检索结果-内蒙古大学图书馆

Dynamic Offloading and Scheduling Strategy for Telematics Tasks Based on Latency Minimization

computers, Materials & Continua 2024年第8期80卷 1809-1829页

作者： Yu Zhou Yun Zhang Guowei Li Hang Yang Wei Zhang Ting Lyu Yueqiang Xu North China Institute of Computing Technology Beijing Beijing100080China School of Computer and Communication Engineering University of Science and Technology BeijingBeijing100083China

In current research on task offloading and resource scheduling in vehicular networks,vehicles are commonly assumed to maintain constant speed or relatively stationary states,and the impact of speed variations on task offloading is often *** is frequently assumed that vehicles can be accurately modeled during actual motion ***,in vehicular dynamic environments,both the tasks generated by the vehicles and the vehicles’surroundings are constantly changing,making it difficult to achieve real-time modeling for actual dynamic vehicular network *** into account the actual dynamic vehicular scenarios,this paper considers the real-time non-uniform movement of vehicles and proposes a vehicular task dynamic offloading and scheduling algorithm for single-task multi-vehicle vehicular network scenarios,attempting to solve the dynamic decision-making problem in task offloading *** optimization objective is to minimize the average task completion time,which is formulated as a multi-constrained non-linear programming *** to the mobility of vehicles,a constraint model is applied in the decision-making process to dynamically determine whether the communication range is sufficient for task offloading and ***,the proposed vehicular task dynamic offloading and scheduling algorithm based on muti-agent deep deterministic policy gradient(MADDPG)is applied to solve the optimal solution of the optimization *** results show that the algorithm proposed in this paper is able to achieve lower latency task computation ***,the average task completion time of the proposed algorithm in this paper can be improved by 7.6%compared to the performance of the MADDPG scheme and 51.1%compared to the performance of deep deterministic policy gradient(DDPG).

关键词： Component vehicular dynamic task offloading resource scheduling

来源：评论

学校读者我要写书评

暂无评论

An EETR Approach for Therapeutic Response Prediction Using Gene Expression and Drug Properties 3rd

An EETR Approach for Therapeutic Response Prediction Using G...

引用

3rd International Conference on computing and Communication Networks, ICCCN 2023

作者： Selvi Rajendran, P. Jawahar, Janiel Computer Science and Engineering School of Computing Hindustan Institute of Technology and Science Chennai India

ISBN: (纸本)9789819726707

In recent years, the role of computational methods such as machine learning and deep learning has evolved to help better understand an individual’s response to drugs. Through advancements in the discipline of precision medicine, cancer therapies are made based on an individual's pharmacogenomics data. In this way, doctors can make informed decisions about patient outcomes and reduce treatment costs. Beyond these advancements, there is enough void to precisely predict drug response. A drug’s response to therapy is dependent on a number of factors such as the drug’s physicochemical properties, pharmacokinetics, metabolism, protein, mutation, somatic variation, environment, and much more. Studying the correlation of more of these factors and their association with the drug is one of the promising ways to bridge the gap in improving results. Extra tree regression is an ensemble-based algorithm and is less prone to overfitting than other ensemble learning algorithms particularly when low bias and reduced overfitting are desired, and computational efficiency is important. In this paper, we have applied the drug’s physicochemical properties to predict the Inhibition values using an enhanced extra tree regression (EETR) algorithm. The EETR algorithm prediction outperformed both the random forest and original ETR algorithm in terms of both MSE and R2 score. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Caching Strategies in NDN Based Wireless Ad Hoc Network:A Survey

引用

computers, Materials & Continua 2024年第7期80卷 61-103页

作者： Ahmed Khalid Rana Asif Rehman Byung-Seo Kim Department of Computer Science FAST School of ComputingNational University of Computer and Emerging SciencesLahore54000Pakistan Department of Software and Communications Engineering Hongik UniversitySejong City30016Republic of Korea

Wireless Ad Hoc Networks consist of devices that are wirelessly *** Ad Hoc Networks(MANETs),Internet of Things(IoT),and Vehicular Ad Hoc Networks(VANETs)are the main domains of wireless ad hoc *** is used in wireless ad hoc *** is based on Transmission Control Protocol(TCP)/Internet Protocol(IP)network where clients and servers interact with each other with the help of IP in a pre-defined *** fetches data from a fixed *** redundancy,mobility,and location dependency are the main issues of the IP network *** these factors result in poor performance of wireless ad hoc *** main disadvantage of IP is that,it does not provide in-network ***,there is a need to move towards a new network that overcomes these *** Data Network(NDN)is a network that overcomes these *** is a project of Information-centric Network(ICN).NDN provides in-network caching which helps in fast response to user *** NDN in wireless ad hoc network provides many benefits such as caching,mobility,scalability,security,and *** considering the certainty,in this survey paper,we present a comprehensive survey on Caching Strategies in NDN-based Wireless *** cachingmechanism-based results are also *** the last,we also shed light on the challenges and future directions of this promising field to provide a clear understanding of what caching-related problems exist in NDN-based wireless ad hoc networks.

关键词： Content centric network Internet of Things mobile ad hoc network named data network vehicular ad hoc network

来源：评论

学校读者我要写书评

暂无评论

SmartEagleEye:A Cloud-Oriented Webshell Detection System Based on Dynamic Gray-Box and Deep Learning

引用

Tsinghua Science and Technology 2024年第3期29卷 766-783页

作者： Xin Liu Yingli Zhang Qingchen Yu Jiajun Min Jun Shen Rui Zhou Qingguo Zhou School of Information Science and Engineering Lanzhou UniversityLanzhou 730000China College of Computer Science and Technology Zhejiang UniversityHangzhou 310058China School of Computing and Information Technology University of WollongongWollongong 2500Australia

Compared with traditional environments,the cloud environment exposes online services to additional vulnerabilities and threats of cyber attacks,and the cyber security of cloud platforms is becoming increasingly prominent.A piece of code,known as a Webshell,is usually uploaded to the target servers to achieve multiple *** Webshell attacks has become a hot spot in current ***,the traditional Webshell detectors are not built for the cloud,making it highly difficult to play a defensive role in the cloud ***,a Webshell detection system based on deep learning that is successfully applied in various scenarios,is proposed in this *** system contains two important components:gray-box and neural network *** gray-box analyzer defines a series of rules and algorithms for extracting static and dynamic behaviors from the code to make the decision *** neural network analyzer transforms suspicious code into Operation Code(OPCODE)sequences,turning the detection task into a classification *** experiment results show that SmartEagleEye achieves an encouraging high detection rate and an acceptable false-positive rate,which indicate its capability to provide good protection for the cloud environment.

关键词： Webshell detection cloud web security deep learning

来源：评论

学校读者我要写书评

暂无评论

Seamless Service Evolution: Enhancing Customer Satisfaction Using AWS-Driven AI Chatbots for Restaurant Ordering 4

Seamless Service Evolution: Enhancing Customer Satisfaction ...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Ali, Mohammed Jaffer Vyshnavi, M.R.V. Kumar, Konda V.S. Harshith Vishnubhatla, Sravya Rajagopal, Shinu M. Amrita School of Computing Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798331540364

In the current restaurant business environment, factors have emerged in the manner in which consumers are attended to and the ways orders are placed. As good as these traditional systems may be, they do not offer the optimum flexibility and consumer convergence that today's client demands for fast and convenient services. Recent approaches using only basic form of automation and rule-based chatbots do offer some enhancements but lack adequate capabilities to deal with huge volumes of orders, custom recommendations and scalability according to demand. Further, the existing systems have problems with scalability, versatility to different customers' trends and needs, and real-time interactions. To overcome these challenges our work, will utilize modern advances in artificial intelligence and cloud technology. The proposed system uses Amazon Lex for NLU, A WS Lambda for processing multiple booking requests simultaneously without any intervention from the users and Amazon Polly for making interaction more interactive with personalized audio. In addition, Amazon Rekognition and A WS S3 for images will be used for analysis of images and proper storage of data respectively, enhancing the customer satisfaction by recommending products based on a past order. All these technologies integrated with A WS ecosystem in our solution will provide convenience, efficiency and passion to restaurant business proprietors to fulfill the increasing demands of modern customer. The system also supports linkage with some commonly used applications such as WhatsApp, guaranteeing that the customers receive timely updates. Thus, this solution is designed to create an improved status of restaurant ordering and eliminate the problematic experiences placed in current schemes. © 2024 IEEE.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Enhanced Security Measures for Image Privacy: Encryption Perspectives 2

Enhanced Security Measures for Image Privacy: Encryption Per...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Omshith, R. Balaji, Vemisetti Pavan Rahul, Rayapudi Venkata Kumaran, U. Amrita School of Computing Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350327533

A key technology in information security, picture encryption is intended to safeguard the integrity and confidentiality of digital photographs. Using a variety of cryptographic techniques and algorithms, the original image is transformed into an encrypted format throughout this process, making it more difficult for unauthorized users to view or understand the content. Secure communication, picture sharing, medical imaging, and many more fields requiring the protection of sensitive visual data find widespread use in image encryption. A key technology in information security, picture encryption is intended to safeguard the integrity and confidentiality of digital photographs. It also discusses the difficulties and potential paths for picture encryption, highlighting the rising demand for reliable, effective, and secure image encryption solutions in a world that is becoming more and more networked and data-driven. Advanced Encryption Standard (AES) is more secure than (Exclusive OR) XOR, Fernet. © 2024 IEEE.

关键词： Advanced Encryption Standard Confidentiality Encryption Exclusive OR (XOR) Fernet Integrity

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in Classroom Using Convolutional Neural Networks 6th

Anomaly Detection in Classroom Using Convolutional Neural Ne...

引用

6th International Conference on Soft computing and Signal Processing, ICSCSP 2023

作者： Vidhyasagar, B.S. Doppalapudi, Harshith Chowdary, Sritej Dagumati, VishnuVardhan Charan Kumar Reddy, N. Department of Computer Science and Engineering Amrita School of Computing AmritaVishwaVidyapeetham Chennai India

ISBN: (纸本)9789819984503

Anomaly detection is a task that involves identifying patterns or events that deviate significantly from the expected or normal behavior. In the context of classroom settings, it is essential to identify mischievous behavior exhibited by students to ensure a productive and conducive learning environment. This paper proposes a new method to identify abnormal behavior in a classroom setting using computer vision and deep learning techniques. This method uses convolutional neural networks (CNNs) and recurrent neural networks (RNN) algorithms to detect hand-raising, sleeping, talking, and fighting behaviors in the classroom with live video surveillance. It involves using the You Only Look Once (YOLO) algorithm to locate the position of students in the frame and an RNN algorithm to classify their behavior as normal or anomalous. RNN algorithm is trained on a labeled image and video dataset containing examples of normal and abnormal behaviors. This system can trigger real-time alerts, allowing teachers to act appropriately to maintain a conducive learning environment. It also helps to identify and address disruptive behaviors. Real-time, revolutionizing classroom monitoring: Our algorithm has the potential to improve student safety and well-being, as well as their academic performance. This research could lead to further developments in the field of the classroom. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Advanced Multi-Task Reinforcement Learning Utilising Task-Adaptive Episodic Memory with Hypernetwork Integration 2

Advanced Multi-Task Reinforcement Learning Utilising Task-Ad...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Prasanna Kumar, R. Prasanna Kumar, B.G. Sri Ramakrishna Prabhu, A. Upadhyay, Yash Teja, Nunna Vishnu Swamy, Penta Aravinda Amrita Vishwa Vidyapeetham School of Computing Computer Science and Engineering Chennai India

ISBN: (纸本)9798350327533

In deep reinforcement learning, sampling ineffi-ciency is addressed by mimicking human learning which lever-Ages past experiences stored in the hippocampus. Integrating this idea, the proposed approach utilizes a task-conditioned hypernetwork retrieval network with MobileNet for feature extraction from past experiences. Furthermore, BERT was in-Tegrated for advanced natural language understanding, enabling our DRL agents to better interpret and act upon language-based tasks. This approach ensures dynamic adaptability and fosters a more efficient collaboration between retrieval and decision-making processes. Evaluation in MiniGrid demonstrates that the proposed method outperforms strong baselines, showing significant advancements in deep reinforcement learning with natural language processing capabilities. This advancement not only marks progress in sampling efficiency but also opens new avenues for multi-Task learning, paving the way for more intelligent, autonomous AI systems. © 2024 IEEE.

关键词： Bidirectional Encoder Representations from Transformers Deep Reinforcement Learning Episodic Memory Hypernetwork Multi-Task Learning

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation and Comparative Ranking of LLM Variants in Entity Relationship Prediction 15

Performance Evaluation and Comparative Ranking of LLM Varian...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Vardhni, Krisha Devaraja, G. Dharhshita, R. Chowdary, Ritesh Krishna Mahadevan, Anbazhagan Amrita School of Computing Department of Computer Science and Engineering Coimbatore641112 India

ISBN: (纸本)9798350370249

This paper presents a comprehensive evaluation and ranking of five Large Language Models - Mistral, Vicuna, Phi, Llama 2, and Zephyr - across five temperature variants. The focus is on their ability to predict the likelihood of a relationship between pairs of entities within a given context. Each LLM variant is assessed based on stability over multiple epochs, speed, dispersion of results, and the number of incorrect responses. The study aims to provide insights into the performance of these LLMs, thereby facilitating their effective utilization in generating meaningful tabular data. The findings are expected to contribute significantly to the field of artificial intelligence and data analysis. The paper concludes with a comparative ranking of the 25 LLM variants, providing a clear perspective on their relative performances. © 2024 IEEE.

关键词： Artificial Intelligence Data Analysis Entity Relationship Prediction Large Language Models Performance Evaluation Ranking Variants Tabular Data Generation Temperature Variants

来源：评论

学校读者我要写书评

暂无评论

meMIA: Multilevel Ensemble Membership Inference Attack

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第1期6卷 93-106页

作者： Ullah, Najeeb Aman, Muhammad Naveed Sikdar, Biplab National University of Singapore Department of Electrical and Computer Engineering 117583 Singapore University of Nebraska-Lincoln School of Computing LincolnNE68588 United States

Leakage of private information in machine learning models can lead to breaches of confidentiality, identity theft, and unauthorized access to personal data. Ensuring the safe and trustworthy deployment of AI systems necessitates addressing privacy concerns to prevent unintentional disclosure and discrimination. One significant threat, membership inference (MI) attacks, exploit vulnerabilities in target learning models to determine if a given sample was part of the training set. However, the effectiveness of existing MI attacks is often limited by the number of classes in the dataset or the need for diverse multilevel adversarial features to exploit overfitted models. To enhance MI attack performance, we propose meMIA, a novel framework based on stacked ensemble learning. meMIA integrates embeddings from a neural network (NN) and a long short-term memory (LSTM) model, training a subsequent NN, termed the meta-model, on the concatenated embeddings. This method leverages the complementary strengths of NN and LSTM models;the LSTM captures order differences in confidence scores, while the NN discerns probability distribution differences between member and nonmember samples. We extensively evaluate meMIA on seven benchmark datasets, demonstrating that it surpasses current state-of-the-art MI attacks, achieving accuracy up to 94.6% and near-perfect recall. meMIA's superior performance, especially on datasets with fewer classes, underscores the urgent need for robust defenses against privacy attacks in machine learning, contributing to the safer and more ethical use of AI technologies. © 2024 IEEE.

关键词： Information leakage

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：