检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Communications, computing, Cybersecurity and Informatics, CCCI 2023

作者： Abdussami, Mohammad Dwivedi, Sanjeev Kumar Obaidat, Mohammad S. Amin, Ruhul Vollala, Satyanarayana Sadoun, Balqies Department of Cse Chhattisgarh 493661 India VIT-AP University Inavolu Andhra Pradesh Amaravati522237 India School of Computer and Communication Engineering University of Science and Technology Beijing Beijing100083 China School of Computing Srm University Department of Computational Intelligence TN Kattankulathur603203 India School of Engineering The Amity University UP Noida201301 India College of Engineering Al-Balqa' Applied University Al-Salt19117 Jordan

ISBN: (纸本)9798350302561

The Internet of Vehicles (IoV) is a fast developing field that seeks to use cutting-edge technologies to enhance the sustainability, efficiency, and safety of transportation networks. The IoV can gain greatly from integrating blockchain in terms of security, trust, decentralization, smart contracts, and data management. This paper presents the weakness of a blockchain based lightweight authentication and key agreement scheme for internet of vehicles(BLAIV) proposed by Zheng et al. [1]. By performing thorough security analysis we have observed that the BLAIV scheme is vulnerable to various security attacks. The main cause for the security attacks is the BLAIV scheme stores the security parameters in the Onboard unit(OBU) of vehicle, due to which the BLAIV scheme is vulnerable to various attacks like vehicle or OBU capture attacks, session key computation attacks, and impersonation attacks. The paper also suggests possible changes to improve the BLAIV scheme. © 2023 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Networks based Meta-Learning for Network Intrusion Detection

arXiv

引用

arXiv 2023年

作者： Sohail, Anabia Ayisha, Bibi Hammed, Irfan Zafar, Muhammad Mohsin Alquhayz, Hani Khan, Asifullah Pattern Recognition Lab Department of Computer & Information Sciences Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan Department of Computer Science Faculty of Computing and Artificial Intelligence Air University E-9 Islamabad Pakistan Faculty of Computer Science and Engineering Ghulam Ishaq Khan Institute of Engineering Sciences and Technology Topi District Swabi Khyber Pakhtunkhwa23640 Pakistan Department of Computer Science and Information College of Science in Zulfi Majmaah University Al-Majmaah11952 Saudi Arabia Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan

The digitization of different components of industry and inter-connectivity among indigenous networks have increased the risk of network attacks. Designing an intrusion detection system to ensure security of the industrial ecosystem is difficult as network traffic encompasses various attack types, including new and evolving ones with minor changes. The data used to construct a predictive model for computer networks has a skewed class distribution and limited representation of attack types, which differ from real network traffic. These limitations result in dataset shift, negatively impacting the machine learning models' predictive abilities and reducing the detection rate against novel attacks. To address the challenges, we propose a novel deep neural network based Meta-Learning framework;INformation FUsion and Stacking Ensemble (INFUSE) for network intrusion detection. First, a hybrid feature space is created by integrating decision and feature spaces. Five different classifiers are utilized to generate a pool of decision spaces. The feature space is then enriched through a deep sparse autoencoder that learns the semantic relationships between attacks. Finally, the deep Meta-Learner acts as an ensemble combiner to analyze the hybrid feature space and make a final decision. Our evaluation on stringent benchmark datasets and comparison to existing techniques showed the effectiveness of INFUSE with an F-Score of 0.91, Accuracy of 91.6%, and Recall of 0.94 on the Test+ dataset, and an F-Score of 0.91, Accuracy of 85.6%, and Recall of 0.87 on the stringent Test-21 dataset. These promising results indicate the strong generalization capability and the potential to detect network attacks. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Investigating the computation of smoothed deceptive routes in topographic terrains for agent-based simulation systems

Investigating the computation of smoothed deceptive routes i...

引用

Computational Intelligence in Security, Defence and Biometrics (CISDB), IEEE Symposium on

作者： Luigi P. Souza Thiago R. S. Leão Crhistopher Lenhard Edison P. Freitas Luis A. L. Silva Graduate Program in Computer Science Federal Univ. of Santa Maria Santa Maria Brazil Undergraduate Course in Computer Science Federal Univ. of Santa Maria Santa Maria Brazil Institute of Informatics Federal Univ. of Rio Grande do Sul Porto Alegre Brazil Applied Computing Department Federal Univ. of Santa Maria Santa Maria Brazil

ISBN: (数字)9798331508296

ISBN: (纸本)9798331508302

The capacity to deceptively move in hilly terrains is fundamental to agents in simulation systems for tactical and strategic military training. Such an ability to deceive the adversary can ensure a relevant advantage by hiding the real goals of a mission. Using pairs of real and deceptive mission goals, this paper investigates the planning of realistic deceptive routes for simulated agents. With real-world terrain elevation maps, it shows how to explore pathfinding algorithms with relevant path-smoothing characteristics (Theta* and WJPS*, contrasting with the standard $A^{*}$ algorithm) in terrains with pronounced relief features. The study analyzes the effects of terrain elevation costs and the representation of relief contour lines on the determination of more realistic deceptive paths. This work also investigates how users can adjust a Last Topographic Deceptive Point ($L D P_{T}$) calculation to enhance the pathfinding algorithm’s ability to produce more deceptively dense and topographically aware routes. Experimental results for different deceptive topographic path planning strategies are evaluated according to statistical models showing that Theta*, despite being slower than the base $A^{*}$ method in most cases, generated smoothed paths while maintaining a similar deception density for the proposed strategies. On the other hand, WJPS outperformed both in execution time for certain strategies while maintaining the smoothed path characteristic and resulting in a path with lower deceptive capacity.

关键词： Training Hands Biometrics Costs Path planning Planning Security Standards Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

Alzheimer’s Disease Diagnosis and Categorization using Deep Learning

Alzheimer’s Disease Diagnosis and Categorization using Deep...

引用

Cognitive Robotics and Intelligent Systems (ICC - ROBINS), International Conference on

作者： M. Sangeetha Hemalatha Gunasekaran Azalini T Nakshathra J Uma Mageshwari P Manjula Devi. R Department of Information Technology Dr.N.G.P.Institute of Technology Coimbatore Tamilnadu India College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Sultanate of Oman Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore Tamilnadu India

ISBN: (数字)9798350372748

ISBN: (纸本)9798350372755

Alzheimer's disease (AD) is a significant global health concern, accounting for the sixth highest cause of mortality worldwide. Early diagnosis is critical to improving patient care and treatment outcomes. This study aims to classify Alzheimer's disease (AD) using Magnetic Resonance Imaging (MRI) brain images, allowing for prompt intervention and optimal disease treatment. The dataset consists of 6400 MRI pictures classified into four categories: very mildly demented, mildly demented, moderately demented, and non-demented, with an 80-10-10 split for training, validation, and testing. Initially, the utilization of VGG16 architecture results with an accuracy of 87%. To improve accuracy and reduce training time, the GoogleNet (Inception V3) Convolutional Neural Network (CNN) architecture was used. This method resulted with an accuracy of 97.62%.

关键词： Training Deep learning Magnetic resonance imaging Planning Convolutional neural networks Medical diagnosis Alzheimer's disease

来源：评论

学校读者我要写书评

暂无评论

RALB-HC: A resource-aware load balancer for heterogeneous cluster

RALB-HC: A resource-aware load balancer for heterogeneous cl...

引用

作者： Ahmed, Usman Aleem, Muhammad Noman Khalid, Yasir Arshad Islam, Muhammad Azhar Iqbal, Muhammad Department of Computing Mathematics and Physics Faculty of Engineering and Science Western Norway University of Applied Sciences Bergen Norway Islamabad Pakistan Department of Computer Science Capital University of Science and Technology Islamabad Pakistan SWJTU-Leeds Joint School Southwest Jiaotong University Chengdu China

In the heterogeneous computing environment, programmers map the applications either on CPUs or GPUs. However, this default mapping process does not produce improved results, particularly on the heterogeneous clusters. If one resource of the cluster is more compute capable, then most of the scheduling schemes favor that powerful device. In this scenario, the scheduling schemes overload the powerful resources while making all other compute resources remain under utilized. This load imbalance problem results in higher energy consumption and increased execution time. In this research, a novel Resource-Aware Load Balancer for the Heterogeneous Cluster (RALB-HC) is proposed that distributes workload based on resources computing capabilities and applications computing needs. The RALB-HC uses supervised machine learning approach to classify applications using the static code-features. The RALB-HC framework comprises of two phases: (1) job mapping based on the availability of the resources and (2) the resource-aware load balancing to achieve the higher resource utilization ratio. The experimental results on a large set of real-world and synthetic workloads show that the RALB-HC reduces execution time by 31.61%, increased resource utilization ratio by 67.8% and improved throughout 147.35% as compared to baseline scheduling schemes. © 2019 John Wiley & Sons, Ltd.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Convolutional Bi-LSTM Based Human Gait Recognition Using Video Sequences

引用

computers, Materials & Continua 2021年第8期68卷 2693-2709页

作者： Javaria Amin Muhammad Almas Anjum Muhammad Sharif Seifedine Kadry Yunyoung Nam ShuiHua Wang University of Wah Wah Cantt47040Pakistan National University of Technology(NUTECH) Islamabad44000Pakistan COMSATS University Islamabad Wah CampusWah CanttPakistan Faculty of Applied Computing and Technology Noroff University CollegeKristiansandNorway Department of Computer Science and Engineering Soonchunhyang UniversityAsan31538Korea Department of Mathematics University of LeicesterLeicesterUK

Recognition of human gait is a difficult assignment,particularly for unobtrusive surveillance in a video and human identification from a large ***,a method is proposed for the classification and recognition of different types of human *** proposed approach is consisting of two *** phase I,the new model is proposed named convolutional bidirectional long short-term memory(Conv-BiLSTM)to classify the video frames of human *** this model,features are derived through convolutional neural network(CNN)named ResNet-18 and supplied as an input to the LSTM model that provided more distinguishable temporal *** phase II,the YOLOv2-squeezeNet model is designed,where deep features are extricated using the fireconcat-02 layer and fed/passed to the tinyYOLOv2 model for recognized/localized the human gaits with predicted *** proposed method achieved up to 90%correct prediction scores on CASIA-A,CASIA-B,and the CASIA-C benchmark *** proposed method achieved better/improved prediction scores as compared to the recent existing works.

关键词： Bi-LSTM YOLOv2 open neural network resNet-18 gait squeezeNet

来源：评论

学校读者我要写书评

暂无评论

Boosting Earth System Model Outputs And Saving PetaBytes in their Storage Using Exascale Climate Emulators

arXiv

引用

arXiv 2024年

作者： Abdulah, Sameh Baker, Allison H. Bosilca, George Cao, Qinglei Castruccio, Stefano Genton, Marc G. Keyes, David E. Khalid, Zubair Ltaief, Hatem Song, Yan Stenchikov, Georgiy L. Sun, Ying Extreme Computing & Statistics & Earth Science King Abdullah University of Science and Technology KSA Saudi Arabia Computational and Information Sciences Lab NSF National Center for Atmospheric Research United States NVIDIA United States Department of Computer Science Saint Louis University United States Department of Applied and Computational Mathematics and Statistics University of Notre Dame United States

We present the design and scalable implementation of an exascale climate emulator for addressing the escalating computational and storage requirements of high-resolution Earth System Model simulations. We utilize the spherical harmonic transform to stochastically model spatio-temporal variations in climate data. This provides tunable spatio-temporal resolution and significantly improves the fidelity and granularity of climate emulation, achieving an ultra-high spatial resolution of 0.034◦ (∼3.5 km) in space. Our emulator, trained on 318 billion hourly temperature data points from a 35-year and 31 billion daily data points from an 83-year global simulation ensemble, generates statistically consistent climate emulations. We extend linear solver software to mixed-precision arithmetic GPUs, applying different precisions within a single solver to adapt to different correlation strengths. The PaRSEC runtime system supports efficient parallel matrix operations by optimizing the dynamic balance between computation, communication, and memory requirements. Our BLAS3-rich code is optimized for systems equipped with four different families and generations of GPUs, scaling well to achieve 0.976 EFlop/s on 9,025 nodes (36,100 AMD MI250X multi-chip module (MCM) GPUs) of Frontier (nearly full system), 0.739 EFlop/s on 1,936 nodes (7,744 Grace-Hopper Superchips (GH200)) of Alps, 0.243 EFlop/s on 1,024 nodes (4,096 A100 GPUs) of Leonardo, and 0.375 EFlop/s on 3,072 nodes (18,432 V100 GPUs) of Summit. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Recorder: Comprehensive Parallel I/O Tracing and Analysis

arXiv

引用

arXiv 2025年

作者： Wang, Chen Yildirim, Izzet Devarajan, Hariharan Mohror, Kathryn Snir, Marc Center for Applied Scientific Computing Lawrence Livermore National Laboratory 7000 E. Ave LivermoreCA94550 United States Department of Computer Science Illinois Institute of Technology 10 W 35th St ChicagoIL60616 United States Department of Computer Science University of Illinois Urbana-Champaign 201 N Goodwin Ave UrbanaIL61801 United States

This paper presents Recorder, a parallel I/O tracing tool designed to capture comprehensive I/O information on HPC applications. Recorder traces I/O calls across various I/O layers, storing all function parameters for each captured call. The volume of stored information scales linearly the application’s execution scale. To address this, we present a sophisticated pattern-recognition-based compression algorithm. This algorithm identifies and compresses recurring I/O patterns both within individual processes and across multiple processes, significantly reducing space and time overheads. We evaluate the proposed compression algorithm using I/O benchmarks and real-world applications, demonstrating that Recorder can store more information while requiring approximately 12× less storage space compared to its predecessor. Notably, for applications with typical parallel I/O patterns, Recorder achieves a constant trace size regardless of execution scale. Additionally, a comparison with the profiling tool Darshan shows that Recorder captures detailed I/O information without incurring substantial overhead. The richer data collected by Recorder enables new insights and facilitates more in-depth I/O studies, offering valuable contributions to the I/O research community. Copyright © 2025, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Towards Holistic Analysis of Wireless Capsule Endoscopic Videos: A Taxonomy-Driven Machine Learning Framework for Clinically Comprehensive WCE Frame Level Analysis

Towards Holistic Analysis of Wireless Capsule Endoscopic Vid...

引用

Electrics and computer (INTCEC), Interdisciplinary Conference on

作者： Haroon Wahab Rita Goel Maida Alamgir Irfan Mehmood Khan Muhammad Hassan Ugail Centre for Visual Computing & Intelligent Systems School of Computer Science AI and Electronics University of Bradford Bradford England UK Department of Applied Artificial Intelligence Visual Analytics Knowledge Laboratory (VIS2KNOW) Sungkyunkwan University Seoul Republic of Korea

ISBN: (数字)9798350349450

ISBN: (纸本)9798350349467

Manual perusal of capsule endoscopic videos is laborious due to their length, redundancy, and poor quality frames, risking misdetection. Limited representation of diverse anomalies and subtle lesions led to less generalized approaches targeting only individual or few anomalous findings. To deploy automated analysis in clinical settings effectively, a holistic, end-to-end approach is crucial, distinguishing between frame-level analysis and disease-level diagnosis. This study proposes a holistic framework for frame-level analysis based on a taxonomy of findings, leveraging clinical consensus. Clinical knowledge implicit in the taxonomy can enhance computer Aided Diagnostics (CAD) systems. Convolutional Neural Networks (CNNs) trained at appropriate granularity levels in the taxonomy show improved performance metrics. Validation on the Kvasir-capsule dataset demonstrates a 2-4% performance boost. Taxonomy-based inference scores effectively resolve mimicked anomalies without additional learning.

关键词： Training Wireless communication Measurement Taxonomy Redundancy Merging Manuals

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-based Obstacle Avoidance for Robot Movement in Warehouse Environments 6

Deep Reinforcement Learning-based Obstacle Avoidance for Rob...

引用

6th IEEE International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2024

作者： Li, Keqin Chen, Jiajing Yu, Dezhi Dajun, Tao Qiu, Xinyu Lian, Jieting Ji, Ryan Zhang, Shengyuan Wan, Zhenyu Sun, Baiwei Hong, Bo Ni, Fanghao Han, Jiaqi Ama University Department of Computer Science Quezon Philippines Courant Institute New York University 251 Mercer St New YorkNY10012 United States University of California Berkeley University Avenue and Oxford St School of Information BerkeleyCA94720 United States Carnegie Mellon University Master of Science in Mechanical Engineering School of Engineering 5000 Forbes Avenue PittsburghPA United States Northeastern University College of Engineering Seattle United States School of Professional Studies New York University Master of Science in Database Technology 50 West 4th Street New YorkNY United States Cornell University College of Engineering 616 Thurston Ave IthacaNY14853 United States Cornell University Master of Professional Science in Applied Statistics-Data Science College of Computing and Information Science 616 Thurston Ave IthacaNY United States Independent Researcher Beijing China University of California Irvine Master of Computer Science Donald Bren School of Information and Computer Sciences 510 Aldrich Hall IrvineCA United States Northern Arizona University School of Informatics Computing and Cyber Systems FlagstaffAZ United States Shanghai Institute of Technology Shanghai China

ISBN: (纸本)9798350389418

This paper proposes a deep reinforcement learning based on the warehouse environment, the mobile robot obstacle avoidance Algorithm. Firstly, the value function network is improved based on the pedestrian interaction. We can learn to obtain the relative importance of the current state and the historical trajectory state as well as the joint impact on the robot's obstacle avoidance strategy. Secondly, the reward function of reinforcement learning is designed based on the spatial behaviour of pedestrians, and the robot is punished for the state where the angle changes too much, so as to achieve the requirement of comfortable obstacle avoidance. Finally, the feasibility and effectiveness of the deep reinforcement learning-based mobile robot obstacle avoidance algorithm in the warehouse environment in the complex environment of the warehouse are verified through simulation experiments. © 2024 IEEE.

关键词： Deep reinforcement learning

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：