检索结果-内蒙古大学图书馆

IEEE/CVF Winter conference on Applications of Computer Vision (WACV)

作者： Ramachandra, Raghavendra Venkatesh, Sushma Norwegian Univ Sci & Technol NTNU Gjovik Norway AiBA AS Gjovik Norway

ISBN: (纸本)9798350318920;9798350318937

Biometric verification systems are deployed in various security-based access-control applications that require user-friendly and reliable person verification. Among the different biometric characteristics, fingervein biometrics have been extensively studied owing to their reliable verification performance. Furthermore, fingervein patterns reside inside the skin and are not visible outside;therefore, they possess inherent resistance to presentation attacks and degradation due to external factors. In this paper, we introduce a novel fingervein verification technique using a convolutional multihead attention network called VeinAtnNet. The proposed VeinAtnNet is designed to achieve light weight with a smaller number of learnable parameters while extracting discriminant information from both normal and enhanced fingervein images. The proposed VeinAtnNet was trained on the newly constructed fingervein dataset with 300 unique fingervein patterns that were captured in multiple sessions to obtain 92 samples per unique fingervein. Extensive experiments were performed on the newly collected dataset FV-300 and the publicly available FV-USM and FV-PolyU fingervein dataset. The performance of the proposed method was compared with five state-of-the-art fingervein verification systems, indicating the efficacy of the proposed VeinAtnNet.

关键词： Algorithms Algorithms and algorithms Applications Biometrics body pose face formulations gesture Machine learning architectures Smartphones / end user devices

来源：评论

学校读者我要写书评

暂无评论

Multi-beam Optical Beamformer PICs for LiDAR and RADAR Applications 24

Multi-beam Optical Beamformer PICs for LiDAR and RADAR Appli...

引用

24th International conference on Transparent Optical networks (ICTON)

作者： Ketzaki, Dimitra Maximidis, Ronis Kovaios, Stephanos Tsakiridis, Apostolos Moralis-Pegios, Miltiadis Pleros, Nikolaos Aristotle Univ Thessaloniki Ctr Interdisciplinary Res & Innovat Thessaloniki Greece Aristotle Univ Thessaloniki Dept Informat Thessaloniki Greece

ISBN: (纸本)9798350377330;9798350377323

.he optical beamformers that rely on Photonic Integrated Circuits (PICs) have emerged as highly reliable alternatives compared to the bulky and energy-hungry RF chains and mechanical steering systems. Stemming from the rapid penetration of PIC technologies into both the radiofrequency ( RF) and the free-space optics (FSO) application areas, Optical Multi-beam Beamformer network (OMBFN) architectures have been demonstrated as a solution to the inevitable increase of the radiating elements when a single antenna array is employed for the generation of multiple beams. So far, these architectures rely primarily on the adaptation of network solutions developed for RF implementation, most prevalent to be Butler or Blass matrices. These solutions, however, come with their disadvantages supporting either static beams distribution or preventing every beam from being generated and steered independently. In this work, we present the exploitation of the crossbar (Xbar)-based universal linear operator as an OMBFN, offering the independent generation and control of multiple simultaneous beams.

关键词： Optical Beam forming Cross-bar architecture multi-beam optical network

来源：评论

学校读者我要写书评

暂无评论

Hybrid Intrusion Detection System for Industrial control System

Hybrid Intrusion Detection System for Industrial Control Sys...

引用

World conference on Information systems for Business Management, ISBM 2023

作者： Raj, S. Aravinth Amritha, P.P. Sethumadhavan Seshadhri, Srinivasan TIFAC-CORE in Cyber Security Amrita School of Engineering Amrita Vishwa Vidyapeetham Coimbatore India Kalasalingam Academy of Research and Education Tamil Nadu Srivilliputhur India

ISBN: (纸本)9789819986118

With the rise in cyber-attacks and the prevalence of industrial control systems, network security has become a critical requirement for organizations operating in industrial environments. This paper addresses the need to enhance network security in Industrial control systems by utilizing Raspberry Pi as a power-efficient, low-cost. The organizations are to adapt their operations, including remote work and the reliance on Industrial control systems. This shift has increased the vulnerability to potential cyber-attacks. To mitigate these risks, it is essential to update and strengthen the security of the underlying network infrastructure. By deploying Raspberry Pi as a security component in a control system environment, we propose the implementation of critical security measures such as IDS. These components will help detect and prevent attacks targeting industrial networks. To evaluate the effectiveness of the proposed system, we have simulated types of common attacks encountered in industrial environments like Modbus attack, IMCP smurf attack, UDP reflection/amplification attack, and TCP RST refection attack. The performance of the Raspberry Pi and the security components are measured during these simulations. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： network security

来源：评论

学校读者我要写书评

暂无评论

Modular Neural network Policies for Learning In-flight Object Catching with a Robot Hand-Arm System

Modular Neural Network Policies for Learning In-flight Objec...

引用

IEEE/RSJ International conference on Intelligent Robots and systems (IROS)

作者： Hu, Wenbin Acero, Fernando Triantafyllidis, Eleftherios Liu, Zhaocheng Li, Zhibin Univ Edinburgh Sch Informat Edinburgh Scotland UCL Dept Comp Sci London England

ISBN: (纸本)9781665491907

We present a modular framework designed to enable a robot hand-arm system to learn how to catch flying objects, a task that requires fast, reactive, and accurately-timed robot motions. Our framework consists of five core modules: (i) an object state estimator that learns object trajectory prediction, (ii) a catching pose quality network that learns to score and rank object poses for catching, (iii) a reaching control policy trained to move the robot hand to pre-catch poses, (iv) a grasping control policy trained to perform soft catching motions for safe and robust grasping, and (v) a gating network trained to synthesize the actions given by the reaching and grasping policy. The former two modules are trained via supervised learning and the latter three use deep reinforcement learning in a simulated environment. We conduct extensive evaluations of our framework in simulation for each module and the integrated system, to demonstrate high success rates of in-flight catching and robustness to perturbations and sensory noise. Whilst only simple cylindrical and spherical objects are used for training, the integrated system shows successful generalization to a variety of household objects that are not used in training.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An Efficient Distributed Dispatching Vehicles Protocol for Intersection Traffic control 28th

An Efficient Distributed Dispatching Vehicles Protocol for I...

引用

28th International conference on Engineering of Complex Computer systems (ICECCS)

作者： Qi, Fang Wang, Rui Guan, Yong Song, Xiaoyu Capital Normal Univ Informat Engn Coll Beijing Peoples R China Portland State Univ ECE Dept Portland OR 97207 USA

ISBN: (纸本)9783031664557;9783031664564

Passing the intersection is a crucial traffic scenario in urban traffic network. Rapid development of vehicle technologies makes vehicles cross the intersection more efficiently. In this paper, we propose a protocol where vehicles can pass the intersection safely and efficiently at a 6-lane dual carriageway. To ensure the safety of the protocol, we formally model the protocol and verify some necessary properties using the tool Uppaal. To evaluate the performance of our protocol, we conduct extensive experiments. After analyzing experimental data, the average rate of time reduction in a circle is over 92%. The results demonstrate that our protocol is both efficient and effective.

关键词： urban traffic network intersection dispatch vehicles formal methods Uppaal

来源：评论

学校读者我要写书评

暂无评论

Optimal Graph Structure Based Short-Term Solar PV Power Forecasting Method Considering Surrounding Spatio-Temporal Correlations

引用

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS 2023年第1期59卷 345-357页

作者： Zhang, Meng Zhen, Zhao Liu, Nian Zhao, Hongjun Sun, Yiqian Feng, Changyou Wang, Fei North China Elect Power Univ Dept Elect Engn Baoding 071003 Peoples R China North China Elect Power Univ State Key Lab Alternate Elect Power Syst Renewable Beijing 102206 Peoples R China State Grid Xinjiang Elect Power Co Ltd Dispatch & Control Ctr Urumqi 100031 Peoples R China State Grid Corp China Dispatch & Control Ctr Beijing 100031 Peoples R China North China Elect Power Univ Hebei Key Lab Distributed Energy Storage & Microgr Baoding 071003 Peoples R China

Accurate short-term photovoltaic (PV) power forecasting is of great significance for the safe and stable operation of power system. Spatial information from neighboring PV sites contributes to improving forecasting performance. However, most of the current methods considering the spatial information of neighboring sites indiscriminately use all sites data for modeling, which will lead to information redundancy, resulting in low forecasting accuracy. Therefore, this paper proposes a short-term solar power forecasting method based on optimal graph structure considering surrounding spatio-temporal correlations. Firstly, the neighboring sites data is analyzed from the perspective of geographical and weather factors to select typical PV sites. Secondly, based on the complex network theory, a new index is proposed to evaluate the connectivity of the graph structure, which improves the predictive ability of the Graph Convolutional network (GCN) model. Finally, considering numerical weather prediction (NWP) data, a hierarchical directed graph structure is constructed to indicate the unidirectional relationship between input samples, which is used as the input of GCN model to mine the spatio-temporal correlation around the targeted site. Through carrying out the case study, the proposed method shows excellent performance in improving accuracy of power forecasting compared with other benchmark methods.

关键词： Forecasting Correlation Predictive models Photovoltaic systems Feature extraction Power generation Power systems Graph connectivity graph convolution network meteorological information PV power forecasting spatio-temporal correlation

来源：评论

学校读者我要写书评

暂无评论

Neural Horizon Model Predictive control - Increasing Computational Efficiency with Neural networks

Neural Horizon Model Predictive Control - Increasing Computa...

引用

American control conference (ACC)

作者： Alsmeier, H. Savchenko, A. Findeisen, R. Tech Univ Darmstadt Control & Cyber Phys Syst Lab Darmstadt Germany

ISBN: (纸本)9798350382662;9798350382655

The expansion in automation of increasingly fast applications and low-power edge devices poses a particular challenge for optimization based control algorithms, like model predictive control. Our proposed machine-learning supported approach addresses this by utilizing a feed-forward neural network to reduce the computation load of the online-optimization. We propose approximating part of the problem horizon, while maintaining safety guarantees - constraint satisfaction - via the remaining optimization part of the controller. The approach is validated in simulation, demonstrating an improvement in computational efficiency, while maintaining guarantees and near-optimal performance. The proposed MPC scheme can be applied to a wide range of applications, including those requiring a rapid control response, such as robotics and embedded applications with limited computational resources.

关键词： Predictive control for nonlinear systems Neural networks Machine learning

来源：评论

学校读者我要写书评

暂无评论

Applied Artificial Neural networks for Industrial Decision-Making Optimization 5th

Applied Artificial Neural Networks for Industrial Decision-M...

引用

5th International conference on Smart Applications and Data Analysis for Smart Cyber Physical systems

作者： Mellouli, Hala Meddaoui, Anwar Zaki, Abdelhamid Hassan II Univ ENSAM Casablanca Morocco

ISBN: (纸本)9783031770425;9783031770432

Industrial decision-making processes today face significant challenges due to the increasing complexity of problems. This complexity arises from the wide range of optimization constraints to consider, the vast amounts of information to process, and the numerous potential solutions to explore. Incorporating Artificial Intelligence (AI) into industrial decision-making processes has emerged as a transformative force, converting organizational strategies and operational paradigms to unlock new levels of efficiency, production, and profitability while preserving the lead. This study presents a novel decision-making optimization approach that efficiently uses artificial neural networks and the analytic hierarchy process to generate optimal decisions based on real-time performance data analysis and prior in-stance learning.

关键词： Artificial Neural network Machine Learning Multi Criteria-Decision-Making performance Optimization

来源：评论

学校读者我要写书评

暂无评论

A Novel Adaptive Learning systems for Type-2 Fuzzy controller Based on Elman Neural network 7

A Novel Adaptive Learning Systems for Type-2 Fuzzy Controlle...

引用

7th International conference on Green Technology and Sustainable Development, GTSD 2024

作者： Nguyen, Minh-Triet Tri, Do Duc Le, Tien-Loc Ho Chi Minh City University of Technology and Education Faculty Mechatronics Ho Chi Minh City Viet Nam Ho Chi Minh City University of Technology and Education Faculty of Electrical and Electronics Engineering Ho Chi Minh City Viet Nam Lac Hong University Faculty of Electrical and Electronics Engineering Dong Nai Viet Nam

ISBN: (纸本)9798350386073

Although its advantages of handling input uncertainties and noises, Type-2 Fuzzy controller faces the challenge of the trial-and-error process for evaluating so many control parameters. To overcome this issue, an Elman neural network with the adaptation laws was proposed to make a hybrid model that leverages the expressive power of Type-2 Fuzzy Logic and the predictive capability of Elman Neural networks to capture temporal dependencies. The adaptation laws employ the gradient descent method to dynamically update network parameters in realtime. To demonstrate the effectiveness and practical utility of the proposed control system, numerical simulation results are presented, specifically on its performance in trajectory tracking control for cart inverted pendulum systems. © 2024 IEEE.

关键词： Elman neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-agent system-assisted fault section location scheme for distribution networks with DFIG-based wind DGs

引用

ELECTRIC POWER systems RESEARCH 2024年 233卷

作者： Li, Xu Gui, Lin Chen, Jun Lu, Yuping Yangzhou Univ Coll Elect Energy & Power Engn Yangzhou 225009 Peoples R China Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China Nanjing Tech Univ Coll Elect Engn & Control Sci Nanjing 211816 Peoples R China Southeast Univ Sch Elect Engn Nanjing 210096 Peoples R China

This paper proposes a multi -agent system (MAS)-assisted relaying scheme to identify the fault section in a distribution network (DN) that incorporates doubly -fed induction generators (DFIG)-based wind distributed generations (DGs). Firstly, to mitigate the adverse effect of the uncertain fault behavior of DFIGs on conventional directional elements, the fault direction identifiers (FDIs) are assigned at the I -type and ii -type buses in the DN using the high -frequency component principle. Furthermore, a MAS-assisted relaying structure is devised to collect and integrate these identifiers and then accomplish the fault section location. On the one hand, since the setting of FDIs only requires local current information and the logical signals are solely exchanged within each predetermined associated region, the proposed fault section location scheme can be implemented in an immature DN with a limited number of voltage transformers or under weak synchronization conditions. On the other hand, the autonomy and cooperation of intelligent Agents also enable the proposed scheme to determine the fault section in a decentralized decision -making (DDM) mode, eliminating the dependence on strong central control and reducing redundant data transmission in a multi -bus distribution system. Simulation results under representative faulty scenarios validate the expected performance of the protection scheme.

关键词： Multi -agent system (MAS) Distribution network (DN) Doubly -fed induction generator (DFIG) Fault section location Decentralized decision mode (DDM) High -frequency component principle

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：