检索结果-内蒙古大学图书馆

Attack-detection and multi-clock source cooperation-based accurate time synchronization for PLC-AIoT in smart parks

Digital Communications and Networks 2024年第6期10卷 1732-1740页

作者： Zhigang Du Sunxuan Zhang Zijia Yao Zhenyu Zhou Muhammad Tariq State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power UniversityBeijing 102206China Electrical Engineering Department National University of Computer and Emerging SciencesIslamabad 44000Pakistan

Power Line Communications-Artificial Intelligence of Things(PLC-AIo T)combines the low cost and high coverage of PLC with the learning ability of Artificial Intelligence(AI)to provide data collection and transmission capabilities for PLC-AIo T devices in smart *** the development of smart parks,their emerging services require secure and accurate time synchronization of PLC-AIo T ***,the impact of attackers on the accuracy of time synchronization cannot be *** solve the aforementioned problems,we propose a tampering attack-aware Deep Q-Network(DQN)-based time synchronization ***,we construct an abnormal clock source detection ***,the abnormal clock source is detected and excluded by comparing the time synchronization information between the device and the ***,the proposed algorithm realizes the joint guarantee of high accuracy and low delay for PLC-AIo T in smart parks by intelligently selecting the multi-clock source cooperation strategy and timing *** results show that the proposed algorithm has better time synchronization delay and accuracy performance.

关键词： Smart park Power line communications Artificial intelligence of things Tampering attack awareness Abnormal clock source detection Multi-clock source cooperation

来源：评论

学校读者我要写书评

暂无评论

A QOE-AWARE STRATEGY FOR ENERGY SAVING IN A FOG-BASED ENVIRONMENTAL MONITORING system

引用

International Journal of Electrical engineering 2023年第2期30卷 43-52页

作者： Haung, Yieh-Ran Yin, Chia-Ling Liu, Jenchi Department of Computer Science and Engineering Yuan Ze University Taiwan Electronic and Optoelectronic System Research Laboratories Industrial Technology Research Institute Taiwan

In the Fog-based Environmental Monitoring system (FEMS), the frequency at which Internet of Thing (IoT) devices upload monitoring data and the frequency at which users obtain monitoring data can highly affect energy consumption, data timeliness, and user quality of experience (QoE). How to reduce energy consumption while achieving high data timeliness and user QoE is not only important but also challenging. We propose a QoE-aware strategy to schedule the frequency at which users obtain monitoring data and the frequency at which IoT devices upload monitoring data. The QoE-aware strategy sets the changing tolerance (CT) of monitoring data according to the requirements of different applications in different environments. CT indicates the sensitivity of the application to the change of the environmental data. Only when the changing rate of monitoring data exceeds the CT value set, the IoT device uploads monitoring data to the fog server. Besides, to meet the requirements of reducing data traffic and achieving high data timeliness, users can set different values of QoE Index (QI), i.e., the achievement rate for timely access, according to different environmental requirements. With the QI value, the fog server can calculate the optimal time interval (i.e., access period, AP) for users to access monitoring data. Consequently, by setting the values of CT, QI, and AP according to the requirements of different applications in different environments, the QoE-aware strategy is able to achieve the lowest energy consumption and the highest data timeliness. © 2023, Chinese Institute of Electrical engineering. All rights reserved.

关键词： Fog

来源：评论

学校读者我要写书评

暂无评论

Leveraging Transfer Learning for Spatio-Temporal Human Activity Recognition from Video Sequences

引用

computers, Materials & Continua 2023年第3期74卷 5017-5033页

作者： Umair Muneer Butt Hadiqa Aman Ullah Sukumar Letchmunan Iqra Tariq Fadratul Hafinaz Hassan Tieng Wei Koh School of Computer Sciences Universiti Sains MalaysiaPenang1180Malaysia Department of Computer Science The University of ChenabGujrat50700Pakistan Department of Software Engineering and Information System Universiti Putra MalaysiaSelangor43400Malaysia

Human Activity Recognition(HAR)is an active research area due to its applications in pervasive computing,human-computer interaction,artificial intelligence,health care,and social ***,dynamic environments and anthropometric differences between individuals make it harder to recognize *** study focused on human activity in video sequences acquired with an RGB camera because of its vast range of real-world *** uses two-stream ConvNet to extract spatial and temporal information and proposes a fine-tuned deep neural ***,the transfer learning paradigm is adopted to extract varied and fixed frames while reusing object identification *** state-of-the-art pre-trained models are exploited to find the best model for spatial feature *** temporal sequence,this study uses dense optical flow following the two-stream ConvNet and Bidirectional Long Short TermMemory(BiLSTM)to capture *** state-of-the-art datasets,UCF101 and HMDB51,are used for evaluation *** addition,seven state-of-the-art optimizers are used to fine-tune the proposed network ***,this study utilizes an ensemble mechanism to aggregate spatial-temporal features using a four-stream Convolutional Neural Network(CNN),where two streams use RGB *** contrast,the other uses optical flow ***,the proposed ensemble approach using max hard voting outperforms state-ofthe-art methods with 96.30%and 90.07%accuracies on the UCF101 and HMDB51 datasets.

关键词： Human activity recognition deep learning transfer learning neural network ensemble learning spatio-temporal

来源：评论

学校读者我要写书评

暂无评论

Dynamic generative R-CNN

引用

Neural Computing and Applications 2025年第10期37卷 7107-7120页

作者： Saffarini, Rasha Khamayseh, Faisal Awwad, Yousef Sabha, Muath Eleyan, Derar IT Engineering Arab American University Jenin Palestine Department of Computer Science Palestine Polytechnic University Hebron Palestine Department of Computer System Engineering Palestine Technical University Tulkarm Palestine Department of Multimedia Technology Arab American University Jenin Palestine Department of Applied Computing Palestine Technical University Tulkarm Palestine

Different techniques have been developed for object detection and recognition. These techniques can be divided into single-shot and two-shot methods. Single-shot methods focus on real-time applications, while two-shot methods are used in applications requiring higher accuracy. However, different versions of the two-shot techniques produce limited results in terms of accuracy and speed, or both. Therefore, this study proposes a novel model called dynamic generative R-CNN (DGR-CNN) that reduces the number of proposed regions using a dynamic programming model that applies the graph similarity method over graph-based image segmentation. Additionally, the proposed model employs DCGAN technique to improve detection performance. DGR-CNN reduces the overall detection and classification time and enhances the detection accuracy. The PASCAL VOC2007 and MS COCO datasets were utilized to evaluate the model. The results showed that DGR-CNN significantly reduces the number of candidate regions compared to the selective search algorithm employed in R-CNN and fast R-CNN. Although fast R-CNN utilizes 2000 regions and faster R-CNN utilizes 300 regions, DGR-CNN reduces the number of regions to approximately 130. The mean average precision of the proposed method was 75.1% on the PASCAL VOC2007, while fast and faster R-CNN scored 66.9% and 69.9%, respectively. Moreover, the DGR-CNN model significantly improved the classification accuracy when tested on the MS COCO dataset, achieving an MAP of 68.76%, compared with 32.64% and 42.3% for fast and faster R-CNN. This increase in accuracy was achieved without significantly compromising the speed compared with faster R-CNN. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Improving LoRaWAN Connectivity in Smart Agriculture Contexts Using Aerial IoT

Improving LoRaWAN Connectivity in Smart Agriculture Contexts...

引用

2023 IEEE Globecom Workshops, GC Wkshps 2023

作者： Sanguesa, Julio A. Torres-Sanz, V. Serna, Felix Martinez, Francisco J. Garrido, Piedad Calafate, Carlos T. University of Zaragoza Computer Science and System Engineering Department Spain Universitat Politècnica de València Department of Computer Engineering Spain

ISBN: (纸本)9798350370218

The emergence of the Internet of Things (IoT) has enabled the creation of new solutions to real-world problems, including digitalization and real-time monitoring. Plenty of research has been done in applying IoT schemes in various areas, such as Industry 4.0, smart cities or, as in the case of this paper, smart agriculture. One of the main problems in rural areas is the Internet coverage. In many cases, the infrastructure is very poor, and mountainous terrain further complicates the communication among devices. In this paper, we develop an IoT framework based on the Long Range (LoRa) wireless technology, specially designed to solve this issue (i.e., the lack of communication coverage). In particular, we have endowed Unmanned Aerial Vehicles (UAVs) with a LoRa gateway to improve the coverage of LoRa devices in mountainous regions. Our experiments show that not only the distance between sender and receiver but also both the height of the UAV and the Fresnel zone clearance are critical factors for communications performance in mountainous areas. © 2023 IEEE.

关键词： communications coverage IoT LoRaWAN smart agriculture UAV

来源：评论

学校读者我要写书评

暂无评论

Soft-GNN:towards robust graph neural networks via self-adaptive data utilization

引用

Frontiers of computer Science 2025年第4期19卷 1-12页

作者： Yao WU Hong HUANG Yu SONG Hai JIN National Engineering Research Center for Big Data Technology and System Service Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China College of Information and Communication National University of Defense TechnologyWuhan 430019China Department of Computer Science and Operations Research Universitéde MontréalMontreal H3C 3J7Canada

Graph neural networks(GNNs)have gained traction and have been applied to various graph-based data analysis tasks due to their high ***,a major concern is their robustness,particularly when faced with graph data that has been deliberately or accidentally polluted with *** presents a challenge in learning robust GNNs under noisy *** address this issue,we propose a novel framework called Soft-GNN,which mitigates the influence of label noise by adapting the data utilized in *** approach employs a dynamic data utilization strategy that estimates adaptive weights based on prediction deviation,local deviation,and global *** better utilizing significant training samples and reducing the impact of label noise through dynamic data selection,GNNs are trained to be more *** evaluate the performance,robustness,generality,and complexity of our model on five real-world datasets,and our experimental results demonstrate the superiority of our approach over existing methods.

关键词： graph neural networks node classification label noise robustness

来源：评论

学校读者我要写书评

暂无评论

MV-DUO: multi-variate discrete unified optimization for psychological vital assessments

引用

Neural Computing and Applications 2024年第31期36卷 19777-19793页

作者： Pethuraj, Mohamed Shakeel Burhanuddin, M.A. Dzakiyullah, Nur Rachman Department of Information System Faculty of Computer and Engineering Universitas Alma Ata Yogyakarta Indonesia Faculty of Information and Communication Technology Universiti Teknikal Malaysia Melaka Durian Tunggal Melaka Malaysia

Psychological vital assessments are required for monitoring health conditions and observing body reactions toward diseases and medications. Wearable sensors play a vital role in sensing body vitals and presenting them as signals for computer-based analysis. The problem relies on the signal decoding due to its input stream that turns out to be discrete/ continuous. Therefore for addressing the above specific issue, this article introduces MV-DUO (Multi-Variate Discrete Unified Optimization) method. This method addresses the above problem from a multi-variate perspective by sensing differential signals across healthy and unhealthy conditions. The healthy and unhealthy conditions are trained using neural learning by augmenting/ ceasing external vital data. The unification is performed using single-point artificial ecosystem-based optimization for identifying discrete sequences collaborated with continuous signals. The single-point reference is grouped based on the maximum continuity fitness observed under various sensing intervals. In this process, the non-grouped sequences are identified as unhealthy or discrete for which additional detection training and classification are required. Considerably the changes between successive sensing intervals are used for variations detection from unified high-fitness groups. Those grouped instances are used for training new vital changes observed at distinct intervals. This improves detection accuracy under controlled errors. For the varying sensing intervals, the proposed method achieves 14.13% high accuracy, 8.29% high grouping rate, 10.77% less error, and 10.07% less detection time. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： computer aided analysis

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Method to Measure Distribution Consistency of Mixed-Attribute Datasets

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第1期4卷 182-196页

作者： He, Yulin Ye, Xuan Huang, Defa Fournier-Viger, Philippe Huang, Joshua Zhexue College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China

Random sample partition (RSP) is a newly developed data management and processing model for Big Data processing and analysis. To apply the RSP model for Big Data computation tasks, it is very important to measure the distribution consistency of different datasets. Existing measurement methods for continuous-attribute and discrete-attribute datasets cannot directly deal with mixed-attribute datasets. In this article, we design a hybrid method to measure the distribution consistency among different mixed-attribute datasets by using a multilayer extreme learning machine (MLELM) and the generalized maximum mean discrepancy (GMMD) criterion, abbreviated as MLELM-GMMD. MLELM is first used to transform original mixed-attribute datasets into corresponding deep encoding datasets. Then, the GMMD criterion is applied to check the distribution consistency of the deep encoding datasets. Four experiments have been done to validate the feasibility and effectiveness of MLELM-GMMD, i.e., the impact of MLELM on the amount of information during mixed-attribute data transformation, the impact of MLELM on distributions of mixed-attribute data, the distribution consistencies of RSP and non-RSP data blocks, and the comparison with other measurement methods. Experimental results show that the proposed MLELM-GMMD method can measure the distribution consistency of mixed-attribute datasets more accurately than one-hot encoding-based methods. © 2022 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Functionalised B-Cu@F-Ag@Au trimetallic nanomaterials with long term stability for rapid and highly sensitive in situ SERS detection of furfural in transformer oil

引用

High Voltage 2023年第2期8卷 293-304页

作者： Yu Lei Changding Wang Weiping Kong Mingliang Wang Xinyuan Zhang Abdolmaleki Nima Caisheng Wang Weigen Chen Fu Wan School of Electrical Engineering Chongqing UniversityChongqingChina State Key Laboratory of Power Transmission Equipment and System Security and New Technology Chongqing UniversityChongqingChina Electrical and Computer Engineering Wayne State UniversityWayneNebraskaUSA

The surface-enhanced Raman scattering(SERS)substrates enable a highly sensitive detection of furfural in the transformer ***,detection substrates with long-term stability are still extremely *** this work,we anchored the thiol-containing coupling agents 2,5-dimercapto-1,3,4-thiadiazole(DMTD)and 1,4-benzenedithiol(BDT)on the surface of bubble copper(B-Cu)and flower-like silver nanoparticles(FAg),*** three-dimensional SERS detection substrates with long-term stability by using a combination of chemical reduction and self-assembly methods were *** substrate has a minimum detection limit of 10^(−9) M for rhodamine B in oil with an enhancement factor of up to 2.23×10^(7).Importantly,the three-crystal BCu@F-Ag_(1)@Au_(5) substrate was used for the detection of furfural in the transformer oil with a detection limit of 2 mg/L and a relative standard deviation value of 2.46%.After 60 days of a simulated operation,the detection signal of furfural in the transformer oil samples at 75℃ and still reached the initial value of 77.53%,indicating that the substrate has a good long-term *** triple frame structured SERS detection platform shows great potential in tracking furfural in the aging transformer oil mixing systems.

关键词： stability. stability SERS

来源：评论

学校读者我要写书评

暂无评论

Production Scheduling Heuristic for Mass Customization with Partial Rescheduling 7

Production Scheduling Heuristic for Mass Customization with ...

引用

7th International Conference on Mechanical Manufacturing and Industrial engineering, MMIE 2024

作者： Tsui, Zhe-Luen Chou, Ywh-Leh Yuan, Cadmus Feng Chia University Department of Industrial Engineering and System Management Taiwan Feng Chia University Department of Mechanical and Computer-Aided Engineering Taiwan

ISBN: (数字)9781510683297

ISBN: (纸本)9781510683280

This research responds to the complex challenges of mass customization and multi-objective parameter optimization. Leveraging the Call-Auction Matching proposed by Cadmus Yuan, Zhe-Luen Tsui, and Ywh-Leh Chou[1], we improved a Production Date Prediction Call-Auction Matching (PDP-CAM) scheduling algorithm. Our numerical analysis validated the ability of algorithm to implement a partial rescheduling mechanism and generate scheduling results in the face of mass customization scenarios. Importantly, the effectiveness of the PDP-CAM scheduling algorithm in minimizing instance rescheduling was demonstrated, thereby enhancing the computational efficiency of the algorithm. © 2024 SPIE.

关键词： Cleaning

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：