The purpose of the article is to create new program operators for a fundamentally new type of neural network with parallel computing, and not with the usual parallel computing through sequential computing.
{"title":"Program Operators SIT, tS, S1 e, Set1","authors":"","doi":"10.33140/jsndc.03.01.07","DOIUrl":"https://doi.org/10.33140/jsndc.03.01.07","url":null,"abstract":"The purpose of the article is to create new program operators for a fundamentally new type of neural network with parallel computing, and not with the usual parallel computing through sequential computing.","PeriodicalId":91517,"journal":{"name":"International journal of sensor networks and data communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134905789","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}
This article aims to ensure continuity between classical methods of ul-traviolet microscopy or/and micromanipulation using ultraviolet mi-crobeam and lens-less ultraviolet microscopy and microbeam exposure of cells and tissues. Considering the history of the development of the method and the possibility of working with different methods of mechanical scanning, the authors propose to use mirror galvanometers and an electromechanical scanning system in the mechanical engineering of lensless microbeam installations. These installations make it possible to provide both scanning with an ultraviolet microbeam to obtain a line scan image, and precision micromanipulation at the level of individual cells or individual organelles (in the case of large cells). We propose to extrapolate mathematical models previously developed for galvanic mirrors of light-beam oscilloscopes for microbeam scanning systems, position-sensitive micromanipulation, and real-time microphotometric cell analysis.
{"title":"Towards Ultraviolet Microbeam Scanning and Lens-Less UV Microbeam Microscopy with Mirror Galvanometric Scanners: From the History of Research Instrumentation to Engineering of Modern Mechatronic Optical Systems","authors":"","doi":"10.33140/jsndc.03.01.06","DOIUrl":"https://doi.org/10.33140/jsndc.03.01.06","url":null,"abstract":"This article aims to ensure continuity between classical methods of ul-traviolet microscopy or/and micromanipulation using ultraviolet mi-crobeam and lens-less ultraviolet microscopy and microbeam exposure of cells and tissues. Considering the history of the development of the method and the possibility of working with different methods of mechanical scanning, the authors propose to use mirror galvanometers and an electromechanical scanning system in the mechanical engineering of lensless microbeam installations. These installations make it possible to provide both scanning with an ultraviolet microbeam to obtain a line scan image, and precision micromanipulation at the level of individual cells or individual organelles (in the case of large cells). We propose to extrapolate mathematical models previously developed for galvanic mirrors of light-beam oscilloscopes for microbeam scanning systems, position-sensitive micromanipulation, and real-time microphotometric cell analysis.","PeriodicalId":91517,"journal":{"name":"International journal of sensor networks and data communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135459826","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}
Big data applications are consuming most of the space in industry and research area. Among the widespread examples of big data, the role of video streams from CCTV cameras is equally important as other sources like social media data, sensor data, agriculture data, medical data and data evolved from space research. Surveillance videos have a major contribution in unstructured big data. CCTV cameras are implemented in all places where security having much importance. Manual surveillance seems tedious and time consuming. Security can be defending in different terms in different contexts like theft identification, violence detection, chances of explosion etc. In crowded public places the term security covers almost all type of abnormal events. Among them violence detection is difficult to handle since it involves group activity. The anomalous or abnormal activity analysis in a crowd video scene is very difficult due to several real world constraints. The paper includes a deep rooted survey which starts from object recognition, action recognition, crowd analysis and finally violence detection in a crowd environment. Majority of the papers reviewed in this survey are based on deep learning technique. Various deep learning methods are compared in terms of their algorithms and models. The main focus of this survey is application of deep learning techniques in detecting the exact count, involved persons and the happened activity in a large crowd at all climate conditions. Paper discusses the underlying deep learning implementation technology involved in various crowd video analysis methods. Real time processing, an important issue which is yet to be explored more in this field is also considered. Not many methods are there in handling all these issues simultaneously. The issues recognized in existing methods are identified and summarized. Also, future direction is given to reduce the obstacles identified. The survey provides a bibliographic summary of papers from Science-direct, IEEE Xplore and ACM digital library.
{"title":"Smart Surveillance: A Review & Survey Through Deep Learning Techniques for Detection & Analysis","authors":"","doi":"10.33140/jsndc.03.01.05","DOIUrl":"https://doi.org/10.33140/jsndc.03.01.05","url":null,"abstract":"Big data applications are consuming most of the space in industry and research area. Among the widespread examples of big data, the role of video streams from CCTV cameras is equally important as other sources like social media data, sensor data, agriculture data, medical data and data evolved from space research. Surveillance videos have a major contribution in unstructured big data. CCTV cameras are implemented in all places where security having much importance. Manual surveillance seems tedious and time consuming. Security can be defending in different terms in different contexts like theft identification, violence detection, chances of explosion etc. In crowded public places the term security covers almost all type of abnormal events. Among them violence detection is difficult to handle since it involves group activity. The anomalous or abnormal activity analysis in a crowd video scene is very difficult due to several real world constraints. The paper includes a deep rooted survey which starts from object recognition, action recognition, crowd analysis and finally violence detection in a crowd environment. Majority of the papers reviewed in this survey are based on deep learning technique. Various deep learning methods are compared in terms of their algorithms and models. The main focus of this survey is application of deep learning techniques in detecting the exact count, involved persons and the happened activity in a large crowd at all climate conditions. Paper discusses the underlying deep learning implementation technology involved in various crowd video analysis methods. Real time processing, an important issue which is yet to be explored more in this field is also considered. Not many methods are there in handling all these issues simultaneously. The issues recognized in existing methods are identified and summarized. Also, future direction is given to reduce the obstacles identified. The survey provides a bibliographic summary of papers from Science-direct, IEEE Xplore and ACM digital library.","PeriodicalId":91517,"journal":{"name":"International journal of sensor networks and data communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135547786","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}
This study has been undertaken to investigate and implement multiple detection systems into a single surveillance system and check whether the input videos may comprise and capture a variety of realistic anomalies or not. In this paper, we propose to learn various anomalies by exploiting both normal and anomalous videos and implemented it to new model. Real time object detection is a vast, vibrant and sophisticated area of computer vision aimed towards object identification and recognition. Object detection detects the semantic objects of a class objects using Open source Computer Vision, which is a library of programming functions mainly trained towards real time computer vision in digital images and videos. The main aim behind this real time object detection is to help the peoples to overcome their difficulty. Real time object detection finds its uses in the areas like tracking objects, video surveillance, pedestrian detection, people counting, self-driving cars, face detection, tracking in sports and many more. This is achieved using Convolution, Probabilistic Neural Networks, etc. which are a representative tool of Deep learning. This project acts as an aiding tool for peoples who wants to take care of everything inside, outside, and around their house just for their full security expectations. Surveillance is a must for small houses to large-scale industries as they fulfil our safety aspects because theft and burglary have always been a problem. By combining this Surveillance idea to IoT and some Machine Learning stuff this will be a major product. The proposed project is a single autonomous surveillance system, based on analysis and detection technology. The proposed system is capable of monitoring all actions at once and alerts the concerned officials immediately and precisely.
{"title":"Deep Surveillance System","authors":"","doi":"10.33140/jsndc.03.01.04","DOIUrl":"https://doi.org/10.33140/jsndc.03.01.04","url":null,"abstract":"This study has been undertaken to investigate and implement multiple detection systems into a single surveillance system and check whether the input videos may comprise and capture a variety of realistic anomalies or not. In this paper, we propose to learn various anomalies by exploiting both normal and anomalous videos and implemented it to new model. Real time object detection is a vast, vibrant and sophisticated area of computer vision aimed towards object identification and recognition. Object detection detects the semantic objects of a class objects using Open source Computer Vision, which is a library of programming functions mainly trained towards real time computer vision in digital images and videos. The main aim behind this real time object detection is to help the peoples to overcome their difficulty. Real time object detection finds its uses in the areas like tracking objects, video surveillance, pedestrian detection, people counting, self-driving cars, face detection, tracking in sports and many more. This is achieved using Convolution, Probabilistic Neural Networks, etc. which are a representative tool of Deep learning. This project acts as an aiding tool for peoples who wants to take care of everything inside, outside, and around their house just for their full security expectations. Surveillance is a must for small houses to large-scale industries as they fulfil our safety aspects because theft and burglary have always been a problem. By combining this Surveillance idea to IoT and some Machine Learning stuff this will be a major product. The proposed project is a single autonomous surveillance system, based on analysis and detection technology. The proposed system is capable of monitoring all actions at once and alerts the concerned officials immediately and precisely.","PeriodicalId":91517,"journal":{"name":"International journal of sensor networks and data communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135470902","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 decentralized network environments, collaborative efforts are crucial to bolstering network security against everevolving threats from malicious actors. Federated Learning has emerged as a promising solution, enabling multiple nodes to collectively train machine learning models while preserving data privacy. This research proposes SentinelNet, a novel Federated Learning framework specifically designed for collaborative network security. The framework emphasizes secure threat intelligence sharing, privacy-preserving techniques, and adaptive learning mechanisms. Through comprehensive evaluations and real-world case studies, SentinelNet demonstrates its efficacy in enhancing network security while maintaining data confidentiality. The research highlights the significance of collaborative approaches and advocates the adoption of Federated Learning to fortify decentralized network ecosystems.
{"title":"Federated Learning for Collaborative Network Security in Decentralized Environments","authors":"","doi":"10.33140/jsndc.03.01.03","DOIUrl":"https://doi.org/10.33140/jsndc.03.01.03","url":null,"abstract":"In decentralized network environments, collaborative efforts are crucial to bolstering network security against everevolving threats from malicious actors. Federated Learning has emerged as a promising solution, enabling multiple nodes to collectively train machine learning models while preserving data privacy. This research proposes SentinelNet, a novel Federated Learning framework specifically designed for collaborative network security. The framework emphasizes secure threat intelligence sharing, privacy-preserving techniques, and adaptive learning mechanisms. Through comprehensive evaluations and real-world case studies, SentinelNet demonstrates its efficacy in enhancing network security while maintaining data confidentiality. The research highlights the significance of collaborative approaches and advocates the adoption of Federated Learning to fortify decentralized network ecosystems.","PeriodicalId":91517,"journal":{"name":"International journal of sensor networks and data communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135721252","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}
We present a novel dataset captured from a BMW X5 test carrier within the German research project KI-ASIC for use in radar sensor development and autonomous driving research. Our work aims at providing a blueprint for the process of creating labeled datasets for the development of neural networks for pattern recognition in radar data in the automotive environment. With a variety of different sensor types such as wide angle color cameras, a high-resolution color stereo camera, an Ouster OS1-64 laser scanner and three novel Infineon radar sensors, we recorded over 100,000 scenes of real traffic scenarios as well as defined test scenarios with a frequency of 10 Hz. The scenarios in real traffic contain inner-city situations, but also scenes from rural areas with static and dynamic objects. Besides, the defined test scenarios are based on the NCAP scenarios and focus mostly on turning, overtaking and follow-up maneuvers. The data from the different sensors is calibrated, synchronized and timestamped including raw and rectified information. Our dataset also contains labels for all detected objects from a defined class list with distance and angle properties. The content of the paper aims at the description of the recording test carrier, the format of the provided sensor data and the structure of the overall dataset
{"title":"The KI-ASIC Dataset","authors":"","doi":"10.33140/jsndc.03.01.02","DOIUrl":"https://doi.org/10.33140/jsndc.03.01.02","url":null,"abstract":"We present a novel dataset captured from a BMW X5 test carrier within the German research project KI-ASIC for use in radar sensor development and autonomous driving research. Our work aims at providing a blueprint for the process of creating labeled datasets for the development of neural networks for pattern recognition in radar data in the automotive environment. With a variety of different sensor types such as wide angle color cameras, a high-resolution color stereo camera, an Ouster OS1-64 laser scanner and three novel Infineon radar sensors, we recorded over 100,000 scenes of real traffic scenarios as well as defined test scenarios with a frequency of 10 Hz. The scenarios in real traffic contain inner-city situations, but also scenes from rural areas with static and dynamic objects. Besides, the defined test scenarios are based on the NCAP scenarios and focus mostly on turning, overtaking and follow-up maneuvers. The data from the different sensors is calibrated, synchronized and timestamped including raw and rectified information. Our dataset also contains labels for all detected objects from a defined class list with distance and angle properties. The content of the paper aims at the description of the recording test carrier, the format of the provided sensor data and the structure of the overall dataset","PeriodicalId":91517,"journal":{"name":"International journal of sensor networks and data communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136101109","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}
One of the laborious communication tasks in a mobile ad hoc network is packet transmission. Due to the MANET node's power backup, many routing paths may experience unsuccessful packet delivery. The routing algorithm chooses the path that packets take as they travel from the source node to the destination nodes, but it makes no guarantees regarding packet delivery. In order to determine the most effective path between nodes, this paper proposed a new routing algorithm with the use of the T-test process. This suggested technique determines the best path between nodes for communication in a recursive manner, ensuring that each node participating in the route discovery has enough energy for transmission. The criteria for evaluating the nodes that are chosen and rejected throughout the route discovery process are defined and supported by the T-Test procedure. This technique, together with T-Test, supports effective packet transmission in MANET packet flow. It is also built with the help of network simulation and compared to the current routing protocol, demonstrating that it performs better overall.
{"title":"Routing Algorithm for Efficient Packet Transmission in Manet Using T–Test Procedure","authors":"","doi":"10.33140/jsndc.03.01.01","DOIUrl":"https://doi.org/10.33140/jsndc.03.01.01","url":null,"abstract":"One of the laborious communication tasks in a mobile ad hoc network is packet transmission. Due to the MANET node's power backup, many routing paths may experience unsuccessful packet delivery. The routing algorithm chooses the path that packets take as they travel from the source node to the destination nodes, but it makes no guarantees regarding packet delivery. In order to determine the most effective path between nodes, this paper proposed a new routing algorithm with the use of the T-test process. This suggested technique determines the best path between nodes for communication in a recursive manner, ensuring that each node participating in the route discovery has enough energy for transmission. The criteria for evaluating the nodes that are chosen and rejected throughout the route discovery process are defined and supported by the T-Test procedure. This technique, together with T-Test, supports effective packet transmission in MANET packet flow. It is also built with the help of network simulation and compared to the current routing protocol, demonstrating that it performs better overall.","PeriodicalId":91517,"journal":{"name":"International journal of sensor networks and data communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136380667","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}
The pervasive presence of fake news on social media platforms poses a significant threat to the credibility of information, the functioning of democracies, and the stability of societies. This paper presents a comprehensive analysis of the application of machine learning techniques in managing fake news on social media. We discuss the challenges and opportunities in employing machine learning for fake news detection and mitigation, review the state-of-the-art methods, and suggest future research directions. We also highlight ethical considerations and the importance of maintaining user privacy while combating fake news.
{"title":"Managing Fake News on Social Media Through Machine Learning - A Comprehensive Analysis","authors":"","doi":"10.33140/jsndc.03.01.12","DOIUrl":"https://doi.org/10.33140/jsndc.03.01.12","url":null,"abstract":"The pervasive presence of fake news on social media platforms poses a significant threat to the credibility of information, the functioning of democracies, and the stability of societies. This paper presents a comprehensive analysis of the application of machine learning techniques in managing fake news on social media. We discuss the challenges and opportunities in employing machine learning for fake news detection and mitigation, review the state-of-the-art methods, and suggest future research directions. We also highlight ethical considerations and the importance of maintaining user privacy while combating fake news.","PeriodicalId":91517,"journal":{"name":"International journal of sensor networks and data communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135098097","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}
Vehicle Ad Hoc Networks (VANETs) provide efficient and secure communications between vehicles and infrastructure. Reliable data exchange between vehicles and Roadside Units (RSUs) is the main objective of the Intelligent Transportation System (ITS). One of the main tasks associated with automotive communications is the development of methods for predicting the behavior of VANET communication channels in critical conditions. This article explored data transfer between service provider, vehicles, and infrastructure in ITS. Since VANET requires communication channels with low packet loss, minimal message travel time and high Quality of Service (QoS) with the least number of bit errors, we simulated the simplest wireless communication channel in VANET and obtained data about possible packet losses at the RSU unit, message travel time over the network, the load of the vehicle communication link with the infrastructure, as well as information about the effect of the packet loss in the Internet and the influence of bit errors. The importance and usefulness of the performed numerical simulation lies in the ability to set traffic parameters and observe the resulting channel load, packet loss, message travel time, the number of bit errors and QoS in VANET under certain transmission modes.
{"title":"Loss Estimation in VANET Communications","authors":"","doi":"10.33140/jsndc.03.01.11","DOIUrl":"https://doi.org/10.33140/jsndc.03.01.11","url":null,"abstract":"Vehicle Ad Hoc Networks (VANETs) provide efficient and secure communications between vehicles and infrastructure. Reliable data exchange between vehicles and Roadside Units (RSUs) is the main objective of the Intelligent Transportation System (ITS). One of the main tasks associated with automotive communications is the development of methods for predicting the behavior of VANET communication channels in critical conditions. This article explored data transfer between service provider, vehicles, and infrastructure in ITS. Since VANET requires communication channels with low packet loss, minimal message travel time and high Quality of Service (QoS) with the least number of bit errors, we simulated the simplest wireless communication channel in VANET and obtained data about possible packet losses at the RSU unit, message travel time over the network, the load of the vehicle communication link with the infrastructure, as well as information about the effect of the packet loss in the Internet and the influence of bit errors. The importance and usefulness of the performed numerical simulation lies in the ability to set traffic parameters and observe the resulting channel load, packet loss, message travel time, the number of bit errors and QoS in VANET under certain transmission modes.","PeriodicalId":91517,"journal":{"name":"International journal of sensor networks and data communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135598645","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}
Next-generation 5G networks require a high-speed, low-latency, and robust communication backbone to support new applications such as IoT, cloud computing, and virtual reality. Optical burst switching (OBS) is a promising method for 5G networks due to its ability to handle high-speed data transit and excellent bandwidth utilisation. Traditional OBS networks, on the other hand, have a high blocking probability, low resource utilisation, and limited scalability. To address these challenges, this work provides a unique OBS design that integrates machine learning, probabilistic modelling, and efficient algorithms. The usage of machine learning-based burst assembly algorithms, which dynamically predict the best resource allocation for each burst based on network conditions and QoS requirements, is a key component of the proposed architecture. A complete simulation analysis is performed using a typical Wavelength Division Multiplexing (WDM) traffic dataset to evaluate the performance of the proposed architecture. The simulation results show that, as compared to standard OBS networks, the suggested architecture reduces the likelihood of obstruction and improves resource utilisation significantly. Furthermore, when compared to previous OBS systems, the suggested design is more efficient at managing dynamic traffic and enables greater scalability. The simulation study's performance tests demonstrate that the suggested architecture has a blocking probability of less than 10-6, a throughput of more than 95%, and a latency of less than 4 milliseconds. These findings show that the suggested OBS design for next-generation 5G networks is both feasible and effective.
{"title":"Next-Generation OBS Architecture Transforms 5G Networks Powered by Machine Learning, Probabilistic Modeling and Algorithm Optimisation","authors":"","doi":"10.33140/jsndc.03.01.10","DOIUrl":"https://doi.org/10.33140/jsndc.03.01.10","url":null,"abstract":"Next-generation 5G networks require a high-speed, low-latency, and robust communication backbone to support new applications such as IoT, cloud computing, and virtual reality. Optical burst switching (OBS) is a promising method for 5G networks due to its ability to handle high-speed data transit and excellent bandwidth utilisation. Traditional OBS networks, on the other hand, have a high blocking probability, low resource utilisation, and limited scalability. To address these challenges, this work provides a unique OBS design that integrates machine learning, probabilistic modelling, and efficient algorithms. The usage of machine learning-based burst assembly algorithms, which dynamically predict the best resource allocation for each burst based on network conditions and QoS requirements, is a key component of the proposed architecture. A complete simulation analysis is performed using a typical Wavelength Division Multiplexing (WDM) traffic dataset to evaluate the performance of the proposed architecture. The simulation results show that, as compared to standard OBS networks, the suggested architecture reduces the likelihood of obstruction and improves resource utilisation significantly. Furthermore, when compared to previous OBS systems, the suggested design is more efficient at managing dynamic traffic and enables greater scalability. The simulation study's performance tests demonstrate that the suggested architecture has a blocking probability of less than 10-6, a throughput of more than 95%, and a latency of less than 4 milliseconds. These findings show that the suggested OBS design for next-generation 5G networks is both feasible and effective.","PeriodicalId":91517,"journal":{"name":"International journal of sensor networks and data communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135598647","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：