检索结果-内蒙古大学图书馆

43rd International conference on computer-aided design, ICCAD 2024

作者： Zhou, Yifei Kämpfe, Thomas Ni, Kai Amrouch, Hussam Zhuo, Cheng Yin, Xunzhao Zhejiang University Hangzhou China Fraunhofer IPMS Dresden Germany Department of Electrical Engineering University of Notre Dame Notre Dame United States Technical University of Munich TUM School of Computation Information and Technology Munich Institute of Robotics and Machine Intelligence Munich Germany Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province China

ISBN: (纸本)9798400710773

Compute-in-memory (CiM) emerges as a promising solution to solve hardware challenges in artificial intelligence (AI) and the Internet of Things (IoT), particularly addressing the"memory wall" issue. By utilizing nonvolatile memory (NVM) devices in a crossbar structure, CiM efficiently accelerates multiply-accumulate (MAC) computations, the crucial operations in neural networks and other AI models. Among various NVM devices, Ferroelectric FET (FeFET) is particularly appealing for ultra-low-power CiM arrays due to its CMOS compatibility, voltage-driven write/read mechanisms and high ION/IOFF ratio. Moreover, subthreshold-operated FeFETs, which operate at scaling voltages in the subthreshold region, can further minimize the power consumption of CiM array. However, subthreshold-FeFETs are susceptible to temperature drift, resulting in computation accuracy degradation. Existing solutions exhibit weak temperature resilience at larger array size and only support 1-bit. In this paper, we propose TReCiM, an ultra-low-power temperature-resilient multibit 2FeFET-1T CiM design that reliably performs MAC operations in the subthreshold-FeFET region with temperature ranging from 0°C to 85°C at scale. We benchmark our design using NeuroSim framework in the context of VGG-8 neural network architecture running the CIFAR-10 dataset. Benchmarking results suggest that when considering temperature drift impact, our proposed TReCiM array achieves 91.31% accuracy, with 1.86% accuracy improvement compared to existing 1-bit 2T-1FeFET CiM array. Furthermore, our proposed design achieves 48.03 TOPS/W energy efficiency at system level, comparable to existing designs with smaller technology feature sizes. © 2024 Copyright is held by the owner/author(s).

关键词： MISFET devices

来源：评论

学校读者我要写书评

暂无评论

design of Low-Cost PLC to Drive Three-Phase Induction Motor using Variable Frequency Drive

Design of Low-Cost PLC to Drive Three-Phase Induction Motor ...

引用

control Instrumentation system conference (CISCON) - Guiding Tomorrow - Emerging Trends in control, Instrumentation, and systems Engineering

作者： Rout, Rajashree Samal, Sudhansu Kumar Modak, Gautam Centurion Univ Technol & Management Dept CSE R Sitapur 752050 Odisha India Centurion Univ Technol & Management Dept EEE R Sitapur 752050 Odisha India

ISBN: (纸本)9798350375480;9798350375497

In this paper, we have designed a low-cost indigenous logical control that is not only affordable by micro-and small-scale industries to further the manufacturing and production processes but also to add value to the accuracy and reliability of process automation. A Programmable Logic controller (PLC) is a specialized computer used for the control and operation of manufacturing processes and machinery. The logical control is designed with two microcontrollers, which are programmed to interface with the Human Machine Interface (HMI) panel and also to communicate with the variable frequency drive. Here, the analog signal scaling method is used to vary the frequency for induction motor speed control. The range of speed achieved was both step-wise and in a continuous manner. The developed prototype is verified in the laboratory as well as with loading conditions, i.e., lathe and computer numerical control (CNC) machines at 40 degrees C.

关键词： Industrial Automation system PLC ATMEGA Optocoupler MOSFET Relay

来源：评论

学校读者我要写书评

暂无评论

Batch-Based Learning Consensus of Multiagent systems With Faded Neighborhood Information

引用

ieee TRANSACTIONS ON NEURAL NETWORKS AND LEARNING systemS 2023年第6期34卷 2965-2977页

作者： Qu, Ganggui Shen, Dong Yu, Xinghuo Beijing Univ Chem Technol Coll Informat Sci & Technol Beijing 100029 Peoples R China Renmin Univ China Sch Math Beijing 100872 Peoples R China RMIT Univ Sch Engn Royal Melbourne Inst Technol Melbourne Vic 3001 Australia

This article addresses the batch-based learning consensus for linear and nonlinear multiagent systems (MASs) with faded neighborhood information. The motivation comes from the observation that agents exchange information via wireless networks, which inevitably introduces random fading effect and channel additive noise to the transmitted signals. It is therefore of great significance to investigate how to ensure the precise consensus tracking to a given reference leader using heavily contaminated information. To this end, a novel distributed learning consensus scheme is proposed, which consists of a classic distributed control structure, a preliminary correction mechanism, and a separated design of learning gain and regulation matrix. The influence of biased and unbiased randomness is discussed in detail according to the convergence rate and consensus performance. The iterationwise asymptotic consensus tracking is strictly established for linear MAS first to demonstrate the inherent principles for the effectiveness of the proposed scheme. Then, the results are extended to nonlinear systems with nonidentical initialization condition and diverse gain design. The obtained results show that the distributed learning consensus scheme can achieve high-precision tracking performance for an MAS under unreliable communications. The theoretical results are verified by two illustrative simulations.

关键词： Fading channels Indexes Distance learning computer aided instruction Topology Convergence Trajectory Channel randomness faded neighborhood information (FNI) iterative learning control (ILC) multiagent system (MAS)

来源：评论

学校读者我要写书评

暂无评论

The Application of Intelligent Speech Analysis in College English Oral Learning system

The Application of Intelligent Speech Analysis in College En...

引用

2024 International conference on Mechatronics and Intelligent control, ICMIC 2024

作者： Luo, Huan Hunan University of Medicine Hunan China

ISBN: (数字)9781510686847

ISBN: (纸本)9781510686830

computer assisted language learning has developed rapidly and has received widespread attention from more and more scholars. This discipline mainly promotes simple foreign language teaching activities through the assistance of computers and information technology. This article designs and implements an English speaking learning system based on speech recognition technology, which provides users with more time and space convenience advantages as well as diverse interactive characteristics when learning English speaking. The focus of this paper is on the computer-aided evaluation method of pronunciation quality in English speaking follow-up reading. Participants in the oral test can randomly select speech samples from the speech training database and follow them according to their standard pronunciation. During the operation of the system, the feature information of the two is extracted for comparison, and the pronunciation quality is evaluated by calculating the Euclidean distance between the feature parameters of the standard template and the training template. Finally, through experiments and testing, it was confirmed that the system can effectively improve the system's scoring performance by introducing average pronunciation level, and has a certain effect on improving users' oral pronunciation level. © 2025 SPIE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Actuator Saturation Compensator design for Disturbance Observer Based control Structure Supporting Piezo Driven Nanopositioning systems 5

Actuator Saturation Compensator Design for Disturbance Obser...

引用

5th ieee International conference on Information systems and computer aided Education, ICISCAE 2022

作者： Liang, Heng Liu, Kai Li, Man Du, Peng Shandong Academy of Environmental Sciences Environmental Engineering Co. Ltd. Jinan China Shandong Soil Pollution Prevention and Control Center Jinan China

ISBN: (数字)9781665481229

ISBN: (纸本)9781665481229

In this research, we developed a saturation compensator based disturbance observer control structure for piezo driven nanopositioning systems. By regarding the effects of hysteresis nonlinearities, model uncertainties, motion coupling and external disturbances as a lumped disturbance added to the control channel, a disturbance observer is established for the nanopositioning system for purpose of compensating the lumped disturbance, such that improved control performance is obtained for the unsaturated nanopositioning system. On top of the specific control structure of disturbance observer, a robust saturation compensator is employed to deal with the unexpected actuator saturations. On the basis of the input/output relationships, the compensator design is transformed as a control problem with the dead zone nonlinearity, which is constraint by a sector boundary. By combining the saturation compensation robustness with model uncertainties, we formulate the compensator design as an H∞ optimization problem. Experimental results on a prototype of the piezo driven nanopositioner demonstrate the excellent motion performance and saturation compensation capability of the proposed control strategy. © 2022 ieee.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Research on Question Answering system of Intelligent Robot Based on Deep Learning 5

Research on Question Answering System of Intelligent Robot B...

引用

5th ieee International conference on Power, Electronics and computer Applications, ICPECA 2025

作者： Dexing, Bian Wenjing, Wang Honghao, Bai Tianjin Richsoft Electric Power Information Technology Co. Ltd Digital Applications Business Unit Tianjin China

ISBN: (纸本)9798331533694

The preset function modules of intelligent customer service robot question-answering system are usually executed on the basis of the imported question-answering objectives, and the question-answering has deviation, which leads to the stable recall rate. Therefore, the design and research of intelligent customer service robot question-answering system based on deep learning are proposed. According to the current measurement, we access the central processing unit, set up DM368 memory control and voice circuit, and realize the design of system hardware;Combined with deep learning technology, the question-and-answer deviation is controlled, and the question-and-answer function module of customer service robot is designed, and the application connection with dynamic switching database is established to realize the design of system software. The system test shows that: For randomly selected test groups, in the context of 6 time periods, the deep learning intelligent customer service robot QA system designed this time has a faster task processing speed and a higher recall rate, which shows that the system itself has strong pertinence and stability, and the QA processing efficiency is obviously improved, which has practical application value and innovative significance. © 2025 ieee.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

MexSync: Software Covert Channels Exploiting Mutual Exclusion and Synchronization

引用

ieee TRANSACTIONS ON computer-aided design OF INTEGRATED CIRCUITS AND systemS 2023年第12期42卷 4491-4504页

作者： Zhang, Jiliang Shen, Chaoqun Qu, Gang Hunan Univ Coll Integrated Circuits Changsha 410082 Peoples R China Hunan Univ Chip Secur Inst Changsha 410082 Peoples R China Hunan Univ Changsha 410082 Peoples R China Univ Maryland Dept Elect & Comp Engn College Pk MD 20742 USA

The mutual exclusion and synchronization mechanism (MESM) is a basic process management mechanism in modern operating systems. However, we first found that MESM has serious vulnerabilities. In this article, a new set of MESM-based software covert channels, named Mex +Sync, are proposed to transmit confidential information. Mex +Sync offer several advantages: 1) the covert channels are constructed at the software level and can be deployed on any hardware;2) the closed shared resource ensures the quality of the channels with low interference and makes them hard to be detected;and 3) the attack utilizes the system ’s software resources which abound and hence difficult to isolate. We build the covert channels on Linux and Windows with the following MESMs: flock, FileLockEX, Mutex, Semaphore, Event, and WaitableTimer. Experimental results demonstrate that these covert channels can achieve transmission rate of 13.105, 12.383, and 6.552 kb/s, respectively, in the scenarios of local, cross-sandbox and cross-virtual machine, all with bit error rate under 1 %. Meanwhile, we carefully analyze and verify the impact of noise on channel performance.

关键词： Trojan horses Synchronization Software Hardware Process control Linux Time measurement Covert channel mutual exclusion synchronization

来源：评论

学校读者我要写书评

暂无评论

Efficient Strategy for Building Colorectal Cancer Classification CAD system using Weakly-Annotated Whole Slide Images 5

Efficient Strategy for Building Colorectal Cancer Classifica...

引用

5th International conference on Artificial Intelligence, Robotics and control (AIRC)

作者： Saeed, Ahmed Ghanem, Nagia M. Ismail, Mohamed A. Alexandria Univ Fac Engn Comp & Syst Engn Alexandria Egypt

ISBN: (纸本)9798350385083;9798350385076

Colorectal cancer (CRC) is one of the most deadly diseases nowadays. With the advancement of deep learning, it has become feasible to build CAD (computer-aided diagnosis) systems that help doctors in the process of disease diagnosis and prognosis. In this research, we study the CRC classification problem using weakly-annotated whole slide images (WSIs) based on the multiple instance learning (MIL) approach. We concentrate on applying efficient preprocessing steps that output a computational power-efficient representation of the data;and performing a set of experiments to determine the best model structures and hyperparameters suiting the problem being studied, which serves as a preliminary step toward improving the learning algorithm. Our research proves that the correct choice of these factors can potentially improve the learning process and the model performance. The results we achieved demonstrate significant superiority over the baseline work that leveraged the weakly-annotated slides, where we achieved an 89.58% accuracy compared to 84.17%. Our results even outperformed the original work evaluation results obtained by applying a pre-training step using a set of strongly-annotated slides.

关键词： colorectal cancer (CRC) computer-aided diagnosis (CAD) whole slide image (WSI) multiple instance learning (MIL) Hematoxylin and Eosin (H&E) region of interest (ROI) deep learning (DL) convolutional neural network (CNN) quadratic weighted kappa (QWK) categorical cross-entropy (CCE)

来源：评论

学校读者我要写书评

暂无评论

Organization-Level Identification in the Power IoT system

Organization-Level Identification in the Power IoT System

引用

2025 Asia-Europe conference on Cybersecurity, Internet of Things and Soft Computing, CITSC 2025

作者： Deng, Guangzhi Ding, Sheng Ma, Zekun Wu, Minrong Wu, Haikun Ma, Yingning State Grid Ningxia Electric Power Co. Ltd. Yinchuan Power Supply Company Yinchuan China

ISBN: (数字)9798331504205

ISBN: (纸本)9798331504205

This study proposes a survivability enhancement technique for Power IoT based on checkpoint fault tolerance technology. It aims to improve system survivability by periodically saving the system state and restoring it to the most recent checkpoint in the event of a failure. This paper introduces the basic principles of checkpoint fault tolerance technology and its application in Power IoT, detailing the implementation methods for performance monitoring, checkpoint setting, and recovery. Experimental results show that this technology effectively enhances system survivability and ensures the continuous operation of critical services. © 2025 ieee.

关键词： Power systems computer aided design

来源：评论

学校读者我要写书评

暂无评论

Safety Critical control of a Quadrupedal Robot Using MPC-CBF

Safety Critical Control of a Quadrupedal Robot Using MPC-CBF

引用

2025 ieee International conference on Mechatronics, ICM 2025

作者： Mcconnellogue, Peter James Van, Mien Mcmullan, Rhyss Mcelroy, Ronan Naeem, Wasif School of Electronics Electrical Engineering and Computer Science Queen's University Belfast Belfast United Kingdom

ISBN: (纸本)9798331533892

Quadrupedal robots have been deployed in numerous challenging environments, such as nuclear facility inspections and industrial surveys. These unstructured and dynamic environments expose the robots to significant safety risks. Therefore, this paper proposes a novel design for a safety-critical control system for quadrupedal robots, integrating Model Predictive control (MPC) with control Barrier Functions (CBF) to enhance overall system safety. A comprehensive simulation environment has been established, and results demonstrate that the proposed MPCCBF controller outperforms the conventional MPC controller. Specifically, while the MPC controller alone provides adequate tracking of a desired trajectory in a trot gait, integrating CBF enhances obstacle avoidance and improves stability. This combination allows for navigation through more challenging environments while maintaining accurate trajectory tracking. © 2025 ieee.

关键词： Predictive control systems

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：