检索结果-内蒙古大学图书馆

International Conference on Control, Instrumentation, and Automation

作者： Mohammad Olyai Khalil Alipour Bahram Tarvirdizadeh Majid Sorouri Mohammad Ghamari Department of Mechatronics Eng. School of Intelligent Systems Engineering College of Interdisciplinary Science and Technology Advanced Service Robots (ASR) Laboratory University of Tehran Tehran Iran Department of Electronic Engineering Maynooth University Maynooth Co. Kildare Ireland Department of Computer and Mechatronics Engineering Science and Research Branch Islamic Azad University Tehran Iran Electrical Engineering Department California Polytechnic State University San Luis Obispo CA USA

ISBN: (数字)9798331509972

ISBN: (纸本)9798331509989

One type of wheeled mobile robot widely used in public transportation and for carrying high payloads is the tractor-trailer wheeled robots (TTWRs). This study considers a differentially-driven tractor under pure rolling conditions, which is subject to nonholonomic constraints. Controlling a TTWR in both backward and forward motion is challenging due to inherent instability. To address this issue and achieve trajectory tracking control for these systems, this paper employs dynamic feedback linearization (DFL) to overcome the limitations of static feedback linearization (SFL). The system’s response will be examined under various trajectories and initial conditions for both forward and backward motion.

关键词： Trajectory tracking Dynamics Wheels Kinematics Reinforcement learning Feedback linearization Trajectory Mobile robots Public transportation Payloads

来源：评论

学校读者我要写书评

暂无评论

An Artificial Intelligence Solution for Energy Management in Smart Grid

An Artificial Intelligence Solution for Energy Management in...

引用

Artificial Intelligence & Green Energy (ICAIGE), IEEE International Conference on

作者： Ferdaws Ben Naceur Sana Toumi Chokri Ben Salah Mohamed Ali Mahjoub LATIS- Laboratory of Advanced Technology and Intelligent Systems National School of Engineers of Sousse University of Sousse Sousse Tunisia Higher Institute of Computer Science and Communication Technologies of Hammam Sousse University of Sousse Sousse Tunisia Department of Electrical Engineering Laboratory of Automation Electrical Systems and Environment (LASEE) National School of Engineers University of Monastir Monastir Tunisia Institut de Recherche Dupuy de Lôme (UMR CNRS 60 27 IRDL) Brest France Laboratory of Automation Electrical Systems and Environment (LASEE) ISSAT Sousse University of Sousse Sousse Tunisia

This paper deals with an intelligent decision-making strategy of energy management for a smart grid within an element storage in order to reduce the system cost and improve its reliability. Indeed, the integration of distributed energy storage devices allows the customers to store energy and reuse at a later time or delayed some appliances operation according to a time-varying price signal. The adopted strategy is based on an artificial intelligence control algorithm “fuzzy logic”. The main objective is to determine the appropriate source (grid or battery) used for meeting the consumer. The decision solution shows the system reliability where the switches are synchronized. Switches draw electricity from the grid for both load and battery when price is low and in contrary when electricity price is high, we find a variation's price correspondance with the switch drawing electricity from the battery. The obtained results are verified carrying out Matlab simulation using real data such as the electricity price (Price (t)) and the battery state of charge (SOC (t)).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Vision-Based Safe Landing of UAV using Tiny-SURF Algorithm

Vision-Based Safe Landing of UAV using Tiny-SURF Algorithm

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Priyanka Gupta Bhavya Pareek Ranjeet Kumar Avinash Chandra Aeron Computer Science Engineering JECRC Foundation Jaipur India Electronics and Communication Engineering LNM Institute of Information Technology Jaipur India TATA Advanced Systems Limited (TASL) Bangalore India

ISBN: (纸本)9781665442084

A general rule of flying is applicable when developing an aircraft system and the same rule is applicable on Unmanned Aerial Vehicles (UAVs) as well when developing an intelligent autonomous flying machine. The rule states, "Take-off is optional but landing is necessary and safe landing in emergency conditions is mandatory." However, in case of a manned aircraft, human intelligence plays a major role in safe landing of vehicle, but in case of autonomous UAV, it is the intelligence of the machine, which marks for safe landing. Hence, this work presents a UAV safe landing system using computer vision algorithm. We have proposed a novel tiny version of existing Speeded Up Robust Features (SURF) algorithm that reduces the computational complexity without compromising the detection of safe landing areas in a given frame. The observation suggests that results obtained from proposed Tiny-SURF are well suited for solving the problem.

关键词： computer vision Human intelligence Conferences Autonomous aerial vehicles Feature extraction Aircraft Computational complexity

来源：评论

学校读者我要写书评

暂无评论

ZnG: Architecting GPU Multi-Processors with New Flash for Scalable Data Analysis

ZnG: Architecting GPU Multi-Processors with New Flash for Sc...

引用

Annual International Symposium on computer Architecture, ISCA

作者： Jie Zhang Myoungsoo Jung Computer Architecture and Memory Systems Laboratory Korea Advanced Institute of Science and Technology (KAIST)

ISBN: (数字)9781728146614

ISBN: (纸本)9781728146621

We propose ZnG, a new GPU-SSD integrated architecture, which can maximize the memory capacity in a GPU and address performance penalties imposed by an SSD. Specifically, ZnG replaces all GPU internal DRAMs with an ultra-low-latency SSD to maximize the GPU memory capacity. ZnG further removes performance bottleneck of the SSD by replacing its flash channels with a high-throughput flash network and integrating SSD firmware in the GPU's MMU to reap the benefits of hardware accelerations. Although flash arrays within the SSD can deliver high accumulated bandwidth, only a small fraction of such bandwidth can be utilized by GPU's memory requests due to mismatches of their access granularity. To address this, ZnG employs a large L2 cache and flash registers to buffer the memory requests. Our evaluation results indicate that ZnG can achieve 7.5× higher performance than prior work.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New-fangled Classification Algorithm for Medical Heart Diseases Analysis using Wavelet Transforms

引用

Open Public Health Journal 2024年 17卷

作者： Nayak, Soumya Ranjan Selvarasu, Sivakumar Sripathy, B. Singh, Prabhishek Diwakar, Manoj Gupta, Indrajeet Ravi, Vinayakumar Mazroa, Alanoud Al School of Computer Engineering KIIT Deemed to be University Odisha Bhubaneswar 751024 India Department of Computer Applications Faculty of Science and Humanities SRM Institute of Science and Technology Kattankulathur Chennai 603203 India Department of Mathematics School of Advanced Sciences Vellore Institute of Technology (VIT) Vellore 632 014 India School of Computer Science Engineering & Technology Bennett University Greater Noida India CSE Department Graphic Era deemed to be University Uttarakhand Dehradun India Graphic Era Hill University Uttarakhand Dehradun India School of Computer Science & AI SR University Telangana Warangal 506371 India Center for Artificial Intelligence Prince Mohammad Bin Fahd University Khobar Saudi Arabia Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University (PNU) P.O. Box 84428 Riyadh 11671 Saudi Arabia

Background: In this article, the Mixed Mode Database Miner (MMDBM) algorithm is introduced for the classification of data. This algorithm depends on the decision tree classifier, which handles the numerical and categorical attributes. For the experimental analysis in a well-explored heart disease data set collected from the UCI Repository. Aims: Understanding the fundamentals of every classification method and how to apply them to CUDA is the aim of this study. After reviewing the literature, the approach that is most suited is selected for implementing the suggested algorithm in the MMDM classifier along with the discrete wavelet decomposition. From this experimental analysis, we observed that the use of the wavelet technique in the MMDBM algorithm provides better and more accurate results for data classification. Objective: The main objective of the manuscript is to identify the early stage of heart attack that was caused either by smoking, smoking with tobacco, or non-smoking. Additionally, this study aims to check the validity of the MMDM classifier along with the discrete wavelet decomposition. From this experimental analysis, we observed that the use of the wavelet technique in the MMDBM algorithm provides better and more accurate results for data classification. Methods: In the modern digital world today, data has a major impact on everyone’s life. Every database contains a lot of information hidden either in the form of numerical data, characteristic data, or a mixture of both. Moreover, to accurately decode every dataset, a fast and efficient classifier is essential.. Moreover, by using this hybrid technique based on both MMDBM and Wavelet processes, it compresses the data with minimum storage capacity. Results: The experimental results are compared with the classified data to wavelet data output. These results prove that our presented technique is more prominent and robust in an analysis of heart diseases. Conclusion: This algorithm is based on a decision

关键词： Big data Classification Algorithms Data mining Haar wavelets Healthcare Tobacco

来源：评论

学校读者我要写书评

暂无评论

Resistive Memory-based Neural Differential Equation Solver for Score-based Diffusion Model

arXiv

引用

arXiv 2024年

作者： Yang, Jichang Chen, Hegan Chen, Jia Wang, Songqi Wang, Shaocong Yu, Yifei Chen, Xi Wang, Bo Zhang, Xinyuan Cui, Binbin Li, Yi Lin, Ning Xu, Meng Li, Yi Xu, Xiaoxin Qi, Xiaojuan Wang, Zhongrui Zhang, Xumeng Shang, Dashan Wang, Han Liu, Qi Cheng, Kwang-Ting Liu, Ming Department of Electrical and Electronic Engineering the University of Hong Kong Hong Kong ACCESS – AI Chip Center for Emerging Smart Systems InnoHK Centers Hong Kong Science Park Hong Kong Laboratory of Microelectronic Devices and Integrated Technology Institute of Microelectronics Chinese Academy of Sciences Beijing100029 China State Key Laboratory of Integrated Chips and Systems Frontier Institute of Chip and System Fudan University Shanghai200433 China Institute of the Mind the University of Hong Kong Hong Kong University of Chinese Academy of Sciences Beijing100049 China School of Integrated Circuits Hubei Key Laboratory for Advanced Memories Huazhong University of Science and Technology Wuhan430074 China Department of Electronic and Computer Engineering the Hong Kong University of Science and Technology Hong Kong

Human brains image complicated scenes when reading a novel. Replicating this imagination is one of the ultimate goals of AI-Generated Content (AIGC). However, current AIGC methods, such as score-based diffusion, are still deficient in terms of rapidity and efficiency. This deficiency is rooted in the difference between the brain and digital computers. Digital computers have physically separated storage and processing units, resulting in frequent data transfers during iterative calculations, incurring large time and energy overheads. This issue is further intensified by the conversion of inherently continuous and analog generation dynamics, which can be formulated by neural differential equations, into discrete and digital operations. Inspired by the brain, we propose a time-continuous and analog in-memory neural differential equation solver for score-based diffusion, employing emerging resistive memory. The integration of storage and computation within resistive memory synapses surmount the von Neumann bottleneck, benefiting the generative speed and energy efficiency. The closed-loop feedback integrator is time-continuous, analog, and compact, physically implementing an infinite-depth neural network. Moreover, the software-hardware co-design is intrinsically robust to analog noise. We experimentally validate our solution with 180 nm resistive memory in-memory computing macros. Demonstrating equivalent generative quality to the software baseline, our system achieved remarkable enhancements in generative speed for both unconditional and conditional generation tasks, by factors of 64.8 and 156.5, respectively. Moreover, it accomplished reductions in energy consumption by factors of 5.2 and 4.1. Our approach heralds a new horizon for hardware solutions in edge computing for generative AI applications. © 2024, CC BY-NC-SA.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Path Following of a Tractor-Trailer System via Dynamic Extension in Forward and Backward Motion

Path Following of a Tractor-Trailer System via Dynamic Exten...

引用

RSI/ISM International Conference on Robotics and Mechatronics (ICROM)

作者： Mohammad Olyai Khalil Alipour Bahram Tarvirdizadeh Majid Sorouri Mohammad Ghamari Department of Mechatronics Eng. Advanced Service Robots (ASR) Laboratory School of Intelligent Systems Engineering College of Interdisciplinary Science and Technology University of Tehran Tehran Iran Department of Electronic Engineering Maynooth University Maynooth Co. Kildare Ireland Department of Computer and Mechatronics Engineering Science and Research Branch Islamic Azad University Tehran Iran Electrical Engineering Department California Polytechnic State University San Luis Obispo CA USA

ISBN: (数字)9798331529734

ISBN: (纸本)9798331529741

Tractor-trailer wheeled robots (TTWRs) have gained significant attention across various industries and control studies due to their complex dynamics and non-minimum phase behavior, which pose substantial control challenges. This study investigates the control of a differentially-driven tractor to follow a specified path under pure rolling conditions in both forward and backward motion. Notably, it has been established that using static feedback linearization (SFL) leads to instability during backward motion. In contrast, this research uses dynamic feedback linearization (DFL), also known as dynamic extension, for controlling the tractor-trailer system in both directions for the first time. Our findings demonstrate that the internal dynamics of the system remain stable in both forward and backward motions, enabling successful adherence to the desired path.

关键词： Industries Mechatronics Service robots Dynamics Wheels Optimal control Reinforcement learning Agricultural machinery Feedback linearization Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Continuous-Time Digital Twin with Analogue Memristive Neural Ordinary Differential Equation Solver

arXiv

引用

arXiv 2024年

作者： Chen, Hegan Yang, Jichang Chen, Jia Wang, Songqi Wang, Shaocong Wang, Dingchen Tian, Xinyu Yu, Yifei Chen, Xi Lin, Yinan He, Yangu Wu, Xiaoshan Li, Yi Zhang, Xinyuan Lin, Ning Xu, Meng Li, Yi Zhang, Xumeng Wang, Zhongrui Wang, Han Shang, Dashan Liu, Qi Cheng, Kwang-Ting Liu, Ming Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong ACCESS – AI Chip Center for Emerging Smart Systems InnoHK Centers Hong Kong Science Park Hong Kong Institute of the Mind The University of Hong Kong Hong Kong Key Laboratory of Microelectronic Devices & Integrated Technology Institute of Microelectronics Chinese Academy of Sciences Beijing100029 China University of Chinese Academy of Sciences Beijing100049 China School of Integrated Circuits Hubei Key Laboratory for Advanced Memories Huazhong University of Science and Technology Wuhan430074 China State Key Laboratory of Integrated Chips and Systems Frontier Institute of Chip and System Fudan University Shanghai200433 China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

Digital twins, the cornerstone of Industry 4.0, replicate real-world entities through computer models, revolutionising fields such as manufacturing management and industrial automation. Recent advances in machine learning provide data-driven methods for developing digital twins using discrete-time data and finite-depth models on digital computers. However, this approach fails to capture the underlying continuous dynamics and struggles with modelling complex system behaviour. Additionally, the architecture of digital computers, with separate storage and processing units, necessitates frequent data transfers and Analogue-Digital (A/D) conversion, thereby significantly increasing both time and energy costs. Here, we introduce a memristive neural ordinary differential equation (ODE) solver for digital twins, which is capable of capturing continuous-time dynamics and facilitates the modelling of complex systems using an infinite-depth model. By integrating storage and computation within analogue memristor arrays, we circumvent the von Neumann bottleneck, thus enhancing both speed and energy efficiency. We experimentally validate our approach by developing a digital twin of the HP memristor, which accurately extrapolates its nonlinear dynamics, achieving a 4.2-fold projected speedup and a 41.4-fold projected decrease in energy consumption compared to state-of-the-art digital hardware, while maintaining an acceptable error margin. Additionally, we demonstrate scalability through experimentally grounded simulations of Lorenz96 dynamics, exhibiting projected performance improvements of 12.6-fold in speed and 189.7-fold in energy efficiency relative to traditional digital approaches. By harnessing the capabilities of fully analogue computing, our breakthrough accelerates the development of digital twins, offering an efficient and rapid solution to meet the demands of Industry 4.0. © 2024, CC BY-NC-SA.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Scalable parallel flash firmware for many-core architectures 20

Scalable parallel flash firmware for many-core architectures

引用

Proceedings of the 18th USENIX Conference on File and Storage Technologies

作者： Jie Zhang Miryeong Kwon Michael Swift Myoungsoo Jung Computer Architecture and Memory Systems Laboratory Korea Advanced Institute of Science and Technology Computer Architecture and Memory Systems Laboratory University of Wisconsin at Madison

ISBN: (纸本)9781939133120

NVMe is designed to unshackle flash from a traditional storage bus by allowing hosts to employ many threads to achieve higher bandwidth. While NVMe enables users to fully exploit all levels of parallelism offered by modern SSDs, current firmware designs are not scalable and have difficulty in handling a large number of I/O requests in parallel due to its limited computation power and many hardware *** propose DeepFlash, a novel manycore-based storage platform that can process more than a million I/O requests in a second (1MIOPS) while hiding long latencies imposed by its internal flash media. Inspired by a parallel data analysis system, we design the firmware based on many-to-many threading model that can be scaled horizontally. The proposed DeepFlash can extract the maximum performance of the underlying flash memory complex by concurrently executing multiple firmware components across many cores within the device. To show its extreme parallel scalability, we implement DeepFlash on a many-core prototype processor that employs dozens of lightweight cores, analyze new challenges from parallel I/O processing and address the challenges by applying concurrency-aware optimizations. Our comprehensive evaluation reveals that DeepFlash can serve around 4.5 GB/s, while minimizing the CPU demand on microbenchmarks and real server workloads.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A switchable multi-wavelength EDFL using cascaded Sagnac fiber loops with mode differential delay line

引用

Optik 2021年 248卷 168182-168182页

作者： Ren, Fang Zhang, Jinyu Niu, Jingjing Lei, Xiao Zhang, Yanfei Yu, Jinyi School of Computer and Communication Engineering University of Science and Technology Beijing 100083 China Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services University of Science and Technology Beijing Beijing100083 China State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Engineering and Computer Science Peking University Beijing100871 China

We propose and experimentally demonstrate a switchable multi-wavelength Erbium-doped fiber laser that employs cascaded weakly-coupled few-mode fiber (FMF) Sagnac fiber loops with mode differential delay line. A comb filter of multiple specific wavelengths is performed by incorporating a weakly-coupled FMF in cascaded Sagnac fiber loops. The incorporation of the weakly-coupled FMF is realized with all-fiber mode multiplexer/demultiplexer (MUX/DEMUX), which can simultaneously generate transversal LP01 and LP11 modes. The comb filter characteristics of cascaded Sagnac fiber loops are simulated and analyzed by Jones matrix. By adjusting the polarization controllers (PCs), the fiber laser can operate in single-, dual-, and triple-wavelength laser states around C band. The side mode suppression ratio is larger than 30.0 dB. Moreover, the laser output stabilities for single-, dual-, and triple-wavelength lasing are investigated in a range of over 30 min at room temperature. Experimental results indicate that this work has potential applications in WDM systems, sensing, and instrument testing. © 2021 Elsevier GmbH

关键词： Fiber lasers

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：