检索结果-内蒙古大学图书馆

A review of travel behavioural pattern using GPS dataset: A systematic literature review

Measurement: Sensors 2024年 32卷

作者： Sivalingam, Prahaladhan Asirvatham, David Marjani, Mohsen Syed Masood, Jafar Ali Ibrahim Chakravarthy, N.S. Kalyan Veerisetty, Gopinath Lestari, Martha Tri Faculty of Innovation & Technology Taylor's University Subang Jaya Malaysia Department of Internet of Things School of Computer Science and Engineering Vellore Institute of Technology Tamilnadu Vellore632 014 India Center for Data Science School of Computer Science and Engineering QIS College of Engineering and Technology Andhra Pradesh Ongole523272 India Department of Mechanical Engineering QIS College of Engineering and Technology Andhra Pradesh Ongole523272 India Department of Business Communication Telkom University Indonesia

In the last few years, the Global positioning system (GPS) has been used to study travel patterns with the advancement of data collection techniques. A GPS device precisely records the time and the location data of an individual travel. The accuracy of travel studies is usually improved by integrating travel surveys or travel activity diaries with GPS data. GPS surveys are implemented to replace paper-based techniques and reduce human error on trip-misreporting issues. Several reviews have been performed previously on GPS travel studies. Still, a detailed systematic review on the comparison of different modes and methods on the entire procedure of GPS data processing has not been thoroughly studied. This review identified 116 peer-reviewed studies and journal papers from 2013 to 2020, and 53 papers were studied. The review focused on travel behavior pattern (TBP) analysis using GPS studies only and a combination of travel surveys. Our review reveals that 53 only 40 have quality assessment scores of >50 %, meaning the remaining TBP studies are conventional methods. The study also benefits data analysis and researchers to select the most appropriate data collection techniques for studying TBP and improvise them further for meta-analysis travel behavior studies. © 2024 The Authors

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

Energy efficient VM scheduling in Reservation supported Cloud data Centers under availability constraints

Energy efficient VM scheduling in Reservation supported Clou...

引用

2021 International Conference on Intelligent Technologies, CONIT 2021

作者： Charan, Bhavya Goutham, K S Mampilli, Ruben John Kempaiah, Bharani Ujjaini Phalachandra, H L PES University Center for Cloud Computing and Big Data Dept of Computer Science and Engineering Bangalore India

ISBN: (纸本)9781728185835

The exponential surge in digital usage is resulting in a significant need for computational resources. This has led to businesses migrating to the cloud for benefits like usage of resources as a service, scalability, etc. Infrastructures supporting these businesses will need to conserve energy in the context of the ever-increasing size of the data centers and provide a highly available environment with mechanisms for business continuity, disaster recovery, etc. These would need to be supported at minimal costs while meeting the expected performance along with conformance to the SLAs. This paper considers a cost-efficient resource reservation based environment and evolves an approach to perform energy-efficient VM scheduling with migrations, while factoring in the network Overheads, having Availability as a constraint, and orchestrating the devices in terms of Dynamic Voltage Frequency Scaling, for optimal energy usage. Two novel algorithms are proposed: the Power and Availability Aware Best Fit Decreasing (PAABFD) allocation policy and the Power Availability Network DVFS Aware (PANDA) migration policy, when combined achieving up to 82.35% improvement in data center energy while offering an availability of 99.999% when compared with other scheduling policies. © 2021 IEEE.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Toward Cost-effective Adaptive Random Testing: An Approximate Nearest Neighbor Approach

arXiv

引用

arXiv 2023年

作者： Huang, Rubing Cui, Chenhui Lian, Junlong Towey, Dave Sun, Weifeng Chen, Haibo The School of Computer Science and Engineering Macau University of Science and Technology Taipa999078 China The School of Computer Science and Communication Engineering Jiangsu University Jiangsu Zhenjiang212013 China The School of Computer Science University of Nottingham Ningbo China Zhejiang Ningbo315100 China The School of Big Data and Software Engineering Chongqing University Chongqing401331 China

Adaptive Random Testing (ART) enhances the testing effectiveness (including fault-detection capability) of Random Testing (RT) by increasing the diversity of the random test cases throughout the input domain. Many ART algorithms have been investigated such as Fixed-Size-Candidate-Set ART (FSCS) and Restricted Random Testing (RRT), and have been widely used in many practical applications. Despite its popularity, ART suffers from the problem of high computational costs during test-case generation, especially as the number of test cases increases. Although several strategies have been proposed to enhance the ART testing efficiency, such as the forgetting strategy and the k-dimensional tree strategy, these algorithms still face some challenges, including: (1) Although these algorithms can reduce the computation time, their execution costs are still very high, especially when the number of test cases is large;and (2) To achieve low computational costs, they may sacrifice some fault-detection capability. In this paper, we propose an approach based on Approximate Nearest Neighbors (ANNs), called Locality-Sensitive Hashing ART (LSH-ART). When calculating distances among different test inputs, LSH-ART identifies the approximate (not necessarily exact) nearest neighbors for candidates in an efficient way. LSH-ART attempts to balance ART testing effectiveness and efficiency. © 2023, CC BY.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Advanced Malware Classification Using Convolutional Neural Networks and Image Transformation Techniques

Advanced Malware Classification Using Convolutional Neural N...

引用

Advancements and Key Challenges in Green Energy and Computing (AKGEC), International Conference on

作者： Shweta Bhattacharjee Porna Md Zakir Hossain Abdullah Al Naseeh Chowdhury M Govind Raj Roise Uddin Mukit Al Elahi Abdul Basit Mohammad Aman Ullah Khan Girigula Durga Bhavani Department of Computer Science and Engineering Ahsanullah University of Science and Technology Dhaka Bangladesh Department of Data Science Grand Canyon University USA Computer Science and Engineering Sylhet Engineering College Sylhet Bangladesh Department of ECE Malla Reddy Engineering College Maisammaguda Telangana India Computer and Information Systems Security Cyber California State University San Bernardino USA Department of CSE Pacific states university Los Angeles California USA Department of CSE Pacific states university 4651 Rosewood St USA Department of CSE School of Data and Sciences BRAC University Dhaka Bangladesh School of Computer Science and Engineering VIT-AP University Amaravati Andhra Pradesh India

ISBN: (数字)9798350390179

ISBN: (纸本)9798350390186

Malware seriously compromises cybersecurity and calls for sophisticated and effective categorization methods to find and lessen its effects. This research article offers a complete method based on image processing and deep learning to classify malware. ResNet18, VGG16, VGG19, AlexNet, and our custom-designed MalwareNet are among the several deep learning models we use to categorize malware photos from the nine different classes in the Big 2015 dataset-which shows a clear class imbalance. Using hyperband and bayesian optimization approaches, our strategy maximizes hyperparameters to provide the greatest performance. The hyperparameters for ResNet18, VGG16, VGG19, and AlexNet models comprise learning rate, kernel size, number of epochs, dropout rate, and dense layer size as well as particular parameters for MalwareNet including the number of neurons in each layer and the fully connected layer size. With MalwareNet obtaining especially remarkable results, the examination of our models shows great accuracy, precision, recall, and F1 scores. We examine the training accuracy, F1 score, and log loss measures in great detail; we then show the classification performance over all classes using confusion matrices. With notable increases in malware detection and categorization, the suggested model offers a strong and practical answer for uses in cybersecurity. Supported by diligent hyperparameter adjustment and performance evaluation, this work expands the field by providing a comprehensive comparison of many deep learning architectures and how effectively they classify malware. The results show how well deep learning models might improve malware detection systems and protect digital environments against hostile attacks.

关键词： Deep learning Training Performance evaluation Accuracy Neurons Malware Loss measurement computer security Kernel Optimization

来源：评论

学校读者我要写书评

暂无评论

SwimVG: Step-wise Multimodal Fusion and Adaption for Visual Grounding

arXiv

引用

arXiv 2025年

作者： Shi, Liangtao Liu, Ting Hu, Xiantao Hu, Yue Yin, Quanjun Hong, Richang Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Hefei230009 China Ministry of Education and School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China School of systems engineering National University of Defense Technology Hunan Province Changsha410073 China Department of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210014 China

Visual grounding aims to ground an image region through natural language, which heavily relies on cross-modal alignment. Most existing methods transfer visual/linguistic knowledge separately by fully fine-tuning uni-modal pre-trained models, followed by a simple stack of visual-language transformers for multimodal fusion. However, these approaches not only limit adequate interaction between visual and linguistic contexts, but also incur significant computational costs. Therefore, to address these issues, we explore a step-wise multimodal fusion and adaption framework, namely SwimVG. Specifically, SwimVG proposes step-wise multimodal prompts (Swip) and cross-modal interactive adapters (CIA) for visual grounding, replacing the cumbersome transformer stacks for multimodal fusion. Swip can improve the alignment between the vision and language representations step by step, in a token-level fusion manner. In addition, weight-level CIA further promotes multimodal fusion by cross-modal interaction. Swip and CIA are both parameter-efficient paradigms, and they fuse the cross-modal features from shallow to deep layers gradually. Experimental results on four widely-used benchmarks demonstrate that SwimVG achieves remarkable abilities and considerable benefits in terms of efficiency. Our code is available at https://***/liuting20/SwimVG. Copyright © 2025, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Joint UAV Deployment, Power Allocation, and Coalition Formation for Physical Layer Security in Heterogeneous Networks

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Zhang, Yalin Gao, Xiaozheng Ye, Neng Niyato, Dusit Han, Zhu Yang, Kai Beijing Institute of Technology School of Information and Electronics Beijing100081 China Beijing Institute of Technology School of Cyberspace Science and Technology Beijing100081 China Nanyang Technological University College of Computing and Data Science 639798 Singapore University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

In the coming sixth-generation era, unmanned aerial vehicles (UAVs) have been explored for convenient air access and strong environmental adaptability to provide communication services for ground Internet-of-Things (IoT) devices. However, the inherent broadcast nature of wireless communications makes UAV communications vulnerable to eavesdropping attacks. This paper explores a secure uplink communication in a heterogeneous network, where a UAV provides communication services to ground IoT nodes in the presence of an eavesdropper. We propose a transmission scheme to maximize the overall sum secrecy rate, in which the cooperative jamming technique and coalition formation game are employed, and the UAV endurance is considered. Specifically, a double-layer optimization problem is formulated, including a non-convex optimization problem in the lower layer, and a game theory problem in the upper layer. We use block coordinate descent and successive convex approximation methods to decompose the lower layer problem into UAV deployment and power allocation sub-problems, and convert them into a difference of two convex functions programming problem and a second-order cone programming problem, respectively. Moreover, we develop an algorithm to solve the upper layer problem, obtaining a stable coalition formation. Simulation results show that the proposed transmission scheme can effectively improve the overall sum secrecy rate, and has dynamic adaptability to eavesdropping attacks. © 1967-2012 IEEE.

关键词： Jamming

来源：评论

学校读者我要写书评

暂无评论

Robust UAV Policy Learning for Urban Infrastructure Surface Screening*

Robust UAV Policy Learning for Urban Infrastructure Surface ...

引用

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Bingqing Du Uddin Md. Borhan Tianxing Chen Jianyong Chen Jianqiang Li Jie Chen College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

Unmanned Aerial Vehicles (UAVs) have emerged as pivotal tools for infrastructure inspection, mitigating risks to human life and enhancing operational efficiency. Despite advancements, achieving autonomous surface coverage inspection in GPS-denied environments remains a significant challenge. This paper presents a novel approach to enhance UAV policy learning for surface screening of urban infrastructure in environments lacking GPS. Utilizing Deep Reinforcement Learning (DRL), the methodology enables UAVs to autonomously conduct surface coverage inspections more robustly and efficiently. A key innovation is the Optimal Speed Decision (OSD) model, which allows UAVs to adjust flight speed dynamically based on scene perception, enhancing efficiency and safety. Additionally, an Off-Policy Critic-Based Reward Shaping (OPCBRS) method is introduced to improve learning efficiency and performance by addressing the issue of sparse rewards using offline data. Simulation results confirm the effectiveness of these methods, with the OSD model demonstrating significant improvements in navigating complex scenarios and maintaining a balance between efficiency and robustness over traditional uniform speed policies. This research offers a robust framework for UAV-based infrastructure inspection in GPS-denied environments, advancing autonomous UAV applications.

关键词： Technological innovation Navigation Simulation Inspection Autonomous aerial vehicles Deep reinforcement learning Robustness Real-time systems Safety Robots

来源：评论

学校读者我要写书评

暂无评论

A Dual-Level Cancelable Framework for Palmprint Verification and Hack-Proof data Storage

arXiv

引用

arXiv 2024年

作者： Yang, Ziyuan Kang, Ming Teoh, Andrew Beng Jin Gao, Chengrui Chen, Wen Zhang, Bob Zhang, Yi The College of Computer Science Key Laboratory of Data Protection and Intelligent Management Ministry of Education Sichuan University Chengdu610065 China The School of Cyber Science and Engineering Sichuan University Chengdu610065 China The School of Electrical and Electronic Engineering College of Engineering Yonsei University Seoul Korea Republic of The College of Computer Science Sichuan University Chengdu610065 China The Pattern Analysis and Machine Intelligence Group Department of Computer and Information Science University of Macau Taipa China The School of Cyber Science and Engineering Key Laboratory of Data Protection and Intelligent Management Ministry of Education Sichuan University Chengdu610065 China

In recent years, palmprints have been widely used for individual verification. The rich privacy information in palmprint data necessitates its protection to ensure security and privacy without sacrificing system performance. Existing systems often use cancelable technologies to protect templates, but these technologies ignore the potential risk of data leakage. Upon breaching the system and gaining access to the stored database, a hacker could easily manipulate the stored templates, compromising the security of the verification system. To address this issue, we propose a dual-level cancelable palmprint verification framework in this paper. Specifically, the raw template is initially encrypted using a competition hashing network with a first-level token, facilitating the end-to-end generation of cancelable templates. Different from previous works, the protected template undergoes further encryption to differentiate the second-level protected template from the first-level one. The system specifically creates a negative database (NDB) with the second-level token for dual-level protection during the enrollment stage. Reversing the NDB is NP-hard and a fine-grained algorithm for NDB generation is introduced to manage the noise and specified bits. During the verification stage, we propose an NDB matching algorithm based on matrix operation to accelerate the matching process of previous NDB methods caused by dictionary-based matching rules. This approach circumvents the need to store templates identical to those utilized for verification, reducing the risk of potential data leakage. Extensive experiments conducted on public palmprint datasets have confirmed the effectiveness and generality of the proposed framework. Upon acceptance of the paper, the code will be accessible at https://***/Deep-Imaging-Group/NPR. Copyright © 2024, The Authors. All rights reserved.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Classification and Discovery of Brain Tumor Using Ensemble Deep Learning

Classification and Discovery of Brain Tumor Using Ensemble D...

引用

Network, Multimedia and Information Technology (NMITCON) International Conference on

作者： Kasanagottu Srilatha Chekka Sravani Mikkilineni Vasudevarao Ajmeera Kiran D Chitra Pundru Chandra Shaker Reddy Department of Data Science Geethanjali College of Engineering and Technology Hyderabad India Computer Science and Engineering Marri Laxman Reddy Institute of Technology and Management Hyderabad Telangana India Department Of Computer Applications Dayananda Sagar Business Academy Karnataka India Computer Science and Engineering MLR Institute of Technology Dundigal Hyderabad Telangana India Master of Business Administration Panimalar Engineering College Chennai Tamil Nadu India School of Computer Science and Artificial Intelligence SR University Warangal Telangana India

ISBN: (数字)9798350372892

ISBN: (纸本)9798350372908

As healthcare IT develops at a dizzying rate, the age of big data is drawing near. Tumor disease prediction, monitoring, diagnosis, and treatment are all profoundly affected by data mining and analysis. Brain-tumors(BT) are considered the most terrible and deadly disease due to their aggressive nature, short survival rate, and diverse spectrum of symptoms. Inadequate medical therapy for patients with misdiagnosed brain tumors lowers their survival prospects. The ability to differentiate amid abnormal &normal tissues makes BT detection extremely difficult. An accurate diagnosis allows the patient to undergo effective therapy and has a better chance of long-term survival. Because of the abnormal pattern of lesion distribution, there are still convinced difficulties in diagnosing BTs, even though there has been a lot of research on the subject. Because tiny areas may seem healthy, it might be challenging to locate a zone with few lesions. Classification accuracy is negatively impacted, and selecting and extracting useful characteristics becomes more difficult. An important part is the automated categorization of precancerous BTs utilizing deep &machine learning strategies. This study presents a Convolutional-Neural-Network-Long-Short-Term-Memory (CNN-LSTM) model, a hybrid DL-technique, for the purpose of MRI-based brain tumor classification and prediction. An MRI brain imaging collection is utilized for our experiments. An effective preprocessing of the data is the first step in using a CNN to extract major characteristics from images. With a 99.3% significant classification accuracy, 99.2% precision, 99.1% recall, and 99.1% F1-measure, the suggested model successfully predicts the brain tumor.

关键词： Accuracy Computational modeling Medical treatment Predictive models Brain modeling Feature extraction Convolutional neural networks Lesions data mining Diseases

来源：评论

学校读者我要写书评

暂无评论

STIOS: A Novel Self-supervised Diffusion Model for Trajectory Imputation in Open Environment Scenarios

STIOS: A Novel Self-supervised Diffusion Model for Trajector...

引用

IEEE/ACM Int'l Conference on & Int'l Conference on Cyber, Physical and Social Computing (CPSCom) Green Computing and Communications (GreenCom)

作者： Zhijing Hu Hao Yan Yuhao Zheng Hua He Chao Chen Changjun Fan Kuihua Huang Laboratory for Big Data Data and Decision National University of Defense Technology Changsha China School of Computer Science and Engineering Central South University Changsha China Laboratory for Big Data Data and Decision National University of Defense Technology China

ISBN: (数字)9798350351637

ISBN: (纸本)9798350351644

With the growth of location-based services, the accumulation of large amounts of trajectory data comes with the challenge of missing data. Existing trajectory imputation methods rely on deterministic models that cannot take into account open environments scenarios without auxiliary information. This may lead to poor performance in learning the long-term dependencies of trajectories. In this paper, we propose a novel Self-supervised diffusion model for Trajectory Imputation in Open environment Scenarios (STIOS), which combines a deterministic model and a conditional diffusion model. In addition, we propose a self-supervised training method inspired by masked language modelling that divides the data into conditional information and estimation targets. Extensive experiments on two real datasets demonstrate the superiority of STIOS for trajectory imputation.

关键词： Training Social computing Uncertainty Computational modeling Roads Estimation Diffusion models Imputation data models Trajectory

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：