检索结果-内蒙古大学图书馆

A Personalized Flight Recommender System Based on Link Prediction in Aviation Data

IEEE ACCESS 2024年 12卷 36961-36973页

作者： Kan, Ho Yin Wong, Dennis Chau, Keith Macao Polytech Univ Ctr Continuing Educ Macau Peoples R China Macao Polytech Univ Fac Appl Sci Macau Peoples R China Hong Kong Polytech Univ Coll Profess & Continuing Educ Hong Kong Peoples R China

Providing suitable flight recommendations to passengers is one of the essential requirements for ensuring customer satisfaction and maintaining a strong relationship with them in airline companies. Determining the appropriateness of a flight for a passenger is a complex issue that can depend on various factors. Factors such as individual preferences, flight quality, and the possibility of flight cancellations or delays need to be simultaneously considered in the process of making appropriate flight recommendations. Additionally, the vast amount of flight data adds to the complexity of this issue. In this article, a personalized flight recommender system is presented to address these challenges. The proposed method utilizes a link prediction strategy to model user profiles and habits, limiting the set of feasible recommendations. Furthermore, a Convolutional neural network (CNN) is employed to predict the likelihood of flight cancellations or delays, enabling the system to provide passengers with recommendations that maximize their satisfaction based on this information combined with flight features. To reduce the complexity of handling large flight datasets and increase processing speed, the proposed approach utilizes clustering. In this technique, data is distributed into a set of clusters using the K-Means algorithm, and the recommendation process is based on the cluster with the least distance to the user's features. The performance of the proposed method was tested using real flight data. The experiments evaluated the model's accuracy in predicting flight delays/cancellations and the accuracy of the recommendations it provides. The results demonstrated that the CNN model employed in the proposed method achieved an average accuracy of 95.13% in predicting flight delays/cancellations, showing at least a 2.4% improvement over the compared methods. Additionally, the proposed recommender system reported an accuracy value of 72.31%, surpassing the compared works by 15

关键词： Delays Airline industry Recommender systems Atmospheric modeling Reviews Predictive models Convolutional neural networks Aerospace engineering Linked data Aviation data recommender system link prediction clustering convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Communication-Efficient Federated DNN Training: Convert, Compress, Correct

引用

IEEE INTERNET OF THINGS JOURNAL 2024年第24期11卷 40431-40447页

作者： Chen, Zhong-Jing Hernandez, Eduin E. Huang, Yu-Chih Rini, Stefano Natl Yang Ming Chiao Tung Univ Inst Commun Engn Hsinchu 30010 Taiwan Natl Yang Ming Chiao Tung Univ Dept Elect & Elect Engn Hsinchu 30010 Taiwan

In the federated training of a deep neural network (DNN), model updates are transmitted from the remote users to the parameter server (PS). In many scenarios of practical relevance, one is interested in reducing the communication overhead to enhance training efficiency. To address this challenge, we introduce CO3 . CO3 takes its name from three processing applied which reduce the communication load when transmitting the local DNN gradients from the remote users to the PS. Namely, 1) gradient quantization through floating-point conversion;2) lossless compression of the quantized gradient;and 3) correction of quantization error. We carefully design each of the steps above to ensure good training performance under a constraint on the communication rate. In particular, in steps 1) and 2), we adopt the assumption that DNN gradients are distributed according to a generalized normal distribution, which is validated numerically in this article. For step 3), we utilize an error feedback with a memory decay mechanism to correct the quantization error introduced in step 1). We argue that the memory decay coefficient -similar to the learning rate-can be optimally tuned to improve convergence. A rigorous convergence analysis of the proposed CO3 with stochastic gradient descent (SGD) is provided. Moreover, with extensive simulations, we show that CO3 offers improved performance as compared with existing gradient compression schemes proposed in the literature which employ sketching and nonuniform quantization of the local gradients.

关键词： Training Quantization (signal) Artificial neural networks Convergence Vectors Stochastic processes Optimization Deep neural network (DNN) training error feedback (EF) federated learning (FL) gradient compression gradient modeling

来源：评论

学校读者我要写书评

暂无评论

Graph-Based Cross-Granularity Message Passing on Knowledge-Intensive Text

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE processing 2024年 32卷 4409-4419页

作者： Yan, Chenwei Fu, Xiangling You, Xinxin Wu, Ji Liu, Xien Beijing Univ Posts & Telecommun Beijing 100876 Peoples R China Minist Educ Key Lab Trustworthy Distributed Comp & Serv BUPT Beijing 100876 Peoples R China Tsinghua Univ Dept Elect Engn Beijing 100190 Peoples R China Tsinghua Univ Coll AI Beijing 100190 Peoples R China

In knowledge-intensive fields such as medicine, the text often contains numerous professional terms, specific text fragments, and multidimensional information. However, most existing text representation methods ignore this specialized knowledge and instead adopt methods similar to those used in the general domain. In this paper, we focus on developing a learning module to enhance the representation ability of knowledge-intensive text by leveraging a graph-based cross-granularity message passing mechanism. To this end, we propose a novel learning framework, the Multi-Granularity Graph neural network (MG-GNN), to integrate fine-grained and coarse-grained knowledge at the character, word, and phase levels. The MG-GNN performs learning in two stages: 1) inter-granularity learning and 2) intra-granularity learning. During inter-granularity learning, semantic knowledge is extracted from character, word, and phrase granularity graphs, whereas intra-granularity learning focuses on fusing knowledge across different granularity graphs to achieve comprehensive message integration. To enhance the fusion performance, we propose a context-based gating mechanism to guide cross-graph propagation learning. Furthermore, we apply MG-GNN to address two important medical applications. Experimental results demonstrate that our proposed MG-GNN model significantly enhances the performance in both diagnosis prediction and medical named entity recognition tasks.

关键词： Multi-granularity graph neural network electronic medical record medical NER diagnosis prediction Multi-granularity graph neural network electronic medical record medical NER diagnosis prediction

来源：评论

学校读者我要写书评

暂无评论

Security and Privacy Preservation via Interference Tolerant Fast Convergence Zeroing neural network With Reptile Search Optimization Algorithm in Fog-Cloud Computing

引用

TRANSACTIONS ON EMERGING TELECOMMUNICATIONS TECHNOLOGIES 2025年第4期36卷

作者： Kumar, Pakkarisamy Janakiraman Sathish Verma, Neha Gupta, Shivani Jothilakshmi, Rajendran Panimalar Engn Coll Dept Comp Sci & Engn Chennai Tamil Nadu India GGSIPU Vivekananda Inst Profess Studies Dept Informat Technol Delhi India Vellore Inst Technol Sch Comp Sci & Engn Chennai Tamil Nadu India RMD Engn Coll Dept Informat Technol Chennai Tamil Nadu India

More vertical service areas than only data processing, storing, and communication are promised by fog-cloud computing. Due to its great efficiency and scalability, distributed deep learning (DDL) across fog-cloud computing environments is a widely used application among them. With training limited to sharing parameters, DDL can offer more privacy protection than centralized deep learning. Nevertheless, DDL still faces two significant security obstacles when it comes to fog-cloud computing are How to ensure that users' identities are not stolen by outside enemies, and How to prevent users' privacy from being disclosed to other internal participants in the process of training. In this manuscript, Interference Tolerant Fast Convergence Zeroing neural network for Security and Privacy Preservation with Reptile Search Optimization Algorithm in Fog-Cloud Computing environment (SPP-ITFCZNN-RSOA-FCC) is proposed. ITFCZNN is proposed for security and privacy preservation, Then Reptile Search Optimization Algorithm (RSOA) is proposed to optimize the ITFCZNN, and Effective Lightweight Homomorphic Cryptographic Algorithm (ELHCA) is used to encrypt and decrypt the local gradients. The proposed SPP-ITFCZNN-RSOA-FCC system attains a better security balance, efficiency, and functionality than existing efforts. The proposed SPP-ITFCZNN-RSOA-FCC is implemented using Python. The performance metrics like accuracy, resource overhead, computation overhead, and communication overhead are considered. The performance of the SPP-ITFCZNN-RSOA-FCC approach attains 29.16%, 20.14%, and 18.93% high accuracy, and 11.03%, 26.04%, and 23.51% lower Resource overhead compared with existing methods including FedSDM: Federated learning dependent smart decision making component for ECG data at internet of things incorporated Edge-Fog-Cloud computing (SPP-FSDM-FCC), A collaborative computation with offloading in dew-enabled vehicular fog computing to compute-intensive with latency-sensitive dependence-awar

关键词： effective lightweight homomorphic cryptographic algorithm fog-cloud computing interference-tolerant fast convergence zeroing neural network privacy preserving reptile search optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A Paillier Homomorphic Encryption-Based Lightweight Privacy Protection Model for Mobile Crowd Sensing networks

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第7期49卷 115-128页

作者： Feng, Shijie Qin, Yanyan Zeng, Zhixiang Wen, Bing Zhong, Weijie Wang, Ning Guo, Wei Zhang, Yunan Hainan Power Grid Co. Ltd. Haikou570203 China Information and Telecommunication Branch of Hainan Power Grid Haikou570203 China CSG Electric Power Research Institute Co. Ltd. Guangdong Provincial Key La-boratory of Power System Network Security Guangzhou510663 China

The objective of this study is to enhance the privacy protection capability of mobile crowd perception networks and improve the detection accuracy of security threat data. To this end, a three-level collaborative distributed architecture is designed, which combines the concept of zero trust and proposes a lightweight security threat detection model based on the Paillier homomorphic encryption, deep neural networks, and box graph methods. Firstly, by optimizing the mobile crowd sensing networks framework and introducing three different network structures, a collaborative distributed system of terminal edge cloud was constructed. Secondly, the Paillier homomorphic encryption algorithm was designed to protect data privacy. The experimental results showed that the designed model achieved a detection accuracy of 98.84%, a mean square error of 0.03, and an average detection time of 0.15 seconds for A-class threats. In terms of processing efficiency, this model significantly improved data transmission efficiency, had lower computational overhead, and was suitable for various types of security threat detection. Therefore, the security threat detection model proposed in this study provides effective privacy protection technology for mobile crowd-sensing networks, significantly improving network security. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

SHATTER: Searching Heterogeneous Combat network Attack Sequences Through network Embedding and Reinforcement Learning

引用

IEEE SYSTEMS JOURNAL 2023年第3期17卷 4497-4508页

作者： Zeng, Chengyi Liu, Hongfu Lu, Lina Chen, Jing Zhou, Zongtan Natl Univ Def Technol Coll Intelligence Sci & Technol Changsha Peoples R China Natl Univ Def Technol Coll Intelligence Sci & Technol Changsha Peoples R China Natl Univ Def Technol Coll Intelligence Sci & Technol Changsha Peoples R China Natl Univ Def Technol Coll Intelligence Sci & Technol Changsha Peoples R China Natl Univ Def Technol Coll Intelligence Sci & Technol Changsha Peoples R China

A distributed combat system consists of various types of combat units interconnected through the network, which can be abstracted as a complex heterogeneous combat network (HCN). It is of great military value to study the disintegration of the operational capability of HCNs for operational mission planning and improving the survivability of operational networks. Heterogeneous networks can effectively fuse more information than homogeneous networks can. The function implementation of heterogeneous networks is also more complex. Finding the key nodes and obtaining an efficient attack sequence is our focus. Most current research on network disintegration has difficulty achieving efficiency and timeliness. In this article, we specifically propose searching heterogeneous combat network attack sequences through network embedding and reinforcement learning (SHATTER) model, which uses the induction algorithm combined with the graph neural network and reinforcement learning to solve the network disintegration sequence problem. Through experiments with synthetic heterogeneous network datasets and real heterogeneous networks, we determined that SHATTER significantly outperformed existing technologies.

关键词： Reinforcement learning Heterogeneous networks Deep learning Task analysis Approximation algorithms Signal processing algorithms Training Graph neural network (GNN) heterogeneous combat network (HCN) network disintegration reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Edge-Cloud Collaborative Streaming Video Analytics With Multi-Agent Deep Reinforcement Learning

引用

IEEE network 2025年第1期39卷 165-173页

作者： Qian, Bin Xuan, Yubo Wu, Di Wen, Zhenyu Yang, Renyu He, Shibo Chen, Jiming Ranjan, Rajiv Newcastle Univ Sch Comp Newcastle Upon Tyne NE4 5TG England Zhejiang Univ Technol Coll Comp Sci & Technol Hangzhou 310023 Peoples R China Univ St Andrews Sch Comp Sci St Andrews KY16 9AJ Scotland Zhejiang Univ Technol Inst Cyberspace Secur Hangzhou 310023 Peoples R China Beihang Univ Sch Software Beijing 100191 Peoples R China Zhejiang Univ Coll Control Sci & Engn Hangzhou 310058 Peoples R China Zhejiang Univ State Key Lab Ind Control Technol Hangzhou 310058 Peoples R China Hangzhou Dianzi Univ Sch Automat Hangzhou 310018 Peoples R China

Streaming video analytics focuses on the real-time analysis of streaming video data from multiple resources, such as security cameras, and IoT devices with video capabilities. It involves applications of various techniques to extract valuable information from live video streams. Edge computing and cloud computing facilitate video stream analytics by utilizing computation resources across both ends, enabling both high accuracy and low latency. However, video streaming behaviours are dynamic and constantly evolving across the edge and the cloud. The network conditions, computing resources, and video content can change rapidly, making it crucial to continuously adjust the analytics methods to provide accurate results. Previous works both based on deep neural networks (DNNs) or heuristic algorithms learn a suitable deployment plan for streaming video analytics applications from historical data or synthetic data and therefore are not able to capture the dynamics. Hence, we propose reinforcement learning-based methods that can adapt to ongoing changes in video streaming behaviours. To ensure the scalability of video analytics in distributed environments, we implement OsmoticGate2, a distributed streaming video analytics system that features optimized processing pipelines and multi-agent RL-based controllers for fast adapting the system configurations across the edge and the cloud. Experiments on a real testbed show that our method outperforms baselines, assuring real-time video analysis and high accuracy in dynamic and distributed environments.

关键词： Streaming media Visual analytics Cloud computing Servers Streams Real-time systems Delays real-time video analytics distributed system multiagent deep reinforcement learning edge cloud collaboration

来源：评论

学校读者我要写书评

暂无评论

Efficient Application of Deep neural networks for Identifying Small and Multiple Weed Patches Using Drone Images

引用

IEEE ACCESS 2024年 12卷 71982-71996页

作者： Singh, Vyomika Singh, Dharmendra Kumar, Harish Indian Inst Technol Roorkee Dept Elect & Commun Engn Roorkee 247667 India King Khalid Univ Coll Comp Sci Dept Comp Sci Abha 61413 Saudi Arabia

Deep learning (DL) based camouflage target localization, classification and detection using UAV data is currently an evolving and promising hotspot in the field of digital image processing and computer vision. Weed, an undesirable plant that hinders crop growth, acts as a camouflage target w.r.t sugarcane crop (Saccharum Officinarum). Weed exhibits green-on-green color-based merging capability (background matching) and similar spectral behavior with the sugarcane crop, resulting in a visually complex camouflage habitat, making it difficult to distinguish and detect weed from crop. The concealed nature of weed in the sugarcane field, qualifies it as a camouflage target. In this scenario, weed is distributed in the form of multiple small patches across the UAV imagery, making the detection even more complicated, leading to a requirement of a pixel-based classification and subsequent target detection technique. The research problem is to successfully detect weed (camouflage target) at the smallest resolvable pixel size (2-4 cm/px), keeping in mind the similar behavior (merging color) and its difficulty to differentiate it from the sugarcane crop (background). To achieve this challenge, color and texture are exploited as important feature representations. They are extracted via UAV image(s), which can aid in small and multiple weed patch detection, by implementing a rich feature-based Deep neural network (DNN). In this revolutionary era of AI and modern drones, DNNs provide feature based elastic transformations, expedited processing, improved accuracy, and optimized mapping and detection. These representation-based networks traverse deeper into color and texture feature representations as a unified component, pixel by pixel, eventually detecting the camouflage targets by their self-learning capabilities in comparison to traditional classification approaches. DNNs exhibit good capabilities to solve camouflage target detection problems, therefore we have proposed a method

关键词： Feature extraction Autonomous aerial vehicles Crops Object detection Deep learning Location awareness Image color analysis Computer vision UAV deep neural networks classification target detection computer vision

来源：评论

学校读者我要写书评

暂无评论

An Efficient Privacy-Aware Split Learning Framework for Satellite Communications

引用

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2024年第12期42卷 3355-3365页

作者： Sun, Jianfei Wu, Cong Mumtaz, Shahid Tao, Junyi Cao, Mingsheng Wang, Mei Frascolla, Valerio Nanyang Technol Univ Sch Comp Sci & Engn Singapore 639798 Singapore Nottingham Trent Univ Dept Engn Nottingham NG1 4FQ England Kyung Hee Univ Dept Elect Engn Yongin 17104 Gyeonggi Do South Korea SUNY Stony Brook Dept Comp Sci Stony Brook NY 11794 USA Univ Elect Sci & Technol China Network & Data Secur Key Lab Sichuan Prov Chengdu 610056 Peoples R China Ningbo WebKing Technol Joint Stock Co Ltd Ningbo 315000 Zhejiang Peoples R China Shandong Univ Sch Cyber Sci & Technol Qingdao 266237 Peoples R China Intel Deutschland GmbH D-85579 Neubiberg Germany

In the rapidly evolving domain of satellite communications, integrating advanced machine learning techniques, particularly split learning, is crucial for enhancing data processing and model training efficiency across satellites, space stations, and ground stations. Traditional ML approaches often face significant challenges within satellite networks due to constraints such as limited bandwidth and computational resources. To address this gap, we propose a novel framework for more efficient SL in satellite communications. Our approach, Dynamic Topology-Informed Pruning, namely DTIP, combines differential privacy with graph and model pruning to optimize graph neural networks for distributed learning. DTIP strategically applies differential privacy to raw graph data and prunes GNNs, thereby optimizing both model size and communication load across network tiers. Extensive experiments across diverse datasets demonstrate DTIP's efficacy in enhancing privacy, accuracy, and computational efficiency. Specifically, on Amazon2M dataset, DTIP maintains an accuracy of 0.82 while achieving a 50% reduction in floating-point operations per second. Similarly, on ArXiv dataset, DTIP achieves an accuracy of 0.85 under comparable conditions. Our framework not only significantly improves the operational efficiency of satellite communications but also establishes a new benchmark in privacy-aware distributed learning, potentially revolutionizing data handling in space-based networks.

关键词： Satellites Computational modeling Data models Training Space stations Satellite communications Bandwidth Satellite communication privacy split learning graph neural networks

来源：评论

学校读者我要写书评

暂无评论

EDDIS: Accelerating distributed Data -Parallel DNN Training for Heterogeneous GPU Cluster

EDDIS: Accelerating Distributed Data -Parallel DNN Training ...

引用

1st International Conference on Smart Energy Systems and Artificial Intelligence (SESAI)

作者： Ahn, Shinyoung Ahn, Hooyoung Choi, Hyeonseong Lee, Jaehyun ETRI Supercomp Syst Res Sect Daejeon South Korea MangoBoost Software Team Seoul South Korea Puzzle AI Inc Res Inst Daejeon South Korea

ISBN: (纸本)9798350364613;9798350364606

EDDIS is a novel distributed deep learning library designed to efficiently utilize heterogeneous GPU resources for training deep neural networks (DNNs), addressing scalability and conuminication challenges in distributed training environments. It offers three training modes (synchronous, asynchronous, and hybrid) and supports TensorFlow and PyTorch frameworks. EDDIS significantly accelerates DNN training in heterogeneous GPU settings, achieving up to 17.5x faster training with 16 nodes compared to a single node. Remarkably, the Hybrid training mode surpasses Horovod, achieving training speeds 2.53 times faster for the ResNet50 model.

关键词： Terms Deep neural network DNN Heterogeneous GPU distributed Training Data -parallel Training EDDIS SoftMemoryBox SSGD EASGD Hybrid SGD

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：