检索结果-内蒙古大学图书馆

Fast intra prediction mode decision algorithm for 4×4 blocks in H.264/MPEG-4 AVC

Tamkang Journal of science and engineering 2008年第1期11卷 49-54页

作者： Chiang, Jen-Shiun Hsia, Chih-Hsien Teng, Tsai-Yuan Multimedia IC Design Lab. Department of Electrical Engineering Tamkang University Tamsui 251 Taiwan Department of Computer Science and Information Engineering Tamkang University Tamsui 251 Taiwan

The H.264/MPEG-4 (Advanced Video Coding) AVC video coding includes a multidirectional spatial prediction method to reduce spatial redundancy by using neighboring samples as a prediction for the samples in a block of data to be encoded. The main goal of the intra prediction is to achieve better compression efficiency. For finding the optimal prediction modes, H.264/MPEG-4 AVC adopts the full search algorithm in the standard. The high computation complexity of the full search algorithm makes the encoding of H.264/MPEG-4 AVC to be difficult to meet real time applications. In this work, we proposed a Fast Intra Prediction Mode Decision Algorithm (FIPMDA) for 4 × 4 intra blocks, which is based on the partially sampling prediction and symmetry of the adjacent angle modes, to reduce the computational time and low complexity of the 4 × 4 block intra-prediction. Experimental results show that the proposed method can reduce the encoder time of the intra prediction by more than 60% while maintaining similar video bit rate and quality.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

Triplet-Attention Residual Network for Breast Cancer Histopathology Image Classification 21

Triplet-Attention Residual Network for Breast Cancer Histopa...

引用

Proceedings of the 5th International Conference on Advances in Image Processing

作者： Lu Cao Shan Huang Jianxin Zhang School of Computer Science and Engineering Dalian Minzu University China School of Computer Science and Engineering Dalian Minzu University China and Key Lab of Advanced Design and Intelligent Computing(Ministry of Education) Dalian University China

ISBN: (纸本)9781450385183

Recently, breast cancer histopathology image classification using convolutional neural networks has achieved more and more attentions with the great progress. To capture more discriminant deep features for the classification, this paper proposes a novel triplet-attention residual network, i.e., TAResNet, to distinguish the breast cancer histopathology image. TAResNet employs the representative ResNet18 model to extract deep features of histopathology images, followed by a triplet-attention module to further boost the discriminability of deep features through expanding feature diversity and enhancing inter-dimensional dependency. Extensive experiments carried out on the public BreakHis dataset well evaluate the effectiveness the given TAResNet model. More specifically, TAResNet achieves its optimal classification accuracy of 98.34% and 98.77% at the image level and patient level, respectively.

关键词： Breast cancer Triplet attention Histopathological image classification Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

A Write-Improved Half-Select-Free Low-Power 11T Subthreshold SRAM with Double Adjacent Error Correction for FPGA-LUT design 22nd

A Write-Improved Half-Select-Free Low-Power 11T Subthreshold...

引用

22nd International Symposium on VLSI design and Test, VDAT 2018

作者： Sharma, Vishal Bisht, Pranshu Dalal, Abhishek Chouhan, Shailesh Singh Jattana, H.S. Vishvakarma, Santosh Kumar Nanoscale Devices VLSI Circuit and System Design Lab Electrical Engineering Indian Institute of Technology Indore IndoreM.P.453552 India EISLAB Department of Computer Science Electrical and Space Engineering Lulea University of Technology Lulea Sweden SCL Mohali Department of Space Govt. of India AjitgarhPunjab India

ISBN: (纸本)9789811359491

This work presents a new bit-interleaving low-power 11T subthreshold SRAM cell with the Data-Dependent Partial-Feedback Cutting to improve the write ability. The isolated read path of 11T enhances the read static noise margin (RSNM) which is equivalent to that of its hold SNM (HSNM), while the incorporated PMOS stacking in each of the inverter helps to reduce the leakage power of the cell. The half-select free behavior of the proposed 11T cell facilitates the bit-interleaving architecture of memory array that reduces the multi-bits error occurrence in a single word of data, and thus enhance the soft error tolerance. Using the proposed cell, a four-input FPGA lookup table (LUT) has been implemented working on 0.4V supply, which consumes 0.59 less leakage power as compared to that of 6T LUT. Finally, a two adjacent bits error correction technique is also suggested to incorporate with the proposed bit-interleaving 11T array, so that the effect of soft error can almost be neglected. It consumes comparable leakage and read access energy to that of one-bit error correcting conventional hamming code. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Table lookup

来源：评论

学校读者我要写书评

暂无评论

Fuzzy logic controller design for intelligent air-conditioning system 2

Fuzzy logic controller design for intelligent air-conditioni...

引用

2nd International Conference on Control science and Systems engineering, ICCSSE 2016

作者： Ahamed, Nizam Uddin Taha, Zahari Bin Bin, Ismail Khairuddin, Mohd Rabbi, M.F. Rahaman, S.A.M. Matiur Sundaraj, Kenneth Mechatronic and System Design Lab Faculty of Manufacturing Engineering Universiti Malaysia Pahang Pekan Malaysia Faculty of Electrical and Electronics Engineering Universiti Malaysia Pahang Pekan Malaysia College of Computer Science and Information System Najran University Saudi Arabia AI-Rehab Research Group Universiti Teknikal Malaysia Melaka Melaka Malaysia

ISBN: (纸本)9781467398725

In efficient air cooling systems may cause of wasting energy in a great amount specially in the urban area. Being the most popular cooling system, air-conditioners have been used in domestic usage as well as in industrial applications. However, the unintelligent nature of such cooling system gives rise to excess energy consumption which causes a huge problem in the current energy hungry world. In this paper, we present design of a fuzzy logic controller for the intelligent airconditioning system. The performance of the controller is also simulated. The proposed controller has the adaptive nature to control fan and compressor speed which leads to reducing power consumption. Also, the system controls the operation mode to retain the healthy oxygen level and humid condition of the indoor environment. © 2016 IEEE.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Lessons Learnt from designing a Smart Clothing Telehealth System for Hospital Use 32

Lessons Learnt from Designing a Smart Clothing Telehealth Sy...

引用

32nd Australian computer-Human Interaction Conference, OzCHI 2020

作者： Aggarwal, Deepti Hoang, Thuong Ploderer, Bernd Vetere, Frank Khot, Rohit Ashok Bradford, Mark Hafp Research Lab Rmit University Australia School of Information Technology Deakin University Australia School of Electrical Engineering and Computer Science Queensland University of Technology Australia Interaction Design Lab School of Computing and Information Systems The University of Melbourne Australia Dept. of Anaesthesia and Pain Management Royal Children's Hospital Australia

ISBN: (纸本)9781450389754

In this paper, we describe the design journey of a smart clothing system, SoPhy from the research laboratory to finally being evaluated in the hospital setting. SoPhy is a smart socks-based system, designed to make physiotherapy video consultations effective for assessing lower limb issues. SoPhy is the result of a 3-year journey of development, study and refinement of a research prototype done in collaboration with a physiotherapist. Drawing on this journey, we present seven lessons that emphasize on the importance of fostering strong collaborations with clinicians to move beyond laboratory studies and reach the target health setting. We provide contextual narratives on how we designed a comfortable smart clothing for patients;how we created an intuitive mapping of sensor data for clinicians;how we integrated hospital practice in the system design, and how we managed the ethics clearance for the field evaluation. We hope that these lessons are useful for HCI and health researchers who aim to innovate the field of health but feel restricted with the little knowledge of design and electronics. © 2020 ACM.

关键词： Research laboratories

来源：评论

学校读者我要写书评

暂无评论

Big Data and Cloud Computing 1

引用

丛书名： Lecture Notes in Electrical engineering

1000年

作者： Neelanarayanan Venkataraman Lipo Wang Xavier Fernando Ahmed F. Zobaa

来源：评论

学校读者我要写书评

暂无评论

FPGA for secured hardware & IP ownership

FPGA for secured hardware & IP ownership

引用

IEEE Electron Devices Kolkata Conference (EDKCON)

作者： Suman Lata Tripathi Abhishek Kumar Mufti Mahmud VLSI Design Lab Lovely Professional University Punjab NTU India VLSI Design Lab Lovely Professional University Punjab India Department of Computer Science & Engineering Nottingham Trent University UK

ISBN: (纸本)9781665472067

Reconfigurable nature of embedded FPGAs (EFPGA) are commonly used hardware for system-on-chip design due to additional features of upgradability, and security with high computational powers. SoC design with high portability EFPGA has the potential to replace time-consuming, less compatible full custom SoC design. Security is a major concern of designers to avoid illegal use of IPs for SoC design from external attacks or treats without paying charges to the owner. Security challenges are associated with bitstream loading on FPGA, design functionality, and onboard memory blocks. Several techniques are used to generate secured IP are explored mainly secured bitstream generation, generating physical unclonable functions (PUF), security protocol etc. Xilinx FPGA boards are frequently used for IP design prototyping with software like Vivado tool using HDLs. This paper is a comprehenssive study of current state of art of secured hardware design with FPGA.

关键词： Protocols Loading Watermarking Physical unclonable function SRAM cells Software System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Membership Inference Attacks Against Temporally Correlated Data in Deep Reinforcement Learning

arXiv

引用

arXiv 2021年

作者： Gomrokchi, Maziar Amin, Susan Aboutalebi, Hossein Wong, Alexander Precup, Doina Department of Computer Science McGill University Mila Canada Cheriton School of Computer Science University of Waterloo VIP Lab Canada Department of Systems Design Engineering University of Waterloo VIP Lab DarwinAI Canada Department of Computer Science McGill University Mila DeepMind Canada

While significant research advances have been made in the field of deep reinforcement learning, there have been no concrete adversarial attack strategies in literature tailored for studying the vulnerability of deep reinforcement learning algorithms to membership inference attacks. In such attacking systems, the adversary targets the set of collected input data on which the deep reinforcement learning algorithm has been trained. To address this gap, we propose an adversarial attack framework designed for testing the vulnerability of a state-of-the-art deep reinforcement learning algorithm to a membership inference attack. In particular, we design a series of experiments to investigate the impact of temporal correlation, which naturally exists in reinforcement learning training data, on the probability of information leakage. Moreover, we compare the performance of collective and individual membership attacks against the deep reinforcement learning algorithm. Experimental results show that the proposed adversarial attack framework is surprisingly effective at inferring data with an accuracy exceeding 84% in individual and 97% in collective modes in three different continuous control Mujoco tasks, which raises serious privacy concerns in this regard. Finally, we show that the learning state of the reinforcement learning algorithm influences the level of privacy breaches significantly. Copyright © 2021, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Network energy consumption analysis and dormancy mechanism based on ant colony algorithm in cloud computing environment for IOT service and real-time embedded industrial control system 27

Network energy consumption analysis and dormancy mechanism b...

引用

27th Chinese Control and Decision Conference, CCDC 2015

作者： Shi, Shaoling Jing, Zhang Chen, Moliang Hui, Rong Yi, Cui Fu, Xiaodong Computer Technology Application Key Lab of Yunnan Province Kunming University of Science and Technology Kunming Yunnan China Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming Yunnan China Faculty of Art and Design Kunming Metallurgy College Kunming Yunnan China Yunnan Academy of Scientific and Technical Information Kunming Yunnan China

ISBN: (纸本)9781479970179

At present, cloud computing technology is widely used in IOT(Internet of Things) service and real-time embedded industrial control system energy consumption, problem in the cloud computing has always been the hot topic of industry and academic research. This paper analyzes the energy consumption of each equipment under the dormancy mechanism in the cloud computing environment. Meanwhile, this paper introduces the ant colony algorithm into a basic network energy consumption model, thereby building a new model for the energy consumption optimization. The simulation experiments were implemented on a cloud computing simulation platform CLOUDSIM. In comparison with two algorithms - Min LP and Dijkstra, the model presented in this paper was proved to be effective and more energy-efficient. © 2015 IEEE.

关键词： ant colony algorithm cloud computing dormancy mechanism energy consumption analysis IOT service real-time embedded industrial control system

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Robotics: The Biology, Intelligence and Technology of Self-Organizing Machines [Review Article]

引用

Artificial Life 2001年第4期7卷 419-424页

作者： Hod Lipson Cornell Computer Aided Design Lab Mechanical and Aerospace Engineering and Computing and Information Science Cornell University Ithaca NY 14853-2801 USA hod.lipson@cornell.edu

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：