检索结果-内蒙古大学图书馆

2024 international Conference on distributed systems, computer networks and Cybersecurity, ICDSCNC 2024

作者： Naidu, D J Samatha Jain, Upma Shruthi, S. Rao, K. B. V. Brahma Iqbal, Syed Mohammad Uzair Natrayan, L. Annamacharya Pg College of Computer Studies Department of Master of Computer Applications India Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India Bms Institute of Technology and Management Department of Artificial Intelligence and Machine Learning Bengaluru India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering India Symbiosis Law School Department of Law Pune India Simats Saveetha School of Engineering Department of Mechanical Engineering India

ISBN: (纸本)9798350375442

The Internet of Things (IoT) enables intelligent data exchange across many kinds of interconnected devices in a diverse and unpredictable physical setting. The Internet of Things (IoT) network used in this study is a cluster-based sensor network that includes a base station and an application server that offers various services in a cloud setting. In this setting, assaults may occur in both device-to-device and user-to-device communication. For pervasive devices with limited resources, the use of conventional encryption techniques to address this problem is not practical. In addition, the majority of current trust-based security solutions either address the user level or the devices level. Therefore, this study aims to tackle environment-specific security concerns at the device and user levels in light of the environment's inherent dynamic and dispersed nature. This research explored the usage of a Trust Based Security Framework (TBSF) and Reputation Based systems in the Internet of Things (IoT) to accurately describe the actions of devices and users. Fuzzy logic was used to calculate both the device trust and the user trust. A trust-based access control system, secure cluster head selection, and safe routing were all built using these trust values. At first, the security of device-to-device communication was addressed by the design and effective implementation of the Trust Aware Device Access Control System (TADACS). © 2024 IEEE.

关键词： Access control

来源：评论

学校读者我要写书评

暂无评论

Reconnaissance Detection in Decentralised IoT System using Model-Contrastive Federated Learning 18

Reconnaissance Detection in Decentralised IoT System using M...

引用

18th IEEE international Conference on Advanced networks and Telecommunications systems, ANTS 2024

作者： Dutta, Rajdeep Kumar Chhetry, Bishal Matam, Rakesh Barbhuiya, Ferdous Ahmed Indian Institute of Information Technology Dept. of Computer Science and Engineering Guwahati India

ISBN: (纸本)9798350391725

The detection of reconnaissance attacks is crucial for safeguarding Internet of Things (IoT) environments, which are inherently more vulnerable and resource-constrained compared to traditional computing systems. Traditional centralised detection methods face significant challenges, such as privacy concerns and limited scalability due to the need to aggregate raw data on a central server. These issues become particularly pronounced in IoT environments where devices are diverse and geographically distributed. To address these challenges, we propose ReconGuard, a novel approach leveraging Model Contrastive Federated Learning (MCFL). ReconGuard enables collaborative training across multiple IoT devices without the necessity of sharing raw data, thereby preserving user privacy and enhancing data security. The approach integrates contrastive learning techniques, which improve the model's ability to discriminate between benign and malicious activities by contrasting positive (similar) and negative (dissimilar) data pairs. Our experimental results demonstrate that the ReconGuard-based detection system provides a scalable and privacy-preserving solution for identifying reconnaissance activities. These activities are often the initial step in more severe cyber threats, such as botnet attacks, which can lead to significant disruption and damage. By effectively detecting reconnaissance activities, ReconGuard enhances the overall cybersecurity framework of IoT environments. This research presents a viable and innovative method for improving cybersecurity in IoT systems, addressing the critical need for scalable, efficient, and privacy-preserving intrusion detection solutions. The use of MCFL in ReconGuard not only mitigates the challenges of data centralisation but also leverages the distributed nature of IoT networks to enhance robustness against cyber threats. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Improving Accuracy in Network Intrusion Detection via Machine Learning Algorithms: An In-Depth Examination

Improving Accuracy in Network Intrusion Detection via Machin...

引用

2024 international Conference on distributed systems, computer networks and Cybersecurity, ICDSCNC 2024

作者： Suriya Prakash, J. Trishlaa, S. Soniya, R. Lakshmanan, V. Kiran, S. Department of Cse Ramnagara India Rajarajeshwari College of Engineering Department of Artificial Intelligence and Machine Learning Bengaluru India Sri Eshwar College of Engineering Department of Computer Science and Engineering Coimbatore India Nitte Meenakshi Institute of Technology Department of Mathematics Bengaluru India

ISBN: (纸本)9798350375442

Intrusion detection is essential for securing computer networks by monitoring and analyzing activity to detect and respond to unauthorized access and malicious behavior. By examining network traffic and system logs, intrusion detection systems (IDS) help protect data integrity and availability, enabling swift responses to potential security incidents. In an ever-evolving cyber threat landscape, IDS plays a critical role in maintaining network security. This research investigates the performance of various machine learning algorithms for classification tasks using a dataset from Kyoto collected on December 31st, 2015. The algorithms explored include Naive Bayes, K-Nearest Neighbors (KNN), Extreme Gradient Boosting (XGBoost), AdaBoost, and CatBoost. Training and testing the model with different data splits (80/20, 70/30, 60/40) revealed that AdaBoost, LGBM, XGBoost, Decision Tree, Gradient Boosting, and Random Forest consistently delivered the highest accuracy. The study concludes that selecting the appropriate algorithms and data splits is crucial for enhancing IDS effectiveness, providing valuable insights for future research. Explore the code behind this study at https://***/Trishlaa07/Kyoto_2015_Dec_day31 © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Resource Optimization of Stream Processing in Layered Internet of Things 42

Resource Optimization of Stream Processing in Layered Intern...

引用

42nd international symposium on Reliable distributed systems (SRDS)

作者： Momtaz, Anik Medhat, Ramy Bonakdarpour, Borzoo Michigan State Univ E Lansing MI 48824 USA Google LLC Waterloo ON Canada

ISBN: (纸本)9798350329100

IoT (Internet of Things) applications often involve stream processing using multiple complex layers of processing nodes, where in each layer, data is received by the nodes, processed, and then transmitted to the nodes in subsequent layers. Such systems present a tradeoff between reliability and resource usage, including CPU power, energy, network bandwidth, memory, etc. Reducing the reliability at which a node processes inbound data in a layer can have repercussions on nodes in subsequent layers in the network that receive less reliable data, and in turn impact the reliability of the application as a whole. In this paper, we present a generalized model of streaming IoT applications as a layered network of producers and consumers. Our model captures trade-offs between reliability and resource usage of the system. We present an efficient algorithm using SMT constraint solvers to determine the optimal selection of processing quality for each node in the network, such that target system reliability is achieved while respecting the given resource bounds, and resource usage is minimized. In addition, we present a lightweight machine learning based solution to drastically improve our model in terms of run time. We have fully implemented our technique and report experimental results on a layered IoT network.

关键词： computer Network Constraint Solving Internet of Things Machine Learning Reliability Resource Optimization Stream Processing

来源：评论

学校读者我要写书评

暂无评论

Deception Detection from Linguistic and Physiological Data Streams Using Bimodal Convolutional Neural networks 5

Deception Detection from Linguistic and Physiological Data S...

引用

5th international Conference on Information Science, Parallel and distributed systems, ISPDS 2024

作者： Li, Panfeng Abouelenien, Mohamed Mihalcea, Rada Ding, Zhicheng Yang, Qikai Zhou, Yiming University of Michigan Department of Electrical and Computer Engineering Ann Arbor United States University of Michigan Department of Computer Science Ann Arbor United States Columbia University Fu Foundation School of Engineering and Applied Science New York United States University of Illinois Urbana-Champaign Department of Computer Science Urbana United States Saarland University of Applied Science Department of Engineer Sciences Saarland Germany

ISBN: (纸本)9798350352719

Deception detection is gaining increasing interest due to ethical and security concerns. This paper explores the application of convolutional neural networks for the purpose of multimodal deception detection. We use a dataset built by interviewing 104 subjects about two topics, with one truthful and one falsified response from each subject about each topic. In particular, we make three main contributions. First, we extract linguistic and physiological features from this data to train and construct the neural network models. Second, we propose a fused convolutional neural network model using both modalities in order to achieve an improved overall performance. Third, we compare our new approach with earlier methods designed for multimodal deception detection. We find that our system outperforms regular classification methods;our results indicate the feasibility of using neural networks for deception detection even in the presence of limited amounts of data. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Leveraging Machine Learning and Deep Learning Models for Enhanced Stock Price Prediction: A State-of-the-Art Analysis 21st

Leveraging Machine Learning and Deep Learning Models for Enh...

引用

21st international symposium on distributed Computing and Artificial Intelligence

作者： Alaoui, Safae Belamfedel Hafid, Abdelatif Sayyouri, Mhamed Rahouti, Mohamed Ecole Natl Sci Appl ENSA LISA 72 Fes Morocco Ecole Super Ingn Sci Appl ESIS ESISA Analyt 505 Fes Morocco Fordham Univ Comp & Informat Sci Dept New York NY USA

ISBN: (纸本)9783031820724;9783031820731

The prediction of stock prices has recently gained considerable attention as a complex and challenging issue within the realms of economics and finance. Stock prices are affected by various factors, such as the business environment, stock market operations, inflation, and unexpected events. Since the stock market is volatile and nonlinear, finding the most effective model to forecast stock prices is one of the most challenging problems. Researchers have increasingly explored various Machine Learning (ML) and Deep Learning (DL) models to address this issue due to their capacity to handle time series data and nonlinear patterns. These models often outperform traditional approaches in predicting stock prices with high accuracy and lower root mean square error (RMSE). This paper reviews various works that have utilized ML approaches for stock price prediction, covering research published between 2017 and 2023. This literature review discusses various techniques, their performance, limitations, and future work. We assess the latest techniques in many studies, including ML and DL models. The findings of this review conclude that Neural networks (NNs) are the most commonly used approaches in predicting stock prices due to their effectiveness in detecting complex patterns in financial data.

关键词： Stock price prediction Machine Learning Deep Learning Neural networks Sentiment Analysis

来源：评论

学校读者我要写书评

暂无评论

Traffic Engineering in Large-scale networks via Multi-Agent Deep Reinforcement Learning with Joint-Training 33

Traffic Engineering in Large-scale Networks via Multi-Agent ...

引用

33rd IEEE international Conference on computer Communications and networks (ICCCN)

作者： Van An Le Duc Long Nguyen Phi Le Nguyen Ji, Yusheng Natl Inst Adv Ind Sci & Technol Tokyo Japan Hanoi Univ Sci & Technol Hanoi Vietnam Natl Inst Informat Tokyo Japan

ISBN: (纸本)9798350348439;9798350384611

Reinforcement learning (RL) has been successfully applied in many fields for building autonomous systems, such as robotics and telecommunications. With its self-learning ability, RL provides a framework for learning from historical experience and adapting to dynamic environments. In response to the surge in network traffic and the evolving nature of traffic behavior, RL has emerged as a crucial technique for developing intelligent and adaptive traffic engineering (TE) solutions. However, most prior studies have focused on using a centralized unit (i.e., a single agent) to construct RL-based TE systems. While the centralized approach leverages global network information for solid performance, it encounters challenges related to scalability, dynamic network topology, and high monitoring overhead for collecting network information. This paper addresses these issues by introducing a jointly trained multi-agent reinforcement learning-based traffic engineering (MATE-JT) system, which operates as a distributed TE solution. Our approach utilizes multiple agents within a network node so that each agent can make independent routing decisions for a subset of flows. We take the approach of sharing parameters among agents and introduce a joint-training technique that facilitates simultaneous learning from multiple agents' experiences. As a result, our proposed method enhances system performance while reducing training time. We evaluate the proposed approach using various network traffic datasets and demonstrate that MATE-JT improves the performance of TE (about 6.5%) and achieves faster convergence (about 35%) in large-scale networks when compared to state-of-the-art methods.

关键词： Multi-agent Deep Reinforcement Learning Traffic Engineering Large-scale networks

来源：评论

学校读者我要写书评

暂无评论

Federated Learning with Spiking Neural networks in Heterogeneous systems 26

Federated Learning with Spiking Neural Networks in Heterogen...

引用

26th IEEE-computer-Society Annual symposium on VLSI (ISVLSI)

作者： Tumpa, Sadia Anjum Singh, Sonali Khan, Md Fahim Faysal Kandemir, Mahmut Tylan Narayanan, Vijaykrishnan Das, Chita R. Penn State Univ Sch Elect Engn & Comp Sci University Pk PA 16802 USA

ISBN: (纸本)9798350327694

With the advances in IoT and edge-computing, Federated Learning is ever more popular as it offers data privacy. Low-power spiking neural networks (SNN) are ideal candidates for local nodes in such federated setup. Most prior works assume that the participating nodes have uniform compute resources, which may not be practical. In this work, we propose a federated SNN learning framework for a realistic heterogeneous environment, consisting of nodes with diverse memory-compute capabilities through activation-checkpointing and time-skipping that offers similar to 4x reduction in effective memory requirement for low-memory nodes while improving the accuracy upto 10% for non-independent and identically-distributed data.

关键词： Federated Learning Neuromorphic Computing Spiking Neural Network (SNN) Heterogeneous systems Internet of Things

来源：评论

学校读者我要写书评

暂无评论

The Deep Learning Based Analysis and Prediction of Juniper Apple Rust Disease in Apple Plants using ResNet-50 Hybrid Algorithm

The Deep Learning Based Analysis and Prediction of Juniper A...

引用

2024 international Conference on distributed systems, computer networks and Cybersecurity, ICDSCNC 2024

作者： Sharma, Ravi Bhushan Ali, Aleem Farooq, Sheikh Afaan Suryakanta, Suryakanta Chandigarh University Department of Computer Science Mohali India

ISBN: (纸本)9798350375442

Juniper Apple Rust, also known as Cedar-Apple Rust, is a fungal disease caused by Gymnosporangium juniperi-virginianae. The disease requires two hosts, primarily Eastern red cedars and apple trees, to complete its life cycle. The apple plantations can be affected by this disease as it can result in falling of leafs and the lower-quality fruit. This disorder emerges as yellow-orange spots on the leaves that have black centers and red borders. Managing this disease includes using fungicides during the grave spring infection period, planting the disease-resistant apple varieties, and removing the juniper galls. This study introduces a deep-learning classifier designed to distinguish between two types of image data, one showing apple leaves affected by Cedar-apple rust disease and the other showing healthy apple leaves. The images undergo de-noising to improve quality. The cleaned data is then used to train ResNet-50 networks, achieving high precision. In summary, this research aims to develop a highly accurate image classifier for detecting Cedar-apple rust disease, achieving an accuracy rate of 98.99%. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Omega multistage interconnection network manages double-pattern traffic with a regulator and high-speed forwarding method

引用

international JOURNAL OF PARALLEL EMERGENT AND distributed systems 2023年第4期38卷 313-326页

作者： Stergiou, Eleftherios Liarokapis, Dimitrios Margariti, Spiridoula Bombotsaris, Ilias Univ Ioannina Dept Informat & Telecommun Campus Arta Arta 47100 Greece

This study proposes a flexible and effective solution for developing high-performance multistage interconnection networks to maximize the performance of parallel computer systems, cloud computing infrastructure, grids, etc. An omega-type multistage interconnection network, consisting of regulated switchboxes, is used as a testbed to handle flexible two-class load patterns. The wormhole routing method and a special forwarding technique controlled by a global regulator are adopted to alleviate internal 'tree saturation' caused by periodic hotspot traffic combined with uniform traffic. Simulation experiments prove that this concept reduces packet latency, and an additional layer inserted in the final stage further improves the network's architecture.

关键词： Multistage interconnection networks omega network latency hotspot traffic uniform traffic simulation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：