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 efficient cloud based face recognition system for e-health secured login using steerable pyramid transform and local directional pattern

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第1期15卷 1017-1027页

作者： Dosaj, Ayush Satapathy, Suresh Chandra Soundrapandiyan, Rajkumar Kaur, Mannat Hannoon, Naeem School of Computer Science and Engineering Vellore Institute of Technology Vellore India School of Computer Science and Engineering Kalinga Institute of Industrial Technology Deemed to be University Odisha Bhubaneswar India Faculty of Electrical Engineering Universiti Teknologi MARA Shah Alam Malaysia

This paper proposes a face recognition system based on steerable pyramid transform (SPT) and local directional pattern (LDP) for e-health secured login in cloud domain. In an e-health login, patients periodically forget their self-made login username and password. This face recognition system can replace the traditional login system. In the proposed system, SPT can decompose a face image into several sub-bands of different scales and orientations, and LDP can encode the sub-bands in binary texture pattern. The LDP binary pattern was obtained by computing the edge response values in all eight directions at each pixel position and generating a code from the relative strength magnitude. Therefore, SPT–LDP design represents a face image in a robust way which includes multiple information sources from different scales and orientations. The proposed system is tested on standard benchmark facial recognition technology (FERET) and extended Yale-B databases. Further, the efficiency of the proposed system is proved by comparing recognition rates with other existing descriptor based methods. From the experimental results it is observed that the proposed system achieves 99.79% recognition in fb set, 90.72% in fc set, 84.97% in dup I set, and 87.69% in dup II set for FERET database and 100% in sub2 set, 100% in sub3 set, 96% in sub4 set and 95% in sub5 set for extended Yale-B database which is better than the existing methods. © Springer-Verlag GmbH Germany, part of Springer Nature 2018.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Deep Hierarchies and Invariant Disease-Indicative Feature Learning for computer Aided Diagnosis of Multiple Fundus Diseases 39

Deep Hierarchies and Invariant Disease-Indicative Feature Le...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Lin, Yuxin Wang, Wei Luo, Xiaoling Wu, Zhihao Liu, Chengliang Wen, Jie Xu, Yong School of Computer Science and Technology Harbin Institute of Technology Shenzhen China College of Computer Science and Software Engineering Shenzhen University China Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

ISBN: (纸本)157735897X

With the advancement of computer vision, numerous models have been proposed for screening of fundus diseases. However, the recognition of multiple fundus diseases is often hampered by the simultaneous presence of multiple disease types and the confluence of lesion types in fundus images. This paper addresses these challenges by conceptualizing them as multi-level feature fusion and self-supervised disease-indicative feature learning problems. We decode fundus images at various levels of granularity to delineate scenarios wherein multiple diseases and lesions co-occur. To effectively integrate these features, we introduce a hierarchical vision transformer (HVT) that adeptly captures both inter-level and intra-level dependencies. A novel forward-attention module is proposed to enhance the integration of lower-level semantic information into higher semantic layers, thereby enriching the representation of complex features. Additionally, we introduce a novel self-supervised mask-consistent feature learner (MCFL). Unlike traditional mask-autoencoders that reconstruct original images using encoder-decoder structures, MCFL utilizes a teacher-student framework to reconstruct mask-consistent feature maps. In this setup, exponential moving averaging is employed to derive classification-guided features, serving as labels for reconstruction rather than merely reconstructing the original images. This innovative approach facilitates the extraction of disease-indicative features. Extensive experiments demonstrate that our method significantly outperforms existing state-of-the-art models. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

HFBLGERC: Design of an Efficient Hybrid Fusion of BiLSTM, BiGRU, with ES-RNN for Responsive Resource Scheduling 15

HFBLGERC: Design of an Efficient Hybrid Fusion of BiLSTM, Bi...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Kazi, Aihtesham Chaudhari, Dinesh Bajaj Institute of Technology Department of Computer Engineering Wardha India Jawaharlal Darda Institute of Engineering & Technology Computer Science & Engineering Yavatmal India

ISBN: (纸本)9798331300579

The efficient scheduling of tasks on virtual machines (VMs) is paramount in cloud computing environments. The complexity and dynamism of today's applications require a more insightful and adaptive approach to task allocation to ensure optimal resource utilization and service delivery. Traditional scheduling approaches often fall short when it comes to considering the multi-dimensional attributes of tasks and VMs, such as makespan, deadline, memory, and bandwidth requirements. These methodologies lack the ability to dynamically adapt to the ever-evolving requirements of tasks and the capacities of VMs, leading to suboptimal performance and resource wastage. In this paper, we present a novel approach that fuses BiLSTM & BiGRU with Exponential Smoothing Recurrent Neural Network (ES-RNN) to create a more robust and adaptive task scheduling mechanism under real-time scenarios. This model holistically assesses task capacity based on its makespan, deadline, memory, and bandwidth requirements. Similarly, VM capacity is evaluated based on its RAM, MIPS, bandwidth, and the number of processing elements. The fusion of these advanced neural architectures provides a deeper understanding of the task-VM mapping, enabling a more intelligent and efficient scheduling decision. Our approach demonstrates a marked improvement over traditional techniques, with tangible benefits such as reduced makespan by 4.9% and improved VM computation efficiency by 3.5%. The practical implications of our methodology are profound. By integrating our model into real-world cloud environments, organizations can expect to see an enhanced deadline hit ratio by 1.5%, ensuring that critical tasks meet their time-sensitive objectives. Moreover, the decision-making process becomes significantly more agile, resulting in a decision delay reduction of 4.5%, thereby promoting more responsive and efficient cloud computing operations. This work paves the way for a new era of intelligent cloud resource management, opt

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

An energy-efficient task and virtual machine placement in virtualised cloud server using FY-SFLA and RMMS-DLVQ

引用

International Journal of Networking and Virtual Organisations 2023年第2期29卷 144-167页

作者： Sudhakar, E.P. Saravanan, M. Department of Computer Science and Engineering SRM Institute of Science and Technology Kattankulathur Chennai603203 India Department of Networking and Communications College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai603203 India

Creating infrastructures, virtual servers, computing resources, along with devices is termed virtualisation. In this methodology, to augment resource usage along with to mitigate the total power consumption, mapping of a group of virtual machine (VM) onto a set of physical machines (PM) is performed in a data centre (DC). Nevertheless, a crucial challenge is presented by the VM allocation together with the higher energy consumption (EC) of cloud data centres (CDC). Thus, to alleviate the resource wastage along with to mitigate the DCs' EC, an effectual Fisher Yates-Shuffled frog leaping algorithm (FY-SFLA) is proposed here: 1) task feature extraction;2) resource information extraction;3) task separation by utilising cosine distance - K means algorithm (CD-KMA);4) task placement in VM by employing the FY-SFLA task;5) VM status identification by deploying random mutation monkey search deep learning vector quantisation (RMMS - DLVQ) are '5' phases comprised in the proposed methodology. © 2023 Inderscience Enterprises Ltd.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

Enhanced Facial Emotion Recognition Using Transfer Learning with ResNet152

Enhanced Facial Emotion Recognition Using Transfer Learning ...

引用

2024 International Conference on Intelligent Computing and Sustainable Innovations in technology, IC-SIT 2024

作者： Tripathy, Sasmita Pattanaik, Satya Ranjan Sahoo, Prakash Dash, Ratnakar Centurion University of Technology and Management Department of Computer Science and Engineering Bhubaneswar India Gandhi Institute for Technology Department of Computer Science and Engineering Bhubaneswar India National Institute of Technology Rourkela Department of Computer Science and Engineering Rourkela India

ISBN: (纸本)9798350369175

The prospective applications of facial expression-based emotion recognition have sparked a lot of interest in domains like camera technology, mental health analysis, and human-computer interaction. Using the ResNet152 architecture, we suggest a unique facial emotion recognition (FER) technique that makes use of preprocessing, data augmentation, and transfer learning. While deep learning techniques, particularly when combined with CNNs, are known to be successful for classification problems, conventional methods have difficulty optimizing both feature extraction and classification at the same time. Through extensive testing on a dataset, the research shows that the suggested method is effective, with ResNet152 obtaining an accuracy of $\mathbf{8 4 \%}$. Experiments on randomly selected photos from different sources revealed encouraging outcomes for precise and instantaneous FER. This study presents a strong method for FER that makes use of transfer learning and deep learning, providing notable improvements over traditional methods. © 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

A Novel Trustworthiness Measurement Model Based on Weight and User Feedback

引用

Chinese Journal of Electronics 2022年第4期31卷 612-625页

作者： ZHOU Wei MA Yanfang PAN Haiyu School of Computer Science and Technology Huaibei Normal University School of Computer Science and Information Engineering Changzhou Institute of Technology School of Computer Science and Information Security Guilin University of Electronic Technology

Software trustworthiness is an essential criterion for evaluating software quality. In componentbased software, different components play different roles and different users give different grades of trustworthiness after using the software. The two elements will both affect the trustworthiness of software. When the software quality is evaluated comprehensively, it is necessary to consider the weight of component and user feedback. According to different construction of components, the different trustworthiness measurement models are established based on the weight of components and user feedback. Algorithms of these trustworthiness measurement models are designed in order to obtain the corresponding trustworthiness measurement value automatically. The feasibility of these trustworthiness measurement models is demonstrated by a train ticket purchase system.

关键词： Component-based software Trustworthiness Weight User feedback Measurement

来源：评论

学校读者我要写书评

暂无评论

An intrusion attack classification using bio-inspired optimization technique and ensemble learning model for edge computing environments

引用

Multimedia Tools and Applications 2024年 1-28页

作者： Rahamathulla, Mohemmed Yousuf Ramaiah, Mangayarkarasi School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamilnadu Vellore India

The phenomenal rise in network traffic across various sectors, driven by advancements in network communication, has led to an explosion of connected devices. While internet-based service providers have enhanced smart environments, these environments remain highly vulnerable to security risks. Due to their resource- constrained nature, Internet of Things (IoT) systems rely on edge servers for processing. Cutting-edge machine learning algorithms have significantly improved the security of edge computing systems by enabling early intrusion detection. However, the dynamic nature of our society demands more sophisticated Network Intrusion Detection Systems (NIDS) that can balance the challenge of managing the explosive growth of network traffic data with effectively responding to attacks. This paper proposes a novel NIDS that can train and learn from massive amounts of data in a centralized environment. To identify the best subset of features for improved data representation and classification, a bio-inspired algorithm, the Improved Firefly Optimization Algorithm (IFOA), is employed. Furthermore, a hyper-tuned Extremely Randomized Trees (ERT) attack detection model is developed to accurately identify malicious behavior while minimizing false positives. The experimental results demonstrate that the proposed approach achieves superior accuracy and execution speed compared to alternative solutions and its baseline versions. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Solar-Powered Waterborne Debris Collector Equipped with Sprinkler System 2

Solar-Powered Waterborne Debris Collector Equipped with Spri...

引用

2nd International Conference on Emerging Trends in Information technology and engineering, ic-ETITE 2024

作者： Keerthika, C. Jenitha Blesy, A. Grace Gnanam, J. Narmadha, D. Sundar, G. Naveen School of Computer Science and Engineering Karunya Institute of Technology and Sciences Divison of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350328202

Conventional machine models of water trash collection is here enhanced with the integration of sprinkler system. This enhanced model for water trash collection combines conventional methods integrated with a sprinkler system. The incorporation of the sprinkler system enhances water quality by agitating the surface, elevating oxygen levels, and facilitating the decomposition of organic substances. Moreover, the sprinkler system allows for the introduction of medications and necessary supplements to further improve water conditions. As a primary focus, the collection of debris is carried out with the help of a conveyor belt which Operates with the help of a motor which is connected to the power supply obtained from solar panels. The energy obtained from the solar panel is harnessed and stored for usage in times of less or no sunlight. With the optimized usage of sensors and imaging cameras, the target trash is identified. The direction of movement of the mechanism is instructed by the condition generated on analyzing the objects ahead to be identified as obstacles. The overall features of the mechanism are effective in energy efficiency and data-driven decision contributing to a holistic approach to the majority of the problems faced during the expected phases of operation. © 2024 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Heart Disease Detection Using Machine Learning Models 2

Heart Disease Detection Using Machine Learning Models

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Singh, Amrit Mahapatra, Harisankar Biswal, Anil Kumar Mahapatra, Madhumita Singh, Debabrata Samantaray, Milan Berhampur India Berhampur India Dept. of Computer Science Udayanath Autonomous College of Science and Technology Cuttack India Dept. of Computer Science and Engineering Delhi Technical Campus UP Greater Noida India Bhubaneswar India Department of Computer Science and Engineering Silicon Institute of Technology Bhubaneswar India

An enormous number of deaths occur every year as a result of heart disease, making it a major concern in world health. Improving patient outcomes and lowering death rates, early detection and correct diagnosis of cardiac disease play a key role. When the heart's arteries become blocked, oxygen-poor blood cannot reach the heart properly, resulting in coronary heart disease. Early detection of cardiac disease is viable because it reduces medical costs and potentially saves the patient's life. Recently presented methods have improved heart failure detection accuracy on testing data without sacrificing accuracy on training data, yet most of these algorithms are suffering from the issue of overfitting. Models that were created end up fitting the test data too well. In this study, we create a novel diagnostic system to address this issue, and the resulting system demonstrates high intelligence and excellent performance on both training and testing data. Machine learning (ML) algorithms have demonstrated promising potential in assisting healthcare professionals with timely and accurate diagnosis. In this paper, is based on supervised machine learning methods are decision tree (DT), random forest (RF), Support vector Machine (SVM), Principal Component Analysis(PCA). We compare their accuracy with each other by using bar plot. © 2024 Elsevier B.V.. All rights reserved.

关键词： Blood pressure

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：