检索结果-内蒙古大学图书馆

InvMetrics: Measuring Privacy Risks for Split Model-Based Customer Behavior Analysis

IEEE Transactions on Consumer Electronics 2024年第1期70卷 4168-4177页

作者： Deng, Ruijun Hu, Shijing Lin, Junxiong Yang, Jirui Lu, Zhihui Wu, Jie Huang, Shih-Chia Duan, Qiang Fudan University Sch. of Comp. Science and the Engineering Research Center of Cyber Security Auditing and Monitoring Ministry of Education Shanghai200433 China Fudan University School of Computer Science Shanghai200433 China Shanghai Blockchain Engineering Research Center Shanghai200433 China National Taipei University of Technology Department of Electronic Engineering Taipei City10608 Taiwan Pennsylvania State University Information Sciences and Technology Department AbingtonPA19001 United States

Mobile Edge Computing (MEC) has great potential to facilitate cheap and fast customer behavior analysis (CBA). Model splitting, widely adopted in collaborative learning of MEC, partitions the CBA models between the customer device and the edge server in a layer-wise manner to support efficient distributed learning. However, the split-model architecture (SMA) is vulnerable to data reconstruction attacks for privacy leakage in intermediate data, of which the risk measurements remain unexplored. In this paper, we propose a privacy risk measurement framework, called InvMetrics, for split model-based CBA systems, which assess the degree of privacy leakage from both the CBA owners' and the regulators' perspectives. For CBA owners, we propose a privacy metric, Distance Loss (DLoss), based on distance correlation, which is computationally efficient, and thus eligible for being deployed on the customers' devices. For third-party evaluators, we propose Uncertainty Loss (ULoss) based on entropy, which can measure privacy risk without accessing raw data. Evaluation results on three CBA datasets and one image dataset demonstrate that InvMetrics framework with DLoss and ULoss can accurately measure privacy risk and is more efficient than the state-of-the-art. © 1975-2011 IEEE.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Implementing Machine Learning Algorithms to Indentify Distributed Denial-of-Service Attacks 7

Implementing Machine Learning Algorithms to Indentify Distri...

引用

7th International Conference on Image Information Processing, ICIIP 2023

作者： Mehra, Ankush Singh, Gurpreet Badotra, Sumit Kaur, Balwinder Verma, Amit Lovely Professional University Department of Computer Science And Engineering Punjab Phagwara India Bennett University School of Computer Science Engineering And Technology Greater Noida India University Center For Research And Development Chandigarh University Department of Computer Science And Engineering Mohali Gharuan India

ISBN: (纸本)9798350371406

An Internet server, service, or network may be the subject of a distributed denial-of-service (DDoS) assault, in which the attacker attempts to interrupt regular traffic by flooding the target with an excessive amount of data requests. Network security has been severely compromised as a result. We choose the vast majority of network parameters to characterize the traffic in order to get a complete picture of it. As a further step toward lowering the detection time complexity, we employ the PCA approach to compress the features' dimensions. Using principal component analysis (PCA), we can save much of the original data while drastically cutting down on forecast time. After data dimensionality reduction, the RNN is used to train and get a detection model. In comparison to other approaches for detecting DDoS assaults, PCA-RNN performs much better on the real-world dataset, as shown by the evaluation results. © 2023 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Advancing Network Anomaly Detection: Comparative Analysis of Machine Learning Models

Advancing Network Anomaly Detection: Comparative Analysis of...

引用

International Conference on. Cryptology and Network Security with Machine Learning, ICCNSML 2023

作者： Pandey, Rashmikiran Pandey, Mrinal Nazarov, Alexey Department of Radio Engineering and Cybernetics Moscow Institute of Physics and Technology Moscow Russia Federal Research Center Computer Science and Control Russian Academy of Science Moscow Russia

ISBN: (纸本)9789819706402

In the rapidly evolving realm of cyber-security, the detection of network anomalies serves as a pivotal line of defense against a myriad of malicious activities and cyberthreats. This research undertakes the task of enhancing the accuracy and efficacy of network anomaly detection by employing a comparative analysis of various individual machine learning models. The study delves into the performance of distinct models, including Random Forest, Gradient Boosting, AdaBoost, neural networks, and SVM, meticulously scrutinizing their capabilities in detecting network anomalies. The crux of this study lies in its meticulous evaluation of each individual model on the revered NSL-KDD dataset—an established benchmark within the field of network intrusion detection. Through a systematic blend of rigorous mathematical frameworks, precise model implementations, and comprehensive experimental assessments, this research offers a deep understanding of the inner workings of each algorithm. The pivotal aspect of this study revolves around the comprehensive comparative analysis of these standalone models. Going beyond the mere quantifica-tion of accuracy, the exploration delves into aspects of precision, recall, F1-score, and more, shedding light on their diverse facets of performance. With achieved accuracies of 99.2419% for Random Forest, 99.5197% for Gradient Boosting, 86.6044% for AdaBoost, 84.00% for neural networks, and 87.00% for SVM, this research underlines the distinctive attributes and potential of each model in the context of network anomaly detection. As the study unravels the distinct strengths and limitations of each model, it contributes to the broader landscape of cyber-security by providing insights into the efficacy of individual machine learning approaches. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Data Fusion:A Fuzzy AHP Approach for Open Issues

引用

computers, Materials & Continua 2023年第12期77卷 2899-2914页

作者： Vinay Kukreja Asha Abraham K.Kalaiselvi K.Deepa Thilak Shanmugasundaram Hariharan Shih-Yu Chen Chitkara University Institute of Engineering and Technology Chitkara UniversityPunjab140401India Department of Networking and Communications SRM Institute of Science and TechnologyKattankulathurChengalpattuTamil Nadu603203India Department of Networking and Communications Faculty of Engineering and TechnologySRM Institute of Science and TechnologyKattankulathurChengalpattuTamil Nadu603203India Department of Computer Science and Engineering Vardhaman College of EngineeringHyderabad501218India Department of Computer Science and Information Engineering National Yunlin University of Science and TechnologyYunlin64002Taiwan Intelligence Recognition Industry Service Research Center National Yunlin University of Science and TechnologyYunlin64002Taiwan

Data fusion generates fused data by combining multiple sources,resulting in information that is more consistent,accurate,and useful than any individual source and more reliable and consistent than the raw original data,which are often imperfect,inconsistent,complex,and *** data fusion methods like probabilistic fusion,set-based fusion,and evidential belief reasoning fusion methods are computationally complex and require accurate classification and proper handling of raw *** fusion is the process of integrating multiple data *** filtering means examining a dataset to exclude,rearrange,or apportion data according to the *** sensors generate a large amount of data,requiring the development of machine learning(ML)algorithms to overcome the challenges of traditional *** advancement in hardware acceleration and the abundance of data from various sensors have led to the development of machine learning(ML)algorithms,expected to address the limitations of traditional ***,many open issues still exist as machine learning algorithms are used for data *** the literature,nine issues have been identified irrespective of any *** decision-makers should pay attention to these issues as data fusion becomes more applicable and successful.A fuzzy analytical hierarchical process(FAHP)enables us to handle these *** helps to get the weights for each corresponding issue and rank issues based on these calculated *** most significant issue identified is the lack of deep learning models used for data fusion that improve accuracy and learning quality weighted *** least significant one is the cross-domain multimodal data fusion weighted 0.076 because the whole semantic knowledge for multimodal data cannot be captured.

关键词： Signal level fusion feature level fusion decision level fusion fuzzy hierarchical process machine learning

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Shop Scheduling Using Space-Cooperation Multi-Objective Optimization

IEEE Transactions on Sustainable Computing

引用

IEEE Transactions on Sustainable Computing 2024年第3期10卷 601-615页

作者： Ding, Jiepin Xia, Jun Yang, Yaning Zhou, Junlong Chen, Mingsong Li, Keqin East China Normal University MoE Engineering Research Center of Software/Hardware Co-Design Technology and Application Shanghai200062 China Ningxia Normal University School of Physics and Electronic Information Engineering Guyuan756500 China Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China State University of New York Department of Computer Science New PaltzNY12561 United States

Since Industry 5.0 emphasizes that manufacturing enterprises should raise awareness of social contribution to achieve sustainable development, more and more meta-heuristic algorithms are investigated to save energy in manufacturing systems. Although non-dominated sorting-based meta-heuristics have been recognized as promising multi-objective optimization methods for solving the energy-efficient flexible job shop scheduling problem (EFJSP), it is hard to guarantee the quality of the Pareto front (e.g., total energy consumption, makespan) due to the lack of population diversity. This is mainly because an improper individual comparison inevitably reduces population diversity, thus limiting exploration and exploitation abilities during population updates. To achieve efficient population evolution, this paper introduces a novel space-cooperation multi-objective optimization (SCMO) method that can effectively solve EFJSP to obtain scheduling schemes with better trade-offs. By cooperatively evaluating the similarity among individuals in both the decision space and objective space, we propose a space-cooperation population update method based on a three-vector representation that can accurately eliminate repetitive individuals to derive higher-quality Pareto solutions. To further improve search efficiency, we propose a difference-driven local search, which selectively changes the positions of operations with higher differences to search for neighbors effectively. Based on the Taguchi method, we conduct experiments to obtain a suitable parameter combination of SCMO. Comprehensive experimental results show that, compared to state-of-the-art methods, our SCMO method achieves the highest HV and NR and the lowest IGD, with an average of 0.990, 0.952, and 0.001, respectively. Meanwhile, compared to traditional local search approaches, our difference-driven local search obtains twice the HV on instance Mk12 and reduces the solving time from 1521s to 475s. © 2016 IEEE.

关键词： Job shop scheduling

来源：评论

学校读者我要写书评

暂无评论

IoT-Based Intelligent Energy Management for EV Charging Stations

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2024年第11期51卷 1853-1861页

作者： Dasi, Swathi Bondalapati, Swarupa Rani Subbaraju, Mummidi P. Nimma, Divya Jangir, Pradeep Reddy, R. Vijaya Kumar Zareena, N. Electronics and Communication Engineering Department Prasad V. Potluri Siddhartha Institute of Technology Andhra Pradesh Vijayawada India Electrical and Electronics Engineering Department Velagapudi Ramakrishna Siddhartha Engineering College Andhra Pradesh Vijayawada India Electrical and Electronics Engineering Department Aditya University Andhra Pradesh Surampalem India University of Southern Mississippi United States Biosciences Department Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India associated with Applied Science Research Center Applied Science Private University Amman Jordan. Computer Science and Engineering Department Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Computer Science and Engineering Department R.V.R. & J. C. College of Engineering Guntur India

The electronics panels and controllers used in electric vehicle (EV) charging stations need to function securely and optimally in countries such as India, where the external temperature remains high for a significant part of the year. This study is the first to use a solar-battery storage integrated switchable glazing architecture to supply HVAC (heating, ventilation, and air conditioning) in the control rooms of electric vehicle charging stations throughout the day. The EV charging station has been equipped with a rooftop-mounted solar PV source as part of an initiative to promote renewable energy and sustainable forms of mobility. The utilization of a vanadium redox flow battery (VRFB) by the system ensures energy security through the provision of a durable solution for storing energy over an extended period of time. A smart scheduling system utilizing IoT technology was demonstrated to effectively meet the glazing load need of buildings in real-time, taking into account dynamic climatic conditions. This system incorporates solar PV, VRFB storage, and the neighborhood power grid. The efficiency of the suggested method was validated using four separate transitory scenarios: sunny, intermittently cloudy, prolongedly cloudy, and low solar radiation with frequent grid outages. Due to its versatility to be applied in various situations, the suggested method has the potential to greatly enhance capacity. © (2024), (International Association of Engineers). All rights reserved.

关键词： Air conditioning

来源：评论

学校读者我要写书评

暂无评论

A Detailed Structured Monitoting System for ICU Patient Mortality rate by using AI Algorithm 5

A Detailed Structured Monitoting System for ICU Patient Mort...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Joshi, Shivani Kumar, Rajiv Rai, Vipin Dwivedi, Avinash Tripathi, Vikash Chandra G L Bajaj Institute of Technology and Management Department of Computer Science and Engineering Greater Noida India G L Bajaj Institute of Technology and Management Nvidia Ai and Learning & Research Center Department of Applied Computational Science and Engineering Greater Noida India Galgotias University Department of Computer Science & Engineering Greater Noida India

ISBN: (纸本)9798350383522

The complexity and seriousness of diseases in ICU patients, though, make it difficult for medical practitioners to identify high-risk patients who may face irreversible harm. With ANN (Artificial Neural Network), this study will provide an ICU admission prediction model to help identify high-risk patients at an earlier stage. After collecting and analyzing extensive data from various perspectives including demographics, medical history, vital signs, test results and treatment modalities, exploratory data analysis has been conducted. These are used as markers on how statistical techniques and machine learning algorithms can be used to predict mortality among critically ill patients. Consequently, the parameters are designed within the ANN model to create a predictive model that will be able to effectively classify those at higher risk. Advanced machine learning algorithms together with modern tools such as deep learning techniques will aid in the prompt analysis of complex information for accurate forecasts by this predictive model. The ANN model's training set will include a large dataset of ICU patients so that it can become reliable and valid. This makes the predictive model developed capable of accurately identifying high risk cases expeditiously © 2024 IEEE.

关键词： accuracy Artificial Neural Networks (ANN) exploratory data analysis high-risk patients ICU patient admission medical technology mortality outcomes periodic updates prediction model

来源：评论

学校读者我要写书评

暂无评论

CSE-NER: A Category Semantic Enhanced Multi-Task Learning Framework for Named Entity Recognition 5

CSE-NER: A Category Semantic Enhanced Multi-Task Learning Fr...

引用

5th International Seminar on Artificial Intelligence, Networking and Information Technology, AINIT 2024

作者： Dai, Dongbo Zhang, Guangjie Li, Shengzhou Song, Na Xu, Yubao Tang, Zheng Zhang, Huiran School of Computer Engineering and Science Shanghai University Shanghai China University of Tsukuba Department of Computer Science Tsukuba Japan Shanghai University Research Center of Nanoscience and Nanotechnology Shanghai China University of Toyama Faculty of Engineering Toyama Japan

ISBN: (纸本)9798350385557

Named Entity Recognition (NER) is a fundamental and crucial task in natural language processing. Currently, the use of large pre-trained models has become the mainstream for NER. However, when there is a distributional difference between pre-training data and downstream task data, such extensive prior training may lead to issues like 'knowledge hallucination' or 'domain shift' in the downstream task. To address this, we propose a Category Semantic Enhanced framework for Named Entity Recognition (CSE-NER) in this paper. By introducing more downstream task information during the fine-tuning phase, we enhance the model's adaptability. Specifically, we incorporate a Category Semantic Embedding layer, providing category semantic information distinct from context embeddings. Additionally, we introduce an auxiliary task, Entity Type Classification, to help the model effectively utilize the added category semantic information. Experiments on five datasets demonstrate the effectiveness of our proposed framework, outperforming various state-of-the-art methods. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Cross-View Meets Diffusion: Aerial Image Synthesis with Geometry and Text Guidance

Cross-View Meets Diffusion: Aerial Image Synthesis with Geom...

引用

2025 IEEE/CVF Winter Conference on Applications of computer vision, WACV 2025

作者： Arrabi, Ahmad Zhang, Xiaohan Sultani, Waqas Chen, Chen Wshah, Safwan University of Vermont Vermont Artificial Intelligence Lab Department of Computer Science United States Information Technology University Intelligent Machines Lab Pakistan University of Central Florida Center for Research in Computer Vision United States

ISBN: (纸本)9798331510831

Aerial imagery analysis is critical for many research fields. However, obtaining frequent high-quality aerial images is not always accessible due to its high effort and cost requirements. One solution is to use the Ground-to-Aerial (G2A) technique to synthesize aerial images from easily collectible ground images. However, G2A is rarely studied, because of its challenges, including but not limited to, the drastic view changes, occlusion, and range of visibil-ity. In this paper, we present a novel Geometric Preserving Ground-to-Aerial (G2A) image synthesis (GPG2A) model that can generate realistic aerial images from ground images. GPG2A consists of two stages. The first stage predicts the Bird's Eye View (BEV) segmentation (referred to as the BEV layout map) from the ground image. The second stage synthesizes the aerial image from the predicted BEV layout map and text descriptions of the ground image. To train our model, we present a new multimodal cross-view dataset, namely VIGORv2, built upon VIGOR [64] with newly collected aerial images, maps, and text descriptions. Our extensive experiments illustrate that GPG2A synthesizes better geometry-preserved aerial images than existing models. We also present two applications, data augmentation for cross-view geo-localization and sketch-based region search, to further verify the effectiveness of our GPG2A. The code and dataset are available at https://***/AhmadArrabi/GPG2A. © 2025 IEEE.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

Thermo-hydro-poro-mechanical responses of a reservoir-induced landslide tracked by high-resolution fiber optic sensing nerves

引用

Journal of Rock Mechanics and Geotechnical engineering 2024年第3期16卷 1018-1032页

作者： Xiao Ye Hong-Hu Zhu Gang Cheng Hua-Fu Pei Bin Shi Luca Schenato Alessandro Pasuto School of Earth Sciences and Engineering Nanjing UniversityNanjing210023China School of Computer Science North China Institute of Science and Technology(National Safety Training Center of Coal Mines)Beijing101601China State Key Lab of Coastal and Offshore Engineering Department of Geotechnical EngineeringDalian University of TechnologyDalian116024China National Research Council-Research Institute for Geo-Hydrological Protection(CNR-IRPI) Padova35127Italy Department of Information Engineering University of PadovaPadova35131Italy

Thermo-poro-mechanical responses along sliding zone/surface have been extensively ***,it has not been recognized that the potential contribution of other crucial engineering geological interfaces beyond the slip surface to progressive ***,we aim to investigate the subsurface multiphysics of reservoir landslides under two extreme hydrologic conditions(*** and dry),particularly within sliding *** on ultra-weak fiber Bragg grating(UWFBG)technology,we employ specialpurpose fiber optic sensing cables that can be implanted into boreholes as“nerves of the Earth”to collect data on soil temperature,water content,pore water pressure,and *** Xinpu landslide in the middle reach of the Three Gorges Reservoir Area in China was selected as a case study to establish a paradigm for in situ thermo-hydro-poro-mechanical *** UWFBG-based sensing cables were vertically buried in a 31 m-deep borehole at the foot of the landslide,with a resolution of 1 m except for the pressure *** reported field measurements covering the period 2021 and 2022 and produced the spatiotemporal profiles throughout the *** show that wet years are more likely to motivate landslide motions than dry *** annual thermally active layer of the landslide has a critical depth of roughly 9 m and might move downward in warmer *** dynamic groundwater table is located at depths of 9e15 m,where the peaked strain undergoes a periodical response of leap and withdrawal to annual hydrometeorological *** interface behaviors may support the interpretation of the contribution of reservoir regulation to slope stability,allowing us to correlate them to local damage events and potential global *** paper also offers a natural framework for interpreting thermo-hydro-poro-mechanical signatures from creeping reservoir bank slopes,which may form the basis for a landslide monitoring and early warning system.

关键词： Reservoir landslide Thermo-hydro-poro-mechanical response Ultra-weak fiber bragg grating(UWFBG) subsurface evolution engineering geological interface Geotechnical monitoring

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：