检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Samiuddin, Jilan Boulet, Benoit Wu, Di The Intelligent Automation Lab the Centre for Intelligent Machines the Department of Electrical and Computer Engineering McGill University MontrealQCH3A 0E9 Canada

The hype around self-driving cars has been growing over the past years and has sparked much research. Several modules in self-driving cars are thoroughly investigated to ensure safety, comfort, and efficiency, among which the controller is crucial. The controller module can be categorized into longitudinal and lateral controllers in which the task of the former is to follow the reference velocity, and the latter is to reduce the lateral displacement error from the reference path. Generally, a tuned controller is not sufficient to perform in all environments. Thus, a controller that can adapt to changing conditions is necessary for autonomous driving. Furthermore, these controllers often depend on vehicle models that also need to adapt over time due to varying environments. This paper uses graphs to present novel techniques to learn the vehicle model and the lateral controller online. First, a heterogeneous graph is presented depicting the current states of and inputs to the vehicle. The vehicle model is then learned online using known physical constraints in conjunction with the processing of the graph through a Graph Neural Network structure. Next, another heterogeneous graph – depicting the transition from current to desired states – is processed through another Graph Neural Network structure to generate the steering command on the fly. Finally, the performance of this self-learning model-based lateral controller is evaluated and shown to be satisfactory on an open-source autonomous driving platform called CARLA. © 2024, CC BY-NC-ND.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Research Design and Manufacture of Automatic Edging and Trimming System for Wood Board from Wagon in Sawing Line Using PLC Control System 6

Research Design and Manufacture of Automatic Edging and Trim...

引用

6th International Conference on Green Technology and Sustainable Development, GTSD 2022

作者： Hoang, Son Le Hong, Truong Bui Thuc, Anh Nguyen Pham Van, Tuong Tran Van, Tinh Pham Van, Trung Nguyen Vietnam National University of Forestry Faculty of Mechanics and Civil Engineering Hanoi Viet Nam Vietnam National University of Forestry Hanoi College for Electro-mechanical Faculty of Mechanics and Civil Engineering Hanoi Viet Nam School of Electrical Engineering Hanoi University of Science and Technology Department of Industrial Automation Hanoi Viet Nam Lac Hong University Dongnai Viet Nam

ISBN: (数字)9781665466288

ISBN: (纸本)9781665466288

The optimization of the processing stages in the sawmill line occupies a strategic position in processing wood products from raw materials (logs). The main objectives of this paper are to propose a design and manufacture an automatic edging and trimming (AET) system for a wood board to synchronize with the sawing line using programmable logic controller (PLC) system. To verify the design of integration, 20 different board samples were used to evaluate the effectiveness of the manufactured system. The results indicated that the AET system meets the basic requirements in cutting the edge waste out of the board and improving rate of wood recovery. Therefore, the idea of the AET system displays merits further research and may be applicable to future sawmills © 2022 IEEE.

关键词： Trimming

来源：评论

学校读者我要写书评

暂无评论

Simulation of Hybrid TWDM-PON with broadband AWG in topology 23

Simulation of Hybrid TWDM-PON with broadband AWG in topology

引用

23rd Slovak-Czech-Polish Optical Conference on Wave and Quantum Aspects of Contemporary Optics

作者： Šiška, Petr Látal, Jan Hejduk, Stanislav Seyringer, Dana Dohnal, Fadi Chovan, Jozef Uherek, František Štípal, Jiří Trubák, Kamil Department of Telecommunications Faculty of Electrical Engineering and Computer Science VSB-Technical University of Ostrava 17. listopadu 2172/15 Ostrava-Poruba708 00 Czech Republic Research Centre for Microtechnology Vorarlberg University of Applied Sciences Hochschulstraße 1 Dornbirn6850 Austria Slovak Centre of Scientific and Technical Information International Laser Centre Ilkovičova 3 Bratislava841 04 Slovakia Institute of Electronics and Photonics Faculty of Electrical Engineering and Information Technology Slovak University of Technology Ilkovičova 3 Bratislava812 19 Slovakia

ISBN: (数字)9781510688094

ISBN: (纸本)9781510688087

This work deals with the study of implementation possibilities of broadband optical multiplexer/demultiplexer in the form of AWG (Arrayed Waveguide Gratings) in TWDM-PON topology (Time and Wavelength Division Multiplexing Passive Optical Network) by norm G.989.1 as a key component of the hybrid network. The functionality possibilities of the TWDM-PON system are observed where the goal of AWG design is to support also wavelengths different from standard wavelengths used for TWDM-PON in C-band (Conventional) ranges from 1530 nm to 1565nm and L-band (Long-wavelength, 1565-1625nm) bands. This should allow for older communication systems (for example EPON (Ethernet Passive Optical Network) given by norm IEEE 802.3ah and GPON (Gigabit-capable Passive Optical Network) by norm ITU-T G.984) to be operating concurrently over ODN (optical distribution network) without mutual disturbance with newer xPON communication systems. The network topology operating in this manner makes efficient use of passive infrastructure, including reducing the cost of construction (CAPEx) or operation (OPEx) while creating hybrid types of optical networks. © 2025 SPIE.

关键词： Arrayed waveguide gratings

来源：评论

学校读者我要写书评

暂无评论

Evolving Restricted Boltzmann Machine-Kohonen Network for Online Clustering

arXiv

引用

arXiv 2024年

作者： Senthilnath, J. Bhattiprolu, Adithya Singh, Ankur Zhou, Bangjian Wu, Min Benediktsson, Jón Atli Li, Xiaoli Singapore138632 Singapore The Department of Electrical & Electronics Engineering Birla Institute of Technology and Science Pilani333031 India The Faculty of Electrical and Computer Engineering University of Iceland Reykjavik107 Iceland School of Computer Science and Engineering Nanyang Technological University Singapore and A*STAR Centre for Frontier AI Research Singapore138632 Singapore

A novel online clustering algorithm is presented where an Evolving Restricted Boltzmann Machine (ERBM) is embedded with a Kohonen Network called ERBM-KNet. The proposed ERBM-KNet efficiently handles streaming data in a single-pass mode using the ERBM, employing a bias-variance strategy for neuron growing and pruning, as well as online clustering based on a cluster update strategy for cluster prediction and cluster center update using KNet. Initially, ERBM evolves its architecture while processing unlabeled image data, effectively disentangling the data distribution in the latent space. Subsequently, the KNet utilizes the feature extracted from ERBM to predict the number of clusters and updates the cluster centers. By overcoming the common challenges associated with clustering algorithms, such as prior initialization of the number of clusters and subpar clustering accuracy, the proposed ERBM-KNet offers significant improvements. Extensive experimental evaluations on four benchmarks and one industry dataset demonstrate the superiority of ERBM-KNet compared to state-of-the-art approaches. Copyright © 2024, The Authors. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-Band Radio Frequency Energy Predictor for Advanced Energy Harvesting Cellular Bands Systems

Multi-Band Radio Frequency Energy Predictor for Advanced Ene...

引用

Novel Intelligent and Leading Emerging Sciences Conference (NILES)

作者： Shaimaa H. Mohammed Ashraf S. Mohra Ashraf Y. Hassan Ahmed F. Elnokrashy Department of Electrical Engineering Benha Faculty of Engineering Benha University Benha Egypt Benha Faculty of Engineering Benha University Benha Egypt School of Information Technology and Computer Science Nile University Giza Egypt

Radio Frequency (RF) energy harvesting has been employed to power wireless devices. Nevertheless, RF energy harvesting encounters restrictions regarding the quantity of power it can harvest depending on signal accessibility. As a result, accurately predicting energy levels becomes crucial for enhancing the performance of energy harvesting circuits. Most research efforts have concentrated on enhancing power harvesting policies or theoretically estimating the energy obtained through RF energy harvesting. Moreover, the existing literature has primarily focused on single-band prediction approaches. This paper presents a multi-band RF energy prediction approach for RF energy harvesting systems. We collect real-time RF energy using software-defined radio technology. The proposed approach leverages Long Short-Term Memory (LSTM) neural networks to accurately predict the mean RF energy in different frequency bands for the next 100 samples, which corresponds to approximately one hour and a half. The research explores the research gap in modeling the radio frequency signal and the need for multi-band prediction techniques. The results demonstrate the effectiveness of the proposed approach in predicting RF energy across different frequency bands, with average accuracies above 98%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HEAVY TRAFFIC LIMIT WITH DISCONTINUOUS COEFFICIENTS VIA A NON-STANDARD SEMIMARTINGALE DECOMPOSITION

arXiv

引用

arXiv 2025年

作者： Atar, Rami Miyazawa, Masakiyo Viterbi Faculty of Electrical and Computer Engineering Technion – Israel Institute of Technology Haifa Israel Department of Information Sciences Tokyo University of Science Chiba Noda Japan

This paper studies a single server queue in heavy traffic, with general inter-arrival and service time distributions, where arrival and service rates vary discontinuously as a function of the (diffusively scaled) queue length. It is proved that the weak limit is given by the unique-in-law solution to a stochastic differential equation in [0, ∞) with discontinuous drift and diffusion coefficients. The main tool is a semimartingale decomposition for point processes introduced in [6], which is distinct from the Doob-Meyer decomposition of a counting process. Whereas the use of this tool is demonstrated here for a particular model, we believe it may be useful for investigating the scaling limits of queueing models very *** Codes 60K25, 60H10, 60H30 © 2025, CC BY.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning-Based Privacy-Preserving Approach to Incorporate Distributed Generators in AC Optimal Power Flow

A Machine Learning-Based Privacy-Preserving Approach to Inco...

引用

IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT Europe)

作者： Burak Dindar Can Berk Saner Dogukan Yigit Polat Hüseyin Kemâl Çakmak Veit Hagenmeyer Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Germany Department of Electrical and Computer Engineering National University of Singapore Singapore School of Computing National University of Singapore Singapore

ISBN: (数字)9798350390421

ISBN: (纸本)9798350390438

In order to achieve the goal of a carbon-neutral power system, significant changes to the power grid are underway, necessitating enhanced interoperability between Transmission System Operators (TSOs) and Distribution System Operators (DSOs) for effective grid operation, particularly in light of the growing number of distributed generators (DGs). Data privacy concerns, however, complicate decision-making processes, particularly when integrating DGs into system-wide dispatch decisions. In this paper, we propose a machine-learning (ML)-based method to incorporate DGs located within the distribution system (DS) into dispatch decisions, adhering to data privacy by mitigating the exchange of sensitive data, such as system topology and demand profiles, between TSOs and DSOs. The methodology involves training three ML models to represent the behavior of the DS, thereby replacing the standard power flow model that contains sensitive information. Notably, we utilize a novel tailored neural network (NN) architecture to enhance computational efficiency in mapping the feasible region of the DS. Additionally, we employ open-source data to construct the Baden-Wü rttemberg (Germany) electricity grid, allowing to test our method not only on standard systems but also on a model that more accurately represents real-world power systems. The numerical case studies verify that the proposed method achieves results comparable to standard AC optimal power flow (AC-OPF) in both cost-optimality and computational time.

关键词： Data privacy Computational modeling Europe Machine learning computer architecture Generators Data models Standards Interoperability Load flow

来源：评论

学校读者我要写书评

暂无评论

Scientometric Analysis in the Field of Big Data and Artificial Intelligence in Industry 1

Scientometric Analysis in the Field of Big Data and Artifici...

引用

1st International Conference on Information System and Information Technology, ICISIT 2022

作者： Maulana, Fairuz Iqbal Febriantono, M. Aldiki Hamim, Miftahul Fajri, Bayu Ramadhani Arifuddin, Rahman Bina Nusantara University School of Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Entrepreneurship Business Creation BINUS Business School Jakarta11480 Indonesia Faculty of Engineering Universitas Negeri Padang Department of Animation Padang Indonesia University of Merdeka Malang Department of Electrical Engineering Malang Indonesia

ISBN: (数字)9781665402002

ISBN: (纸本)9781665402002

Big Data and Artificial Intelligence (BDAI) in Industry have grown so prevalent, and the potential they provide is so revolutionary that they are seen as critical for competitive growth. Because the number of organizations BDAI on Industry technology is increasing exponentially, so is the need for BDAI on Industry practitioners. Until we conducted this research, only 1399 academic documents on BDAI in Industry found from 2002 to 2020 were obtained by searching the Scopus database. BDAI in the industrial sector is examined in-depth in this paper. This study uses bibliometric analysis and indexed digital methods to map scientific publications worldwide. This study uses the Scopus database to collect information and online analysis via the Scopus website and VOSViewer to demonstrate bibliometric network mapping. We use the article selection process, starting with the keywords to be searched for, the year limitation, then the database is exported into RIS and CSV format files. From the database, we also perform network mapping using VOSViewer. Researchers in China have the most articles published and indexed by Scopus among the most prolific authors (373), followed by the United States (239) and India with 125 academic publications. Data analysis reveals an upward trend in the number of worldwide publications in BDAI in Industry, as measured by the Scopus index. © 2022 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Lightweight Authenticated Task Offloading in 6G-Cloud Vehicular Twin Networks

Lightweight Authenticated Task Offloading in 6G-Cloud Vehicu...

引用

2025 IEEE Wireless Communications and Networking Conference, WCNC 2025

作者： Al-Shareeda, Sarah Ozguner, Fusun Redmill, Keith Duong, Trung Q. Canberk, Berk The Ohio State University Electrical and Computer Engineering Department United States Bts Group Turkey Istanbul Technical University Department of Ai and Data Engineering Turkey School of Electronics Electrical Engineering and Computer Science Queen's University Belfast United Kingdom Memorial University of Newfoundland Faculty of Engineering and Applied Science St. John'sNL Canada School of Computing Engineering and The Built Environment Edinburgh Napier University United Kingdom

ISBN: (纸本)9798350368369

Task offloading management in 6G vehicular net-works is crucial for maintaining network efficiency, particularly as vehicles generate substantial data. Integrating secure communication through authentication introduces additional computational and communication overhead, significantly impacting offloading efficiency and latency. This paper presents a unified framework incorporating lightweight Identity-Based Cryptographic (IBC) authentication into task offloading within cloud-based 6G Vehicular Twin Networks (VTNs). Utilizing Proximal Policy Optimization (PPO) in Deep Reinforcement Learning (DRL), our approach optimizes authenticated offloading decisions to minimize latency and enhance resource allocation. Performance evaluation under varying network sizes, task sizes, and data rates reveals that IBC authentication can reduce offloading efficiency by up to 50% due to the added overhead. Besides, increasing network size and task size can further reduce offloading efficiency by up to 91.7%. As a countermeasure, increasing the transmission data rate can improve the offloading performance by as much as 63%, even in the presence of authentication overhead. The code for the simulations and experiments detailed in this paper is available on GitHub for further reference and reproducibility [1]. © 2025 IEEE.

关键词： Authentication Deep Reinforcement Learning Identity-Based Cryptography Proximal Policy Optimization Task Offloading Vehicular Twin Networks

来源：评论

学校读者我要写书评

暂无评论

Improved Runtime for the Synchronous Multi-door Filling

Periodica polytechnica Electrical engineering and computer s...

引用

Periodica polytechnica electrical engineering and computer science 2022年第1期66卷 12-19页

作者： Hideg, Attila Lukovszki, Tamás Forstner, Bertalan Department of Automation and Applied Informatics Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics Magyar tudósok krt. 2 BudapestH-1117 Hungary Faculty of Informatics Eötvös Loránd University Pázmány Péter sétány 1/C. BudapestH-1117 Hungary

In this paper, a particular type of dispersion is further investigated, which is called Filling. In this problem, robots are injected one by one into an a priori not known area and have to travel across until the whole area is covered. The coverage is achieved by a robotic team whose hardware capabilities are restricted in order to maintain low production costs. This includes limited viewing and communication ranges. In this work, we present an algorithm solving the synchronous Filling problem in O((k + ∆)·n) time steps by n robots with a viewing range of 1 hop, where k is the number of doors, n is the number of vertices of the graph, and ∆ is the maximum degree of the graph. This improves the best previously known running time bound of O(k · ∆ · n). Furthermore, we remove the constraint from the previous algorithm that the door vertices need to have a degree of 1. © 2022 Budapest University of Technology and Economics. All rights reserved.

关键词： Multipurpose robots

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：