One of the most anticipated features of 5G and subsequent networks is wireless virtual reality (VR), which promises to transform human interaction via its immersive experiences and game-changing capabilities. Wireless virtual reality systems, and VR games in particular, are notoriously slow due to rendering issues. But most academics don't care about data correlation or real-time rendering. Using mobile edge computing (MEC) and mmWave-enabled wireless networks, we provide an adaptive VR system that enables high-quality wireless VR. By using this architecture, VR rendering operations may be adaptively offloaded to MEC servers in real-time, resulting in even greater performance advantages via caching.The limited processing power of VR devices, the need for a high quality of experience (QoE), and the small latency in VR activities make it difficult to connect wireless VR consumers to high-quality VR content in real-time. To solve these problems, we provide a wireless VR network that is enabled by MEC. This network makes use of recurrent neural networks (RNNs) to provide real-time predictions about each user's field of vision (FoV). It is feasible to simultaneously move the rendering of virtual reality material to the memory of the MEC server. To improve the long-term VR users' quality of experience (QoE) while staying within the VR interaction latency limitation, we provide decoupling deep reinforcement learning algorithms that are both centrally and distributedly run, taking into consideration the connection between requests' fields of vision and their locations. When compared with rendering on VR headsets, our proposed MEC rendering techniques and DRL algorithms considerably improve VR users' long-term experience quality and reduce VR interaction latency, according to the simulation results.
{"title":"A Deep Reinforcement Learning Strategy for MEC Enabled Virtual Reality in Telecommunication Networks","authors":"Kodanda Rami Reddy Manukonda","doi":"10.47941/ijce.1820","DOIUrl":"https://doi.org/10.47941/ijce.1820","url":null,"abstract":"One of the most anticipated features of 5G and subsequent networks is wireless virtual reality (VR), which promises to transform human interaction via its immersive experiences and game-changing capabilities. Wireless virtual reality systems, and VR games in particular, are notoriously slow due to rendering issues. But most academics don't care about data correlation or real-time rendering. Using mobile edge computing (MEC) and mmWave-enabled wireless networks, we provide an adaptive VR system that enables high-quality wireless VR. By using this architecture, VR rendering operations may be adaptively offloaded to MEC servers in real-time, resulting in even greater performance advantages via caching.The limited processing power of VR devices, the need for a high quality of experience (QoE), and the small latency in VR activities make it difficult to connect wireless VR consumers to high-quality VR content in real-time. To solve these problems, we provide a wireless VR network that is enabled by MEC. This network makes use of recurrent neural networks (RNNs) to provide real-time predictions about each user's field of vision (FoV). It is feasible to simultaneously move the rendering of virtual reality material to the memory of the MEC server. To improve the long-term VR users' quality of experience (QoE) while staying within the VR interaction latency limitation, we provide decoupling deep reinforcement learning algorithms that are both centrally and distributedly run, taking into consideration the connection between requests' fields of vision and their locations. When compared with rendering on VR headsets, our proposed MEC rendering techniques and DRL algorithms considerably improve VR users' long-term experience quality and reduce VR interaction latency, according to the simulation results.","PeriodicalId":198033,"journal":{"name":"International Journal of Computing and Engineering","volume":" 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140681600","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}
Purpose: Exploring AI techniques to improve the quality control of semiconductor production brings numerous advantages, such as enhanced precision, heightened efficiency, and early detection of issues, cost reduction, continuous enhancement, and a competitive edge. These benefits establish this area of research and its practical application in the semiconductor industry as valuable and worthwhile. Methodology: It aims to highlight the advancements, methodologies employed, and outcomes obtained thus far. By scrutinizing the current state of research, the primary objective of this paper is to identify significant challenges and issues associated with AI approaches in this domain. These challenges encompass data quality and availability, selecting appropriate algorithms, interpreting AI models, and integrating them with existing production systems. It is vital for researchers and industry professionals to understand these challenges to effectively address them and devise effective solutions. Moreover, it aims to lay the groundwork for future researchers, offering them a theoretical framework to devise potential solutions for enhancing quality control in semiconductor production. This review aims to drive a research on the semi-conductor production with the AI techniques to enhance the Quality control. Findings: The main findings to offer research is more efficient and accurate approach compared to traditional manual methods, leading to improved product quality, reduced costs, and increased productivity. Armed with this knowledge, future researchers can design and implement innovative AI-driven solutions to enhance quality control in semiconductor production. Unique contribution to theory, policy and practice: Overall, the theoretical foundation presented in this paper will aid researchers in developing novel solutions to improve quality control in the semiconductor industry, ultimately leading to enhanced product reliability and customer satisfaction.
{"title":"A Review of Artificial Intelligence Techniques for Quality Control in Semiconductor Production","authors":"Rajat Suvra Das","doi":"10.47941/ijce.1815","DOIUrl":"https://doi.org/10.47941/ijce.1815","url":null,"abstract":"Purpose: Exploring AI techniques to improve the quality control of semiconductor production brings numerous advantages, such as enhanced precision, heightened efficiency, and early detection of issues, cost reduction, continuous enhancement, and a competitive edge. These benefits establish this area of research and its practical application in the semiconductor industry as valuable and worthwhile. \u0000Methodology: It aims to highlight the advancements, methodologies employed, and outcomes obtained thus far. By scrutinizing the current state of research, the primary objective of this paper is to identify significant challenges and issues associated with AI approaches in this domain. These challenges encompass data quality and availability, selecting appropriate algorithms, interpreting AI models, and integrating them with existing production systems. It is vital for researchers and industry professionals to understand these challenges to effectively address them and devise effective solutions. Moreover, it aims to lay the groundwork for future researchers, offering them a theoretical framework to devise potential solutions for enhancing quality control in semiconductor production. This review aims to drive a research on the semi-conductor production with the AI techniques to enhance the Quality control. \u0000Findings: The main findings to offer research is more efficient and accurate approach compared to traditional manual methods, leading to improved product quality, reduced costs, and increased productivity. Armed with this knowledge, future researchers can design and implement innovative AI-driven solutions to enhance quality control in semiconductor production. \u0000Unique contribution to theory, policy and practice: Overall, the theoretical foundation presented in this paper will aid researchers in developing novel solutions to improve quality control in the semiconductor industry, ultimately leading to enhanced product reliability and customer satisfaction.","PeriodicalId":198033,"journal":{"name":"International Journal of Computing and Engineering","volume":" 35","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140684948","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}
GPUs (Graphics Processing Units) are widely used due to their impressive computational power and parallel computing ability.It have shown significant potential in improving the performance of HPC applications. This is due to their highly parallel architecture, which allows for the execution of multiple tasks simultaneously. However, GPU computing is synonymous with CUDA in providing applications for GPU devices. This offers enhanced development tools and comprehensive documentation to increase performance, while AMD’s ROCm platform features an application programming interface compatible with CUDA. Hence, the main objective of the systematic literature review is to thoroughly analyze and compute the performance characteristics of two prominent GPU computing frameworks, namely NVIDIA's CUDA and AMD's ROCm (Radeon Open Compute). By meticulously examining the strengths, weaknesses, and overall performance capabilities of CUDA and ROCm, a deeper understanding of these concepts is gained and will benefit researchers. The purpose of the research on GPU accelerated HPC is to provide a comprehensive and unbiased overview of the current state of research and development in this area. It can help researchers, practitioners, and policymakers understand the role of GPUs in HPC and facilitate evidence-based decision making. In addition, different real-time applications of CUDA and ROCm platforms are also discussed to explore potential performance benefits and trade-offs in leveraging these techniques. The insights provided by the study will empower the way to make well-informed decisions when choosing between CUDA and ROCm approaches that apply to real-world software.
图形处理器（GPU）因其强大的计算能力和并行计算能力而得到广泛应用。这得益于其高度并行的架构，可以同时执行多个任务。然而，在为 GPU 设备提供应用程序方面，GPU 计算与 CUDA 是同义词。它提供了增强的开发工具和全面的文档来提高性能，而 AMD 的 ROCm 平台具有与 CUDA 兼容的应用编程接口。因此，系统性文献综述的主要目的是全面分析和计算两个著名 GPU 计算框架的性能特点，即英伟达公司的 CUDA 和 AMD 公司的 ROCm（Radeon Open Compute）。通过仔细研究 CUDA 和 ROCm 的优缺点和整体性能，可以加深对这些概念的理解，从而使研究人员受益匪浅。有关 GPU 加速 HPC 的研究旨在全面、公正地概述该领域的研究和开发现状。它可以帮助研究人员、从业人员和决策者了解 GPU 在高性能计算中的作用，并促进基于证据的决策制定。此外，还讨论了 CUDA 和 ROCm 平台的不同实时应用，以探索利用这些技术的潜在性能优势和权衡。本研究提供的见解将帮助人们在选择适用于真实世界软件的 CUDA 和 ROCm 方法时做出明智的决策。
{"title":"A Systematic Literature Review on Graphics Processing Unit Accelerated Realm of High-Performance Computing","authors":"Rajat Suvra Das, Vikas Gupta","doi":"10.47941/ijce.1813","DOIUrl":"https://doi.org/10.47941/ijce.1813","url":null,"abstract":"GPUs (Graphics Processing Units) are widely used due to their impressive computational power and parallel computing ability.It have shown significant potential in improving the performance of HPC applications. This is due to their highly parallel architecture, which allows for the execution of multiple tasks simultaneously. However, GPU computing is synonymous with CUDA in providing applications for GPU devices. This offers enhanced development tools and comprehensive documentation to increase performance, while AMD’s ROCm platform features an application programming interface compatible with CUDA. Hence, the main objective of the systematic literature review is to thoroughly analyze and compute the performance characteristics of two prominent GPU computing frameworks, namely NVIDIA's CUDA and AMD's ROCm (Radeon Open Compute). By meticulously examining the strengths, weaknesses, and overall performance capabilities of CUDA and ROCm, a deeper understanding of these concepts is gained and will benefit researchers. The purpose of the research on GPU accelerated HPC is to provide a comprehensive and unbiased overview of the current state of research and development in this area. It can help researchers, practitioners, and policymakers understand the role of GPUs in HPC and facilitate evidence-based decision making. In addition, different real-time applications of CUDA and ROCm platforms are also discussed to explore potential performance benefits and trade-offs in leveraging these techniques. The insights provided by the study will empower the way to make well-informed decisions when choosing between CUDA and ROCm approaches that apply to real-world software.","PeriodicalId":198033,"journal":{"name":"International Journal of Computing and Engineering","volume":" October","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140682781","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 development of semiconductor manufacturing processes is becoming more intricate in order to meet the constantly growing need for affordable and speedy computing devices with greater memory capacity. This calls for the inclusion of innovative manufacturing techniques hardware components, advanced intricate assemblies and. Tensorflow emerges as a powerful technology that comprehensively addresses these aspects of ML systems. With its rapid growth, TensorFlow finds application in various domains, including the design of intricate semiconductors. While TensorFlow is primarily known for ML, it can also be utilized for numerical computations involving data flow graphs in semiconductor design tasks. Consequently, this SLR (Systematic Literature Review) focuses on assessing research papers about the intersection of ML, TensorFlow, and the design of complex semiconductors. The SLR sheds light on different methodologies for gathering relevant papers, emphasizing inclusion and exclusion criteria as key strategies. Additionally, it provides an overview of the Tensorflow technology itself and its applications in semiconductor design. In future, the semiconductors may be designed in order to enhance the performance, and the scalability and size can be increased. Furthermore, the compatibility of the tensor flow can be increased in order to leverage the potential in semiconductor technology.
{"title":"TensorFlow: Revolutionizing Large-Scale Machine Learning in Complex Semiconductor Design","authors":"Rajat Suvra Das","doi":"10.47941/ijce.1812","DOIUrl":"https://doi.org/10.47941/ijce.1812","url":null,"abstract":"The development of semiconductor manufacturing processes is becoming more intricate in order to meet the constantly growing need for affordable and speedy computing devices with greater memory capacity. This calls for the inclusion of innovative manufacturing techniques hardware components, advanced intricate assemblies and. Tensorflow emerges as a powerful technology that comprehensively addresses these aspects of ML systems. With its rapid growth, TensorFlow finds application in various domains, including the design of intricate semiconductors. While TensorFlow is primarily known for ML, it can also be utilized for numerical computations involving data flow graphs in semiconductor design tasks. Consequently, this SLR (Systematic Literature Review) focuses on assessing research papers about the intersection of ML, TensorFlow, and the design of complex semiconductors. The SLR sheds light on different methodologies for gathering relevant papers, emphasizing inclusion and exclusion criteria as key strategies. Additionally, it provides an overview of the Tensorflow technology itself and its applications in semiconductor design. In future, the semiconductors may be designed in order to enhance the performance, and the scalability and size can be increased. Furthermore, the compatibility of the tensor flow can be increased in order to leverage the potential in semiconductor technology.","PeriodicalId":198033,"journal":{"name":"International Journal of Computing and Engineering","volume":" May","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140682472","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}
Purpose: Universally, the semiconductor is the foundation of electronic technology used in an extensive range of applications such as computers, televisions, smartphones, etc. It is utilized to create ICs (Integrated Circuits), one of the vital electronic device components. The Functional verification of semiconductors is significant to analyze the correctness of an IC for appropriate applications. Besides, Functional verification supports the manufacturers in various factors such as quality assurance, performance optimization, etc. Traditionally, semiconductor Functional verification is carried out manually with the support of expertise. However, it is prone to human error, inaccurate, expensive and time-consuming. To resolve the problem, DL (Deep Learning) based technologies have revolutionized the functional verification of semiconductor device. The utilization of various DL algorithms automates the semiconductor Functional verification to improve the semiconductor quality and performance. Therefore, the focus of this study is to explore the advancements in the functional verification process within the semiconductor industry. Methodology: It begins by examining research techniques used to analyse existing studies on semiconductors. Additionally, it highlights the manual limitations of semiconductor functional verification and the need for DL-based solutions. Findings: The study also identifies and discusses the challenges of integrating DL into semiconductor functional verification. Furthermore, it outlines future directions to improve the effectiveness of semiconductor functional verification and support research efforts in this area. The analysis reveals that there is a limited amount of research on deep learning-based functional verification, which necessitates further enhancement to improve the efficiency of functional verification. Unique contribution to theory, policy and practice: The presented review is intended to support the research in enhancing the efficiency of the semiconductor functional verification. Furthermore, it is envisioned to assist the semiconductor manufacturers in the field of functional verification regarding efficient verifications, yield enhancement, improved accuracy, etc.
{"title":"Enhancing Semiconductor Functional Verification with Deep Learning with Innovation and Challenges","authors":"Rajat Suvra Das, Arjun Pal Chowdhury","doi":"10.47941/ijce.1814","DOIUrl":"https://doi.org/10.47941/ijce.1814","url":null,"abstract":"Purpose: Universally, the semiconductor is the foundation of electronic technology used in an extensive range of applications such as computers, televisions, smartphones, etc. It is utilized to create ICs (Integrated Circuits), one of the vital electronic device components. The Functional verification of semiconductors is significant to analyze the correctness of an IC for appropriate applications. Besides, Functional verification supports the manufacturers in various factors such as quality assurance, performance optimization, etc. Traditionally, semiconductor Functional verification is carried out manually with the support of expertise. However, it is prone to human error, inaccurate, expensive and time-consuming. To resolve the problem, DL (Deep Learning) based technologies have revolutionized the functional verification of semiconductor device. The utilization of various DL algorithms automates the semiconductor Functional verification to improve the semiconductor quality and performance. Therefore, the focus of this study is to explore the advancements in the functional verification process within the semiconductor industry. \u0000Methodology: It begins by examining research techniques used to analyse existing studies on semiconductors. Additionally, it highlights the manual limitations of semiconductor functional verification and the need for DL-based solutions. \u0000Findings: The study also identifies and discusses the challenges of integrating DL into semiconductor functional verification. Furthermore, it outlines future directions to improve the effectiveness of semiconductor functional verification and support research efforts in this area. The analysis reveals that there is a limited amount of research on deep learning-based functional verification, which necessitates further enhancement to improve the efficiency of functional verification. \u0000Unique contribution to theory, policy and practice: The presented review is intended to support the research in enhancing the efficiency of the semiconductor functional verification. Furthermore, it is envisioned to assist the semiconductor manufacturers in the field of functional verification regarding efficient verifications, yield enhancement, improved accuracy, etc.","PeriodicalId":198033,"journal":{"name":"International Journal of Computing and Engineering","volume":" 14","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140684346","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 whitepaper delves into the active role of community-led development (CLD) and participatory design (PD) in open source software, highlighting how these complementary approaches bring stakeholders from various backgrounds together to create a cooperative atmosphere for developing stable solutions. It emphasizes the importance of these methodologies in enabling communities to tackle real-world issues effectively and robustly, thus influencing the expansion of open-source development. Integrating CLD and PD within open-source projects fosters a more inclusive collaborative development environment, driving innovation and user-centric solutions. Through case studies like Kubernetes and Konveyor, it is evident that these methodologies significantly contribute to project success by enhancing adaptability, ensuring broad community engagement, and addressing diverse user needs. The findings underscore the vital role of these strategies in creating sustainable and resilient software solutions, highlighting their potential to transform the technology development landscape.
{"title":"Community-Led Development and Participatory Design in Open Source: Empowering Collaboration for Sustainable Solutions","authors":"Savitha Raghunathan","doi":"10.47941/ijce.1803","DOIUrl":"https://doi.org/10.47941/ijce.1803","url":null,"abstract":"This whitepaper delves into the active role of community-led development (CLD) and participatory design (PD) in open source software, highlighting how these complementary approaches bring stakeholders from various backgrounds together to create a cooperative atmosphere for developing stable solutions. It emphasizes the importance of these methodologies in enabling communities to tackle real-world issues effectively and robustly, thus influencing the expansion of open-source development. Integrating CLD and PD within open-source projects fosters a more inclusive collaborative development environment, driving innovation and user-centric solutions. Through case studies like Kubernetes and Konveyor, it is evident that these methodologies significantly contribute to project success by enhancing adaptability, ensuring broad community engagement, and addressing diverse user needs. The findings underscore the vital role of these strategies in creating sustainable and resilient software solutions, highlighting their potential to transform the technology development landscape.","PeriodicalId":198033,"journal":{"name":"International Journal of Computing and Engineering","volume":"10 27","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140696116","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}
Purpose: This paper addresses the comprehensive security challenges inherent in the lifecycle of machine learning (ML) systems, including data collection, processing, model training, evaluation, and deployment. The imperative for robust security mechanisms within ML workflows has become increasingly paramount in the rapidly advancing field of ML, as these challenges encompass data privacy breaches, unauthorized access, model theft, adversarial attacks, and vulnerabilities within the computational infrastructure. Methodology: To counteract these threats, we propose a holistic suite of strategies designed to enhance the security of ML workflows. These strategies include advanced data protection techniques like anonymization and encryption, model security enhancements through adversarial training and hardening, and the fortification of infrastructure security via secure computing environments and continuous monitoring. Findings: The multifaceted nature of security challenges in ML workflows poses significant risks to the confidentiality, integrity, and availability of ML systems, potentially leading to severe consequences such as financial loss, erosion of trust, and misuse of sensitive information. Unique Contribution to Theory, Policy and Practice: Additionally, this paper advocates for the integration of legal and ethical considerations into a proactive and layered security approach, aiming to mitigate the risks associated with ML workflows effectively. By implementing these comprehensive security measures, stakeholders can significantly reinforce the trustworthiness and efficacy of ML applications across sensitive and critical sectors, ensuring their resilience against an evolving landscape of threats.
目的：本文探讨了机器学习（ML）系统生命周期中固有的全面安全挑战，包括数据收集、处理、模型训练、评估和部署。在快速发展的机器学习领域，在机器学习工作流程中建立强大的安全机制变得越来越重要，因为这些挑战包括数据隐私泄露、未经授权的访问、模型盗窃、对抗性攻击以及计算基础设施中的漏洞。方法论：为了应对这些威胁，我们提出了一整套旨在增强 ML 工作流安全性的策略。这些策略包括先进的数据保护技术（如匿名化和加密）、通过对抗训练和加固来增强模型的安全性，以及通过安全计算环境和持续监控来加强基础设施的安全性。研究结果：人工智能工作流程中的安全挑战具有多面性，对人工智能系统的保密性、完整性和可用性构成了重大风险，可能导致严重后果，如经济损失、信任度下降和敏感信息被滥用。对理论、政策和实践的独特贡献：此外，本文主张将法律和道德因素纳入积极主动的分层安全方法中，旨在有效降低与 ML 工作流程相关的风险。通过实施这些全面的安全措施，利益相关者可以大大加强敏感和关键领域的 ML 应用程序的可信度和有效性，确保它们能够抵御不断变化的威胁。
{"title":"Security in Machine Learning (ML) Workflows","authors":"Dinesh Reddy Chittibala, Srujan Reddy Jabbireddy","doi":"10.47941/ijce.1714","DOIUrl":"https://doi.org/10.47941/ijce.1714","url":null,"abstract":"Purpose: This paper addresses the comprehensive security challenges inherent in the lifecycle of machine learning (ML) systems, including data collection, processing, model training, evaluation, and deployment. The imperative for robust security mechanisms within ML workflows has become increasingly paramount in the rapidly advancing field of ML, as these challenges encompass data privacy breaches, unauthorized access, model theft, adversarial attacks, and vulnerabilities within the computational infrastructure. \u0000Methodology: To counteract these threats, we propose a holistic suite of strategies designed to enhance the security of ML workflows. These strategies include advanced data protection techniques like anonymization and encryption, model security enhancements through adversarial training and hardening, and the fortification of infrastructure security via secure computing environments and continuous monitoring. \u0000Findings: The multifaceted nature of security challenges in ML workflows poses significant risks to the confidentiality, integrity, and availability of ML systems, potentially leading to severe consequences such as financial loss, erosion of trust, and misuse of sensitive information. \u0000Unique Contribution to Theory, Policy and Practice: Additionally, this paper advocates for the integration of legal and ethical considerations into a proactive and layered security approach, aiming to mitigate the risks associated with ML workflows effectively. By implementing these comprehensive security measures, stakeholders can significantly reinforce the trustworthiness and efficacy of ML applications across sensitive and critical sectors, ensuring their resilience against an evolving landscape of threats.","PeriodicalId":198033,"journal":{"name":"International Journal of Computing and Engineering","volume":"29 19","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140081635","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}
Purpose: In response to the challenges posed by traditional cloud-centric IoT architectures, this research explores the integration of Proactive Edge Computing (PEC) in context of smart cities. The purpose addresses privacy concerns, enhance system capabilities, and introduce machine learning powered anticipation to revolutionize urban city management. Methodology: The research employs a comprehensive methodology that includes a thorough review of existing literature on use of IoT devices, edge computing and machine learning in context of smart cities. It introduces the concept of PEC to advocate for a shift from cloud-centric to on-chip computing. The methodology is based on several case studies in various domains of smart city management focusing on the improvement of public life. Findings: This research reveal that the integration of PEC in various smart city domains leads to a significant improvement. Real time data analysis, and machine learning predictions contributes to reduced congestion, enhance public safety, sustainable energy practices, efficient waste management, and personalized healthcare. Unique Contribution to Theory, Policy and Practice: The research makes a unique contribution to the field of theory, policy and practice by proposing a paradigm shift associated with IoT for smart cities. The suggested shift not only ensures data security but also offers a more efficient and proactive approach to urban challenges. The case studies provide actionable insights for policymakers and practitioners, fostering a holistic understanding of the complexities associated with deploying IoT devices in smart cities. The research lays the foundation for a more secure, efficient, and anticipatory ecosystem, aligning technological advancements with societal needs in the dynamic landscape of smart cities.
{"title":"Proactive Edge Computing for Smart City: A Novel Case for ML-Powered IoT","authors":"Rohan Singh Rajput, Sarthik Shah, Shantanu Neema","doi":"10.47941/ijce.1605","DOIUrl":"https://doi.org/10.47941/ijce.1605","url":null,"abstract":"Purpose: In response to the challenges posed by traditional cloud-centric IoT architectures, this research explores the integration of Proactive Edge Computing (PEC) in context of smart cities. The purpose addresses privacy concerns, enhance system capabilities, and introduce machine learning powered anticipation to revolutionize urban city management. \u0000Methodology: The research employs a comprehensive methodology that includes a thorough review of existing literature on use of IoT devices, edge computing and machine learning in context of smart cities. It introduces the concept of PEC to advocate for a shift from cloud-centric to on-chip computing. The methodology is based on several case studies in various domains of smart city management focusing on the improvement of public life. \u0000Findings: This research reveal that the integration of PEC in various smart city domains leads to a significant improvement. Real time data analysis, and machine learning predictions contributes to reduced congestion, enhance public safety, sustainable energy practices, efficient waste management, and personalized healthcare. \u0000Unique Contribution to Theory, Policy and Practice: The research makes a unique contribution to the field of theory, policy and practice by proposing a paradigm shift associated with IoT for smart cities. The suggested shift not only ensures data security but also offers a more efficient and proactive approach to urban challenges. The case studies provide actionable insights for policymakers and practitioners, fostering a holistic understanding of the complexities associated with deploying IoT devices in smart cities. The research lays the foundation for a more secure, efficient, and anticipatory ecosystem, aligning technological advancements with societal needs in the dynamic landscape of smart cities.","PeriodicalId":198033,"journal":{"name":"International Journal of Computing and Engineering","volume":"9 31","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139380289","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}
Purpose: In this research, the purpose is to explore E911 call reliability requirements, study real-world issues related to telecommunication networks transitioning from LTE to 5G (NR) and WCDMA, and present network optimization solutions. The primary objective is to ensure the continuous supply of emergency services and improve the dependability of Enhanced 911 (E911) calls. Methodology: The research methodology involves an examination of the transition from LTE to 5G (NR) and WCDMA in telecommunication networks. The study delves into government-mandated E911 call reliability requirements and conducts a detailed analysis of two real-world issues affecting tight connectivity for E911 calls. Additionally, the research proposes network optimization solutions to address these challenges and enhance the overall reliability of emergency services. Findings: The findings of this research reveal insights into government-mandated E911 call reliability requirements and identify two practical issues affecting the continuity of emergency services during the transition from LTE to 5G (NR) and WCDMA. Unique contributor to theory, policy and practice: The study presents network optimization solutions aimed at overcoming these challenges, with the ultimate goal of improving the dependability of E911 calls and enhancing public safety.
{"title":"Enhanced Network Reliability Following Emergency (E911) Calls","authors":"Riteshkumar S. Patel, Jigarkumar Patel","doi":"10.47941/ijce.1600","DOIUrl":"https://doi.org/10.47941/ijce.1600","url":null,"abstract":"Purpose: In this research, the purpose is to explore E911 call reliability requirements, study real-world issues related to telecommunication networks transitioning from LTE to 5G (NR) and WCDMA, and present network optimization solutions. The primary objective is to ensure the continuous supply of emergency services and improve the dependability of Enhanced 911 (E911) calls. \u0000Methodology: The research methodology involves an examination of the transition from LTE to 5G (NR) and WCDMA in telecommunication networks. The study delves into government-mandated E911 call reliability requirements and conducts a detailed analysis of two real-world issues affecting tight connectivity for E911 calls. Additionally, the research proposes network optimization solutions to address these challenges and enhance the overall reliability of emergency services. \u0000Findings: The findings of this research reveal insights into government-mandated E911 call reliability requirements and identify two practical issues affecting the continuity of emergency services during the transition from LTE to 5G (NR) and WCDMA. \u0000Unique contributor to theory, policy and practice: The study presents network optimization solutions aimed at overcoming these challenges, with the ultimate goal of improving the dependability of E911 calls and enhancing public safety.","PeriodicalId":198033,"journal":{"name":"International Journal of Computing and Engineering","volume":"47 27","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139382224","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}
Integrating Artificial Intelligence (AI) into daily life has brought transformative changes, ranging from personalized recommendations on streaming platforms to advancements in medical diagnostics. However, concerns about the transparency and interpretability of AI models, intense neural networks, have become prominent. This paper explores the emerging paradigm of Explainable Artificial Intelligence (XAI) as a crucial response to address these concerns. Delving into the multifaceted challenges posed by AI complexity, the study emphasizes the critical significance of interpretability. It examines how XAI is fundamentally reshaping the landscape of artificial intelligence, seeking to reconcile precision with the transparency necessary for widespread acceptance.
{"title":"Demystifying AI: Navigating the Balance between Precision and Comprehensibility with Explainable Artificial Intelligence","authors":"Narayana Challa","doi":"10.47941/ijce.1603","DOIUrl":"https://doi.org/10.47941/ijce.1603","url":null,"abstract":"Integrating Artificial Intelligence (AI) into daily life has brought transformative changes, ranging from personalized recommendations on streaming platforms to advancements in medical diagnostics. However, concerns about the transparency and interpretability of AI models, intense neural networks, have become prominent. This paper explores the emerging paradigm of Explainable Artificial Intelligence (XAI) as a crucial response to address these concerns. Delving into the multifaceted challenges posed by AI complexity, the study emphasizes the critical significance of interpretability. It examines how XAI is fundamentally reshaping the landscape of artificial intelligence, seeking to reconcile precision with the transparency necessary for widespread acceptance.","PeriodicalId":198033,"journal":{"name":"International Journal of Computing and Engineering","volume":"119 24","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139383239","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：