检索结果-内蒙古大学图书馆

Enhancing Differential Evolution with Commensal Learning and Uniform Local Search

Chinese Journal of Electronics 2017年第4期26卷 725-733页

作者： PENG Hu WU Zhijian DENG Changshou State Key Laboratory of Software Engineering School of Computer Wuhan University School of Information Science and Technology Jiujiang University

Differential evolution(DE) is a popular and powerful evolutionary algorithm for global optimization problems. However, the combination of mutation strategies and parameter settings of DE is problem dependent and choosing the suitable one is a challenge work and timeconsuming. In addition, the deficiency in local exploitation also has a significant influence on the performance of *** order to solve these problems, a DE variant with Commensal learning and uniform local search(CUDE) has been proposed in this paper. In CUDE, commensal learning is proposed to adaptively select optimal mutation strategy and parameter setting simultaneously under the same criteria. Moreover, uniform local search enhances exploitation ability. Comprehensive experiment results on all the CEC2013 test suite and comparison with the state-of-the-art DE variants indicate that the CUDE is very competitive.

关键词： Differential evolution Commensal learn ing Uniform local search Global optimization

来源：评论

学校读者我要写书评

暂无评论

EMG Signals based Human Action Recognition via Deep Belief Networks

引用

IFAC-PapersOnLine 2019年第19期52卷 271-276页

作者： Jianhua Zhang Chen Ling Sunan Li OsloMet AI Lab Department of Computer Science OsloMet - Oslo Metropolitan University 0166 Oslo Norway School of Information Science and Engineering East China University of Science and Technology Shanghai 200237 China

Electromyography (EMG) signals can be used for action classification. Nonetheless, due to their nonlinear and time-varying properties, it is difficult to classify the EMG signals and it is critical to use appropriate algorithms for EMG feature extraction and classification. In previous studies various ML methods have been applied. In this paper, we extract four time-domain features of the EMG signals and use a generative graphical model, Deep Belief Network (DBN), to classify the EMG signals. A DBN is a fast, greedy deep learning algorithm that can find a set of optimal weights rapidly, even in deep networks with many hidden layers and a large number of parameters. To evaluate this model, we acquired EMG signals, extracted their features, and then utilized the DBN model as human action classifiers. The real data analysis results are presented to show the effectiveness of the proposed deep learning technique for 4-class recognition of human actions based on the measured EMG signals. The proposed DBN model has potential to be applied in design of EMG-based user interfaces.

关键词： Deep learning Deep Belief Network (DBN) Restricted Boltzmann Machine (RBM) Electromyography (EMG) Feature extraction Human action recognition

来源：评论

学校读者我要写书评

暂无评论

Mechanical Sensors for Ultraheavy Dark Matter Searches via Long-range Forces

arXiv

引用

arXiv 2025年

作者： Qin, Juehang Amaral, Dorian W.P. Bhave, Sunil A. Cai, Erqian Carney, Daniel Lang, Rafael F. Li, Shengchao Marino, Alberto M. Marvinney, Claire Newton, Jared R. Taylor, Jacob M. Tunnell, Christopher Department of Physics and Astronomy Rice University HoustonTX77005 United States Quantum Science Center Oak Ridge National Laboratory Oak RidgeTN37831 United States OxideMEMS Lab Elmore Family School of Electrical and Computer Engineering Purdue University West LafayetteIN47907 United States Physics Division Lawrence Berkeley National Laboratory BerkeleyCA94720-8153 United States Department of Physics and Astronomy Purdue University West LafayetteIN47907 United States Quantum Information Science Section Computational Sciences and Engineering Division Oak Ridge National Laboratory One Bethel Valley Road Oak RidgeTN37831 United States Joint Quantum Institute National Institute of Standards and Technology College ParkMD20742 United States Joint Center for Quantum Information and Computer Science University of Maryland College ParkMD20742 United States Department of Computer Science Rice University HoustonTX77005 United States

Dark matter candidates with masses around the Planck-scale are theoretically well-motivated, and it has been suggested that it might be possible to search for dark matter solely via gravitational interactions in this mass range. In this work, we explore the pathway towards searching for dark matter candidates with masses around the Planck-scale using mechanical sensors while considering realistic experimental constraints, and develop analysis techniques needed to conduct such searches. These dark matter particles are expected to leave tracks as their signature in mechanical sensor arrays, and we show that we can effectively search for such tracks using statistical approaches to track-finding. We analyze a range of possible experimental setups and compute sensitivity projections for searches for ultraheavy dark matter coupling to the Standard Model via long-range forces. We find that while a search for Planck-scale dark matter purely via gravitational couplings would be exceedingly difficult, requiring > 70 dB of quantum noise reduction with a 1003 array of devices, there is a wide range of currently unexplored dark matter candidates which can be searched for with already existing or near-term experimental platforms. © 2025, CC BY.

关键词： Gravitational effects

来源：评论

学校读者我要写书评

暂无评论

An Edge Computing Platform of Guide-dog Robot for Visually Impaired

An Edge Computing Platform of Guide-dog Robot for Visually I...

引用

International Symposium on Autonomous Decentralized Systems (ISADAS)

作者： Jinhui Zhu Yinong Chen Mei Zhang Qiang Chen Ying Guo Huaqing Min Zhilie Chen School of Software Engineering South China University of Technology Guangzhou China School of Computing Informatics and Decision Systems Engineering Arizona State University Tempe USA School of Automation Science and Control Engineering South China University of Technology Guangzhou China College of computer & information science Southwest University Chongqing China School of Information Science and Technology Qingdao University of Science and Technology Qingdao China EVOC Intelligent Technology Company Limited Shen zhen China

ISBN: (数字)9781728116723

ISBN: (纸本)9781728116730

information processing of guide dog robot requires expensive computing resources to meet real-time performance. We propose an edge computing framework based on Intel Up-Squared board and neural compute stick. Image processing and real-time control are performed on the framework. In addition, the voice recognition and commanding are also implemented, which are processed on Amazon cloud service. Vision, speech, and control services are integrated by ASU VIPLE (Visual IoT/Robotics Programming Language Environment). A prototype is developed, which implements the guide dog's obstacle avoidance, traffic sign recognition and following, and voice interaction with human.

关键词： Dogs Mobile robots Robot sensing systems Wheelchairs Edge computing Cameras

来源：评论

学校读者我要写书评

暂无评论

Graph Convolutional Networks for Temporal Action Localization

Graph Convolutional Networks for Temporal Action Localizatio...

引用

International Conference on computer Vision (ICCV)

作者： Runhao Zeng Wenbing Huang Chuang Gan Mingkui Tan Yu Rong Peilin Zhao Junzhou Huang School of Software Engineering South China University of Technology China Tencent AI Lab Department of Computer Science and Technology Tsinghua University MIT-IBM Watson AI Lab Peng Cheng Laboratory Shenzhen

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

Most state-of-the-art action localization systems process each action proposal individually, without explicitly exploiting their relations during learning. However, the relations between proposals actually play an important role in action localization, since a meaningful action always consists of multiple proposals in a video. In this paper, we propose to exploit the proposal-proposal relations using GraphConvolutional Networks (GCNs). First, we construct an action proposal graph, where each proposal is represented as a node and their relations between two proposals as an edge. Here, we use two types of relations, one for capturing the context information for each proposal and the other one for characterizing the correlations between distinct actions. Then we apply the GCNs over the graph to model the relations among different proposals and learn powerful representations for the action classification and localization. Experimental results show that our approach significantly outperforms the state-of-the-art on THUMOS14(49.1% versus 42.8%). Moreover, augmentation experiments on ActivityNet also verify the efficacy of modeling action proposal relationships.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Selective kernel networks

arXiv

引用

arXiv 2019年

作者： Li, Xiang Wang, Wenhai Hu, Xiaolin Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China Momenta National Key Lab for Novel Software Technology Nanjing University Department of Computer Science and Technology Tsinghua University China

In standard Convolutional Neural Networks (CNNs), the receptive fields of artificial neurons in each layer are designed to share the same size. It is well-known in the neuroscience community that the receptive field size of visual cortical neurons are modulated by the stimulus, which has been rarely considered in constructing CNNs. We propose a dynamic selection mechanism in CNNs that allows each neuron to adaptively adjust its receptive field size based on multiple scales of input information. A building block called Selective Kernel (SK) unit is designed, in which multiple branches with different kernel sizes are fused using softmax attention that is guided by the information in these branches. Different attentions on these branches yield different sizes of the effective receptive fields of neurons in the fusion layer. Multiple SK units are stacked to a deep network termed Selective Kernel Networks (SKNets). On the ImageNet and CIFAR benchmarks, we empirically show that SKNet outperforms the existing state-of-the-art architectures with lower model complexity. Detailed analyses show that the neurons in SKNet can capture target objects with different scales, which verifies the capability of neurons for adaptively adjusting their receptive field sizes according to the input. The code and models are available at https://***/implus/SKNet. Copyright © 2019, The Authors. All rights reserved.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

A novel lightweight PUF-based RFID mutual authentication protocol 6th

A novel lightweight PUF-based RFID mutual authentication pro...

引用

6th International Conference on Frontier Computing, FC 2017

作者： Liang, Wei Xie, Songyou Li, Xiong Long, Jing Xie, Yong Li, Kuan-Ching School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan411201 China Department of Software and Engineering Xiamen University of Technology XiamenFujian361024 China Department of Information Science and Engineering Providence University Taichung City43301 Taiwan

ISBN: (纸本)9789811073977

The widespread use of radio frequency identification (RFID) in IoTs makes authentication of RFID systems be widely concerned. In existing encryption schemes (e.g., Hash function) in electronic products, secure chip is hard to be used in high performance RFID system due to high computation complexity and cost. In this work, we consider problems in these performances and propose a PUF-GIMAP protocol by combining GIMAP protocol and physically unclonable functions (PUFs). The response of PUF is added into protocol. The mutual authentication between label and reader is realized by transmitting information such as secret key and dynamical pseudonym, which greatly ensures data security in transmission. After authentication, the reserved data is updated in time. The protocol analysis shows that the proposed scheme has the advantages of high security and high reliability. © 2018, Springer Nature Singapore Pte Ltd.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Deep Active Learning for Anchor User Prediction

arXiv

引用

arXiv 2019年

作者： Cheng, Anfeng Zhou, Chuan Yang, Hong Wu, Jia Li, Lei Tan, Jianlong Guo, Li Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Centre for Artificial Intelligence School of Software FEIT University of Technology Sydney Australia Department of Computing Macquarie University Sydney Australia School of Computer Science and Information Engineering Hefei University of Technology China

Predicting pairs of anchor users plays an important role in the cross-network analysis. Due to the expensive costs of labeling anchor users for training prediction models, we consider in this paper the problem of minimizing the number of user pairs across multiple networks for labeling as to improve the accuracy of the prediction. To this end, we present a deep active learning model for anchor user prediction (DALAUP for short). However, active learning for anchor user sampling meets the challenges of non-i.i.d. user pair data caused by network structures and the correlation among anchor or non-anchor user pairs. To solve the challenges, DALAUP uses a couple of neural networks with shared-parameter to obtain the vector representations of user pairs, and ensembles three query strategies to select the most informative user pairs for labeling and model training. Experiments on real-world social network data demonstrate that DALAUP outperforms the state-of-the-art approaches. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Harmonized software Quality Improvement Models for Sudanese SME Based on CMMI

Harmonized Software Quality Improvement Models for Sudanese ...

引用

International Conference on computer, Control, Electrical, and Electronics engineering (ICCCEEE)

作者： Zeinab Mahmoud Aiman Solyman Arafat Abdulgader Mohammed Elhag Department of Computer Science Faculty of Science and Technology Nile Valley University Sudan School of software engineering South china University of Technology SCUT China Department of Information System University of Bisha Saudi Arabia

ISBN: (数字)9781728110066

ISBN: (纸本)9781728110073

software institutions recently implement more than one software process model in order to achieve a high value in their products and services. The challenges of implementing several quality models are increasing the risk of Multi-Model Environment (MME) failure and more resources are needed to support the MME. This kind of resources is not available in the Small and Medium Enterprises (SME), especially in Sudanese institutions. This study aims to provide a solution by encouraging the Sudanese SMEs to apply software models in their software development processes. We are seeking to make these institutions understand how to integrate product quality models with software process improvement models. To achieve this goal, we used a systematic harmonization technique to harmonize and map ISO/IEC 25010 standard onto Capability Maturity Model Integrity (CMMI) Dev 1.3 level 2 and 3. Also, we reviewed the related works of the previous studies on MMEs to achieve better results. The results show some of the processes and activities of CMMI Dev 1.3 considering software quality attributes on the early stage of the software Development Lifecycle (SDLC). On the other hand, we presented how to apply the mapped models and suggest a tool for implementation. This kind of approach gives small organizations the ability to apply multi SPI models.

关键词： software quality ISO Standards Capability maturity model Organizations Analytical models

来源：评论

学校读者我要写书评

暂无评论

Deep Learning in Digital Breast Tomosynthesis: Current Status, Challenges, and Future Trends

MedComm

引用

MedComm 2025年第6期6卷 e70247页

作者： Wang, Ruoyun Chen, Fanxuan Chen, Haoman Lin, Chenxing Shuai, Jincen Wu, Yutong Ma, Lixiang Hu, Xiaoqu Wu, Min Wang, Jin Zhao, Qi Shuai, Jianwei Pan, Jingye Oujiang Laboratory (Zhejiang Lab for Regenerative Medicine Vision and Brain Health) Wenzhou Institute University of Chinese Academy of Sciences Wenzhou China Wenzhou Medical University Wenzhou China UCSC Baskin School of Engineering University of California Santa Cruz CA United States Key Laboratory of Intelligent Treatment and Life Support for Critical Diseases of Zhejiang Province Wenzhou China Department of Anatomy Histology & Embryology School of Basic Medical Sciences Fudan University Shanghai China Department of Medicine Harvard Medical School and Brigham and Women's Hospital Boston MA United States Joint Research Centre on Medicine The Affiliated Xiangshan Hospital of Wenzhou Medical University Ningbo China Stony Brook University Stony Brook NY United States School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China Department of Big Data in Health Science The First Affiliated Hospital of Wenzhou Medical University Wenzhou China Zhejiang Engineering Research Center for Hospital Emergency and Process Digitization Wenzhou China

The high-resolution three-dimensional (3D) images generated with digital breast tomosynthesis (DBT) in the screening of breast cancer offer new possibilities for early disease diagnosis. Early detection is especially important as the incidence of breast cancer increases. However, DBT also presents challenges in terms of poorer results for dense breasts, increased false positive rates, slightly higher radiation doses, and increased reading times. Deep learning (DL) has been shown to effectively increase the processing efficiency and diagnostic accuracy of DBT images. This article reviews the application and outlook of DL in DBT-based breast cancer screening. First, the fundamentals and challenges of DBT technology are introduced. The applications of DL in DBT are then grouped into three categories: diagnostic classification of breast diseases, lesion segmentation and detection, and medical image generation. Additionally, the current public databases for mammography are summarized in detail. Finally, this paper analyzes the main challenges in the application of DL techniques in DBT, such as the lack of public datasets and model training issues, and proposes possible directions for future research, including large language models, multisource domain transfer, and data augmentation, to encourage innovative applications of DL in medical imaging. © 2025 The Author(s). MedComm published by Sichuan International Medical Exchange & Promotion Association (SCIMEA) and John Wiley & Sons Australia, Ltd.

关键词： deep learning digital breast tomosynthesis early breast cancer screening medical image analysis public database

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：