检索结果-内蒙古大学图书馆

An improved Gaussian Mixture Model algorithm for background representation

学校读者我要写书评

暂无评论

An improved Gaussian Mixture Model algorithm for background ...

2019 International Conference on Artificial Intelligence Technologies and Applications, ICAITA 2019

作者： Wang, Ping Dong, Shaoxiong School of Electrical Engineering and Electronic Information Xihua University Chengdu Sichuan610039 China Artificial Intelligence Key Laboratory of Sichuan Province Sichuan University of Science and Engineering Zigong Sichuan643000 China Science Computing Intelligent Information Processing GuangXi Higher Education Key Laboratory Guangxi Teachers Education University Nanning530023 China

Initializing a background frame for Gaussian Mixture Model requires no moving objects in the background scene. In this paper, in order to obtain an initial frame when there is a moving object in the background scene, filtering algorithm is used for background frame initialization. This paper proposes an improved method for updating Gaussian mixture models. In the initial stage of the GMM, the update rate of the mean and variance is taken as a larger value, so that the model mean and variance update speed becomes faster, and the model learning speed is accelerated;after training for a period of time with a large update rate, let The mean update rate is unchanged, and the variance update rate becomes smaller, so that the background model can be more stable. © 2019 IOP Publishing Ltd. All rights reserved.

关键词： Gaussian distribution

Multifractal temporally weighted detrended partial cross-correlation analysis to quantify intrinsic power-law cross-correlation of two non-stationary time series affected by common external factors

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Bao-Gen Ling, Dian-Yi Yu, Zu-Guo Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan University Xiangtan Hunan411105 China School of Electrical Engineering and Computer Science Queensland University of Technology GPO Box 2434 BrisbaneQ4001 Australia

When common factors strongly influence two cross-correlated time series recorded in complex natural and social systems, the results will be biased if we use multifractal detrended cross-correlation analysis (MF-DXA) without considering these common factors. Based on multifractal temporally weighted detrended cross-correlation analysis (MF-TWXDFA) proposed by our group and multifractal partial cross-correlation analysis (MF-DPXA) proposed by Qian et al., we propose a new method-multifractal temporally weighted detrended partial cross-correlation analysis (MF-TWDPCCA) to quantify intrinsic power-law cross-correlation of two non-stationary time series affected by common external factors in this paper. We use MF-TWDPCCA to characterize the intrinsic cross-correlations between the two simultaneously recorded time series by removing the effects of other potential time series. To test the performance of MF-TWDPCCA, we apply it, MF-TWXDFA and MF-DPXA on simulated series. Numerical tests on artificially simulated series demonstrate that MF-TWDPCCA can accurately detect the intrinsic cross-correlations for two simultaneously recorded series. To further show the utility of MF-TWDPCCA, we apply it on time series from stock markets and find that there exists significantly multifractal power-law cross-correlation between stock returns. A new partial cross-correlation coefficient is defined to quantify the level of intrinsic cross-correlation between two time series. Copyright © 2020, The Authors. All rights reserved.

关键词： Fractals

A Cost-Driven Fuzzy Scheduling Strategy for intelligent Workflow Decision Making Systems in Uncertain Edge-Cloud Environments

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Lin, Bing Lin, Chaowei Chen, Xing College of Physics and Energy Fujian Normal University Fujian Provincial Key Laboratory of Quantum Manipulation and New Energy Materials Fuzhou350117 China Fujian Provincial Collaborative Innovation Center for Advanced High-Field Superconducting Materials and Engineering Fuzhou350117 China School of Computer Science Peking University 100871 China College of Mathematics and Computer Science Fuzhou University Fuzhou350118 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou350118 China

Workflow decision making is critical to performing many practical workflow applications. Scheduling in edge-cloud environments can address the high complexity problem of workflow applications, while decreasing the data transmission delay between the cloud and end devices. However, because of the heterogeneous resources in edge-cloud environments and the complicated data dependencies among the tasks in a workflow, significant challenges for workflow scheduling remain, including the selection of an optimal tasks-servers solution from the possible numerous combinations. The existing studies have been mainly done subject to rigorous conditions without fluctuations, ignoring the fact that workflow scheduling is typically present in uncertain environments. In this study, we focus on reducing the execution cost of workflow applications mainly caused by task computation and data transmission, while satisfying the workflow deadline in uncertain edge-cloud environments. The Triangular Fuzzy Numbers (TFNs) are adopted to represent the task processing time and data transferring time. A cost-driven fuzzy scheduling strategy based on an Adaptive Discrete Particle Swarm Optimization (ADPSO) algorithm is proposed, which employs the operators of Genetic Algorithm (GA). This strategy introduces the randomly two-point crossover operator, neighborhood mutation operator, and adaptive multipoint mutation operator of GA to effectively avoid converging on local optima. The experimental results show that our strategy can effectively reduce the workflow execution cost in uncertain edge-cloud environments, compared with other benchmark solutions. Copyright © 2021, The Authors. All rights reserved.

关键词： Decision making

Exploring multi-loss function based attention framework for vehicle re-identification 10

学校读者我要写书评

暂无评论

Exploring multi-loss function based attention framework for ...

10th International Conference on information Technology in Medicine and Education, ITME 2019

作者： Liu, Wei Zhang, Yi Luo, Zhiming Li, Shaozi East China Jiaotong University Jiangxi China Cognitive Science Department Xiamen University Fujian China Postdoc Center of Information and Communication Engineering Xiamen University China Key Lab. of Cogn. Computing and Intelligent Information Processing of Fujian Education Institutions Wuyishan China Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering Yi Chang China

ISBN: (纸本)9781728139173

Vehicle Re-identification(Re-ID) refers to the task of matching a specific vehicle across multiple non-overlapping cameras. Precise vehicle Re-ID suffers from two main challenges: (1) different vehicle identities with a similar appearance of the same type have a subtle inter-instance discrepancy, (2) one vehicle usually has large intra-instance differences due to viewpoint and illumination variations. To address these challenges, in this paper, we proposed an Attention-based Framework for Vehicle Re-ID named AFVR, which combines the benefits of both the cross-entropy loss function and the triplet loss function. Experimental results on two popular vehicle Re-ID benchmarks demonstrate the effectiveness of our proposed method, compared with the state of the arts. © 2019 IEEE.

关键词： Vehicles

Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Yu Wang, Tao Kang, Bingyi Tang, Sheng Wang, Chunfeng Li, Jintao Feng, Jiashi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Department of Electrical and Computer Engineering National University of Singapore Singapore Institute of Data Science National University of Singapore Singapore

Solving long-tail large vocabulary object detection with deep learning based models is a challenging and demanding task, which is however under-explored. In this work, we provide the first systematic analysis on the underperformance of state-of-the-art models in front of long-tail distribution. We find existing detection methods are unable to model few-shot classes when the dataset is extremely skewed, which can result in classifier imbalance in terms of parameter magnitude. Directly adapting long-tail classification models to detection frameworks can not solve this problem due to the intrinsic difference between detection and classification. In this work, we propose a novel balanced group softmax (BAGS) module for balancing the classifiers within the detection frameworks through group-wise training. It implicitly modulates the training process for the head and tail classes and ensures they are both sufficiently trained, without requiring any extra sampling for the instances from the tail classes. Extensive experiments on the very recent long-tail large vocabulary object recognition benchmark LVIS show that our proposed BAGS significantly improves the performance of detectors with various backbones and frameworks on both object detection and instance segmentation. It beats all state-of-the-art methods transferred from long-tail image classification and establishes new state-of-the-art. Code is available at https://***/FishYuLi/ BalancedGroupSoftmax. Copyright © 2020, The Authors. All rights reserved.

关键词： Object recognition

A computationally-efficient sandbox algorithm for multifractal analysis of large-scale complex networks with tens of millions of nodes

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ding, Yuemin Liu, Jin-Long Li, Xiaohui Tian, Yu-Chu Yu, Zu-Guo School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China School of Computer Science Queensland University of Technology BrisbaneQLD4000 Australia Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan University Xiangtan Hunan411105 China School of Information Science and Engineering Wuhan University of Science and Technology Wuhan Hubei430081 China

The fractality of complex networks has attracted much attention with extensive investigations over the last 15 years. As a generalization of fractal analysis, multifractal analysis (MFA) is a useful tool to systematically describe the spatial heterogeneity of both theoretical and experimental fractal patterns. One of the widely used methods for fractal analysis is box-covering. It uses the minimum number of covering boxes to calculate the fractal dimension of complex networks, and is known to be NP-hard. More severely, in comparison with fractal analysis algorithms, MFA algorithms have much higher computational complexity. Among various MFA algorithms for complex networks, the sandbox MFA algorithm behaves with the best computational efficiency. However, the existing sandbox algorithm is still computationally expensive. Thus, so far it has only been applied to small-scale complex networks of the size of about tens of thousands of nodes. It becomes challenging to implement the MFA for large-scale networks with tens of millions of nodes. It is also not clear whether or not MFA results can be improved by a largely increased size of a theoretical network. To tackle these challenges, a computationally-efficient sandbox algorithm (CESA) is presented in this paper for MFA of large-scale networks. Distinct from the existing sandbox algorithm that uses the shortest-path distance matrix to obtain the required information for MFA of complex networks, our CESA employs the breadth-first search (BFS) technique to directly search the neighbor nodes of each layer of center nodes, and then to retrieve the required information. Our CESA's input is a sparse data structure derived from the compressed sparse row (CSR) format designed for compressed storage of the adjacency matrix of large-scale network. A theoretical analysis reveals that the CESA reduces the time complexity of the existing sandbox algorithm from cubic to quadratic, and also improves the space complexity from quadratic

关键词： Computational efficiency

Overcoming Classifier Imbalance for Long-Tail Object Detection With Balanced Group Softmax

学校读者我要写书评

暂无评论

Overcoming Classifier Imbalance for Long-Tail Object Detecti...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yu Li Tao Wang Bingyi Kang Sheng Tang Chunfeng Wang Jintao Li Jiashi Feng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Department of Electrical and Computer Engineering National University of Singapore Singapore Institute of Data Science National University of Singapore Singapore

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

关键词： Training Object detection Proposals Adaptation models Feature extraction Computational modeling Detectors

Asymptotic solution of a wide moving jam to a class of higher-order viscous traffic flow models

学校读者我要写书评

暂无评论

Applied Mathematics and Mechanics(English Edition) 2018年第5期39卷 609-622页

作者： Chunxiu WU College of Mathematics and Computer Science Quanzhou Normal UniversityQuanzhou 362000Fujian ProvinceChina Fujian Provincial Key Laboratory of Data Intensive Computing Quanzhou 362000Fujian ProvinceChina Key Laboratory of Intelligent Computing and Information Processing Quanzhou 362000Fujian ProvinceChina

The boundary-layer method is used to study a wide moving jam to a class of higher-order viscous models. The equations for characteristic parameters are derived to determine the asymptotic solution. The sufficient and essential conditions for the wide moving jam formation are discussed in detail, respectively, and then used to prove or disprove the existence of the wide moving jam solutions to many well-known higher-order models. It is shown that the numerical results agree with the analytical results.

关键词： higher-order traffic flow model wide moving jam boundary-layer method,weighted essentially nonoscillatory （WENO） scheme

Cloud-based data-sharing scheme using verifiable and CCA-secure re-encryption from indistinguishability obfuscation 14th

学校读者我要写书评

暂无评论

Cloud-based data-sharing scheme using verifiable and CCA-sec...

14th International Conference on information Security and Cryptology, Inscrypt 2018

作者： Zhang, Mingwu Jiang, Yan Shen, Hua Li, Bingbing Susilo, Willy School of Computers Hubei University of Technology Wuhan China Hubei Key Laboratory of Intelligent Geo-Information Processing China University of Geosciences Wuhan China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Institute of Cybersecurity and Cryptology School of Computing and Information Technology University of Wollongong Wollongong Australia

ISBN: (纸本)9783030142339

A cloud-based re-encryption scheme allows a semi-trusted cloud proxy to convert a ciphertext under delegator’s public-key into a ciphertext of delegatee’s. However, for an untrusted cloud proxy, as the re-encryption program was outsourced on the cloud, the cloud can debug the program and might have illegal activities in practice, such as monitoring the program executing, returning an incorrect re-encryption ciphertext, or colluding with the participants to obtain the sensitive information. In this work, we propose a construction of cloud-based verifiable re-encryption by incorporating new cryptographic primitives of indistinguishability obfuscation and puncturable pseudorandom functions, which can achieve the master-secret security even if the proxy colludes with the delegatee. Furthermore, our scheme can provide the white-box security in re-encryption procedure to implement the sensitive-data protection in the presence of white-box access, and it resists on chosen-ciphertext attacks in both the first-level encryption and the second-level encryption. The decryption is very efficient since it only requires several symmetric PRF operations, which can be deployed and applied in the light-weight security device such as Mobile Phones (MPs), Wireless Body Area Networks (WBANs) and nodes in Internet-of-Things (IoTs). © 2019, Springer Nature Switzerland AG.

关键词： Data obfuscation