检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Sun, Zemin Sun, Geng Wu, Qingqing He, Long Liang, Shuang Pan, Hongyang Niyato, Dusit Yuen, Chau Leung, Victor C.M. The College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun130012 China Department of Electronic Engineering Shanghai Jiao Tong University Shanghai China The School of Information Science and Technology Northeast Normal University Changchun130024 China The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore The School of Electrical and Electronics Engineering Nanyang Technological University Singapore639798 Singapore The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Department of Electrical and Computer Engineering University of British Columbia VancouverBCV6T 1Z4 Canada

Unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) is emerging as a promising paradigm to provide aerial-terrestrial computing services in close proximity to mobile devices (MDs). However, meeting the demands of computation-intensive and delay-sensitive tasks for MDs poses several challenges, including the demand-supply contradiction between MDs and MEC servers, the demand-supply heterogeneity between MDs and MEC servers, the trajectory control requirements on energy efficiency and timeliness, and the different time-scale dynamics of the network. To address these issues, we first present a hierarchical architecture by incorporating terrestrial-aerial computing capabilities and leveraging UAV flexibility. Furthermore, we formulate a joint computing resource allocation, computation offloading, and trajectory control problem to maximize the system utility. Since the problem is a non-convex and NP-hard mixed integer nonlinear programming (MINLP), we propose a two-timescale joint computing resource allocation, computation offloading, and trajectory control (TJCCT) approach for solving the problem. In the short timescale, we propose a price-incentive model for on-demand computing resource allocation and a matching mechanism-based method for computation offloading. In the long timescale, we propose a convex optimization-based method for UAV trajectory control. Besides, we theoretically prove the stability, optimality, and polynomial complexity of TJCCT. Extended simulation results demonstrate that the proposed TJCCT outperforms the comparative algorithms in terms of the system utility, average processing rate, average completion delay, and average completion ratio. Copyright © 2024, The Authors. All rights reserved.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection in Novel WSN-Leach Dos Attack Dataset using Machine Learning based Boosting Algorithms

引用

Procedia computer science 2023年 230卷 90-99页

作者： Dharini N Jeevaa Katiravan Sruthi Priya D M Sakthi Sneghaa V A Associate Professor Department of Computer Science Engineering(Cyber Security) R.M.K. College of Engineering and Technology Thiruvallur 601206 Professor Department of Information Technology Velammal Engineering College Surapet Chennai 600066 Software Engineer embedUR Chennai 600013 Jr. Customer Service Executive Tata Communications Transformation Services Chennai 600037

Security poses a substantial challenge in the context of wireless sensor networks (WSNs). WSNs, which are frequently employed for real-time monitoring in various Internet of Things (IoT)-based applications, are particularly vulnerable to a range of Denial of Service (DoS) attacks. These attacks represent a significant security concern and are among the most prevalent issues confronting WSNs *** our research, we have introduced a WSN DoS dataset using the Matrix Laboratory (MATLAB) tool. This dataset was developed through the utilization of the Leach Protocol and incorporates various types of DoS attacks, including Wormhole, Blackhole, Grayhole, Flooding, and Time Division Multiple Access (TDMA) attacks. In our study, we assessed the performance of several machine learning techniques using our dataset. We employed various performance evaluation metrics that gauge both the classification accuracy and the complexity of these machine learning models. These metrics included parameters such as the number of accurately classified and misclassified instances, along with the time required for constructing the model. This comprehensive evaluation aimed to demonstrate the effectiveness of our proposed *** results of our analysis revealed that the Light Gradient Boosting Machine (LightGBM), Extreme Gradient Boosting (XGBoost), and Bagging algorithms exhibited strong performance on our dataset. They achieved impressive accuracy levels of up to 99.16%, 99.16%, and 99.8%, respectively, when using 14 features. Additionally, these algorithms achieved accuracy rates of 99.16%, 98.75%, and 99.8%, respectively, with 5 features, and 95.41%, 95%, and 93.75%, respectively, when considering only 3 features such as node ID and Energy-Consumed, Attack_type. Notably, LightGBM outperformed the others in terms of speed, as it employs a leaf-wise growth strategy, consumes less memory, and requires less time for model construction. Consequently, LightGBM emerged as the most efficien

关键词： Denial of Service (DoS) attacks Intrusion Detection System (IDS) Leach Protocol WSN DoS dataset Ensemble Learning Feature Selection Accurately Classified and Misclassified instance Light Gradient Boosting Machine (LightGBM)

来源：评论

学校读者我要写书评

暂无评论

Explaining Model Overfitting in CNNS Via GMM Clustering

SSRN

引用

SSRN 2024年

作者： Dou, Hui Mu, Xinyu Yi, Mengjun Han, Feng Zhao, Jian Shen, Furao State Key Laboratory for Novel Software Technology China Department of Computer Science and Technology Nanjing University Nanjing210023 China School of Electronic Science and Engineering Nanjing University Nanjing210023 China School of Artificial Intelligence Nanjing University Nanjing210023 China

Convolutional Neural Networks (CNNs) have demonstrated remarkable prowess in the field of computer vision. However, their opaque decision-making processes pose significant challenges for practical applications. In this study, we provide quantitative metrics for assessing CNN filters by clustering the feature maps corresponding to individual filters in the model via Gaussian Mixture Model (GMM). By analyzing the clustering results, we screen out some anomaly filters associated with outlier samples. We further analyze the relationship between the anomaly filters and model overfitting, proposing three hypotheses. This method is universally applicable across diverse CNN architectures without modifications, as evidenced by its successful application to models like AlexNet and LeNet-5. We present three meticulously designed experiments demonstrating our hypotheses from the perspectives of model behavior, dataset characteristics, and filter impacts. Through this work, we offer a novel perspective for evaluating the CNN performance and gain new insights into the operational behavior of model overfitting. © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Explaining Model Overfitting in CNNs via GMM Clustering

arXiv

引用

arXiv 2024年

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

NIV-Detector: An Automated Approach for Detecting Next- Intent Security Vulnerability in Android Applications

NIV-Detector: An Automated Approach for Detecting Next- Inte...

引用

International Conference on software Defined Systems (SDS)

作者： Zakarea Alshara Anas Shatnawi Yaser Jararweh Software Engineering Department Jordan University of Science and Technology Irbid Jordan DRIT Berger-Levrault Montpellier France Computer Science Department Jordan University of Science and Technology Irbid Jordan

In Android inter-process communication, any component can start another public component using an Intent messaging object nevertheless the components belong to different processes or applications. Besides, the private components should be protected and only be accessible by the same process. However, the malicious application can breach access and directly starts private components from another process, causing Next-Intent Vulnerability (NIV). The leading cause of NIV comes from lunching unsafe Nested Intent sent by the malicious application. In this paper, we propose a new approach and implement its tool to automatically inspect NIV code smells. We integrate our tool, named NIV-Detector, with Android Studio as a plugin to be available during development time. We use NIV-Detector to inspect 100 Android GitHub projects. As a result, we successfully confirmed ten vulnerable projects with 14 NIV smells.

关键词： Codes software Security software development management

来源：评论

学校读者我要写书评

暂无评论

The Rise of Cloud Computing: Data Protection, Privacy, and Open Research Challenges - A Systematic Literature Review (SLR)

引用

Computational Intelligence and Neuroscience 2022年 2022卷 8303504页

作者： Hassan, Junaid Shehzad, Danish Habib, Usman Aftab, Muhammad Umar Ahmad, Muhammad Kuleev, Ramil Mazzara, Manuel Department of Computer Science National University of Computer and Emerging Sciences Islamabad Chiniot-Faisalabad Campus Chiniot35400 Pakistan Department of Computer Science Superior University Lahore54000 Pakistan Faculty of Computer Sciences and Engineering GIK Institute of Engineering Sciences and Technology Topi Swabi Khyber Pakhtunkhwa23640 Pakistan Institute of Software Development and Engineering Innopolis University Innopolis420500 Russia

Cloud computing is a long-standing dream of computing as a utility, where users can store their data remotely in the cloud to enjoy on-demand services and high-quality applications from a shared pool of configurable computing resources. Thus, the privacy and security of data are of utmost importance to all of its users regardless of the nature of the data being stored. In cloud computing environments, it is especially critical because data is stored in various locations, even around the world, and users do not have any physical access to their sensitive data. Therefore, we need certain data protection techniques to protect the sensitive data that is outsourced over the cloud. In this paper, we conduct a systematic literature review (SLR) to illustrate all the data protection techniques that protect sensitive data outsourced over cloud storage. Therefore, the main objective of this research is to synthesize, classify, and identify important studies in the field of study. Accordingly, an evidence-based approach is used in this study. Preliminary results are based on answers to four research questions. Out of 493 research articles, 52 studies were selected. 52 papers use different data protection techniques, which can be divided into two main categories, namely noncryptographic techniques and cryptographic techniques. Noncryptographic techniques consist of data splitting, data anonymization, and steganographic techniques, whereas cryptographic techniques consist of encryption, searchable encryption, homomorphic encryption, and signcryption. In this work, we compare all of these techniques in terms of data protection accuracy, overhead, and operations on masked data. Finally, we discuss the future research challenges facing the implementation of these techniques. © 2022 Junaid Hassan et al.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Multi-Hierarchy Metamorphic Testing for Hyphenated Words in Machine Translation 31

Multi-Hierarchy Metamorphic Testing for Hyphenated Words in ...

引用

31st Asia-Pacific software engineering Conference, APSEC 2024

作者： Zhu, Rui Tao, Chuanqi Gao, Jerry College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Nanjing University of Aeronautics and Astronautics Ministry Key Laboratory for Safety-Critical Software Development and Verification Nanjing China Nanjing University State Key Laboratory for Novel Software Technology Nanjing China San Jose State University Computer Engineering Department San Jose United States

ISBN: (纸本)9798331534011

With the advancement of deep neural networks, machine translation has seen rapid progress in recent years. Individuals often rely on machine translation software to facil-itate various tasks. However, the intricacies of neural networks can lead to translation errors, resulting in misunderstandings or conflicts. The most common method for testing machine translation is metamorphic testing. However, metamorphic testing at the phrase or sentence hierarchy may result in some test cases being incorrectly identified as failures. To mitigate this issue, we added the word hierarchy. We proposed a multi-hierarchy metamorphic testing method, MHT, to test machine translation. Hyphenated words as a specific format prone to translation errors, which are chosen as our research object. Based on the common notion that translations of words within the same sentence should be similar, we extract contents from different hierarchies within sentences containing hyphenated words and compare the similarity of their corresponding translations for these specific words. We conducted the experiments on 881 sentences leveraging Google Translate, Microsoft Bing Translator, and Baidu Translate, which detected 111, 91, and 111 suspicious errors with high precision (78.4 %, 82.4 %, and 81.1 %). Translation errors mainly include mis-translation, under-translation, over-translation, and non-translation. © 2024 IEEE.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Addressing Multi-Core Timing Interference using Co-Runner Locking 42

Addressing Multi-Core Timing Interference using Co-Runner Lo...

引用

42nd IEEE Real-Time Systems Symposium, RTSS 2021

作者： Kim, Hyoseung de Niz, Dionisio Andersson, Bjorn Klein, Mark Lehoczky, John Electrical and Computer Engineering University of California Riverside United States Software Engineering Institute Carnegie Mellon University United States Department of Statistics and Data Science Carnegie Mellon University United States

ISBN: (纸本)9781665428026

This paper presents a task synchronization mechanism, called co-runner locking, to address the timing interference problem in multi-core real-time systems. It prevents certain subsets of tasks from executing simultaneously on different cores in order to avoid large performance penalties from inter-core interference. We provide the general properties of the co-runner locking mechanism and discuss the runtime control policies that determine the execution order of tasks in a co-runnerlocking relationship. For schedulability analysis, we derive a response-time test that upper-bounds the delay from co-runner locking and the slowdown imposed by permitted co-runners by combining two new analytic approaches: job-oriented and load-oriented. In evaluation, we demonstrate that the co-runner locking mechanism is an effective alternative to address the "one-out-of-m" problem and brings about a significant improvement in real-time taskset schedulability. © 2021 IEEE

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Learning Using Noisy-Latent Augmentation

Self-Supervised Learning Using Noisy-Latent Augmentation

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Rasa Khosrowshahli Shahryar Rahnamayan Azam Asilian Bidgoli Masoud Makrehchi Department of Electrical Computer and Software Engineering Nature-Inspired Computational Intelligence (NICI) Lab Ontario Tech University Oshawa ON Canada Engineering Department Nature-Inspired Computational Intelligence (NICI) Lab Brock University St. Catharines ON Canada Nature-Inspired Computational Intelligence (NICI) Lab Faculty of Science Wilfrid Laurier University Waterloo ON Canada Department of Electrical Computer and Software Engineering Ontario Tech University Oshawa ON Canada

Generally speaking, labeled data is difficult and expensive to provide for applications in machine learning and data mining. One of the earliest approaches to tackle this problem is semi-supervised self-training to take advantages of labeled and unlabeled data to create pseudo-labeled data. However, reaching a high level of confidence to predict the unseen data by a classifier with a limited number of labeled samples is a challenging task. Generating pseudo-labeled data can collaboratively improve the self-training to increase its confidence for further predictions. This paper proposes a collaborative framework between augmentation and self-training to accurately train a model with very limited labeled data. Our framework includes two components where the first component is an unsupervised technique to augment labeled data and feed to the second component which is self-training. The first component uses a custom variational autoencoder architecture (VAE) to generate new samples by adding randomly generated noise to encoded latent representation. As a result, the augmentation component can generate the unique and unexplored images with respect to limited input data distribution. We evaluated the proposed framework on handwritten MNIST image dataset. The conducted experiment shows that the generative component can be helpful in overcoming the problem of inaccurate self-training prediction when sufficient labeled data is not accessible.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HoloLens 2 Technical Evaluation as Mixed Reality Guide

arXiv

引用

arXiv 2022年

作者： Guo, Hung-Jui Prabhakaran, Balakrishnan Software Engineering Department The Univerity of Texas DallasTX United States Computer Science Department The Univerity of Texas DallasTX United States

Mixed Reality (MR) is an evolving technology lying in the continuum spanned by related technologies such as Virtual Reality (VR) and Augmented Reality (AR), and creates an exciting way of interacting with people and the environment. This technology is fast becoming a tool used by many people, potentially improving living environments and work efficiency. Microsoft HoloLens [1] has played an important role in the progress of MR, from the first generation to the second generation. In this paper, we systematically evaluate the functions of applicable functions in HoloLens 2 [2]. These evaluations can serve as a performance benchmark that can help people who need to use this instrument for research or applications in the future. The detailed tests and the performance evaluation of the different functionalities show the usability and possible limitations of each function. We mainly divide the experiment into the existing functions of the HoloLens 1, the new functions of the HoloLens 2, and the use of research mode. This research results will be useful for MR researchers who want to use HoloLens 2 as a research tool to design their own MR applications. © 2022, CC BY.

关键词： Mixed reality

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：