检索结果-内蒙古大学图书馆

International Conference on Probabilistic Graphical Models

作者： Pawar, Swaraj Doshi, Prashant Univ Georgia Sch Comp THINC Lab Athens GA 30602 USA

Prominent algorithms for learning sum-product networks (SPN) and sum-product-max networks (SPMN) focus on learning models from data that deliver good modeling performance without regard to the size of the learned network. Consequently, the learned networks can get very large, which negatively impacts inference time. In this paper, we introduce anytime algorithms for learning SPNs and SPMNs. These algorithms generate intermediate but provably valid models whose performance progressively improves as more time and computational resources are allocated to the learning. They flexibly trade off good model performance with reduced learning time, offering the benefit that SPNs and SPMNs of small sizes (but with reduced likelihoods) can be learned quickly. We comprehensively evaluate the anytime algorithms on two testbeds and demonstrate that the network performance improves with time and reflects the expected performance profile of an anytime algorithm. We expect these anytime algorithms to become the default learning techniques for SPNs and SPMNs given their clear benefit over classical batch learning techniques.

关键词： anytime algorithms decision making flexible probabilistic graphical models

来源：评论

学校读者我要写书评

暂无评论

A model of anytime algorithm performance for bi-objective optimization

引用

JOURNAL OF GLOBAL OPTIMIZATION 2021年第2期79卷 329-350页

作者： Jesus, Alexandre D. Paquete, Luis Liefooghe, Arnaud Univ Coimbra DEI CISUC Coimbra Portugal Univ Lille INRIA Cent Lille UMR 9189CRIStALCNRS F-59000 Lille France Univ Tokyo JFLI CNRS IRL 3527 Tokyo 1130033 Japan

anytime algorithms allow a practitioner to trade-off runtime for solution quality. This is of particular interest in multi-objective combinatorial optimization since it can be infeasible to identify all efficient solutions in a reasonable amount of time. We present a theoretical model that, under some mild assumptions, characterizes the "optimal" trade-off between runtime and solution quality, measured in terms of relative hypervolume, of anytime algorithms for bi-objective optimization. In particular, we assume that efficient solutions are collected sequentially such that the collected solution at each iteration maximizes the hypervolume indicator, and that the non-dominated set can be well approximated by a quadrant of a superellipse. We validate our model against an "optimal" model that has complete knowledge of the non-dominated set. The empirical results suggest that our theoretical model approximates the behavior of this optimal model quite well. We also analyze the anytime behavior of an epsilon-constraint algorithm, and show that our model can be used to guide the algorithm and improve its anytime behavior.

关键词： Multi-objective optimization Combinatorial optimization anytime algorithms anytime behavior epsilon-constraint

来源：评论

学校读者我要写书评

暂无评论

Towards monitored tomographic reconstruction: algorithm-dependence and convergence

COMPUTER OPTICS

引用

COMPUTER OPTICS 2023年第4期47卷 658-667页

作者： Bulatov, K. B. Ingacheva, A. S. Gilmanov, M. I. Kutukova, K. Soldatova, Z. V. Buzmakov, A. V. Chukalina, M. V. Zschech, E. Arlazarov, V. V. Smart Engines Serv LLC Prospekt 60 Letiia Oktiabria 9 Moscow 117312 Russia FRC Comp Sci & Control RAS Prospekt 60 Letiia Oktiabria 9 Moscow 119333 Russia Inst Informat Transmiss Problems Kharkevich Inst R Bolshoi Karetnyi Pereulok 19-1 Moscow 127051 Russia DeepXscan GmbH Zeppelinstr 1 Dresden Germany FSRC Crystallog & Photon RAS Leninskii Prospekt 59 Moscow 119333 Russia

The monitored tomographic reconstruction (MTR) with optimized photon flux technique is a pioneering method for X-ray computed tomography (XCT) that reduces the time for data acquisition and the radiation dose. The capturing of the projections in the MTR technique is guided by a scanning protocol built on similar experiments to reach the predetermined quality of the reconstruction. This method allows achieving a similar average reconstruction quality as in ordinary tomography while using lower mean numbers of projections. In this paper, we, for the first time, systematically study the MTR technique under several conditions: reconstruction algorithm (FBP, SIRT, SIRT-TV, and others), type of tomography setup (micro-XCT and nano-XCT), and objects with different morphology. It was shown that a mean dose reduction for reconstruction with a given quality only slightlyvaries with choice of reconstruction algorithm, and reach up to 12.5 % in case of micro-XCT and 8.5 % for nano-XCT. The obtained results allow to conclude that the monitored tomographic reconstruction approach can be universally combined with an algorithm of choice to perform a controlled trade-off between radiation dose and image quality. Validation of the protocol on independent common ground truth demonstrated a good convergence of all reconstruction algorithms within the MTR protocol.

关键词： anytime algorithms monitored tomographic reconstruction micro X-ray computed tomography nano X-ray computed tomography dose reduction time reducing stopping rule

来源：评论

学校读者我要写书评

暂无评论

Some General Heuristics in the Traveling Salesman Problem and the Problem of Reconstructing the DNA Chain Distance Matrix 23

Some General Heuristics in the Traveling Salesman Problem an...

引用

Proceedings of the 2023 7th International Conference on Computer Science and Artificial Intelligence

作者： Boris F. Melnikov Dmitrii Chaikovskii Faculty of Computational Mathematics and Cybernetics Shenzhen MSU-BIT University China

ISBN: (纸本)9798400708688

With all their differences, the two problems under consideration, namely the traveling salesman problem and the problem of restoring the DNA chain distance matrix, have a lot in common. This generality primarily consists in the following. For real problems and for standard methods of solving them, such as gradient descent, these problems can be formally solved, but in fact they are described by systems of equations with several dozen variables, and sometimes hundreds. In this regard, to solve them, we use sequential algorithms (step-by-step) for filling matrices, sometimes also using backtracking for the variables already considered. We show that such heuristics in the situations we are considering give acceptable anytime algorithms.

关键词： DNA matrix anytime algorithms heuristics. partially filled matrix traveling salesman problem

来源：评论

学校读者我要写书评

暂无评论

An Improvement Heuristic Based on Variable Neighborhood Search for a Dynamic Orienteering Problem 1

引用

21st European Conference on Evolutionary Computation in Combinatorial Optimization (EvoCOP)

作者： Le, Hoang Thanh Middendorf, Martin Shi, Yuhui Univ Leipzig Inst Comp Sci Swarm Intelligence & Complex Syst Grp Leipzig Germany Southern Univ Sci & Technol Comp Sci & Engn Shenzhen Peoples R China

ISBN: (数字)9783030729042

ISBN: (纸本)9783030729035;9783030729042

The Dynamic Orienteering Problem (DOP) is studied where nodes change their value over time. An improvement heuristic that is based on Variable Neighborhood Search is proposed for the DOP. The new heuristic is experimentally compared with two heuristics that are based on state-of-the-art algorithms for the static Orienteering Problem. For the experiments several benchmark instances are used as well as instances that are generated from existing road networks. The results show that the new heuristic outperforms the other heuristics with respect to several evaluation criteria and different measures for run time. An additional experiment shows that the new heuristic can be easily adapted to become a standalone algorithm that does not need given initial solutions. The standalone version obtains better results than two state-of-the-art algorithms.

关键词： Dynamic optimization Neighborhood search anytime algorithms Routing problems

来源：评论

学校读者我要写书评

暂无评论

Determining Optimal Frame Processing Strategies for Real-Time Document Recognition Systems 16th

Determining Optimal Frame Processing Strategies for Real-Tim...

引用

16th IAPR International Conference on Document Analysis and Recognition (ICDAR)

作者： Bulatov, Konstantin Arlazarov, Vladimir V. Russian Acad Sci Fed Res Ctr Comp Sci & Control Moscow Russia Smart Engines Serv LLC Moscow Russia

ISBN: (纸本)9783030863319

Mobile document analysis technologies became widespread and important, and growing reliance on the performance of critical processes, such as identity document data extraction and verification, lead to increasing speed and accuracy requirements. Camera-based documents recognition on mobile devices using video stream allows to achieve higher accuracy, however in real time systems the actual time of individual image processing needs to be taken into account, which it rarely is in the works on this subject. In this paper, a model of real-time document recognition system is described, and three frame processing strategies are evaluated, each consisting of a per-frame recognition results combination method and a dynamic stopping rule. The experimental evaluation shows that while full combination of all input results is preferable if the frame recognition time is comparable with frame acquisition time, the selection of one best frame based on an input quality predictor, or a combination of several best frames, with the corresponding stopping rule, allows to achieve higher mean recognition results accuracy if the cost of recognizing a frame is significantly higher than skipping it.

关键词： Mobile recognition Real-time recognition Video stream anytime algorithms Document recognition

来源：评论

学校读者我要写书评

暂无评论

A Modification of a Stopping Method for Text Recognition in a Video Stream with Best Frame Selection 13

A Modification of a Stopping Method for Text Recognition in ...

引用

13th International Conference on Machine Vision

作者： Tolstov, Ilya Martynov, Stanislav Farsobina, Vera Bulatov, Konstantin Russian Acad Sci Keldysh Inst Appl Math Moscow Russia Russian Acad Sci Fed Res Ctr Commuter Sci & Control Moscow Russia Smart Engines Serv LLC Moscow Russia

ISBN: (纸本)9781510640412

One of the most important problem in constructing computer vision systems for embedded and mobile devices is offline recognition of text strings. In this paper, we analyze the problem of text strings recognition process in a video stream using best frame selection. This method allows to incorporate the information from multiple views of the same target object, thus increasing the overall extraction accuracy. A stopping method is proposed, which allows to make an automatic stopping decision, i.e. to terminate the process at the optimal time in order to maximize the responsiveness of the system. Experimental evaluation on open identity document datasets MIDV-500 and MIDV-2019 show that the proposed stopping rule allows to decrease mean error level of the text recognition results in comparison with a baseline approach which stops after a fixed amount of processed frames.

关键词： mobile recognition video stream optical character recognition anytime algorithms optimal stopping

来源：评论

学校读者我要写书评

暂无评论

Monitored Reconstruction: Computed Tomography as an anytime Algorithm

引用

IEEE ACCESS 2020年 8卷 110759-110774页

作者： Bulatov, Konstantin Chukalina, Marina Buzmakov, Alexey Nikolaev, Dmitry Arlazarov, Vladimir V. Russian Acad Sci Fed Res Ctr Comp Sci & Control Moscow 119333 Russia Smart Engines Serv LLC Moscow 121205 Russia Smart Engines Serv LLC Dept Xray Comp Vis Moscow 121205 Russia Russian Acad Sci Fed Sci Res Ctr Crystallog & Photon Moscow 119333 Russia Russian Acad Sci Inst Informat Transmiss Problems Kharkevich Inst Moscow 127051 Russia

Computed tomography is an important technique for non-destructive analysis of an object's internal structure, relevant for scientific studies, medical applications, and industry. Pressing challenges emerging in the field of tomographic imaging include speeding up reconstruction, reducing the time required to obtain the X-ray projections, and reducing the radiation dose imparted to the object. In this paper, we introduce a model of a monitored reconstruction process, in which the acquiring of projections is interspersed with image reconstruction. This model allows to examine the tomographic reconstruction process as an anytime algorithm and consider a problem of finding the optimal stopping point, corresponding to the required number of X-ray projections for the currently scanned object. We outline the theoretical framework for the monitored reconstruction, propose ways of constructing stopping rules for various reconstruction quality metrics and provide their experimental evaluation. Due to stopping at different times for different objects, the proposed approach allows to achieve a higher mean reconstruction quality for a given mean number of X-ray projections. Conversely, fewer projections on average are used to achieve the same mean reconstruction quality.

关键词： Image reconstruction Computed tomography X-ray imaging Monitoring Medical diagnostic imaging anytime algorithms computed tomography dose reduction monitored reconstruction optimal stopping X-ray tomography

来源：评论

学校读者我要写书评

暂无评论

Using Multi-objective Optimization to Generate Timely Responsive BDI Agents 22

Using Multi-objective Optimization to Generate Timely Respon...

引用

Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems

作者： Márcio Fernando Stabile Junior Universidade de São Paulo São Paulo Brazil

ISBN: (纸本)9781450392136

A BDI agent's ability to perform well depends on its reasoning time. If the reasoning is slow, it is possible that the environment has changed and the action selected is no longer optimal by the time the agent has finished to deliberate. This work then builds a BDI architecture using anytime algorithms that can control the amount of time used by the agent to reason and act on the environment. I briefly describe the proposed architecture and its implementation in the Jason agent language.

关键词： BDI agents anytime algorithms multi-objective optimization

来源：评论

学校读者我要写书评

暂无评论

Methods of Weighted Combination for Text Field Recognition in a Video Stream 12

Methods of Weighted Combination for Text Field Recognition i...

引用

12th International Conference on Machine Vision (ICMV)

作者： Petrova, Olga Bulatov, Konstantin Arlazarov, Vladimir L. Russian Acad Sci Fed Res Ctr Comp Sci & Control Moscow Russia Smart Engines Serv LLC Moscow Russia Moscow Inst Phys & Technol MIPT Moscow Russia

ISBN: (纸本)9781510636446

Due to a noticeable expansion of document recognition applicability, there is a high demand for recognition on mobile devices. A mobile camera, unlike a scanner, cannot always ensure the absence of various image distortions, therefore the task of improving the recognition precision is relevant. The advantage of mobile devices over scanners is the ability to use video stream input, which allows to get multiple images of a recognized document. Despite this, not enough attention is currently paid to the issue of combining recognition results obtained from different frames when using video stream input. In this paper we propose a weighted text string recognition results combination method and weighting criteria, and provide experimental data for verifying their validity and effectiveness. Based on the obtained results, it is concluded that the use of such weighted combination is appropriate for improving the quality of the video stream recognition result.

关键词： mobile recognition video stream optical character recognition anytime algorithms

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：