检索结果-内蒙古大学图书馆

Communication, Security and Artificial Intelligence (ICCSAI), International Conference on

作者： Dinesh Rajassekharan V Ramachandran Dilip Kumar Sharma Thirumoorthy Palanisamy Y. Varatharaj Myilsam Ramesh Chandra Poonia Faculty of Computer Science Peninsula College Malaysia Department of Computer Science and Engineering GITAM School of Computing GITAM Deemed to be University Bengaluru India Department of Mathematics Jaypee University of Engineering and Technology Guna Madhya Pradesh India Department of Computer Science and Engineering Nandha Engineering College Erode Tamil Nadu India Department of Electrical and Electronics Engineering V.S.B College of Engineering Technical Campus Coimbatore Tamil Nadu India Department of Computer Science CHRIST (Deemed to be University) Delhi-NCR Ghaziabad Uttar Pradesh India

Wireless Sensor Networks (WSNs) are widely used in diverse applications due to their cost-effectiveness and versatility. However, they face substantial difficulties because of their innate resource constraints and susceptibility to security attacks. A possible method to improve the security of WSNs is clustering-based intrusion detection and responding mechanisms. An in-depth analysis of the clustering-based intrusion detection and response method for WSNs is presented in this study. The suggested method efficiently uses data mining and machine learning techniques to identify unusual behaviour and probable intrusions. The system effectively analyses data inside clusters by grouping Sensor Nodes (SN) into clusters, allowing it to differentiate between legitimate patterns and insecure activity. The network may respond promptly to identified breaches and react to the responsive mechanism, which reduces their impact and protects network integrity. The proposed Mathematically Modified Gene Populated Spectral Clustering Based Intrusion Detection System and Responsive Mechanism (MMMMGPSC-IDS-RM) is compared with existing state-of-art techniques, and MMMMGPSC-IDS-RM outperforms with the highest detection rate of 96%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TabADM: Unsupervised Tabular Anomaly Detection with Diffusion Models

arXiv

引用

arXiv 2023年

作者： Zamberg, Guy Salhov, Moshe Lindenbaum, Ofir Averbuch, Amir School of Electrical Engineering Tel Aviv University Israel School of Computer Science Tel Aviv University Israel Faculty of Engineering Bar-Ilan University Israel Playtika LTD St. Herzllya Israel

Tables are an abundant form of data with use cases across all scientific fields. Real-world datasets often contain anomalous samples that can negatively affect downstream analysis. In this work, we only assume access to contaminated data and present a diffusion-based probabilistic model effective for unsupervised anomaly detection. Our model is trained to learn the density of normal samples by utilizing a unique rejection scheme to attenuate the influence of anomalies on the density estimation. At inference, we identify anomalies as samples in low-density regions. We use real data to demonstrate that our method improves detection capabilities over baselines. Furthermore, our method is relatively stable to the dimension of the data and does not require extensive hyperparameter tuning. © 2023, CC BY.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Optimal Privacy Preserving in Wireless Federated Learning Over Mobile Edge Computing

Optimal Privacy Preserving in Wireless Federated Learning Ov...

引用

IEEE International Conference on Communications (ICC)

作者： Hai M. Nguyen Nam H. Chu Diep N. Nguyen Dinh Thai Hoang Minh Hoàng Hà Eryk Dutkiewicz School of Electrical and Data Engineering University of Technology Sydney Australia JTIRC VNU University of Engineering and Technology Vietnam National University Hanoi Vietnam ORLab Faculty of Computer Science Phenikaa University Hanoi Vietnam

Federated Learning (FL) with quantization and deliberately added noise over wireless networks is a promising approach to preserve the user differential privacy while reducing the wireless resources. Specifically, an FL learning process can be fused with quantized Binomial mechanism-based updates contributed by multiple users to reduce the communication overhead/cost as well as to protect the privacy of participating users. However, the optimization of wireless transmission and quantization parameters (e.g., transmit power, bandwidth, and quantization bits) as well as the added noise while guaranteeing the privacy requirement and the performance of the learned FL model remains an open and challenging problem. In this paper, we aim to jointly optimize the level of quantization, parameters of the Binomial mechanism, and devices' transmit powers to minimize the training time under the constraints of the wireless networks. The resulting optimization turns out to be a Mixed Integer Non-linear Programming (MINLP) problem, which is known to be NP-hard. To tackle it, we transform this MINLP problem into a new problem whose solutions are proved to be the optimal solutions of the original one. We then propose an approximate algorithm that can solve the transformed problem with an arbitrary relative error guarantee. Intensive simulations show that for the same wireless resources the proposed approach achieves the highest accuracy, close to that of the conventional FL with no quantization and no noise added. This suggests the faster convergence/training time of the proposed wireless FL framework while optimally preserving users' privacy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Influence of forecast control of heat supply on energy savings

Influence of forecast control of heat supply on energy savin...

引用

International Multidisciplinary Conference on computer and Energy science (SpliTech)

作者： Tomasz Cholewa Alicja Siuta-Olcha Andrzej Smolarz Piotr Muryjas Piotr Wolszczak Ł ukasz Guz Faculty of Environmental Engineering Lublin University of Technology Lublin Poland Faculty of Electrical Engineering and Computer Science Lublin University of Technology Lublin Poland Faculty of Mechanical Engineering Lublin University of Technology Lublin Poland

ISBN: (纸本)9781665488280

Nowadays, the use of new control techniques of heating systems in existing and new buildings is a very important topic in the light of planed decarbonization of building sector, since the energy efficiency may be significantly increased. One of such solutions may be the forecast control of heat supply for heating, especially if it is easy applicable in existing buildings. This paper shows the influence of forecast control of heat supply for heating on the level of energy consumption based on field research. The building being the subject of case study is a residential building with a traditional heating installation (with vertical risers and convective radiators supplied from one side with the heating medium 80/60°C at outdoor temperature equal to −20°C. The field research covers the period before and after the installation of the forecast control of heating system. The energy savings achieved due to the use of forecast control were above 50%.

关键词： Heating systems Energy consumption HVAC Weather forecasting Low-carbon economy Control systems Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Research on the Structural Design and Basin Characteristics of Pilot Electromagnetic Valves for New Energy Wastewater Treatment Systems

Research on the Structural Design and Basin Characteristics ...

引用

Advanced electrical and Energy Systems (AEES), International Conference on

作者： Na Wang Yueyang Dong Xiaofei Zhen Ruonan Jiao Haoran Fu Yuying Chen School of Mechatronic Engineering Lanzhou Jiaotong University Lanzhou China School of New Energy and Power Engineering Lanzhou Jiaotong University Lanzhou China Faculty of Engineering Computer and Mathematical Sciences The University of Adelaide Adelaide Australia Academy of Electrical and Automation Engineering Shandong University of Science and Technology Qingdao China

ISBN: (数字)9798331517724

ISBN: (纸本)9798331517731

Pilot-operated solenoid valves have the advantage of fast response times and can meet high pressure and large diameter requirements through their structural characteristics, making them widely used in various fields. The pilot-operated solenoid valve discussed in this article is applied in a new energy system a sewage treatment system based on solar photovoltaic and solar thermal technology. The pilot-operated solenoid valve designed in this paper controls the flow rate and velocity of the sewage. This article uses Fluent to calculate the flow coefficient of pilot-type solenoid valves at various openings, exploring the flow characteristics of these valves. Based on computational fluid dynamics, simulations of the cavitation flow field were performed for pilot-type solenoid valve models at different openings, resulting in pressure contour plots and liquid velocity vector diagrams within the pilot valve. The study investigated the effects of the valve opening and the pressure difference at the inlet and outlet on the cavitation conditions within the valve. This provides a foundation for subsequent analysis of the vibration characteristics and structural optimization of solenoid pilot valves. The results indicate that negative pressure occurs within the solenoid pilot valve at all openings, leading to cavitation phenomena. When the opening is greater than or equal to 0.5, significant negative pressure appears near the valve port of the valve sleeve, with more pronounced cavitation phenomena, which can easily lead to cavitation bubbles and deformation.

关键词： Vibrations Analytical models Deformation Computational modeling Valves Vectors Time factors Solenoids Wastewater treatment Optimization

来源：评论

学校读者我要写书评

暂无评论

Visual recognition of wheel hubs with convolutional neural network

Visual recognition of wheel hubs with convolutional neural n...

引用

Consumer Electronics and computer engineering (ICCECE), 2021 IEEE International Conference on

作者： Yining Dai Zaojun Fang Caiming Zhong Faculty of Electrical Engineering and Computer Science Ningbo University NingBo Zhejiang China Zhejiang Key Laboratory of Robotics and Intelligent Manufacturing Equipment Technology Ningbo Institute of Materials Technology & Engineering Chinese Academy of Sciences

The traditional recognition methods of wheel hubs are mainly based on extracted feature matching. In practical production, their accuracy, robustness and processing speed are usually greatly affected. To overcome these problems, this paper proposes a recognition method based on convolutional neural network. The basic steps include two parts: wheel image pre-processing and wheel model classification. The image processing method, mainly using the detection algorithm of hough circles, obtains the center coordinates and radius of the wheel. Then it maps the ring-shaped wheel in right-angle coordinates to polar coordinates by the center coordinates and radius. This stepcan extract the ring-shaped feature information of the wheel image and reduce the influence generated by redundant features. Then a network architecture with an improved Resnet is designed to classify the wheel models. Finally, the wheel model recognition algorithm is evaluated, and the effectiveness of the method is verified through the comparison experiments of SVM, KNN and other models. The experiments show that the recognition accuracy can reach about 99.8% for 10 kinds of wheels.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A new framework to protect privacy of location from malicious applications 8

A new framework to protect privacy of location from maliciou...

引用

8th International Conference on Computing for Sustainable Global Development, INDIACom 2021

作者： Alharbi, Awad Saleh Halikias, George Abi Sen, Adnan Ahmed Yamin, Mohammad School of Mathematics Computer Science and Engineering Dept. of Electrical and Electronic Engg. London United Kingdom Islamic University Faculty of Computer and Information Systems Al-Madinah Saudi Arabia Research School of Computer Science Australian National University Canberra Australia

ISBN: (纸本)9789380544434

Location-based applications have become very popular in recent years, especially during the ongoing COVID-19 pandemic. The pandemic has intensified the trend towards applications for electronic purchases and delivery services, to provide customers the facility of buying from anywhere and anytime, with great ease. However, there are some issues with these kind of purchases and delivery services. In particular, the data collected by these applications has the potential of having their security and privacy breached. Thus, trust of the service provider cannot be taken for granted. In fact, the service provider may prove to be a source of real danger to the privacy of users, especially if the service provider itself is a malicious party. Thus, it is difficult for the user to determine which applications can be trusted, and who to share their home or business location with. To solve this problem, in this research, we propose a new central platform that enables users to gather all of their (main) locations and control access to these locations in one place. Then the user can share them with other applications, such as link with hash-code included in a quick response (QR) barcode without the need to save their data in any application database. Moreover, the QR-code will be deactivated once it is used by the service provider, after the order is delivered. Therefore, the service provider will not be able to exploit the data stored in it, which means greater protection for the user's privacy. The system will offer other features for the user and the service provider as well. We have also implemented this system in a real manner to confirm its ability to improve the level of service in electronic purchase applications, in addition to improving the level of privacy of users' data. © 2021 Bharati Vidyapeeth, New Delhi. Copy Right in Bulk will be transferred to IEEE by Bharati Vidyapeeth.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Sparse Actuator Scheduling for Discrete-Time Linear Dynamical Systems

Sparse Actuator Scheduling for Discrete-Time Linear Dynamica...

引用

Indian Control Conference (ICC)

作者： Krishna Praveen V. S. Kondapi Chandrasekhar Sriram Geethu Joseph Chandra R. Murthy Dept. of ECE Indian Institute of Science (IISc) Bangalore India Dept. of ECE IISc Texas Instruments India Pvt. Ltd. Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft CD Netherlands

ISBN: (数字)9798331517212

ISBN: (纸本)9798331517229

We consider the control of discrete-time linear dynamical systems using sparse inputs where we limit the number of active actuators at every time step. We develop an algorithm for determining a sparse actuator schedule that ensures the existence of a sparse control input sequence, following the schedule, that takes the system from any given initial state to any desired final state. Since such an actuator schedule is not unique, we look for a schedule that minimizes the energy of sparse inputs. For this, we optimize the trace of the inverse of the resulting controllability Gramian, which is an approximate measure of the average energy of the inputs. We present a greedy algorithm along with its theoretical guarantees. Finally, we empirically show that our greedy algorithm ensures the controllability of the linear system with a small number of active actuators per time step without a significant average energy expenditure compared to the fully actuated system.

关键词： Greedy algorithms Linear systems Actuators Schedules Scheduling algorithms Heuristic algorithms Energy measurement Controllability Minimization Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

A Natural Gas Consumption Forecasting System for Continual Learning Scenarios based on Hoeffding Trees with Change Point Detection Mechanism

arXiv

引用

arXiv 2023年

作者： Svoboda, Radek Basterrech, Sebastián Kozal, Jędrzej Platoš, Jan Woźniak, Michal Faculty of Electrical Engineering and Computer Science VŠB-Technical University of Ostrava 17. listopadu 2172/15 Ostrava70833 Czech Republic Department of Applied Mathematics and Computer Science Technical University of Denmark Kongens Lyngby Denmark Department of Systems and Computer Networks University of Science and Technology Wroclaw Poland

Forecasting natural gas consumption, considering seasonality and trends, is crucial in planning its supply and consumption and optimizing the cost of obtaining it, mainly by industrial entities. However, in times of threats to its supply, it is also a critical element that guarantees the supply of this raw material to meet individual consumers' needs, ensuring society's energy security. This article introduces a novel multistep forecasting of natural gas consumption with change point detection integration for model collection selection with continual learning capabilities using data stream processing. The performance of the forecasting models based on the proposed approach is evaluated in a complex real-world use case of natural gas consumption forecasting. Furthermore, the methodology generability was verified in an electricity load forecasting task. We employed Hoeffding tree predictors as forecasting models and the Pruned Exact Linear Time (PELT) algorithm for the change point detection procedure. The change point detection integration enables the selection of a different model collection for successive time frames. Thus, three model collection selection procedures are defined and evaluated for forecasting scenarios with various densities of detected change points. These models were compared with change point agnostic baseline approaches and deep learning models. Our experiments show that the proposed approach provides superior results to deep learning models for both datasets and that fewer change points result in a lower forecasting error regardless of the model collection selection procedure employed. © 2023, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Solar-Powered LVDC Nano-Grid with Smart FPGA-based Residential Power Switching Algorithm

引用

IEEE Access 2023年 1-1页

作者： Shanmugam, Leninisha Balasubramaniam, P.M. Shnain, Ammar Hameed Abdulkader, Rasheed Alharbi, Meshal Pustokhin, Denis A. Pustokhina, Irina V. Mohammed, Sheik Sengan, Sudhakar School of Computer of Science and Engineering Vellore Institute of Technology Chennai Tamil Nadu India Department of Electrical and Electronics Engineering Sri Shakthi Institute of Engineering and Technology Coimbatore Tamil Nadu India Computer Technical Engineering Department The Islamic University Najaf Iraq Electrical Engineering Department King Faisal University Al Hofuf Saudi Arabia Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University Al-Kharj Saudi Arabia Department of Logistics and Marketing Financial University under the Government of the Russian Federation Moscow Russia Department of Entrepreneurship and Logistics Plekhanov Russian University of Economics Moscow Russia Faculty of Engineering Universiti Teknologi Brunei Brunei Darussalam Department of Computer Science and Engineering PSN College of Engineering and Technology Tirunelveli Tamil Nadu India

A Low Voltage Direct Current (LVDC) nano-grid opens new potentials for the electrification of isolated rural settlements, urban residential structures, and the existing grid infrastructure. This study introduces and examines the Power-Sharing Control (PSC) of a solar Photovoltaic (PV) system connected to a low-voltage DC nano-grid. Effective control and power management between the components of a planned LVDC nano-grid system are presented, as is the use of a PSC algorithm implemented on a Field Programmable Gate Array (FPGA). General simulation investigations are tested to analyse the system’s performance using the recommended controller. The proposed LVDC nano-grid idea is developed, and its hardware is assessed. The results of the hardware under different settings are shown and discussed. The proposed nano-grid model is implemented in matrix laboratory (MATLAB)-Simulink and has an FPGA-based Maximum Power Point Tracking (MPPT) controller and a central PSC algorithm;simulation studies are performed, and results are achieved. 100 W nano-grid hardware is set up and tested. Quantitative cost-benefit analyses of the LVDC nano-grid of the proposed controller are given. Author

关键词： DC-DC converters

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：