检索结果-内蒙古大学图书馆

A deep Q-learning model for sequential task offloading in edge AI systems

Intelligent and Converged Networks 2024年第3期5卷 207-221页

作者： Dong Liu Shiheng Gu Xinyu Fan Xu Zheng Department of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 610000China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of ChinaShenzhen 515100China Department of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu 610000China

Currently,edge Artificial Intelligence(AI)systems have significantly facilitated the functionalities of intelligent devices such as smartphones and smart cars,and supported diverse applications and *** fundamental supports come from continuous data analysis and computation over these *** the resource constraints of terminal devices,multi-layer edge artificial intelligence systems improve the overall computing power of the system by scheduling computing tasks to edge and cloud servers for *** efforts tend to ignore the nature of strong pipelined characteristics of processing tasks in edge AI systems,such as the encryption,decryption and consensus algorithm supporting the implementation of Blockchain ***,this paper proposes a new pipelined task scheduling algorithm(referred to as PTS-RDQN),which utilizes the system representation ability of deep reinforcement learning and integrates multiple dimensional information to achieve global task ***,a co-optimization strategy based on Rainbow Deep Q-Learning(RainbowDQN)is proposed to allocate computation tasks for mobile devices,edge and cloud servers,which is able to comprehensively consider the balance of task turnaround time,link quality,and other factors,thus effectively improving system performance and user *** addition,a task scheduling strategy based on PTS-RDQN is proposed,which is capable of realizing dynamic task allocation according to device *** results based on many simulation experiments show that the proposed method can effectively improve the resource utilization,and provide an effective task scheduling strategy for the edge computing system with cloud-edge-end architecture.

关键词： edge computing task scheduling reinforcement learning Rainbow Deep Q-Learning(RainbowDQN)

来源：评论

学校读者我要写书评

暂无评论

Fusion Strategy for Improving Medical Image Segmentation

引用

computers, Materials & Continua 2023年第2期74卷 3627-3646页

作者： Fahad Alraddady E.A.Zanaty Aida HAbu bakr Walaa M.Abd-Elhafiez Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Information System Department Faculty of Computers and InformationSohag UniversitySohagEgypt Mathematical and Computer Science Department Faculty of ScienceAswan UniversityAswanEgypt College of Computer Science&Information Technology Jazan UniversityJazanKingdom of Saudi Arabia Computer Science Department Faculty of Computers and Artificial IntelligenceSohag UniversitySohagEgypt

In this paper,we combine decision fusion methods with four metaheuristic algorithms(Particle Swarm Optimization(PSO)algorithm,Cuckoo search algorithm,modification of Cuckoo Search(CS McCulloch)algorithm and Genetic algorithm)in order to improve the image *** proposed technique based on fusing the data from Particle Swarm Optimization(PSO),Cuckoo search,modification of Cuckoo Search(CS McCulloch)and Genetic algorithms are obtained for improving magnetic resonance images(MRIs)*** algorithms are used to compute the accuracy of each method while the outputs are passed to fusion *** order to obtain parts of the points that determine similar membership values,we apply the different rules of incorporation for these *** proposed approach is applied to challenging applications:MRI images,gray matter/white matter of brain segmentations and original black/white images Behavior of the proposed algorithm is provided by applying to different medical *** is shown that the proposed method gives accurate results;due to the decision fusion produces the greatest improvement in classification accuracy.

关键词： Decision fusion particle swarmoptimization(PSO) cuckoo search algorithm CS McCulloch algorithm genetic algorithm CT and MRI

来源：评论

学校读者我要写书评

暂无评论

A QoS-aware routing approach for Internet of Things-enabled wireless sensor networks in smart cities

引用

Multimedia Tools and Applications 2025年第17期84卷 17951-17977页

作者： Karunkuzhali, D. Meenakshi, B. Lingam, Keerthi Department of Information Technology Panimalar Engineering College Chennai India Department of Electrical and Electronics Engineering Sri Sairam Engineering College Chennai India Department of Computer Science and Engineering Gitam University Visakhapatnam India

In the Internet of Things (IoT), optimizing machine performance through data analysis and improved connectivity is pivotal. Addressing the growing need for environmentally friendly IoT solutions, we focus on "green IoT." Quality in smart cities heavily relies on efficient data gathering and communication. In this study, we propose a novel software architecture tailored for data collection and communication in IoT-enabled smart applications, emphasizing sustainability from the outset. Specifically, for smart cities utilizing IoT-enabled wireless sensor networks, we introduce a Quality of Service (QoS)-aware routing strategy. In the data collection phase, we employ Chaotic Bird Swarm Optimization (CBSO) for creating IoT sensor clusters, accompanied by Improved Differential Search (IDS) to assess the reliability of individual sensor nodes, ultimately designating the most trusted node as the Cluster Head (CH). In the data transport phase, we implement lightweight signcryption to enhance the security of IoT sensor data. Furthermore, we employ an Optimal Data Routing (ODM) approach to compute the most efficient data transmission paths between source and destination nodes within the IoT network. Finally, the performance of our QoS-aware routing strategy is evaluated through network simulations using NS2 and compared against existing approaches, offering valuable insights into its effectiveness and suitability for smart city IoT applications. The main findings of the study indicate that the proposed QoS-aware routing strategy (QOS-AWARE ROUTING) consistently outperforms existing routing algorithms in terms of energy efficiency, network longevity, and latency, both in scenarios with varying sensor node density and over multiple cycles. Additionally, it demonstrates significant advantages, such as up to 90.8% less energy consumption, 66.8% longer network lifespan, and 80.1% reduced latency when compared to the benchmarked methods. © The Author(s), under exclusive licence to S

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

The Smart Predictive Analysis of Stock Market Performance using Restricted Boltzmann Machines

The Smart Predictive Analysis of Stock Market Performance us...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Devrani, Rekha Mahajan, Prerna Kumar, Dinesh Vivekananda Global University Department of Computer Science & Engineering Jaipur India Department of Computer Science and Information Technology Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India

ISBN: (纸本)9798350383348

Restricted Boltzmann Machines (RBMs) are a system getting-to-know algorithm that may be used to predict the overall performance of inventory markets. This painting aims to analyze the overall performance of inventory markets via growing an RBM version. The RBM version will benefit from the temporal correlation of stock marketplace information and put it to use to make more correct predictions. The version is educated using historical facts, and the model parameters are adjusted to optimize the prediction accuracy. This painting demonstrates the use of an RBM model for predicting the returns of stocks and analyzing the stock marketplace's overall performance. The outcomes from these paintings show that the proposed RBM version effectively predicts the overall performance of inventory markets and provides an alternative version for forecasting stock markets. Confined Boltzmann Machines (RBMs) are a form of synthetic neural network which can be used for unsupervised studying tasks consisting of dimensionality discount, function mastering, and collaborative filtering. RBMs have been correctly used in numerous applications, including sentiment evaluation, natural language processing, and computer imagination and prescient. In current years, there was a surge of hobby in using RBMs to expect inventory market overall performance. On the way to expand a predictive model, RBMs extract separable functions from the uncooked market data, which can be pattern inputs. The extracted capabilities are used because of the input to a supervised mastering version to predict stock marketplace overall performance based on previous statistics. A vital advantage of using RBMs for feature extraction is that they can identify latent components of the facts, which would, in any other case, remain hidden from the consumer. By combining RBMs with supervised learning, it is viable to develop models which can be more powerful than those using either technique for my part. Because of this reality,

关键词： algorithms correlations historical inventory stock

来源：评论

学校读者我要写书评

暂无评论

Parametrized Optimization Based on an Investigation of Musical Similarities Using SPARK and Hadoop

引用

SN computer science 2024年第1期5卷 78页

作者： Chaudhary, Savita Karthik, V. Shankar, R. Taranum, Ayesha Naresh, E. Department of Computer Science and Engineering Sir M Visvesvaraya Institute of Technology Bengaluru Bengaluru India Department of Information Science and Engineering Ramaiah Institute of Tech B’lore India Department of Computer Science and Engineering BMS Institute of Technology and Engineering Bengaluru India Department of Computer Science and Engineering Vidyavardhaka College of Engineering Mysuru India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

The big data processing framework Spark is used to power a parameterizable recommender system that can make recommendations for music based on a user’s individual tastes and take into account a variety of musical tonal qualities. The system as it is presently built is completely scalable, which means that additional songs can be contributed to the data, the cluster size could be increased, and new types of audio information, in addition to more cutting-edge similarity evaluations, may be included. Another issue discussed in this research paper is the parallel collection of required audio characteristics on a computer cluster. Song recommendations for a dataset including more than 114,000 songs may be created on a Spark cluster with 16 nodes in under 12 s by integrating eight distinct audio feature types and similarity assessments. After the features have been retrieved, they are sent to the Spark-based recommender system to be processed. The calculated distance was displayed, examined, and graphically depicted. By computing the distance depending on the melody, rhythmic, and timbral components of the music, the final software controls song suggestion. © 2023, The Author(s).

关键词： Big data Hadoop Music information retrieval Optimization Spark

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Optimization for Dynamic Resource Allocation in Heterogeneous Unmanned Aerial Vehicle-Base Station

引用

IEEE Transactions on Vehicular technology 2025年第6期74卷 9016-9026页

作者： Chien, Wei-Che Chen, Songlin Dai, Cheng National Dong Hwa University Department of Computer Science and Information Engineering Hualien Taiwan University of Electronic Science and Technology of China School of Aeronautics and Astronautics Sichuan Chengdu China Sichuan University College of Computer Science Sichuan Chengdu China

In response to the escalating energy demands of mobile networks, exacerbated by the disproportionate usage between urban and suburban areas, this study introduces a transformative approach using a heterogeneous UAV-based station architecture within a C-RAN framework. This innovative architecture promises to revolutionize next-generation networks by offering high reconfigurability and mobility. The core of this system is the dynamic adaptability of the BBU pool connected to the RRH, enabling real-time adjustments based on usage demands. This adaptability is crucial for reducing energy consumption, particularly in dynamic and fluctuating network environments. To optimize the system's performance, the study confronts the inherent trade-offs among handover frequency, transmission delay, and power consumption by formulating a multi-objective optimization problem. To address this complex issue, two resource allocation strategies utilizing meta-heuristic algorithms are proposed: GARAH and SARAH. GARAH focuses on minimizing energy consumption and delay time, proving its effectiveness through simulation. On the other hand, SARAH strikes a balance, maintaining efficient energy use and latency while minimizing handover occurrences. These strategies demonstrate the potential of this UAV-based C-RAN architecture in crafting more sustainable and efficient mobile networks. © 1967-2012 IEEE.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

BEV-Locator:an end-to-end visual semantic localization network using multi-view images

引用

science China(information sciences) 2025年第2期68卷 134-150页

作者： Zhihuang ZHANG Meng XU Wenqiang ZHOU Tao PENG Liang LI Stefan POSLAD School of Vehicle and Mobility Tsinghua University School of Information Technology & Management University of International Business and Economics Qcraft Inc. School of Electronic Engineering and Computer Science Queen Mary University of London

Accurate localization ability is fundamental in autonomous driving. Traditional visual localization frameworks approach the semantic map-matching problem with geometric models, which rely on complex parameter tuning and thus hinder large-scale deployment. In this paper, we propose BEV-Locator: an end-to-end visual semantic localization neural network using multi-view camera images. Specifically, a visual BEV(bird-eye-view) encoder extracts and flattens the multi-view images into BEV space. While the semantic map features are structurally embedded as map query sequences. Then a cross-model transformer associates the BEV features and semantic map queries. The localization information of ego-car is recursively queried out by cross-attention modules. Finally, the ego pose can be inferred by decoding the transformer outputs. This end-to-end model speaks to its broad applicability across different driving environments, including high-speed scenarios. We evaluate the proposed method in large-scale nuScenes and Qcraft datasets. The experimental results show that the BEV-Locator is capable of estimating the vehicle poses under versatile scenarios, which effectively associates the cross-model information from multi-view images and global semantic maps. The experiments report satisfactory accuracy with mean absolute errors of 0.052 m, 0.135 m and 0.251° in lateral, longitudinal translation and heading angle degree.

关键词： visual localization semantic map bird-eye-view transformer pose estimation

来源：评论

学校读者我要写书评

暂无评论

Multi-domain feature-enhanced attribute updater for generalized zero-shot learning

引用

Neural Computing and Applications 2025年第14期37卷 8397-8414页

作者： Shi, Yuyan Jiang, Chenyi Song, Feifan Ye, Qiaolin Long, Yang Zhang, Haofeng School of Computer Science and Engineering Nanjing University of Science and Technology Jiangsu Nanjing210094 China School of Information Science and Technology Nanjing Forestry University Jiangsu Nanjing210037 China Department of Computer Science Durham University DurhamDH1 3LE United Kingdom

The goal of generalized zero-shot learning (GZSL) is to transfer knowledge from seen classes to unseen classes. However, a significant challenge is the single-category attributes are often inadequate to capture the intra-class variability of diverse image samples. During training, the model tends to cluster samples of seen categories based solely on semantic descriptions, overlooking subtle yet important visual differences. To address these challenges, this paper introduces an instance-level attribute updating method, termed as multi-domain feature-enhanced attribute updater (MDAU), which establishes a one-to-one alignment between visual and semantic by obtaining multiple instance-level attributes that closely correspond to the natural intra-class distribution of the image, in contrast to the many-to-one alignment typically used in traditional GZSL approaches. Specifically, we initially compute feature weights for each individual image, and then, the visual information is incorporated as conditions to facilitate the personalized updating of class attributes. We evaluate our model on three benchmark datasets, the results show that our model can achieve the state-of-the-art performance and detailed analysis also illustrates the effectiveness of each proposed module. Code is available at https://***/S-Silvia/MDAU. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Predicting Student Behavior Using a Neutrosophic Deep Learning Model

引用

Neutrosophic Sets and Systems 2025年 76卷 288-310页

作者： Shitaya, Ahmed Mohamed Wahed, Mohamed El Syed Abd El Khalek, Saied Helemy Ismail, Amr Shams, Mahmoud Y. Salama, A.A. Department of Mathematics and Computer Science Faculty of Science Port Said University Egypt Department of Computer Science Faculty of computer and information sciences Suez Canal University Egypt Department. of Communication and Computer Engineering Air Defense University Egypt Department of Cybersecurity College of Engineering and Information Technology Buraydah Private Colleges Buraydah51418 Saudi Arabia Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33516 Egypt

We developed an information system using an object-oriented programming language and a distributed database (DDB) consisting of multiple interconnected databases across a computer network, managed by a distributed database management system (DDBMS) for easy access. An intelligent system was designed to assess the difficulty level of preliminary exams and select top-performing advanced students using a Neutrosophic Deep Learning Model. The dataset was randomly split into training (80%) and testing (20%) sets, and the model, trained with the Adam optimizer at a 0.001 learning rate over 50 epochs, incorporated early stopping based on validation loss. This system, implemented at a traditional Egyptian university, achieved a 95% accuracy in predicting student dropout. Student behavior, influenced by personal, environmental, and academic factors, is often evaluated subjectively, leading to inconsistent results. Traditional machine learning approaches struggle with the inherent uncertainty in behavioral data. To address this, we combined neutrosophic theory—a mathematical framework that accounts for truth, falsity, and indeterminacy—with deep learning, which excels at learning complex data relationships, to predict student outcomes such as dropout rates. Evaluating the model on student data, including attendance and grades, showed superior accuracy, achieving a determination coefficient of 0.95, demonstrating the approach's potential for identifying at-risk students and enabling targeted interventions. © 2025, University of New Mexico. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Finger-vein Secure Access Based on Lightweight Dual-attention Convolutional Neural Network for Quality Distance Education

引用

Sensors and Materials 2024年第3期36卷 945-955页

作者： Ke, Liang-Ying Hsia, Chih-Hsien Department of Computer Science and Information Engineering National Ilan University Yilan Taiwan Department of Business Administration Chaoyang University of Technology Taichung Taiwan

As global average fertility rates decline annually, a crisis brought by declining birthrates gradually emerges, further impacting the existing education system. In response to the impact of declining birthrates on education, countries have recently accelerated the development of distance learning. Distance learning provides guaranteed access to comprehensive and quality education while encouraging continuous learning opportunities for everyone. However, the identity recognition technology used in the current distance learning platform seldom addresses the problem of inconsistent image quality in actual scenarios, making it difficult to ensure the practical application of the model. To solve these issues, we propose a lightweight dual-attention convolutional neural network (LDA-FV) constructed through a dual attention-based inverted residual block (DA-IRB) and implemented using an adaptive margin loss (AML) function for finger-vein recognition. This method not only extracts effective finger-vein features through DA-IRB but also adjusts the training difficulty in accordance with the image quality. Furthermore, owing to its lightweight design, the model can be more flexibly deployed on existing hardware devices (e.g., mouse) in distance education scenarios. The experimental results of this study indicate that the proposed method effectively enhanced the model's recognition capability using the finger-vein database of the University Sains Malaysia (FVUSM) and the PLUSVein dorsal-palmar finger-vein (PLUSVein-FV3) public database, achieving correct identification rates (CIRs) of 99.90% and 97.50%, respectively. © 2024 M Y U Scientific Publishing Division. All rights reserved.

关键词： Convolution

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：