检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Gong, Junfeng Liu, Cheng Cheng, Long Li, Huawei Li, Xiaowei SKLP Institute of Computing Technology Chinese Academy of Sciences Beijing China Dept. of Computer Science University of Chinese Academy of Sciences Beijing China School of Control and Computer Engineering North China Electric Power University Beijing China

Mixed-precision neural network (MPNN) that utilizes just enough data width for the neural network processing is an effective approach to meet the stringent resources constraints including memory and computing of MCUs. Nevertheless, there is still a lack of sub-byte and mixed-precision SIMD operations in MCU-class ISA and the limited computing capability of MCUs remains underutilized, which further aggravates the computing bound encountered in neural network processing. As a result, the benefits of MPNNs cannot be fully unleashed. In this work, we propose to pack multiple low-bitwidth arithmetic operations within a single instruction multiple data (SIMD) instructions in typical MCUs, and then develop an efficient convolution operator by exploring both the data parallelism and computing parallelism in convolution along with the proposed SIMD packing. Finally, we further leverage Neural Architecture Search (NAS) to build a HW/SW co-designed MPNN design framework, namely MCUMixQ. This framework can optimize both the MPNN quantization and MPNN implementation efficiency, striking an optimized balance between neural network performance and accuracy. According to our experiment results, MCU-MixQ achieves 2.1× and 1.4× speedup over CMix-NN and MCUNet respectively under the same resource constraints. © 2024, CC BY-SA.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Distributed Sequential Receding Horizon control of Multi-Agent Systems Under Recurring Signal Temporal Logic

Distributed Sequential Receding Horizon Control of Multi-Age...

引用

European control Conference (ECC)

作者： Eleftherios E. Vlahakis Lars Lindemann Dimos V. Dimarogonas Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Thomas Lord Department of Computer Science Viterbi School of Engineering University of Southern California Los Angeles CA USA

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

We consider the synthesis problem of a multi-agent system under signal temporal logic (STL) specifications representing bounded-time tasks that need to be satisfied recurrently over an infinite horizon. Motivated by the limited approaches to handling recurring STL systematically, we tackle the infinite-horizon control problem with a receding horizon scheme equipped with additional STL constraints that introduce minimal complexity and a backward-reachability-based terminal condition that is straightforward to construct and ensures recursive feasibility. Subsequently, we decompose the global receding horizon optimization problem into agent-level programs the objectives of which are to minimize local cost functions subject to local and joint STL constraints. We propose a scheduling policy that allows individual agents to sequentially optimize their control actions while maintaining recursive feasibility. This results in a distributed strategy that can operate online as a model predictive controller. Last, we illustrate the effectiveness of our method via a multi-agent system example assigned a surveillance task.

关键词： Surveillance Decentralized control Europe Predictive models Fasteners Cost function Infinite horizon

来源：评论

学校读者我要写书评

暂无评论

Ethical Considerations in Explainable AI: Balancing Transparency and User Privacy in English Language-based Virtual Assistants 5

Ethical Considerations in Explainable AI: Balancing Transpar...

引用

5th International Conference on Intelligent Communication Technologies and Virtual Mobile Networks, ICICV 2024

作者： Alijoyo, Franciskus Antonius Sandya Sneha Sri, S. Alapati, Purnachandra Rao Yuldashev, Dilyorjon Ponni Valavan, M. Center for Risk Management and Sustainability Indonesia School of Business and Information Technology Stmik Likmi Bandung Indonesia Krishna University Andhra Pradesh India Prasad v Potluri Siddhartha Institute of Technology Andhra Pradesh Vijayawada Kanuru India Turin Polytechnic University in Tashkent Automatic Control and Computer Engineering Department Tashkent Uzbekistan K.Ramakrishnan College of Engineering Trichy Department of Artificial Intelligence and Data Science Tamil Nadu India

ISBN: (纸本)9798350385649

English Language-Based Virtual Assistants (ELB-VAs) are AI-powered systems designed to comprehend and respond to user queries in the English language, exemplified by virtual assistants like Siri or Alexa. The need for balancing transparency and user privacy in ELB-VAs is paramount due to their pervasive integration into daily life. Ensuring transparency imbues user trust, while safeguarding privacy addresses ethical concerns associated with personal data. Existing methods involve clear privacy policies, user-controlled data sharing settings, and encryption. However, drawbacks include user confusion and potential biases. To address these limitations, this study proposes a novel approach. Methodologically, it integrates pre-processing techniques such as lowercasing and tokenization, coupled with a Natural Language Understanding model. This model undergoes intent and entity recognition training, enhancing accuracy, and incorporates privacy-aware response generation, ensuring informative yet privacy-conscious interactions. The implementation of the study's results is carried out using Python tools, showcasing improved metrics and response times. This approach contributes to a more transparent and privacy-respecting user experience, aligning with evolving ethical norms and setting the stage for advancements in ELB-VA technology. This comprehensive exploration bridges existing gaps, emphasizing the ethical imperative of user-centric and privacy-aware AI interactions in ELB- VAs. The proposed NLU model exhibits a substantial increase in accuracy compared to other methods, with an impressive accuracy value of 99.1%• On average, it outperforms the Random Forest and Decision Tree models by 15.7 percentage points, highlighting its superior predictive capabilities in the evaluated task. This comprehensive exploration aligns with evolving ethical norms and establishes a foundation for future advancements in ELB-VA technology. © 2024 IEEE.

关键词： Transparency

来源：评论

学校读者我要写书评

暂无评论

Energy Consumption Model for LoRaWAN via Field Experiments for Smart Agriculture

Energy Consumption Model for LoRaWAN via Field Experiments f...

引用

IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

作者： Satoshi Yamazaki Taiki Ogura Dept. of Control and Computer Engineering National Institute of Technology Numazu College Numazu Japan Dept. of Electrical Electronics and Information Engineering Nagaoka University of Technology Niigata Japan

This paper proposes a scheme to model the energy consumption of LoRaWAN, which is a popular example of low-power wide-area networks (LPWANs), nodes via the results of outdoor field experiments by assuming regional smart agriculture as a use case for internet of things (IoT). Specifically, we derive an experimental approximation formula to estimate the battery lifetime by introducing parameters such as spread factor and payload length. The validity of the proposed scheme is demonstrated by confirming that the results obtained by the approximate formula, the experimental and theoretical results generally agree, regardless of the node state and spread factor. Furthermore, we show that the obtained approximate formula can be used to identify the current consumption value in the sleep state that should be achieved to achieve the desired battery lifetime.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Profitability of a hybrid heating system for a single-family house in Poland based on a heat pump and photovoltaics

Profitability of a hybrid heating system for a single-family...

引用

2020 Applications of Electromagnetics in Modern Engineering and Medicine, PTZE 2020

作者： Drzymala, A. Korzeniewska, E. Institute of Economics University of Lodz Lodz Poland Institute of Electrical Engineering Systems Faculty of Electrical Electronic Computer and Control Engineering Lodz University of Technology Lodz Poland

The article presents an analysis of the profitability of an investment consisting of a heat pump and a photovoltaic installation located in Poland for an exemplary single-family house. The factors that have a significant impact on the profitability and payback time of such installations operating in a dual configuration are described. A simulation of profitability taking into account the legal regulations and support systems was presented. The considered case of profitability concerns a specific technical solution in which an 8 kW air / water pump was used. The pomp cooperates with a photovoltaic installation with a power of up to 10kW, operating in a discount system with an energy consumption factor of 0.8. For the purposes of this article, the DCF (discounted cash flow) method was used. Using this method, it is possible to calculate the market value of the investment with the assumed boundary criteria. A comparison of the economic efficiency of an investment can be presented using the IRR (internal rate of return) method. © Published under licence by IOP Publishing Ltd.

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

Enhanced LPV-based lateral control using ultra-local model-based slip angle estimation

Enhanced LPV-based lateral control using ultra-local model-b...

引用

IEEE Conference on Decision and control

作者： Dániel Fényes Tamás Hegedűs Péter Gáspár Hungarian Research Network (HUN-REN) Kende u. 13-17 Institute for Computer Science and Control (SZTAKI) Budapest Hungary Department for Control of Transportation and Vehicle Systems Budapest University of Technology and Economics Stoczek u 2 Budapest Hungary

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

The paper presents a combined observer and lateral control design approach for autonomous vehicles. The goal of the observer design is to estimate the front and rear slip angles of the vehicle together with the cornering stiffness. The observer is based on the combination of the polytopic LPV approach and the ultra-local model. The ultra-local model is used to update the cornering stiffness and, in this way, improve the performance level of the LPV observer. Then, the resulted observer is exploited during the LPV-based lateral control design. The improved lateral control can adapt to different circumstances such as low adhesion coefficient. The proposed observer and LPV controller is implemented and tested in MATLAB/Simulink environment and using the high-fidelity simulation software, CarMaker.

关键词： Adaptation models control design Heuristic algorithms Software algorithms Estimation Observers Mathematical models Software MATLAB Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Spatial data intelligence and city metaverse: A review

引用

Fundamental Research 2025年第3期5卷 1169-1193页

作者： Meng, Xiaofeng Li, Yong Liu, Ke Liu, Yu Yang, Bin Song, Xuan Liao, Guoqiong Wang, Senzhang Yu, Ziqiang Chen, Longbiao Pan, Xiao Lin, Yuming School of Information Renmin University of China Beijing 100872 China Department of Electronic Engineering Tsinghua University Beijing 100084 China Department of Information Sciences National Natural Science Foundation of China Beijing 100085 China Institute of Remote Sensing and Geographic Information Systems School of Earth and Space Sciences Peking University Beijing 100871 China School of Data Science and Engineering East China Normal University Shanghai 200062 China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen 518055 China School of Information Management Jiangxi University of Finance and Economics Nanchang 330013 China School of Computer Science and Engineering Central South University Changsha 410017 China School of Computer and Control Engineering Yantai University Yantai 264005 China Department of Computer Science Xiamen University Xiamen 361000 China College of Information Science and Technology Shijiazhuang Tiedao University Shijiazhuang 050043 China

Spatial Data Intelligence (SDI) encompasses acquiring, storing, analyzing, mining, and visualizing spatial data to gain insights into the physical world and uncover valuable knowledge. These understandings and knowledge play a crucial role in connecting physical and virtual realms, such as in developing a City Metaverse (CM) aimed at enhancing and optimizing modern urban environments. The advancement of CM holds immense potential to benefit urban dwellers, making research on SDI an increasingly prominent area of focus. This paper contributes significantly by organizing the relevant research and technologies within a coherent framework. Firstly, we identify SDI technologies capable of collecting real-world information to construct a virtual CM. Subsequently, we delve into the technologies that can be compositely integrated with SDI to facilitate interaction with and management of actual cities from the virtual perspective. Additionally, we emphasize the effectiveness and potential of these methods in practical applications. Lastly, we conclude our survey by discussing emerging challenges associated with technological progress, the industrial chain, legal and regulatory aspects, and ethical and moral considerations. © 2024

关键词： Application prospect City metaverse Smart city Spatial data intelligence Virtual-real interaction

来源：评论

学校读者我要写书评

暂无评论

Improved Dingo Optimization Algorithm for Human-robot Collaborative U-shaped Disassembly Line Balancing Problem

Improved Dingo Optimization Algorithm for Human-robot Collab...

引用

Cyber-Physical Social Intelligence (ICCSI), International Conference on

作者： Jialong Li XiWang Guo Jiacun Wang ShuJin Qin Liang Qi Qi Kang Information and Control Engineering Liaoning Petrochemical University Fushun China Computer Science and Software Eng. Monmouth University Wes Long Branch New Jersey USA Economics and Management Shangqiu Normal University Shangqiu China Computer Science and Technology Shandong University of Science and Technology Qingdao China Electrical and Computer Engineering New Jersey Institute of Technology Newark USA

ISBN: (数字)9798350376739

ISBN: (纸本)9798350376746

There is increasing attention on remanufacturing, with the primary focus in the industry on recovering reusable products to generate profit. In the process of optimizing remanufacturing, addressing the balance issue in the operation of the disassembly line is crucial. Therefore, this study proposes the use of an improved Dingo Optimization Algorithm (IDOA) and designs a mathematical model for human-robot collaboration to explore how to achieve higher profits under these conditions. Finally, the improved IDOA is experimentally compared with the commercial optimization solver CPLEX and another intelligent optimization method—the Battle Royale Optimization (BRO). The results demonstrate that this method offers high quality and efficiency.

关键词： Industries Human-robot interaction Collaboration Mathematical models Social intelligence Optimization

来源：评论

学校读者我要写书评

暂无评论

Adaptive Tracking and Perching for Quadrotor in Dynamic Scenarios

arXiv

引用

arXiv 2023年

作者： Gao, Yuman Ji, Jialin Wang, Qianhao Jin, Rui Lin, Yi Shang, Zhimeng Cao, Yanjun Shen, Shaojie Xu, Chao Gao, Fei Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou310027 China The Huzhou Institute Zhejiang University Huzhou313000 China DJI Technology Co. Shenzhen510810 China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong

Perching on the moving platforms is a promising solution to enhance the endurance and operational range of quadrotors, which could benefit the efficiency of a variety of air-ground cooperative tasks. To ensure robust perching, tracking with a steady relative state and reliable perception is a prerequisite. This paper presents an adaptive dynamic tracking and perching scheme for autonomous quadrotors to achieve tight integration with moving platforms. For reliable perception of dynamic targets, we introduce elastic visibility-aware planning to actively avoid occlusion and target loss. Additionally, we propose a flexible terminal adjustment method that adapts the changes in flight duration and the coupled terminal states, ensuring full-state synchronization with the time-varying perching surface at various angles. A relaxation strategy is developed by optimizing the tangential relative speed to address the dynamics and safety violations brought by hard boundary conditions. Moreover, we take SE(3) motion planning into account to ensure no collision between the quadrotor and the platform until the contact moment. Furthermore, we propose an efficient spatiotemporal trajectory optimization framework considering full state dynamics for tracking and perching. The proposed method is extensively tested through benchmark comparisons and ablation studies. To facilitate the application of academic research to industry and to validate the efficiency of our scheme under strictly limited computational resources, we deploy our system on a commercial drone (DJI-MAVIC3) with a full-size sport-utility vehicle (SUV). We conduct extensive real-world experiments, where the drone successfully tracks and perches at 30 km/h (8.3 m/s) on the top of the SUV, and at 3.5 m/s with 60° inclined into the trunk of the SUV. © 2023, CC BY-NC-ND.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Network Service Identification Method for Electric Power Cloud

Network Service Identification Method for Electric Power Clo...

引用

第34届中国控制与决策会议

作者： Yilu Chen Tongtong Li Zhiyao Liu Zhichao Xu Zibo Wang Hongri Liu School of Computer Science and Technology Harbin Institute of Technology School of Cyber Science and Technology Harbin Institute of Technology China Industrial Control Systems Cyber Emergency Response Team

Electric power cloud data center becomes more and more widely applied,and yet lacks security protection inside *** most direct solution for this issue is internal network *** paper focuses on the first task of the isolation,namely network service identification,and proposes a network service identification framework based on deep *** order to obtain service stream,a network service stream extraction algorithm is proposed based on the flow metric and traffic *** the high dimensionality and complexity of service streams,the denoising and convolutional autoencoders are combined for feature *** then a self-organizing mean maps network is adopted to achieve network service *** results illustrate the effectiveness and superiority of the self-organizing mean maps network with regard to the internal evaluation index of ***,the identification framework proposed seems to provide a foundation for subsequent isolation study.

关键词： Network service identification Deep clustering Autoencoder Self-organizing map

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：