检索结果-内蒙古大学图书馆

CenterNet3D: An anchor free object detector for point cloud

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Guojun Wu, Jian Tian, Bin Teng, Siyu Chen, Long Cao, Dongpu The State Key Laboratory of Automotive Simulation and Control Jilin University Changchun130022 China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100190 China The Department of Computer Science Hong Kong Baptist University Hong Kong The School of Data and Computer Science Sun Yat-Sen University Guangdong Guangzhou510275 China The Department of Mechanical and Mechatronics Engineering University of Waterloo WaterlooONN2L 3G1 Canada

Accurate and fast 3D object detection from point clouds is a key task in autonomous driving. Existing one-stage 3D object detection methods can achieve real-time performance, however, they are dominated by anchor-based detectors which are inefficient and require additional post-processing. In this paper, we eliminate anchors and model an object as a single point-the center point of its bounding box. Based on the center point, we propose an anchor-free CenterNet3D network that performs 3D object detection without anchors. Our CenterNet3D uses keypoint estimation to find center points and directly regresses 3D bounding boxes. However, because inherent sparsity of point clouds, 3D object center points are likely to be in empty space which makes it difficult to estimate accurate boundaries. To solve this issue, we propose an extra corner attention module to enforce the CNN backbone to pay more attention to object boundaries. Besides, considering that one-stage detectors suffer from the discordance between the predicted bounding boxes and corresponding classification confidences, we develop an efficient keypoint-sensitive warping operation to align the confidences to the predicted bounding boxes. Our proposed CenterNet3D is non-maximum suppression free which makes it more efficient and simpler. We evaluate CenterNet3D on the widely used KITTI dataset and more challenging nuScenes dataset. Our method outperforms all state-of-the-art anchor-based one-stage methods and has comparable performance to two-stage methods as well. It has an inference speed of 20 FPS and achieves the best speed and accuracy trade-off. Our source code will be released at https://***/wangguojun2018/CenterNet3d. Copyright © 2020, The Authors. All rights reserved.

关键词： Autonomous vehicles

BthyDra+: Towards a Comprehensive Model to Conduct Cross-project Defect Prediction

学校读者我要写书评

暂无评论

Journal of Computers (Taiwan) 2018年第6期29卷 52-65页

作者： Huang, Ning Fang, Jinglong Wei, Dan Chen, Bin Wang, Xingqi School of Computer Science Hangzhou Dianzi University ZheJiang Province China Key Laboratory of Complex Systems Modeling and Simulation Ministry of Education School of Computer Science Hangzhou Dianzi University ZheJiang Province China

Cross-project defect prediction (CPDP) is a field of study where researchers need to build a universal model by using within-project data to predict defects on other projects. However, variations in the distribution of source and target projects have an influence on the performance of classifiers. To enable effective cross-project defect prediction, we propose a comprehensive model containing data preprocessing and classifier transferring to construct a better classification space and strengthen the performance of classifiers. In preprocessing step, one baseline is calculated for every dataset from its non-defective samples based on the distance to all other non-defective samples and the data is transformed by using rank function. Genetic algorithm and ensemble learning are selected as the way in transferring step to extract effective representation from source projects and boost the capability of weak classifiers. We use Naive Bayes, Support Vector Machine and Classification and Regression Trees as classifiers and apply this model on five open resource projects (one Apache and four Eclipse projects) and NASA MDP dataset. Selecting accuracy as fitness in genetic algorithm improves the performance of classification. The model we proposed yields similar results and obtains higher precision comparing the within-project models. Meanwhile, it obtains better performance than the state-of-the-art methods on cross-project defect prediction. These results show that our model provides an opportunity to training classifiers by using more samples from different projects. © 2018 Computer Society of the Republic of China. All rights reserved.

关键词： Genetic algorithms

DyCREM: Dynamic Credit Risk Management Using Edge-Based Blockchain

学校读者我要写书评

暂无评论

DyCREM: Dynamic Credit Risk Management Using Edge-Based Bloc...

IEEE/ACM Symposium on Edge Computing (SEC)

作者： Youhuizi Li Weisong Shi Mohit Kumar Jun Chen Key Laboratory of Complex Systems Modeling and Simulation Hangzhou Dianzi University Hangzhou China Department of Computer Science Wayne State University Detroit USA Chain Oriental LLC Beijing China

ISBN: (纸本)9781538694466;9781538694459

Banks play an important role in the financial market, and their profit mainly comes from loan service. Traditional risk management approaches, as the key part in the loan services, still have several issues including low data credibility, unreliable checking and alert delay. We propose a novel dynamic credit risk management system which leverages edge-based blockchain technology to improve the performance and provide a fair loan environment. Besides, we discuss the potential challenges that the system may face, such as data standards, security on edge and scalability.

关键词： Risk management Edge computing Data models Computational modeling Real-time systems Analytical models

Mining and measurement of vocational skills and their association rules based on big data 17

学校读者我要写书评

暂无评论

Mining and measurement of vocational skills and their associ...

2017 International Conference on Digital Technology in Education, ICDTE 2017

作者： Wan, Jian Chen, Bin Bin Si, Huayou School of Computer Science and Technology Hangzhou Dianzi University Zhejiang China Key Laboratory of Complex Systems Modeling and Simulation Ministry of Education China

ISBN: (纸本)9781450352833

In recent years, researches on vocational skills are very extensive, most of them concentrated on vocational skills training, effect of vocational skill competition, vocational education and vocational skill identification and so on. But, there is very little research on the inner relationship among vocational skill based on big data. To address the issue, from LinkedIn we first collect tens of thousands of member profiles with vocational skills as empirical data. And then, we dig out high-frequency vocational skills and apply correlation analysis method to explore correlation characteristics of vocational skills. According to our studying, we figure out that there exist a large number of association rules, some of which have very high degrees of confidence, lift, and support. This research reveals the intrinsic association among different vocational skills. These relationships can reflect the general behavior and cognitive rules of human beings. We hope that our research results can provide a theoretical base for other research areas of vocational skills, such as vocational skill training, vocational skill mining, and identification of vocational skills. © 2017 Association for Computing Machinery.

关键词： Association rules

Correction: Impact of ligand fields on Kubas interaction of open copper sites in MOFs with hydrogen molecules: an electronic structural insight

学校读者我要写书评

暂无评论

RSC advances 2024年第44期14卷 32471页

作者： Trang Thuy Nguyen Hoan Van Tran Linh Hoang Nguyen Hoang Minh Nguyen Thang Bach Phan Toan Nguyen-The Yoshiyuki Kawazoe Faculty of Physics University of Science Vietnam National University Hanoi Vietnam nguyenthuytrang@hus.edu.vn. Key Laboratory for Multiscale Simulation of Complex Systems University of Science Vietnam National University Hanoi Vietnam. School of Engineering Physics Hanoi University of Science and Technology Hanoi Vietnam. Center for Innovative Materials and Architectures Vietnam National University Ho Chi Minh City Vietnam. Vietnam National University Ho Chi Minh City Vietnam. New Industry Creation Hatchery Center Tohoku University Sendai 980-8579 Japan. Department of Physics and Nanotechnology SRM Institute of Science and Technology Kattankulathur 603203 Tamilnadu India. School of Physics Institute of Science Suranaree University of Technology 111 University Avenue Nakhon Ratchasima 30000 Thailand.

[This corrects the article DOI: 10.1039/D4RA03946G.].

关键词：

Doubly-heavy tetraquarks

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Yang, Gang Ping, Jialun Segovia, Jorge Department of Physics State Key Laboratory of Low-Dimensional Quantum Physics Tsinghua University Beijing100084 China Department of Physics Jiangsu Key Laboratory for Numerical Simulation of Large Scale Complex Systems Nanjing Normal University Nanjing210023 China Departamento de Sistemas Físicos Químicos y Naturales Universidad Pablo de Olavide SevillaE-41013 Spain

In the framework of the chiral quark model along with complex scaling range, we perform a dynamical study on the low-lying S-wave doubly-heavy tetraquark states (QQq¯q¯, Q = c,b and q = u,d) with an accurate computing approach, Gaussian expansion method. The meson-meson and diquark-antidiquark configurations within all possible color structures for spin-parity quantum numbers JP = 0+, 1+ and 2+, and in the 0 and 1 isospin sectors are considered. Possible tightly bound and narrow resonance states are obtained for doubly-charm and doubly-bottom tetraquarks with IJP = 01+, and these exotic states are also obtained in charm-bottom tetraquarks with 00+ and 01+ quantum numbers. Only loosely bound state is found in charm-bottom tetraquarks of 02+ states. All of these bound states within meson-meson configurations are loosely bound whether in color-singlet channels or coupling to hidden-color ones. However compact structures are available in diquark-antidiquark channels except for charm-bottom tetraquarks in 02+ states. Copyright © 2019, The Authors. All rights reserved.

关键词： Hadrons

Dynamical energy equipartition of the Toda model with additional on-site potentials

学校读者我要写书评

暂无评论

Chinese Physics B 2017年第10期26卷 107-111页

作者：张振俊唐春梅康静童培庆 College of Science Hohai University School of Physics and Technology Nanjing Normal University Jiangsu Provincial Key Laboratory for Numerical Simulation of Large Scale Complex Systems Nanjing Normal University

We study the dynamical energy equipartition properties in the integrable Toda model with additional uniform or disordered on-site energies by extensive numerical simulations. The total energy is initially equidistributed among some of the lowest frequency linear modes. For the Toda model with uniform on-site potentials, the energy spectrum keeps its profile nearly unchanged in a relatively short time scale. On a much longer time scale, the energies of tail modes increase slowly with time. Energy equipartition is far away from being attached in our studied time scale. For the Toda model with disordered on-site potentials, the energy transfers continuously to the high frequency modes and eventually towards energy equipartition. We further perform a systematic study of the equipartition time teq depending on the energy density ε and the nonlinear parameter α in the thermodynamic limit for the Toda model with disordered on-site potentials. We find teq∝ （1/ε）^a（1/α）^b, where b≈ 2a. The values of a and b are increased when increasing the strengths of disordered on-site potentials or decreasing the number of initially excited modes.

关键词： energy transport behaviors Toda model uniform or disordered on-site potentials

Pc-like pentaquarks in hidden strange sector

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Huang, Hongxia Ping, Jialun Department of Physics Jiangsu Key Laboratory for Numerical Simulation of Large Scale Complex Systems Nanjing Normal University Nanjing210023

Analogous to the work of hidden charm molecular pentaquarks, we study possible hidden strange molecular pentaquarks composed of S (or σz∗) and K (or Kz∗) in the framework of quark delocalization color screening model. Our results suggest that the SK, SKz∗and σz∗Kz∗with IJP = 11/22 - and SKz∗, σz∗K and σz∗Kz∗with IJP= 13/22 - are all resonance states by coupling the open channels. The molecular pentaquark σz∗K with quantum numbers IJP= 13/22 - can be seen as a strange partner of the LHCb Pc(4380) state, and it can be identified as the nucleon resonance Nz∗(1875) listed in PDG. The SKz∗with quantum numbers IJP= 13 -/22 can be identified as the Nz∗(2100), which was experimentally observed in the f photo-production. Copyright © 2018, The Authors. All rights reserved.

关键词： Hadrons

Anatomy of Bs → P P decays and effects of the next-to-leading order contributions in the perturbative QCD approach

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Yan, Da-Cheng Liu, Xin Xiao, Zhen-Jun Department of Physics Institute of Theoretical Physics Nanjing Normal University Nanjing Jiangsu210023 China School of Physics and Electronic Engineering Jiangsu Normal University Xuzhou221116 China Jiangsu Key Laboratory for Numerical Simulation of Large Scale Complex Systems Nanjing Normal University Nanjing Jiangsu210023 China

By employing the perturbative QCD (PQCD) factorization approach, we made a systematic investigation for the CP-averaged branching ratios and the CP-violating asymmetries of the thirteen B¯s0 → P P decays (here P = (π, K, η, η′)) with the inclusion of all currently known next-to-leading order (NLO) contributions, and compared our results with the measured values or the theoretical predictions from other different approaches. We focused on the examination of the effects of the NLO contributions and found the following points: (a) for B¯s0 → (K0K¯ 0, K+K−, η′η′, π−K+) decays, the NLO contributions can provide a (40 − 150)% enhancement or a 20% reduction to the corresponding leading order (LO) PQCD predictions for their decay rates and result in a much better agreement between the PQCD predictions and the experimental measurements;(b) for the pure annihilation decay B¯s0 → π+π−, the PQCD prediction still remain consistent with the data after the inclusion of the small NLO reduction;(c) the PQCD predictions for the ratio (fs/fd) · B(Bs0 → π+π−)/B(B0 → K+π−) and (fs/fd) · B(Bs0 → π+K−)/B(B0 → K+π−) become agree very well with the measured ones after the inclusion of a 40% NLO reduction;(d) for B¯s0 → K+K− and B¯s0 → π−K+ decays, the NLO PQCD predictions for their CP-violating asymmetries do agree very well with the measured values in both the sign and the magnitude;and (e) for all B¯s0 → P P decays, we also compared our results with those obtained in the QCD factorization approach and soft-collinear effective theory and discussed their similarities and differences. Copyright © 2019, The Authors. All rights reserved.

关键词： Forecasting