检索结果-内蒙古大学图书馆

3rd Novel Intelligent and Leading Emerging Sciences Conference, NILES 2021

作者： Hussein, Abdelrahman S. Mostafa, Hassan Cairo University Electronics and Communication Engineering Department Giza12613 Egypt University of Science and technology Nanotechnology and Nanoelectronics Program Zewail City of Science and Technology Giza12578 Egypt

ISBN: (纸本)9781665421577

Recently, an emerging instruction set called RISC-V has been considered a paradigm in the computer architecture domain, which has easily got the attention of the hardware community. This is because it is fully open-source, which opens wide horizons for development and innovation. As deep learning applications (DL) are becoming more common, it is very important to evaluate the processors' performance handling such tasks. In these lights, a RISC-V core performance executing a DL task is evaluated. Also, the gap between its ASIC and FPGA implementations is measured in terms of power and area. The main finding is that ASIC achieves better optimization in both aspects more than the FPGA. © 2021 IEEE.

关键词： Rockets

来源：评论

学校读者我要写书评

暂无评论

Efficient HLS Implementation for Convolutional Neural Networks Accelerator on an SoC

Efficient HLS Implementation for Convolutional Neural Networ...

引用

2021 International Conference on Microelectronics, ICM 2021

作者： Sarg, Muhammad Khalil, Ahmed H. Mostafa, Hassan Cairo University Electronics and Communications Engineering Department Giza12613 Egypt University of Science and Technology Nanotechnology and Nanoelectronics Program Zewail City of Science and Technology Giza12578 Egypt

ISBN: (纸本)9781665408394

Convolutional Neural Networks (CNNs) have achieved high accuracy in many applications such as image recognition and classification. However, due to their large amount of parameters and intensive required operations, general purpose processors cannot achieve the desired inference performance levels. Recently, various hardware accelerators for deep CNNs have been carried out to enhance the throughput of CNNs. Among these accelerators, field programmable gate array (FPGA)-based ones have gained a lot of interest due to their high performance, low power consumption, high reconfigurability, and fast development cycle. Furthermore, the availability of high-level synthesis (HLS) tools lowers the programming burden and increases the productivity of the FPGA-based accelerator designers. In this paper, a C++ HLS implementation for FPGA-based accelerator for the convolutional layers of CNNs is proposed. As a case study, we evaluate the proposed accelerator using Resnet50 CNN on Xilinx Zynq UltraScale+ MPSoC ZCU104 evaluation board using SDSoC development environment, achieving up to 339x inference speedup. © 2021 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Exergetic, Sustainability and Exergoeconomic Analyses of a Fully Photovoltaic-Powered Heat Pump Tumble Dryer

SSRN

引用

SSRN 2024年

作者： Atalay, Halil Tunçkal, Cüneyt Türkdoğan, Sunay Direk, Mehmet Department of Mechanical Engineering Faculty of Engineering Yalova University Yalova77200 Turkey Department of Electric and Energy Air Conditioning and Refrigeration Technology Program Yalova Community College Yalova University Yalova77100 Turkey Department of Electrical and Electronics Engineering Faculty of Engineering Yalova University Yalova77200 Turkey Department of Energy Systems Engineering Faculty of Engineering Yalova University Yalova77200 Turkey

In this study, the experimental performance of a commercial heat pump tumble dryer (HPTD) system integrated with photovoltaic (PV) was evaluated using energy and exergy analysis. Additionally, a sustainability and exergoeconomic performance analysis of system components was conducted to identify components in need of improvement. Only 17.6% of the energy generated by the panels was consumed by the HPTD system, with the remaining portion being utilized by other laboratory devices connected to the same grid, contributing to a sustainable future. In addition to meeting the energy demand, the PV system satisfied the entire power requirement of the HPTD system. It was determined that the drying chamber and the compressor together accounted for 74.53% of the total exergy destruction in the system, with this cost being predominantly incurred during the drying process. Moreover, based on the exergy, sustainability, and exergoeconomic analyses conducted, it was concluded that the drying chamber, integrated with the fan unit, exhibited the lowest exergy efficiency (57.04%), the highest waste exergy ratio (0.83) and the lowest exergoeconomic factor value (0.716) among the system components, indicating the need for improvement in the fan-integrated drying chamber. © 2024, The Authors. All rights reserved.

关键词： Exergy

来源：评论

学校读者我要写书评

暂无评论

Reachability Analysis of Nonlinear Discrete-Time Systems Using Polyhedral Relaxations and Constrained Zonotopes*

Reachability Analysis of Nonlinear Discrete-Time Systems Usi...

引用

IEEE Conference on Decision and Control

作者： Brenner S. Rego Guilherme V. Raffo Marco H. Terra Joseph K. Scott Department of Chemical and Biomolecular Engineering Georgia Institute of Technology 311 Ferst Dr. Atlanta GA USA Department of Electrical and Computer Engineering University of Säo Paulo Säo Carlos SP Brazil Department of Electronics Engineering and the Graduate Program in Electrical Engineering Federal University of Minas Gerais Belo Horizonte MG Brazil

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

This paper presents a novel algorithm for reachability analysis of nonlinear discrete-time systems. The proposed method combines constrained zonotopes (CZs) with polyhedral relaxations of factorable representations of nonlinear functions to propagate CZs through nonlinear functions, which is normally done using conservative linearization techniques. The new propagation method provides better approximations than those resulting from linearization procedures, leading to significant improvements in the computation of reachable sets in comparison to other CZ methods from the literature. Numerical examples highlight the advantages of the proposed algorithm.

关键词： Discrete-time systems Linearization techniques Approximation algorithms Complexity theory Reachability analysis

来源：评论

学校读者我要写书评

暂无评论

MMA-Net: Multi-Modal Attention Network for 2-D Object Detection in Autonomous Driving

MMA-Net: Multi-Modal Attention Network for 2-D Object Detect...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Abhilash Gaur Shubh Goel Kanishk Goel Seshan Srirangarajan Po-Hsuan Tseng Kai-Ten Feng IIT Delhi-NYCU Taiwan Joint Doctoral Program Bharti School of Telecommunication Technology and Management Indian Institute of Technology Delhi (IIT Delhi) New Delhi India International College of Semiconductor Technology National Yang Ming Chiao Tung University (NYCU) Hsinchu Taiwan Department of Electrical Engineering IIT Delhi New Delhi India Department of Electrical Engineering Bharti School of Telecommunication Technology and Management IIT Delhi New Delhi India Department of Electronic Engineering National Taipei University of Technology Taipei Taiwan Department of Electronics and Electrical Engineering NYCU Hsinchu Taiwan

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Autonomous driving technology relies heavily on sensor data for environment perception. Heterogeneous sensors such as lidar, radar, and camera have their own strengths and limitations. Therefore, relying on any single sensor would restrict the effectiveness of autonomous driving technology. However, integrating data from such heterogeneous sensors poses challenges due to differences in their representations. This article outlines a deep learning network aimed at designing modality-agnostic multi-modal fusion architecture. We study sensor data from different modalities and learn fine-grained representations using modality-specific feature encoders independently. Then, a multimodal attention-based network (MMA-Net) is proposed to fuse the data from heterogeneous modalities. The proposed MMA-Net fuses multi-modal sensor data by jointly exploiting the inter-modality and intra-modality relationships among camera, lidar, and radar sensors. The effectiveness of the proposed multi-modal fusion architecture is demonstrated using 2-D object detection metrics through extensive experiments on a dataset generated using the CARLA simulator.

关键词： Laser radar Fuses Multimodal sensors Radar detection Object detection Signal processing Cameras Speech processing Autonomous vehicles Meteorology

来源：评论

学校读者我要写书评

暂无评论

VR-Based Implicit Authentication Using Electromyogram and Inertial Measurement Unit

VR-Based Implicit Authentication Using Electromyogram and In...

引用

International Conference on Cyberworlds

作者： Da-Young Yu Hyung-Tak Lee Youngsam Kim Jong-Hyuk Roh Soohyung Kim Jeonghun Ku Han-Jeong Hwang Dept. Electronics and Information Engineering Interdisciplinary Graduate Program for Artificial Intelligence Smart Convergence Technology Korea University Sejong Republic of Korea Dept. Electronics and Information Engineering Korea University Sejong Republic of Korea Electronics and Telecommunications Research Institute (ETRI) Daejeon Republic of Korea Department of Biomedical Engineering College of Medicine Keimyung University Daegu Republic of Korea

ISBN: (数字)9798331527174

ISBN: (纸本)9798331527181

Biometrics based on electromyogram (EMG) and inertial measurement unit (IMU) signals has received significant attention due to its resistance to forgery and tampering, as well as its relatively higher convenience and security compared to other biometric modalities. However, most EMG and IMU signal-based authentication methods require explicit authentication using unnatural gestures, which is not userfriendly. To address this, we collected EMG and IMU data during virtual reality (VR) rhythm game play, which does not require explicit gestures, and performed implicit authentication. Using a linear discriminant analysis (LDA) classifier, we achieved classification accuracies of 91.71% for human identification and 87.91% for human authentication. The result demonstrated the feasibility of a seamless and implicit authentication in VR environments.

关键词： Biometrics Solid modeling Measurement units Accuracy Authentication Inertial navigation Games Virtual reality Rhythm Electromyography

来源：评论

学校读者我要写书评

暂无评论

Using Robot-Assisting Personalized Learning for Children with Autism: A Pilot Study of Robot's Actions

Using Robot-Assisting Personalized Learning for Children wit...

引用

Biomedical engineering International Conference (BMEiCON)

作者： Chatchai Paengkumhag Wisanu Jutharee Warissara Limpornchitwilai Kosin Chamnongthai Boonserm Keawkamnerdpong Biological Engineering Program Faculty of Engineering King Mongkut’s University of Technology Thonburi Bangkok Thailand Institute of Field Robotics King Mongkut’s University of Technology Thonburi Bangkok Thailand Department of Electronics and Telecommunication Engineering Faculty of Engineering King Mongkut’s University of Technology Thonburi Bangkok Thailand

There are a variety of symptoms of autism spectrum disorders. The appropriate interventions are selected according to the symptoms. Moreover, the key to successful intervention is to provide suitable therapy continuously. Unfortunately, the number of autism specialists is insufficient for the growing demands. Thus, for better intervention outcomes, the collaboration of parents/caregivers who help continue the intervention at home is crucial to the success of the intervention. However, it is not easy for inexperienced parents/caregivers. This study aimed to help parents/caregivers by using a robot to assist personalized learning for children with autism. We developed an artificial intelligence-based program to choose actions appropriate to the child user’s learning style or preference so that the child user stays attended to the activities the robot offers. In this pilot study, we tested using a robot to assist personalized learning with six participants in the special education needs school. The result of this study revealed the possibility of using a robot to assist in personalized learning for children with autism, from the perspective of the participants’ teacher. While interacting with the robot, the participants achieved a high average accuracy percentage of 83.36% and demonstrated a positive learning trend.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Local sampled-data gain-scheduling control of quasi-LPV systems 4th

Local sampled-data gain-scheduling control of quasi-LPV syst...

引用

4th IFAC Conference on Embedded Systems, Computational Intelligence and Telematics in Control CESCIT 2021

作者： Coutinho, Pedro H.S. Peixoto, Márcia L.C. Bernal, Miguel Nguyen, Anh-Tu Palhares, Reinaldo M. Federal University of Minas Gerais Graduate Program in Electrical Engineering Brazil Department of Electrical and Electronics Engineering Sonora Institute of Technology Mexico Université Polytechnique Hauts-de-France LAMIH UMR CNRS 8201 France Federal University of Minas Gerais Department of Electronics Engineering Brazil

This paper deals with the problem of sampled-data gain-scheduling control design for affine quasi-LPV systems. As the control implementation is based on sample-data and its update occurs only at specific sampling instants, the state-dependent scheduling functions of the controller are piecewise continuous. This characteristic causes a mismatch between the system model and the controller parameters, namely asynchronous scheduling functions of the controller with respect to the plant during the inter-sampling behavior. To cope with this phenomenon, a polytopic description of the inter-sampling is constructed based on bounding assumptions on the scheduling functions and their time derivatives. Then, regarding a time-delay approach, a constructive and numerically implementable LMI-based synthesis condition is derived, and a convex procedure is proposed for enlarging the estimate of the region of attraction of the origin of the closed-loop system. The time-derivative bounds of the scheduling functions are explicitly accounted into the local analysis to ensure the method's implementation. A numerical example is provided to illustrate the proposed methodology. Copyright © 2021 The Authors. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0/)

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

3D Stackable Vertical Ferroelectric Tunneling Junction (V-FTJ) with on/off Ratio 1500x, Applicable Cell Current, Self-Rectifying Ratio 1000x, Robust Endurance of 10⁹ Cycles, Multilevel and Demonstrated Macro Operation Toward High-Density BEOL NVMs

3D Stackable Vertical Ferroelectric Tunneling Junction (V-FT...

引用

Symposium on VLSI technology

作者： J.-Y. Lee F.-S. Chang K.-Y. Hsiang P.-H. Chen Z.-F. Luo Z.-X. Li J.-H. Tsai C. W. Liu M. H. Lee Institute and Undergraduate Program of Electro-Optical Engineering National Taiwan Normal University Taiwan Graduate School of Advance Technology National Taiwan University Taiwan Department of Electronics Engineering Institute of Electronics National Yang Ming Chiao Tung University Taiwan Department of Electrical Engineering National Taiwan Normal University Taiwan

A 1500x I LRS /I HRS with a high cell current of ~100 nA/ cell (J = 83 A/cm 2 ) is achieved by antiferroelectric (AFE) vertical ferroelectric tunnel junctions (V-FTJs) that demonstrates multilevel, a self-rectifying rate > 1000x, and macro operation. The stackable 3 D architecture integrating multiple layers of AFE V-FTJs with contact optimization further increases memory density. Robust endurance > 10 9 cycles at |4V| and stable nonvolatile data retention > 10 4 sec with extrapolation to 10 years are achieved. The proposed cell contact V-FTJ by AFE is a promising pathway toward BEOL NVMs by a NAND/NOR-based framework.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sensory Perception of Haptic Rendering in Surgical Simulation

Sensory Perception of Haptic Rendering in Surgical Simulatio...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Rohit Kaushik Rachit Sachdeva Chirag Vashisht Krishan Kant Choudhary CS and Mathematics Department Data Analytics Program University of Illinois Springfield USA Electronics and Communication Engineering Department Dr. Akhilesh Das Gupta Institute of Technology and Management New Delhi India Information Technology and Engineering Department Dr. Akhilesh Das Gupta Institute of Technology and Management New Delhi India

The essential ideas behind haptic technology, including haptic interface and haptic rendering methods, as well as its application to surgical simulation, medical education, and other diverse topics, are presented in this paper. In empirical psychology and physiology, this refers to the sense of contact. The process of analyzing and developing capabilities in response to user interactions with virtual entities is elaborated as haptic rendering. Haptic may indicate haptic transmission, haptic perception, and haptic technology. Humans and other animals can respond to one another by using their feelings through haptic technology. Haptic perception is the process of recognizing objects through *** implies tactile response, which means it delivers feedback in the state of sensation as we may sense the material properties and motions of virtual objects devised by a computer. The use of haptic technology in the medical profession has proven extremely beneficial, and it has a wide range of applications in many different industries. Providing effective exchange via virtual reality helps to ease the surgeon’s obligations. Amplify a person’s experience in the virtual environment. The haptics ability ranges from computer graphics to psychophysics, cognitive science, and neurosciences.

关键词：

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：