检索结果-内蒙古大学图书馆

5th IEEE International Conference on Pattern Recognition and Machine Learning, PRML 2024

作者： Wei, Xiang Zhou, Yang Bai, Yaxin Li, Zihui Hu, Mingqi Liu, Qiuming State Grid Jiangxi Elettric Power co. Ltd Nanchang China Information and Communication Branch of State Grid Jiangxi Electric Power Co. Ltd. Nanchang China School of Software Engineering Jiangxi University of Science and Technology Nanchang China Advanced Copper Industry College Jiangxi University of Science and Technology Yingtan China

ISBN: (纸本)9798350355925

Accurate short-term electricity load forecasting is essential to ensure the safe, reliable, and economically efficient operation of power systems. However, traditional forecasting methods are increasingly inadequate to meet the demand for ever more precise load predictions. In response to this issue, a CNN-BILSTM-Attention neural network method optimized based on an improved Sparrow Search Algorithm is proposed for short-term electricity load forecasting. Firstly, the Sin chaotic mapping strategy is utilized to initialize the Sparrow population, enhancing the diversity of population positions. Additionally, the cosine optimization algorithm is introduced into the formula for updating the joiner's position. This aims to address the decrease in global search capability in the later iterations of the Sparrow algorithm, thereby enhancing the accuracy of the Sparrow search algorithm;Next, the ISSA algorithm is employed to optimize the CNN-BILSTM-Attention neural network. This helps avoid overly random initialization of the CNN-BILSTM-Attention neural network's initial weight thresholds, thus enhancing the stability of prediction results;Finally, load forecasting is conducted and compared with other algorithmic models for analysis. Additionally, for the WOA-CNN-BILSTM-Attention model, RMSE decreases by 1.832%, with a corresponding MAE reduction of 1.073%. Similarly, for the PSO-CNN-BILSTM-Attention model, RMSE decreases by 1.804% and MAE by 1.026%. The results of the case study demonstrate that the proposed model can effectively enhance prediction accuracy and is valid for short-term load forecasting. By accurately predicting the power demand, the reasonable distribution and optimal dispatch of power can be realized, and the power grid fluctuations caused by the load mutation can be reduced, so as to ensure the quality of power supply. © 2024 IEEE.

关键词： CNN-BILSTM-Attention ISSA Load Forecasting Sparrow Search Algorithm

来源：评论

学校读者我要写书评

暂无评论

Enhancing Healthcare Data Security in Cloud Computing systems through advanced Homomorphic Encryption Techniques Integrated with Cuckoo Search Optimization Algorithm

Enhancing Healthcare Data Security in Cloud Computing System...

引用

2024 IEEE International Conference on Recent Advances in Science and engineering technology, ICRASET 2024

作者： Sudha, I. Ramesh, P.S. Ponmalar, A. Jagannathan, J. Pandiarajan, Rajkumar Saveetha Institute of Medical and Technical Sciences Simats University Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu Chennai India R.M.K. Engineering College Tamilnadu Chennai India Vellore Institute of Technology School of Computer Science Engineering and Information Systems Department of Software and Systems Engineering Katpadi Vellore India Kalasalingam Academy of Research and Education School of Computing Department of Information and Technology Krishnankoil Virudhunagar India

ISBN: (纸本)9798350388602

The studies in this research are focused on the mix of homomorphic encryption mechanisms and the Cuckoo Search Optimization Algorithm to promote the security of the healthcare data in the cloud computing system. I have observed that cloud solutions are now at the center of the contemporary health care systems, and security of patient's data remains a top priority. Earlier used encryption techniques, though secure if implemented, have problems in the way that data is to be processed first it has to be decrypted and then made ready for use - it is in this phase that data can be easily hacked into. Homomorphic encryption provides solution to this issue since it enables one to perform computations on encrypted data while maintaining its confidentiality. However, it takes a lot of computation which presents a lot of problems even in terms of simple performance. The Cuckoo Search Algorithm, a new nature-inspired metaheuristic, is incorporated into the encryption process to provide further optimization, whilst preserving the security benefits of the algorithm. The use of the proposed methodology takes place employing Python and its deployment at the cloud platform with elaborated dataset containing anonymized records extracted from electronic health records. The outcome proves that there are great enhancements in encryption and decryption time, computational complexity, and capacity, and thereby making the system appropriate for real-world healthcare solutions. This research offers a strong base for protection of healthcare data in cloud and is useful for the enhancement of adaptive, comprehensive and secure cloud computing systems. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

HOG-VGG:VGG Network with HOG Feature Fusion for High-Precision PolSAR Terrain Classification

引用

Journal of Harbin Institute of technology(New Series) 2024年第5期31卷 1-15页

作者： Jiewen Li Zhicheng Zhao Yanlan Wu Jiaqiu Ai Jun Shi School of Computer Science and Information Engineering Hefei University of TechnologyHefei 230009China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui UniversityHefei 230601China School of Artificial Intelligence Anhui UniversityHefei 230601China Intelligent Interconnected Systems Laboratory of Anhui Province(Hefei University of Technology) Hefei 230009China School of Software Hefei University of TechnologyHefei 230009China

This article proposes a VGG network with histogram of oriented gradient(HOG) feature fusion(HOG-VGG) for polarization synthetic aperture radar(PolSAR) image terrain ***-Net has a strong ability of deep feature extraction,which can fully extract the global deep features of different terrains in PolSAR images,so it is widely used in PolSAR terrain ***,VGG-Net ignores the local edge & shape features,resulting in incomplete feature representation of the PolSAR terrains,as a consequence,the terrain classification accuracy is not *** fact,edge and shape features play an important role in PolSAR terrain *** solve this problem,a new VGG network with HOG feature fusion was specifically proposed for high-precision PolSAR terrain ***-VGG extracts both the global deep semantic features and the local edge & shape features of the PolSAR terrains,so the terrain feature representation completeness is greatly ***,HOG-VGG optimally fuses the global deep features and the local edge & shape features to achieve the best classification *** superiority of HOG-VGG is verified on the Flevoland,San Francisco and Oberpfaffenhofen *** show that the proposed HOG-VGG achieves much better PolSAR terrain classification performance,with overall accuracies of 97.54%,94.63%,and 96.07%,respectively.

关键词： PolSAR terrain classification high⁃precision HOG⁃VGG feature representation completeness elevation multi⁃level feature fusion

来源：评论

学校读者我要写书评

暂无评论

Emerging Role of Industry 5.0 Digital Twins in Demand Response Electricity Market and Applications

Emerging Role of Industry 5.0 Digital Twins in Demand Respon...

引用

2023 IEEE PES Innovative Smart Grid Technologies Europe, ISGT EUROPE 2023

作者： Onile, Abiodun E. Belikov, Juri Petlenkov, Eduard Levron, Yoash Department of Software Science Tallinn University of Technology Akadeemia tee 15a Tallinn12618 Estonia Department of Computer Systems Tallinn University of Technology Akadeemia tee 15a Tallinn12618 Estonia Faculty of Electrical and Computer Engineering Technion—Israel Institute of Technology Haifa3200003 Israel

ISBN: (纸本)9798350396782

Traditional power system is facing challenges demanding new operational requirements to meet targets of Net Zero Emissions by 2050. Aggregators are playing progressively important role in the demand response (DR) electricity market but are often riddled with deep level of market monopoly and lack of transparency/secrecy. Emerging real-time information technology (IT) applications and novel modelling of digital twins (DT) of individual electricity assets are challenging this position by promising improvements and openness that allows TSO direct access to available demand side flexibility. Additionally, DT technologies are facilitating how demand response services are delivered to end-users by allowing individual assets participation at the atomic level. In this study, the application potentials of assets’ DT in participating in the demand response electricity market was examined. Again, an overview of DT applications for DR was conducted. The novelty of this study is highlighted in development of new approach that facilitates individual end-user assets’ contribution to demand response efforts. The research identifies key useful questions that might serve as inspiration for stakeholders and policy-makers to further close existing gaps in the field of DT, smart-grid and demand response. © 2023 European Union.

关键词： Aggregators demand response digital twins Industry 5.0 smart-grid

来源：评论

学校读者我要写书评

暂无评论

Exception-aware Lifecycle Model Construction for Framework APIs

arXiv

引用

arXiv 2024年

作者： Yan, Ji-Wei Huang, Jin-Hao Yang, Heng-Qin Yan, Jun Technology Center of Software Engineering Institute of Software Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Beijing University of Technology Beijing100124 China Hangzhou Institute for Advanced Study Hangzhou310024 China

The implementation of complex software systems usually depends on low-level frameworks or third-party libraries. However, the evolution of these frameworks or libraries is independent of the upper-level applications, which brings challenges in upper-level code quality assurance. For example, during code evolution, the APIs adding and removing behaviors may cause unexpected compatibility problems. Precisely analyzing and constructing the framework/ library’s API lifecycle model is of great importance, which could help in understanding changes in APIs as well as supporting the analysis and testing of upper-level code. Nowadays, existing works propose the API existence-changing model for defect detection, while not considering the influence of semantic changes in APIs. In some cases, developers will not remove or deprecate APIs but modify their semantics by adding, removing, or modifying their exception-thrown code, which is used to verify the users’ inputs. It may bring potential defects to upper-level code if the exception-related behaviors in newer versions are changed silently. Therefore, besides the API existence model, it is also necessary for developers to be concerned with the exception-related code evolution in APIs, which requires the construction of exception-aware API lifecycle models for framework/library projects. To achieve automatic exception-aware API lifecycle model construction, this paper adopts static analysis technique to extract exception summary information in the framework API code and adopts a multi-step matching strategy to obtain the changing process of exceptions. Then, it generates exception-aware API lifecycle models for the given framework/library project. Our approach: 1) adopts control-dependency slicing analysis to extract the conditions of the exception-thrown statements;uses a parameter tracing strategy to transform exception-throwing conditions into external-variable-related preconditions;and performs inter-procedure precondition c

关键词： Static analysis

来源：评论

学校读者我要写书评

暂无评论

SFedXL: Semi-Synchronous Federated Learning With Cross-Sharpness and Layer-Freezing

引用

IEEE Internet of Things Journal 2025年第12期12卷 18692-18707页

作者： Zhao, Mingxiong Zhao, Shihao Feng, Chenyuan Yang, Howard H. Niyato, Dusit Quek, Tony Q. S. Yunnan University National Pilot School of Software Kunming650500 China Ministry of Education Engineering Research Center of Integration and Application of Digital Learning Technology Beijing100039 China Ministry of Education Engineering Research Center of Cyberspace Kunming650504 China Yunnan University of Finance and Economics Yunnan Key Laboratory of Service Computing Kunming650221 China EURECOM Sophia Antipolis06410 France Zhejiang University University of Illinois Urbana-Champaign Institute Zhejiang University Haining314400 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore

Federated learning (FL) emerges as a potential solution for enabling multiple terminal devices to collaboratively accomplish computational tasks within an Unmanned Aerial Vehicle (UAV) swarm. However, traditional FL approaches, predicated on synchronous data aggregation, are not feasible for a UAV swarm owing to the inherently variable and dynamic nature of their communication networks compared with terrestrial systems. Furthermore, the data procured by UAVs is often highly heterogeneous, attributable to disparities in deployment environments and device attributes. Considering the distinct flight paths and unique operational conditions encountered by different UAVs, a considerable amount of data remains unlabeled. To tackle the challenges associated with asynchronous operations and the prevalence of unlabeled data, we introduce a novel framework termed Semi-synchronous FL with Cross-Sharpness and Layer-Freezing (SFedXL), tailored for a UAV swarm. In particular, we devise a cross-sharpness model training strategy aimed at optimizing the utilization of both labeled and unlabeled datasets. Additionally, we propose an innovative semi-synchronous model aggregation protocol, complemented by client-specific layer-freezing and client cluster scheduling, designed to expedite the training process. Our simulation results indicate that the proposed algorithm surpasses current FL methods in terms of object recognition accuracy and communication efficiency, albeit with a trade-off of increased local computation latency. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

TraM: Enhancing User Sleep Prediction with Transformer-Based Multivariate Time Series Modeling and Machine Learning Ensembles 15

TraM: Enhancing User Sleep Prediction with Transformer-Based...

引用

15th International Conference on Information and Communication technology Convergence, ICTC 2024

作者： Kim, Jinjae Ma, Minjeong Choi, Eunjee Cho, Keunhee Lee, Changwoo Sch. of Business Administration Kookmin University Seoul Korea Republic of Sch. of Industrial and Management Engineering Korea University Seoul Korea Republic of Sch. of Electrical Engineering Korea University Seoul Korea Republic of Korea Advanced Institute of Science and Technology Civil and Environmental Engineering Daejeon Korea Republic of Sch. of Software Kookmin University Seoul Korea Republic of

ISBN: (纸本)9798350364637

This paper presents a novel approach that leverages Transformer-based multivariate time series model and Machine Learning Ensembles to predict the quality of human sleep, emotional states, and stress levels. A formula to calculate the labels was developed, and the various models were applied to user data. Time Series Transformer was used for labels where time series characteristics are crucial, while Machine Learning Ensembles was employed for labels requiring comprehensive daily activity statistics. Time Series Transformer excels at capturing the characteristics of time series through pre-training, while Machine Learning Ensembles selects machine learning models that meet our categorization criteria. In experiments, the proposed model, TraM, scored 6.10 out of 10, demonstrating superior performance compared to other methodologies. The code and configuration for the TraM framework are available at: https://***/jin-jae/ETRI-Paper-Contest. © 2024 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

MAKT: Multichannel Attention Networks based Knowledge Tracing with Representation Learning 11

MAKT: Multichannel Attention Networks based Knowledge Tracin...

引用

11th IEEE International Conference on Teaching, Assessment and Learning for engineering, TALE 2022

作者： Jiang, Xuyang Ouyang, Yuanxin Liu, Zhuang Rong, Wenge Xiong, Zhang Beihang University State Key Laboratory of Software Development Environment Beijing China Beihang University Engineering Research Center of Advanced Computer Application Technology Ministry of Education Beijing China

ISBN: (纸本)9781665491174

As an effective and emerging component of intelligent education, Knowledge Tracing(KT) achieves the combination of artificial intelligence and individualized learning, whose aim is to assess students' mastery of knowledge concepts and assist in developing learning plans. Several existing KT models either use concepts sequence as input and evaluate students' knowledge state or treat exercise as input to predict students' future performance. In this paper, we introduce a constraint factor to extract concepts' and exercises' relation matrix, design three methods in representation learning, and propose a Multichannel Attention Networks based KT model(MAKT). Specifically, we restrict the co-occurrence relationship within a time window to extract the relation matrix and then train their representations via graph generative learning, graph contrastive learning, and matrix decomposition, respectively. In MAKT, a sliding window is implemented by multichannel where input sequence is sequentially lagged in turn by one position and attention mechanism is applied. We conduct experiments on several benchmark datasets and demonstrate that MAKT with concepts' and exercises' representation trained by matrix decomposition outperforms state-of-the-art models. © 2022 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Intelligent Daycare: Enhancing Child Safety with IoT and Machine Learning Innovations

Intelligent Daycare: Enhancing Child Safety with IoT and Mac...

引用

International Conference on Communication and Electronics systems (ICCES)

作者： Amisha Prathyanga Pasindu Shyaminda Pasan Chamikara Sachin Lakshan Samantha Thelijjagoda Dharshana Kasthurirathna Department of Software Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Computer Systems Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (数字)9798350377972

ISBN: (纸本)9798350377989

Child safety and well-being in daycare settings are important, thus it is vital that the persons in charge be attentive to them. This research tries to solve the problem by introducing a smart and detailed monitoring system that utilizes new technology to enhance safety and support caretakers. The system has various innovative features, such as child missing detection, behavior and facial expression analysis, cry analysis and categorization, and fall detection. Using high-resolution cameras and on-device Edge AI capabilities, it ensures real-time surveillance of children's activities while protecting privacy. The approach integrates behavior and facial expression analysis to assess emotional states, cry recognition to discover childcare needs, as well as a useful fall detection system that can tell the difference between falls and other movements. All these parts synergize to hand over the necessary information to the caregivers on time and in a way that they can act upon. The quantitative experiments in real-time childcare centers show high accuracy through all the components, attesting to the system's reliability and durability. This research has important significance in improving the safety and the frequency response in daycare centers because it gives caregivers automated tools to quickly address the needs of children. While promising, the system has drawbacks, such as potential biases in data models and a reliance on ideal environmental circumstances. Future work intends to improve flexibility across varied daycare situations, improve accuracy through larger datasets, and investigate ethical frameworks for wider application.

关键词： Privacy Ethics Accuracy Surveillance Machine learning Edge AI Real-time systems Safety Time factors Fall detection

来源：评论

学校读者我要写书评

暂无评论

Exploiting Inter-sample and Inter-feature Relations in Dataset Distillation

Exploiting Inter-sample and Inter-feature Relations in Datas...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Wenxiao Deng Wenbin Li Tianyu Ding Lei Wang Hongguang Zhang Kuihua Huang Jing Huo Yang Gao State Key Laboratory for Novel Software Technology Nanjina University China Microsoft Corporation USA University of Wollongong Australia Systems Engineering Institute AMS China School of Systems Engineering University of Defense Technology China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Dataset distillation has emerged as a promising approach in deep learning, enabling efficient training with small synthetic datasets derived from larger real ones. Particularly, distribution matching-based distillation methods attract attention thanks to its effectiveness and low computational cost. However, these methods face two primary limitations: the dispersed feature distribution within the same class in synthetic datasets, reducing class discrim-ination, and an exclusive focus on mean feature consistency, lacking precision and comprehensiveness. To address these challenges, we introduce two novel constraints: a class centralization constraint and a covariance matching constraint. The class centralization constraint aims to enhance class discrimination by more closely clustering samples within classes. The covariance matching constraint seeks to achieve more accurate feature distribution matching between real and synthetic datasets through local feature covariance matrices, particularly beneficial when sample sizes are much smaller than the number of features. Experiments demonstrate notable improvements with these constraints, yielding performance boosts of up to 6.6% on CIFAR10, 2.9% on SVHN, 2.5% on CIFAR100, and 2.5% on TinyImageNet, compared to the state-of-the-art relevant methods. In addition, our method maintains robust performance in cross-architecture settings, with a maximum performance drop of 1.7% on four architectures. Code is avail-able at https://***/VincenDen/IID.

关键词： Training Deep learning Computer vision Face recognition Focusing Computer architecture Computational efficiency

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：