be perceived. Our proposed models i.e., EfficeintNetB7, MobileNetV2 and ResNet50 are tested on thoroughly used datasets, and the results obtained from our proposed models show better accuracy, precision, and recall compared to the other models. Keywords - Aerial Image Classification, Convolutional Neural Network(CNN), Deep Learning, Multi-label Remote Sensing, Spatio-topological relationships.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129503801","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 : 2023-04-05DOI: 10.1109/ICNWC57852.2023.10127375
K. Sasikala, S. Vasuhi
The collecting and exchange of information without human intervention will soon be possible thanks to the Internet of Things. Numerous conflicts with IOT technology are emerging due to the fast increase in connected devices, including those related to diversity, expansibility, service quality, security requirements, and many more. IOT technology has advanced as a result oftechnological developments like machine learning. To reduce learning difficulty by computing features, factor selection, also called feature selection, is crucial, especially for a large, huge data set like network traffic. Despite the ease of the new selection approaches, it is actually not an easy task to do feature selection properly. The Internet of Things will soon make it feasible to gather and transmit information without human involvement. Due to the rapid growth in connected devices, a number of conflicts with IOT technologies are arising. These conflicts include those involving diversity, expansibility, quality of service, security needs, and many more. As a consequence of technical advancements like machine learning, IOT technology has improved. Factor selection, also known as feature selection, is essential to lessen the complexity of learning by computing features, especially for a massive, enormous data set like internet traffic. Even though the new selection methods are simple, selecting features correctly is a difficult undertaking. Systems that detect and prevent intrusions are the most popular technology for spotting suspicious behaviour and defending diverse infrastructures against network intrusions (IDPSs). On the UNSW (University of New South Wales) -NBl5 data set, our suggested logistic regression algorithm makes predictions of anomalies with an accuracy of 98% using the automated feature selection approach since the accuracy of the model depends on the feature. The dimensionality reduction approach is used to reduce the misleading data.
{"title":"Anomaly Based Intrusion Detection on IOT Devices using Logistic Regression","authors":"K. Sasikala, S. Vasuhi","doi":"10.1109/ICNWC57852.2023.10127375","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127375","url":null,"abstract":"The collecting and exchange of information without human intervention will soon be possible thanks to the Internet of Things. Numerous conflicts with IOT technology are emerging due to the fast increase in connected devices, including those related to diversity, expansibility, service quality, security requirements, and many more. IOT technology has advanced as a result oftechnological developments like machine learning. To reduce learning difficulty by computing features, factor selection, also called feature selection, is crucial, especially for a large, huge data set like network traffic. Despite the ease of the new selection approaches, it is actually not an easy task to do feature selection properly. The Internet of Things will soon make it feasible to gather and transmit information without human involvement. Due to the rapid growth in connected devices, a number of conflicts with IOT technologies are arising. These conflicts include those involving diversity, expansibility, quality of service, security needs, and many more. As a consequence of technical advancements like machine learning, IOT technology has improved. Factor selection, also known as feature selection, is essential to lessen the complexity of learning by computing features, especially for a massive, enormous data set like internet traffic. Even though the new selection methods are simple, selecting features correctly is a difficult undertaking. Systems that detect and prevent intrusions are the most popular technology for spotting suspicious behaviour and defending diverse infrastructures against network intrusions (IDPSs). On the UNSW (University of New South Wales) -NBl5 data set, our suggested logistic regression algorithm makes predictions of anomalies with an accuracy of 98% using the automated feature selection approach since the accuracy of the model depends on the feature. The dimensionality reduction approach is used to reduce the misleading data.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129587899","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 : 2023-04-05DOI: 10.1109/ICNWC57852.2023.10127280
R. Depakkumar, N. Prasath
To put it simply, landslides are the collapse of a slope’s worth of land, posing a threat to human, animal, and man-made life under varying and often erratic climatic and lithological conditions. The development of cutting-edge space technology has allowed for the expansion of synthetic aperture radar (SAR) interferometry in the face of disaster. Copernicus Sentinel 1 SAR data products, with a temporal resolution of 12 days, are freely available, enriching periodic monitoring of the Earth’s surface. Over the course of several decades, differential SAR interferometry (DInSAR) techniques have been widely used for the purpose of tracking and identifying surface distortion. Over 105 landslides occurred in the Kodagu district of Karnataka during the 15th and 17th of August 2018. Before and after landslide occurrences, Sentinel-1 datasets acquired in Interferometric Wide Swath (IW) mode are utilised. Topographic and atmospheric inaccuracies have a significant impact on the displacement result derived from DInSAR. Due to its non-uniform accuracy variance, DEMs must be evaluated prior to being used for a variety of applications. DEMs and InSAR produced DEMs are evaluated with respect to their vertical and horizontal accuracy using Survey of India (SOI) toposheets as a standard of comparison. After considering their accuracy in both the vertical and horizontal planes, researchers have concluded that ALOS are the best option for topographic phase removal. Use of ALOS for InSAR analysis over the Kodagu district is recommended as it shows the least amount of error compared to other DEMs. Sentinel 1 can be utilised for assessment of larger landslides, and it is recommended to use corner reflectors to produce promising findings, according to a time series analysis done across the selected landslide regions using the Hybrid Deep Learning approach.
{"title":"Landslide Suspectibility Mapping Using Hybrid Deep Learning","authors":"R. Depakkumar, N. Prasath","doi":"10.1109/ICNWC57852.2023.10127280","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127280","url":null,"abstract":"To put it simply, landslides are the collapse of a slope’s worth of land, posing a threat to human, animal, and man-made life under varying and often erratic climatic and lithological conditions. The development of cutting-edge space technology has allowed for the expansion of synthetic aperture radar (SAR) interferometry in the face of disaster. Copernicus Sentinel 1 SAR data products, with a temporal resolution of 12 days, are freely available, enriching periodic monitoring of the Earth’s surface. Over the course of several decades, differential SAR interferometry (DInSAR) techniques have been widely used for the purpose of tracking and identifying surface distortion. Over 105 landslides occurred in the Kodagu district of Karnataka during the 15th and 17th of August 2018. Before and after landslide occurrences, Sentinel-1 datasets acquired in Interferometric Wide Swath (IW) mode are utilised. Topographic and atmospheric inaccuracies have a significant impact on the displacement result derived from DInSAR. Due to its non-uniform accuracy variance, DEMs must be evaluated prior to being used for a variety of applications. DEMs and InSAR produced DEMs are evaluated with respect to their vertical and horizontal accuracy using Survey of India (SOI) toposheets as a standard of comparison. After considering their accuracy in both the vertical and horizontal planes, researchers have concluded that ALOS are the best option for topographic phase removal. Use of ALOS for InSAR analysis over the Kodagu district is recommended as it shows the least amount of error compared to other DEMs. Sentinel 1 can be utilised for assessment of larger landslides, and it is recommended to use corner reflectors to produce promising findings, according to a time series analysis done across the selected landslide regions using the Hybrid Deep Learning approach.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128234363","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 : 2023-04-05DOI: 10.1109/ICNWC57852.2023.10127483
Saloni Sharma, D. Malathi
It’s no secret that security systems rely heavily on image processing because of its versatility. Two-dimensional visuals, intricate algorithms, and instantaneous decision-making are all challenges that must be met by the system. It is possible to optimize the system at one of four stages: preprocessing, feature extraction, Lip detection, and Recognition. Using modern computing hardware and software, we can create a system that is both easy to use and exactly what we need. Unfortunately, as more characteristics are added, the complexity of implementing these algorithms grows. The process is improved through the development of novel approaches, tools, and strategies. Machine learning and AI techniques have recently been applied to image processing applications. Standard methods of authentication, such as passwords and PINs, are becoming increasingly insecure. Physical and biological characteristics that are unique to each individual provide the best level of security. It is vulnerable to guessing and theft in business and public computer networks. Plastic cards, smart cards, and computer token cards all have non-security flaws in the form of forgery, loss, corruption, and inaccessibility. Identifying techniques based on biometrics have several applications in forensics, finance, and other fields. Voluntary action from the past has the drawbacks of being difficult to implement and not adaptable for covert uses, such as in surveillance applications. Lip image audit and verification during biometrics record keeping is prone to human error. Image quality of the lips is more easily obtained than fingerprint images. Only about five percent of the population has imperfect fingerprints and cannot be verified. Reasons include but are not limited to dry skin, diseased skin, elderly skin, wounded skin, calloused finger, oriental skin, bandaged finger, narrow finger, smeared sensor on reader, etc. Varying lighting conditions are widely recognized as one of the most crucial aspects for accurate Lip recognition but also one of its greatest obstacles. Simultaneously, the same person's lip expression can look extremely different depending on the illumination.
{"title":"Lip Detection and Recognition-A Review1","authors":"Saloni Sharma, D. Malathi","doi":"10.1109/ICNWC57852.2023.10127483","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127483","url":null,"abstract":"It’s no secret that security systems rely heavily on image processing because of its versatility. Two-dimensional visuals, intricate algorithms, and instantaneous decision-making are all challenges that must be met by the system. It is possible to optimize the system at one of four stages: preprocessing, feature extraction, Lip detection, and Recognition. Using modern computing hardware and software, we can create a system that is both easy to use and exactly what we need. Unfortunately, as more characteristics are added, the complexity of implementing these algorithms grows. The process is improved through the development of novel approaches, tools, and strategies. Machine learning and AI techniques have recently been applied to image processing applications. Standard methods of authentication, such as passwords and PINs, are becoming increasingly insecure. Physical and biological characteristics that are unique to each individual provide the best level of security. It is vulnerable to guessing and theft in business and public computer networks. Plastic cards, smart cards, and computer token cards all have non-security flaws in the form of forgery, loss, corruption, and inaccessibility. Identifying techniques based on biometrics have several applications in forensics, finance, and other fields. Voluntary action from the past has the drawbacks of being difficult to implement and not adaptable for covert uses, such as in surveillance applications. Lip image audit and verification during biometrics record keeping is prone to human error. Image quality of the lips is more easily obtained than fingerprint images. Only about five percent of the population has imperfect fingerprints and cannot be verified. Reasons include but are not limited to dry skin, diseased skin, elderly skin, wounded skin, calloused finger, oriental skin, bandaged finger, narrow finger, smeared sensor on reader, etc. Varying lighting conditions are widely recognized as one of the most crucial aspects for accurate Lip recognition but also one of its greatest obstacles. Simultaneously, the same person's lip expression can look extremely different depending on the illumination.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133102105","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 : 2023-04-05DOI: 10.1109/ICNWC57852.2023.10127374
M.K. Mohamed Faizal, S. Geetha, A. Barveen
The face-morphing attack, which occurs in private, public, and governmental institutions, is one of the most well-known in today’s world. Face recognition systems tend to be vulnerable if the face images are manipulated with duplicate images. Manipulated images are combined with the original image so that the images look like legitimate ones. Several face recognition studies are being conducted to determine whether the face images are manipulated. Using the DL algorithm, the face image is trained to attain the original and morphed face images by recognizing the face images. DL algorithms determine the images by classifying whether they are morphs or not recognizable to humans. In this paper, the foremost emphasis is on diagnosing the face recognition from those face-morphed images using the different DL techniques. Different DL techniques are effectively compared, where the ViT transformer attains improved accuracy when compared to Resnet, RNN, and CNN, respectively. This paper provides an overview of the various deep learning algorithms for detecting those face recognition images that focus on challenges and issues in the facial datasets from Face Recognition Kaggle dataset with training and testing image dataset. It determines the higher contrast in image efficiency and the evaluation of the face recognized images with an improved image.
{"title":"Diagnosing Progressive Face Recognition from Face Morphing Using ViT Technique Through DL Approach","authors":"M.K. Mohamed Faizal, S. Geetha, A. Barveen","doi":"10.1109/ICNWC57852.2023.10127374","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127374","url":null,"abstract":"The face-morphing attack, which occurs in private, public, and governmental institutions, is one of the most well-known in today’s world. Face recognition systems tend to be vulnerable if the face images are manipulated with duplicate images. Manipulated images are combined with the original image so that the images look like legitimate ones. Several face recognition studies are being conducted to determine whether the face images are manipulated. Using the DL algorithm, the face image is trained to attain the original and morphed face images by recognizing the face images. DL algorithms determine the images by classifying whether they are morphs or not recognizable to humans. In this paper, the foremost emphasis is on diagnosing the face recognition from those face-morphed images using the different DL techniques. Different DL techniques are effectively compared, where the ViT transformer attains improved accuracy when compared to Resnet, RNN, and CNN, respectively. This paper provides an overview of the various deep learning algorithms for detecting those face recognition images that focus on challenges and issues in the facial datasets from Face Recognition Kaggle dataset with training and testing image dataset. It determines the higher contrast in image efficiency and the evaluation of the face recognized images with an improved image.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134556409","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 : 2023-04-05DOI: 10.1109/ICNWC57852.2023.10127535
J. Jasmine Hephzipah, B. Sarala, M. Logeshwaran, M.G. Kumara Vijay, M. Jyoth Varshan, S. Harish
ZigBee is a low-rate task group 4, Personal Area Network task group. It’s a type of technology for home networking. For controlling and detecting the network, a technological standard called ZigBee was established. For short-range wireless communication, a protocol termed ZigBee resolves the demand for comparatively affordable deployment of low-power devices, with lower bit rates. Under IEEE 802.15.4 ZigBee technology, ZigBee antenna is a radio frequency antenna, with ability to transmit and, receive radio waves. These serve a crucial part in the operation of ZigBee’s low-power, wireless personal area networks. Thus a patch antenna of 2. 4GHz is made with dimensions of 39x47.8mm2 with FR-4(Lossy) as substrate, with thickness of 1. 6mm and copper as a patch. VSWR of 1.06, a bandwidth of 110. 25MHz, and a gain of 2. 76dB, return loss of -29.77dB is achieved. The radiation pattern is omnidirectional. The simulated findings and the values obtained agree rather well.
{"title":"A 2.4GHz Rectangular Shaped Patch Antenna for ZigBee Application","authors":"J. Jasmine Hephzipah, B. Sarala, M. Logeshwaran, M.G. Kumara Vijay, M. Jyoth Varshan, S. Harish","doi":"10.1109/ICNWC57852.2023.10127535","DOIUrl":"https://doi.org/10.1109/ICNWC57852.2023.10127535","url":null,"abstract":"ZigBee is a low-rate task group 4, Personal Area Network task group. It’s a type of technology for home networking. For controlling and detecting the network, a technological standard called ZigBee was established. For short-range wireless communication, a protocol termed ZigBee resolves the demand for comparatively affordable deployment of low-power devices, with lower bit rates. Under IEEE 802.15.4 ZigBee technology, ZigBee antenna is a radio frequency antenna, with ability to transmit and, receive radio waves. These serve a crucial part in the operation of ZigBee’s low-power, wireless personal area networks. Thus a patch antenna of 2. 4GHz is made with dimensions of 39x47.8mm2 with FR-4(Lossy) as substrate, with thickness of 1. 6mm and copper as a patch. VSWR of 1.06, a bandwidth of 110. 25MHz, and a gain of 2. 76dB, return loss of -29.77dB is achieved. The radiation pattern is omnidirectional. The simulated findings and the values obtained agree rather well.","PeriodicalId":197525,"journal":{"name":"2023 International Conference on Networking and Communications (ICNWC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133531128","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：