检索结果-内蒙古大学图书馆

Distributed bandit learning: near-optimal regret with efficient communication

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wang, Yuanhao Hu, Jiachen Chen, Xiaoyu Wang, Liwei Institute for Interdisciplinary Information Sciences Tsinghua University School of Electronics Engineering and Computer Science Peking University Key Laboratory of Machine Perception MOE School of EECS Peking University Center for Data Science Peking University Beijing Institute of Big Data Research

We study the problem of regret minimization for distributed bandits learning, in which M agents work collaboratively to minimize their total regret under the coordination of a central server. Our goal is to design communication protocols with near-optimal regret and little communication cost, which is measured by the total amount of transmitted data. For distributed multi-armed bandits, we propose a protocol with near-optimal regret and only O(M log(MK)) communication cost, where K is the number of arms. The communication cost is independent of the time horizon T , has only logarithmic dependence on the number of arms, and matches the lower bound except for a logarithmic factor. For distributed d-dimensional linear bandits, we propose a protocol that achieves near-optimal regret and has communication cost of order O (Md), which has only logarithmic dependence on T . Copyright © 2019, The Authors. All rights reserved.

关键词： Machine learning

Adaptive unimodal cost volume filtering for deep stereo matching

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhang, Youmin Chen, Yimin Bai, Xiao Yu, Suihanjin Yu, Kun Li, Zhiwei Yang, Kuiyuan State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Jiangxi Research Institute Beihang University Beijing China DeepMotion

State-of-the-art deep learning based stereo matching approaches treat disparity estimation as a regression problem, where loss function is directly defined on true disparities and their estimated ones. However, disparity is just a byproduct of a matching process modeled by cost volume, while indirectly learning cost volume driven by disparity regression is prone to overfitting since the cost volume is under constrained. In this paper, we propose to directly add constraints to the cost volume by filtering cost volume with unimodal distribution peaked at true disparities. In addition, variances of the unimodal distributions for each pixel are estimated to explicitly model matching uncertainty under different contexts. The proposed architecture achieves state-of-the-art performance on Scene Flow and two KITTI stereo benchmarks. In particular, our method ranked the 1st place of KITTI 2012 evaluation and the 4th place of KITTI 2015 evaluation (recorded on 2019.8.20). The codes of AcfNet are available at: https://***/DeepMotionAIResearch/ DenseMatchingBenchmark. Copyright © 2019, The Authors. All rights reserved.

关键词： Uncertainty analysis

Adaptive NMS: Refining pedestrian detection in a crowd

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liu, Songtao Huang, Di Wang, Yunhong Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University State Key Laboratory of Software Development Environment Beihang University School of Computer Science and Engineering Beihang University Beijing100191

Pedestrian detection in a crowd is a very challenging issue. This paper addresses this problem by a novel NonMaximum Suppression (NMS) algorithm to better refine the bounding boxes given by detectors. The contributions are threefold: (1) we propose adaptive-NMS, which applies a dynamic suppression threshold to an instance, according to the target density;(2) we design an efficient subnetwork to learn density scores, which can be conveniently embedded into both the single-stage and two-stage detectors;and (3) we achieve state of the art results on the CityPersons and CrowdHuman benchmarks. Copyright © 2019, The Authors. All rights reserved.

关键词： Machine learning

A Survey on Machine Learning Algorithms in Little-Labeled data for Motor Imagery-Based Brain-Computer Interfaces

学校读者我要写书评

暂无评论

Journal of Information Hiding and Privacy Protection 2019年第1期1卷 11-21页

作者： Yuxi Jia Feng Li Fei Wang Yan Gui School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and TechnologyChangsha410114China School of Mechanical and Aerospace Engineering Nanyang Technological UniversitySingapore639798Singapore

The Brain-Computer Interfaces(BCIs)had been proposed and used in therapeutics for ***,the need of time-consuming calibration phase and the lack of robustness,which are caused by little-labeled data,are restricting the advance and application of BCI,especially for the BCI based on motor imagery(MI).In this paper,we reviewed the recent development in the machine learning algorithm used in the MI-based BCI,which may provide potential solutions for addressing the *** classified these algorithms into two categories,namely,and enhancing the representation and expanding the training ***,these methods of enhancing the representation of features collected from few EEG trials are based on extracting features of multiple bands,regularization,and so *** methods of expanding the training dataset include approaches of transfer learning(session to session transfer,subject to subject transfer)and generating artificial EEG *** result of these techniques showed the resolution of the challenges to some *** a developing research area,the study of BCI algorithms in little-labeled data is increasingly requiring the advancement of human brain physiological structure research and more transfer learning algorithms research.

关键词： Brain-Computer interface electroencephalography(EEG) machine learning

Edge learning with unmanned ground vehicle: Joint path, energy and sample size planning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Dan Wang, Shuai Wen, Zhigang Cheng, Lei Wen, Miaowen Wu, Yik-Chung Beijing Key Laboratory of Work Safety Intelligent Monitoring Department of Electronic Engineering Beijing University of Posts and Telecommunications Beijing100876 China Department of Electrical and Electronic Engineering Southern University of Science and Technology Shenzhen518055 China Department of Computer Science and Technology Southern University of Science and Technology Shenzhen518055 China Shenzhen Research Institute of Big Data Shenzhen Guangdong China School of Electronic and Information Engineering South China University of Technology Guangzhou510641 China Department of Electrical and Electronic Engineering University of Hong Kong Hong Kong

Edge learning (EL), which uses edge computing as a platform to execute machine learning algorithms, is able to fully exploit the massive sensing data generated by Internet of Things (IoT). However, due to the limited transmit power at IoT devices, collecting the sensing data in EL systems is a challenging task. To address this challenge, this paper proposes to integrate unmanned ground vehicle (UGV) with EL. With such a scheme, the UGV could improve the communication quality by approaching various IoT devices. However, different devices may transmit different data for different machine learning jobs and a fundamental question is how to jointly plan the UGV path, the devices’ energy consumption, and the number of samples for different jobs? This paper further proposes a graph-based path planning model, a network energy consumption model and a sample size planning model that characterizes F-measure as a function of the minority class sample size. With these models, the joint path, energy and sample size planning (JPESP) problem is formulated as a large-scale mixed integer nonlinear programming (MINLP) problem, which is nontrivial to solve due to the high-dimensional discontinuous variables related to UGV movement. To this end, it is proved that each IoT device should be served only once along the path, thus the problem dimension is significantly reduced. Furthermore, to handle the discontinuous variables, a tabu search (TS) based algorithm is derived, which converges in expectation to the optimal solution to the JPESP problem. Simulation results under different task scenarios show that our optimization schemes outperform the fixed EL and the full path EL schemes. Copyright © 2020, The Authors. All rights reserved.

关键词： Intelligent vehicle highway systems

Single Cell Sequencing Analysis Identifies Genetics-Modulated ORMDL3+ Cholangiocytes Having Higher Metabolic Effects On Primary Biliary Cholangitis

学校读者我要写书评

暂无评论

Research Square

Research Square 2021年

作者： Xiang, Bingyu Deng, Chunyu Qiu, Fei Li, Jingjing Li, Shanshan Zhang, Huifang Lin, Xiuli Huang, Yukuan Zhou, Yijun Su, Jianzhong Lu, Mingqin Ma, Yunlong Department of Infectious Diseases The First Affiliated Hospital of Wenzhou Medical University Zhejiang Wenzhou325000 China School of Life Science and Technology Harbin Institute of Technology Harbin150080 China Institute of Biomedical Big Data School of Ophthalmology & Optometry and Eye Hospital School of Biomedical Engineering Wenzhou Medical University Zhejiang Wenzhou325027 China State Key Laboratory for Diagnosis and Treatment of Infectious Diseases The First Affiliated Hospital Collaborative Innovation Center for Diagnosis and Treatment of Infectious Diseases Zhejiang University School of Medicine Zhejiang Hangzhou310003 China Wenzhou Institute University of Chinese Academy of Sciences Zhejiang Wenzhou325011 China

Background: Primary biliary cholangitis (PBC) is a classical autoimmune disease, which is highly influenced by genetic determinants. Many genome-wide association studies (GWAS) have reported that numerous genetic loci were significantly associated with PBC susceptibility. However, the effects of genetic determinants on liver cells and its immune microenvironment for PBC remain unclear. Results: We constructed a powerful computational framework to integrate GWAS summary statistics with scRNA-seq data to uncover genetics-modulated liver cell subpopulations for PBC. Based on our multi-omics integrative analysis, 29 risk genes including ORMDL3, GSNK2B, and DDAH2 were significantly associated with PBC susceptibility. By combining GWAS summary statistics with scRNA-seq data, we found that cholangiocytes exhibited a notable enrichment by PBC-related genetic association signals (Permuted P + cholangiocytes have prominently higher metabolism activity score than ORMDL3- cholangiocytes (P = 1.383×10-15). Compared with ORMDL3- cholangiocytes, there were 77 significantly differentially expressed genes among ORMDL3+ cholangiocytes (FDR + cholangiocytes exhibited relatively high communications with macrophage and monocyte. Compared with ORMDL3cholangiocytes, the VEGF signaling pathway is specific for ORMDL3+ cholangiocytes to interact with other cell populations. Conclusions: To the best of our knowledge, this is the first study to integrate genetic information with single cell sequencing data for parsing genetics-influenced liver cells for PBC risk. We identified that ORMDL3+ cholangiocytes with higher metabolism activity play important immune-modulatory roles in the etiology of PBC. © 2021, CC BY.

关键词： Metabolism

CitationAS： A Tool of Automatic Survey Generation Based on Citation Content

学校读者我要写书评

暂无评论

Journal of data and Information Science 2018年第2期3卷 20-37页

作者： jie wang chengzhi zhang mengying zhang sanhong deng School of Information Management Nanjing University Nanjing 210023 China Department of Information Management Nanjing University of Science and Technology Nanjing 210094 China Jiangsu Key Laboratory of Data Engineering and Knowledge Service Nanjing University Nanjing 210023 China

Purpose： This study aims to build an automatic survey generation tool, named CitationAS, based on citation content as represented by the set of citing sentences in the original ***/methodology/approach： Firstly, we apply LDA to analyse topic distribution of citation content. Secondly, in CitationAS, we use bisecting K-means, Lingo and STC to cluster retrieved citation content. Then Word2Vec, Word Net and combination of them are applied to generate cluster labels. Next, we employ TF-IDF, MMR, as well as considering sentence location information, to extract important sentences, which are used to generate surveys. Finally, we adopt manual evaluation for the generated ***： In experiments, we choose 20 high-frequency phrases as search terms. Results show that Lingo-Word2Vec, STC-Word Net and bisecting K-means-Word2Vec have better clustering effects. In 5 points evaluation system, survey quality scores obtained by designing methods are close to 3, indicating surveys are within acceptable limits. When considering sentence location information, survey quality will be improved. Combination of Lingo, Word2Vec, TF-IDF or MMR can acquire higher survey *** limitations： The manual evaluation method may have a certain subjectivity. We use a simple linear function to combine Word2Vec and Word Net that may not bring out their strengths. The generated surveys may not contain some newly created knowledge of some articles which may concentrate on sentences with no *** implications： CitationAS tool can automatically generate a comprehensive, detailed and accurate survey according to user’s search terms. It can also help researchers learn about research status in a certain ***/value： Citaiton AS tool is of practicability. It merges cluster labels from semantic level to improve clustering results. The tool also considers sentence location information when calculating sentence score by TF-IDF and MMR.

关键词： Automatic survey system Citation content Clustering algorithms Labelgeneration approaches Sentence extraction methods

Fourier-modulated CLIP for zero-shot vehicle counting

学校读者我要写书评

暂无评论

Scientific reports 2025年第1期15卷 19732页

作者： Yunpeng Luo Qin Zhang Jiawei Luo Shixin Huang Xiaoyu Wan Xixi Nie School of Vehicle Engineering Chongqing Industry & Trade Polytechnic Chongqing 408000 China. Department of Scientific Research People's Hospital of Yubei District of Chongqing city Chongqing 401120 China. Department of Cardiovascular Surgery and West China Biomedical Big Data Center West China Hospital/West China School of Medicine Sichuan University Sichuan 610041 China. Department of Scientific Research People's Hospital of Yubei District of Chongqing city Chongqing 401120 China. d200101011@***. School of Communication and Information Engineering Chongqing University of Posts and Telecommunications Chongqing 400065 China. wanxy@***. Chongqing Key Laboratory of Image Cognition School of Artificial Intelligence Chongqing 400065 China. niexx@***.

Vehicle counting is a critical task in traffic monitoring and management. Although large vision-language models have achieved significant progress in zero-shot text-image matching, adapting them for vehicle counting remains a challenging task. To tackle this issue, we propose FCLIP-VC, a Fourier-modulated Contrastive Language-image Pre-training (CLIP) for zero-shot vehicle counting. First, a Vision Transformer (ViT)-based CLIP model is employed to encode image features for precise vehicle localization. Additionally, we introduce a learnable visual prompt to avoid tuning global parameters, allowing the pre-trained CLIP knowledge to be effectively applied to dense prediction tasks. Next, for patch-level embedding of images, we introduce a patch-language contrast loss to optimize the effectiveness of the model in capturing fine-grained features of images. Then, we propose a patch-language Discrete Fourier transform (DFT) interaction module, leveraging DFT to extract multi-scale image features in the frequency domain, which improves the ability of the model to handle diverse vehicle sizes and complex traffic environments. Finally, a content-aware density map decoder is designed to generate accurate density map predictions through multi-layer convolution and progressive upsampling. Extensive experiments demonstrate that our proposed FCLIP-VC achieves state-of-the-art accuracy in zero-shot vehicle counting.

关键词： Contrastive language-image pre-training (CLIP) Density map Discrete Fourier transform Vehicle counting Zero-shot

Award for Outstanding Comprehensive Mini-Challenge 2 Solution - RadiationMonitor: An Interactive System for Visualizing and Exploring Spatial-Temporal data

学校读者我要写书评

暂无评论

Award for Outstanding Comprehensive Mini-Challenge 2 Solutio...

IEEE Symposium on Visual Analytics Science and Technology (VAST)

作者： Datong Wei Hanning Shao Zijing Tan Chenlu Li Zhixian Lin Xiaoju Dong Xiaoru Yuan Key Laboratory of Machine Perception Ministry of Education School of EECS Peking University Weinberg College of Arts and Sciences Northwestern University School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University National Engineering Laboratory for Big Data Analysis and Application Peking University

In this paper, we proposed RadiationMonitor, an interactive system for visualizing and exploring spatial-temporal data from static and mobile sensors. We use pixel-based time-series visualization for event presentation, and the trajectories of mobile sensors are discretized to display the spatial distribution of sensor readings. Our system provides cross-filtering and detail-on-demand interactions, which allow users to investigate data from both spatial and temporal aspects.

关键词： Sensor systems Pollution measurement data visualization Uncertainty Image color analysis Measurement uncertainty Awards