检索结果-内蒙古大学图书馆

International Conference on Application Specific systems (ASAP), Architectures and Processors

作者： Wenlai Zhao Haohuan Fu Wayne Luk Teng Yu Shaojun Wang Bo Feng Yuchun Ma Guangwen Yang Ministry of Education Key Laboratory for Earth System Modeling and Center for Earth System Science Tsinghua University China Tsinghua National Laboratory for Information Science and Technology China Department of Computing Imperial college London UK Department of Automatic Test and Control Harbin Institute of Technology China Department of Computer Science and Technology Tsinghua University China

ISBN: (纸本)9781509015047

This paper presents a novel reconfigurable framework for training Convolutional Neural Networks (CNNs). The proposed framework is based on reconfiguring a streaming datapath at runtime to cover the training cycle for the various layers in a CNN. The streaming datapath can support various parameterized modules which can be customized to produce implementations with different trade-offs in performance and resource usage. The modules follow the same input and output data layout, simplifying configuration scheduling. For different layers, instances of the modules contain different computation kernels in parallel, which can be customized with different layer configurations and data precision. The associated models on performance, resource and bandwidth can be used in deriving parameters for the datapath to guide the analysis of design trade-offs to meet application requirements or platform constraints. They enable estimation of the implementation specifications given different layer configurations, to maximize performance under the constraints on bandwidth and hardware resources. Experimental results indicate that the proposed module design targeting Maxeler technology can achieve a performance of 62.06 GFLOPS for 32-bit floating-point arithmetic, outperforming existing accelerators. Further evaluation based on training LeNet-5 shows that the proposed framework achieves about 4 times faster than CPU implementation of Caffe and about 7.5 times more energy efficient than the GPU implementation of Caffe.

关键词： Training Field programmable gate arrays Convolution Computational modeling Bandwidth Neural networks Runtime

来源：评论

学校读者我要写书评

暂无评论

Tail Classes Matter: Long-Tailed Object Detection Revisited

Tail Classes Matter: Long-Tailed Object Detection Revisited

引用

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

作者： Yinglu Zhang Chenbo Zhang Lu Zhang Tianying Liu Jihong Guan Xinkai Liang Jiajia Zhao Shuigeng Zhou Shanghai Key Lab of Intelligent Information Processing and School of Computer Science Fudan University China Department of Computer Science & Technology Tongji University China Science and Technology on Complex System Conroland InelligentAgent Cooperation Laboratory Beijing Electro-Mechanical Engineering Institute China

Real-world data ubiquitously exhibit long-tailed distribution, which sparks the increasing interest in long-tailed object detection (LTOD). However, existing methods neglect that a lack of diverse data in tail classes will cause underrepresented tail class features, making their efforts for balancing foreground classes tend to over-fit tail classes and be less effective. In this paper, we propose a multi-class co-attention generation network to increase data diversity of tail classes by generating augmented samples. To alleviate imbalance, we develop a distribution-aware up-sampling strategy, performing differential up-sampling for different classes and design a bi-directional regulation loss to adjust both positive and negative gradients. Moreover, we construct a new dataset LVIS-X with more rare classes based on existing LTOD benchmark dataset LVIS. Experiments on LVIS and LVIS-X demonstrate the superiority of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An extention of height value algorithm for micro-mouse robot applying for exploring unknown region

An extention of height value algorithm for micro-mouse robot...

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Zhengtian Li Haibin Duan Yan Gao Zhuoning Dong School of Automation Science and Electrical Engineering Beihang University Beijing China Science and Technology on Aircraft Control Laboratory Beihang University Beijing China Provincial Key Laboratory for Information Processing Technology Soochow University Suzhou China School of Electrical and Electronic Engineering Nanyang Technological University Singapore

The micro-mouse competition is gaining immense popularity universally. This paper proposes algorithm referred to the “extended height value algorithm” which is developed to an advanced level, so that the artificial robot could be made capable of exploring unknown regions such as micro-mouse competition maze. All of the 256 units in the standard 16*16 units maze are given a series of numbers, which represent discretely assigned potential levels of turning into the crossway during exploring task. The numbers will be taken into consideration when the robot makes the crossway choice as well as autonomous route decisions. Then the choices will alter when the micro-mouse walks in order to optimize the exploring process. The paper also demonstrates effective measures to avoid duplication exploring as much as possible with artificial intelligence technique. In order to verify the developed algorithm, a simple, yet effective simulation program is coded to show that the improved algorithm has higher average efficiency compared with the less intelligent traditional algorithms.

关键词： Algorithm design and analysis Robot kinematics Arrays Mice Conferences Industrial electronics

来源：评论

学校读者我要写书评

暂无评论

Biocompatible chitosan/polyethylene glycol/multi-walled carbon nanotube composite scaffolds for neural tissue engineering

引用

Journal of Zhejiang University-Science B(Biomedicine & Biotechnology) 2022年第1期23卷 58-73页

作者： Shengbo SANG Rong CHENG Yanyan CAO Yayun YAN Zhizhong SHEN Yajing ZHAO Yanqing HAN Shanxi Key Laboratory of Micro Nano Sensors&Artificial Intelligence Perception College of Information and ComputerTaiyuan University of TechnologyTaiyuan030024China Key Lab of Advanced Transducers and Intelligent Control System of the Ministry of Education Taiyuan University of TechnologyTaiyuan030024China College of Information Science and Engineering Hebei North UniversityZhangjiakou075000China Shanxi Six-Dimensional Artificial Intelligence Biomedical Research Institute Taiyuan030031China Department of Neurology Shanxi Provincial Cardiovascular HospitalTaiyuan030024China

Carbon nanotube(CNT)composite materials are very attractive for use in neural tissue engineering and biosensor *** scaffolds are excellent mimics of extracellular matrix due to their hydrophilicity,viscosity,and *** can also impart conductivity to other insulating materials improve mechanical stability guide neuronal cell behavior and trigger axon *** performance of chitosan(CS)/polyethylene glycol(PEG)composite scaffolds could be optimized by introducing multi-walled CNTs(MWCNTs).CS/PEG/CNT composite scaffolds with CNT content of 1%,3%,and 5%(1%=0.01 g/mL)were prepared by *** physical and chemical properties and biocompatibility were *** electron microscopy(SEM)showed that the composite scaffolds had a highly connected porous *** electron microscope(TEM)and Raman spectroscopy proved that the CNTs were well dispersed in the CS/PEG matrix and combined with the CS/PEG nanofiber *** enhanced the elastic modulus of the *** porosity of the scaffolds ranged from 83%to 96%.They reached a stable water swelling state within 24 h,and swelling decreased with increasing MWCNT *** electrical conductivity and cell adhesion rate of the scaffolds increased with increasing MWCNT *** showed that rat pheochromocytoma(PC12)cells grown in the scaffolds had characteristics similar to nerve *** measured changes in the expression of nerve cell markers by quantitative real-time polymerase chain reaction(qRT-PCR),and found that PC12 cells cultured in the scaffolds expressed growth-associated protein 43(GAP43),nerve growth factor receptor(NGFR),and class IIIβ-tubulin(TUBB3)*** research showed that the prepared CS/PEG/CNT scaffold has good biocompatibility and can be further applied to neural tissue engineering research.

关键词： Multi-walled carbon nanotube(MWCNT) Cell-scaffold PC12 cells Biocompatibility

来源：评论

学校读者我要写书评

暂无评论

Research and application of Transformer based anomaly detection model: A literature review

arXiv

引用

arXiv 2024年

作者： Ma, Mingrui Han, Lansheng Zhou, Chunjie Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Hubei Wuhan430074 China The Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Wuhan430074 China

Transformer, as one of the most advanced neural network models in Natural Language processing (NLP), exhibits diverse applications in the field of anomaly detection. To inspire research on Transformer-based anomaly detection, this review offers a fresh perspective on the concept of anomaly detection. We explore the current challenges of anomaly detection and provide detailed insights into the operating principles of Transformer and its variants in anomaly detection tasks. Additionally, we delineate various application scenarios for Transformer-based anomaly detection models and discuss the datasets and evaluation metrics employed. Furthermore, this review highlights the key challenges in Transformer-based anomaly detection research and conducts a comprehensive analysis of future research trends in this domain. The review includes an extensive compilation of over 100 core references related to Transformer-based anomaly detection. To the best of our knowledge, this is the first comprehensive review that focuses on the research related to Transformer in the context of anomaly detection. We hope that this paper can provide detailed technical information to researchers interested in Transformer-based anomaly detection tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Learning of Depth and Pose Based on Monocular Camera and Inertial Measurement Unit (IMU)

Unsupervised Learning of Depth and Pose Based on Monocular C...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Yanbo Wang Hanwen Yang Jianwei Cai Guangming Wang Jingchuan Wang Yi Huang University of Michigan-Shanghai Jiao Tong University Joint Institute Shanghai Jiao Tong University Shanghai China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Weitong Vision Technology Co. Ltd.

The main content of the research in this paper is the estimation of depth and pose based on monocular vision and Inertial Measurement Unit (IMU). The usual depth estimation network and pose estimation network require depth ground truth or pose ground truth as a supervised signal for training, while the depth ground truth and pose ground truth are hard to obtain, and monocular vision based depth estimation cannot predict absolute depth. In this paper, with the help of IMU, which is inexpensive and widely used, we can obtain angular velocity and acceleration information. Two new supervision signals are proposed and the calculation expressions are given. Among them, the model trained with acceleration constraint shows a good ability to estimate the absolute depth during the test. It can be considered that the model can estimate the absolute depth. We also derive the method of estimating the scale factor during the test from the acceleration constraint, and also achieve good results as the acceleration constraint does. In addition, this paper also studies the method of using IMU information as pose network input and as selecting conditions. Moreover, it analyzes and discusses the experimental results. At the same time, we also evaluate the effect of the pose estimation of the relevant models. This article starts by reviewing the achievements and deficiencies of the work in this field, combines the use of IMU, puts forward three new methods such as a new loss function, and conducts a test analysis and discussion of relevant indicators on the KITTI data set.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SAR image classification based on spiking neural network through spike-time dependent plasticity and gradient descent

arXiv

引用

arXiv 2021年

作者： Chen, Jiankun Qiu, Xiaolan Ding, Chibiao Wu, Yirong National Key Laboratory of Science and Technology on Microwave Imaging Institute of Electronics Aerospace Information Research Institute Beijing10090 China The Key Laboratory of Technology in Geo-spatial Information Processing and Application System Aerospace Information Research Institute Chinese Academy of Sciences Beijing10090 China Aerospace Information Research Institute Chinese Academy of Sciences Beijing100190 China Suzhou Research Institute Aerospace Information Research Institute Chinese Academy of Sciences Suzhou215123 China The University of Chinese Academy of Sciences Beijing10049 China

At present, the Synthetic Aperture Radar (SAR) image classification method based on convolution neural network (CNN) has faced some problems such as poor noise resistance and generalization ability. Spiking neural network (SNN) is one of the core components of brain-like intelligence and has good application prospects. This article constructs a complete SAR image classifier based on unsupervised and supervised learning of SNN by using spike sequences with complex spatio-temporal information. We firstly expound the spiking neuron model, the receptive field of SNN, and the construction of spike sequence. Then we put forward an unsupervised learning algorithm based on STDP and a supervised learning algorithm based on gradient descent. The average classification accuracy of single layer and bilayer unsupervised learning SNN in three categories images on MSTAR dataset is 80.8% and 85.1%, respectively. Furthermore, the convergent output spike sequences of unsupervised learning can be used as teaching signals. Based on the TensorFlow framework, a single layer supervised learning SNN is built from the bottom, and the classification accuracy reaches 90.05%. By comparing noise resistance and model parameters between SNNs and CNNs, the effectiveness and outstanding advantages of SNN are verified. Code to reproduce our experiments is available at https://***/Jiankun-chen/Supervised-SNN-with-GD. © 2021, CC BY.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

A Method of Cattle Follicle Ultrasound Images Detection Based on HOG + Improved LBP + SVM

A Method of Cattle Follicle Ultrasound Images Detection Base...

引用

IEEE Conference on Industrial Electronics and Applications

作者： Yong Lv Jun Liu Wenhao Zeng Hubei Province Key Laboratory of Intelligent Information Processing and Real Time Industrial System Wuhan University of Science and Technology Wuhan

To improve the diagnostic accuracy of follicle ultrasound images detection, this paper proposed a method of cattle follicle ultrasound images detection based on HOG + Improved LBP + SVM. It calculated the Histogram of Oriented Gradient (HOG) feature for all cell in detection window, used improved Local Binary Pattern method to get gray feature, combined with the Support Vector Machine (SVM), it did the feature training and test experiment, last, the proposed method was compared with that single HOG feature detection, single traditional LBP feature detection and HOG + traditional LBP feature detection. Experimental results showed, the proposed method can effectively describe and detect cattle follicle ultrasound images, and it has higher recognition accuracy.

关键词： Histogram of Oriented Gradient (HOG) Local Binary Pattern (LBP) Support Vector Machine (SVM) Feature Combination

来源：评论

学校读者我要写书评

暂无评论

An improved reference point sampling method on Pareto optimal front

An improved reference point sampling method on Pareto optima...

引用

Congress on Evolutionary Computation

作者： Cheng He Linqiang Pan Hang Xu Ye Tian Xingyi Zhang Laboratory of Image Information Processing and Intelligent Control Huazhong University of Science and Technology Wuhan Hubei China Huazhong University of Science and Technology Wuhan Hubei CN Department of Computer Science Xiamen University Xiamen Fujian China Key Lab of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei Anhui China

ISBN: (纸本)9781509006243

In this paper, we propose a sampling approach of reference points used for performance metrics of multi-objective evolutionary algorithms. Traditional reference point sampling methods, such as the Das and Dennis method, usually sample the reference points via a set of uniformly distributed weight vectors generated on an ideal hyper-plane in objective space, which however often ignore the geometric shape of a specific Pareto front. Therefore, we propose a novel reference point sampling approach by taking the specific shape of the Pareto optimal front to be tackled into account for measuring the performance of multi-objective evolutionary algorithms. The performance of the proposed reference point sampling method against the other two state-of-the-art sampling methods is tested on six test instances in various conditions, which clearly demonstrate the effectiveness and superiority of the proposed sampling method.

关键词： Sampling methods Shape Convergence Evolutionary computation Optimization Euclidean distance

来源：评论

学校读者我要写书评

暂无评论

control Strategy of 6-DOF Manipulator based on Improved Active Disturbance Rejection control

Control Strategy of 6-DOF Manipulator based on Improved Acti...

引用

Chinese control and Decision Conference, CCDC

作者： Dongxu Zhang Lixiang Ma Bingyou Liu Pan Yang College of Electrical Engineering Anhui Polytechnic University Key Laboratory of Advanced Perception and Intelligent Control of High-End Equipment Ministry of Education Wuhu China Anhui Institute of Information Technology Wuhu China Anhui Dar Intelligent Control System Stock Co. Ltd Wuhu China

Aiming at the problems of high coupling, parameter uncertainty and external environment interference in practical applications of six degrees of freedom manipulator, a control strategy based on improved active disturbance rejection control was proposed. Firstly, in order to improve the response speed of the system, the sliding mode control tracking differentiator (SMC-TD) is designed based on the synovial *** order to reduce the system jitter, the new sliding mode function is used to improve the sliding mode control law, which reduces the system jitter and improves the system response speed. Secondly, the han function is constructed to realize the design of continuous smooth extended state observer, and the improved fractional extended state observer (FO-ESO) is designed in combination with fractional calculus, which enhances the anti-interference ability of the system. Finally, combined with the traditional nonlinear error feedback control law (NLSEF), an improved active disturbance rejection controller was built, and different control strategies were used to compare the six degrees of freedom manipulator in the same environment. The experimental results show that the controller has good control effect and anti-disturbance robustness, which proves the effectiveness of the proposed method.

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：