检索结果-内蒙古大学图书馆

IEEE Access 2020年 8卷 76595-76595页

作者： Lihong Dai Jinguo Liu Zhaojie Ju Yang Gao State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China School of Electronic and Information Engineering University of Science and Technology Liaoning Anshan China School of Computing University of Portsmouth Portsmouth U.K. Space Technology for Autonomous and Robotic Systems Laboratory (STAR LAB) Surrey Space Centre University of Surrey Guildford U.K.

In the above article [1] , the affiliations of authors Lihong Dai and Yang Gao need to be corrected. Moreover, the biography of Yang Gao needs to be corrected. The specific corrections are as follows.

关键词： Robots Biographies Aerospace electronics Automation Manufacturing Research and development Object recognition

CASICT Tibetanword segmentation system for MLWS2017

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Hu, Jiawei Liu, Qun Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Adapt Centre School of Computing Dublin City University

We participated in the MLWS 2017 on Tibetan word segmentation task, our system is trained in a unrestricted way, by introducing a baseline system and 76w tibetan segmented sentences of ours. In the system character sequence is processed by the baseline system into word sequence, then a subword unit (BPE algorithm 1) split rare words into subwords with its corresponding features, after that a neural network classifier is adopted to token each subword into "B,M,E,S" label, in decoding step a simple rule is used to recover a final word sequence. The candidate system for submition is selected by evaluating the F-score in dev set pre-extracted from the 76w sentences. Experiment shows that this method can fix segmentation errors of baseline system and result in a significant performance gain. Copyright © 2017, The Authors. All rights reserved.

关键词：

Refining source representations with relation networks for neural machine translation

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Zhang, Wen Hu, Jiawei Feng, Yang Liu, Qun Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS China ADAPT Centre School of Computing Dublin City University Ireland

Although neural machine translation (NMT) with the encoder-decoder framework has achieved great success in recent times, it still suffers from some drawbacks: RNNs tend to forget old information which is often useful and the encoder only operates through words without considering word relationship. To solve these problems, we introduce a relation networks (RN) into NMT to refine the encoding representations of the source. In our method, the RN first augments the representation of each source word with its neighbors and reasons all the possible pairwise relations between them. Then the source representations and all the relations are fed to the attention module and the decoder together, keeping the main encoder-decoder architecture unchanged. Experiments on two Chinese-to-English data sets in different scales both show that our method can outperform the competitive baselines significantly. Copyright © 2017, The Authors. All rights reserved.

关键词： Neural machine translation

information-propogation-enhanced neural machine translation by relation model

学校读者我要写书评

暂无评论

arXiv 2017年

Even though sequence-to-sequence neural machine translation (NMT) model have achieved state-of-art performance in the recent fewer years, but it is widely concerned that the recurrent neural network (RNN) units are very hard to capture the long-distance state information, which means RNN can hardly find the feature with long term dependency as the sequence becomes longer. Similarly, convolutional neural network (CNN) is introduced into NMT for speeding recently, however, CNN focus on capturing the local feature of the sequence;To relieve this issue, we incorporate a relation network into the standard encoder-decoder framework to enhance information-propogation in neural network, ensuring that the information of the source sentence can flow into the decoder adequately. Experiments show that proposed framework outperforms the statistical MT model and the state-of-art NMT model significantly on two data sets with different scales. Copyright © 2017, The Authors. All rights reserved.

关键词： Neural machine translation

Accelerating electron tomography reconstruction algorithm ICON with GPU

学校读者我要写书评

暂无评论

Biophysics Reports 2017年第Z1期3卷 36-42页

作者： Yu Chen Zihao Wang Jingrong Zhang Lun Li Xiaohua Wan Fei Sun Fa Zhang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences National Key Laboratory of Biomacromolecules CAS Center for Excellence in Biomacromolecules Institute of Biophysics Chinese Academy of Sciences University of Chinese Academy of Sciences School of Mathematical Sciences University of Chinese Academy of Sciences Center for Biological Imaging Institute of Biophysics Chinese Academy of Sciences

Electron tomography(ET) plays an important role in studying in situ cell ultrastructure in threedimensional space. Due to limited tilt angles, ET reconstruction always suffers from the "missing wedge" problem. With a validation procedure, iterative compressed-sensing optimized NUFFT reconstruction(ICON) demonstrates its power in the restoration of validated missing information for low SNR biological ET dataset. However, the huge computational demand has become a major problem for the application of ICON. In this work, we analyzed the framework of ICON and classified the operations of major steps of ICON reconstruction into three types. Accordingly, we designed parallel strategies and implemented them on graphics processing units(GPU) to generate a parallel program ICON-GPU. With high accuracy, ICON-GPU has a great acceleration compared to its CPU version, up to 83.7×, greatly relieving ICON’s dependence on computing resource.

关键词： Acceleration Electron tomography GPU ICON Missing wedge restoration

Effects of drug resistance in the tumour-immune system with chemotherapy treatment

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Trobia, José Gabrick, Enrique C. Seifert, Evandro G. Borges, Fernando S. Protachevicz, Paulo R. Szezech, José D. Iarosz, Kelly C. Santos, Moises S. Caldas, Iberê L. Tian, Kun Ren, Hai-Peng Grebogi, Celso Batista, Antonio M. Graduate Program in Science - Physics State University of Ponta Grossa Ponta GrossaPR84030-900 Brazil Department of Mathematics and Statistics State University of Ponta Grossa Ponta GrossaPR84030-900 Brazil Department of Physics State University of Ponta Grossa Ponta GrossaPR84030-900 Brazil Center for Mathematics Computation and Cognition Federal University of ABC São Bernardo do CampoSP09606-045 Brazil Institute of Physics University of São Paulo São PauloSP05508-900 Brazil Faculty of Telêmaco Borba FATEB Telêmaco BorbaPR84266-010 Brazil Graduate Program in Chemical Engineering Federal Technological University of Paraná Ponta Grossa Paraná84016-210 Brazil Shaanxi Key Lab of Complex System Control and Intelligent Information Processing Xi’an University of Technology Xi’an710048 China Xi’an Technological University Xi’an710021 China Institute for Complex Systems and Mathematical Biology University of Aberdeen AberdeenAB24 3UE United Kingdom

Cancer is a term used to refer to a large set of diseases. The cancerous cells grow and divide and, as a result, they form tumours that grow in size. The immune system recognise the cancerous cells and attack them, though, it can be weakened by the cancer. One type of cancer treatment is chemotherapy, which uses drugs to kill cancer cells. Clinical, experimental, and theoretical research has been developed to understand the dynamics of cancerous cells with chemotherapy treatment, as well as the interaction between tumour growth and immune system. We study a mathematical model that describes the cancer growth, immune system response, and chemotherapeutic agents. The immune system is composed of resting cells that are converted to hunting cells to combat the cancer. In this work, we consider drug sensitive and resistant cancer cells. We show that the tumour growth can be controlled not only by means of different chemotherapy protocols, but also by the immune system that attacks both sensitive and resistant cancer cells. Furthermore, for all considered protocols, we demonstrate that the time delay from resting to hunting cells plays a crucial role in the combat against cancer cells. Copyright © 2020, The Authors. All rights reserved.

关键词： Chemotherapy

The M-computations induced by accessibility relations in nonstandard models M of Hoare logic

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2016年第4期10卷 717-725页

作者： Cungen CAO Yuefei SUI Zaiyue ZHANG Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Department of Computer Science Jiangsu University of Sciences and Technology Zhenjiang 212003 China

Hoare logic is a logic used as a way of specifying semantics of programming languages, which has been extended to be a separation logic to reason about mutable heap structure. In a model M of Hoare logic, each program α induces an M-computable function fα M on the universe of M; and the M-recursive functions are defined on M. It will be proved that the class of all the M-computable functions fα M induced by programs is equal to the class of all the M- recursive functions. Moreover, each M-recursive function is ∑ 1 NM -definable in M, where the universal quantifier is a num- ber quantifier ranging over the standard part of a nonstandard model M.

关键词： Hoare logic recursive ：Function computable function nonstandard model of Peano arithmetic

Random occlusion-recovery for person re-identification

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Wu, Di Zhang, Kun Cheng, Fei Zhao, Yang Liu, Qi Yuan, Chang-An Huang, De-Shuang Institute of Machine Learning and Systems Biology School of Electronics and Information Engineering Tongji University School of Computing Edinburgh Napier University 10 Colinton Road EdinburghEH10 5DT United Kingdom Science Computing and Intelligent Information Processing of Guang Xi Higher Education Key Laboratory Guangxi Teachers Education University Nanning Guangxi530001 China Beijing E-Hualu Info Technology Co. Ltd Beijing China

As a basic task of multi-camera surveillance system, person re-identification aims to re-identify a query pedestrian observed from non-overlapping multiple cameras or across different time with a single camera. Recently, deep learning-based person re-identification models have achieved great success in many benchmarks. However, these supervised models require a large amount of labeled image data, and the process of manual labeling spends much manpower and time. In this study, we introduce a method to automatically synthesize labeled person images and adopt them to increase the sample number per identity for person re-identification datasets. To be specific, we use block rectangles to randomly occlude pedestrian images. Then, a generative adversarial network (GAN) model is proposed to use paired occluded and original images to synthesize the de-occluded images that similar but not identical to the original image. Afterwards, we annotate the de-occluded images with the same labels of their corresponding raw images and use them to augment the number of samples per identity. Finally, we use the augmented datasets to train baseline model. The experiment results on CUHK03, Market-1501 and DukeMTMC-reID datasets show that the effectiveness of the proposed method. Copyright © 2018, The Authors. All rights reserved.

关键词： Generative adversarial networks

Cross-media analysis and reasoning: advances and directions

学校读者我要写书评

暂无评论

Frontiers of information technology & Electronic Engineering 2017年第1期18卷 44-57页

作者： Yu-xin PENG Wen-wu ZHU Yao ZHAO Chang-sheng XU Qing-ming HUANG Han-qing LU Qing-hua ZHENG Tie-jun HUANG Wen GAO Institute of Computer Science and Technology Peking University Department of Computer Science and Technology Tsinghua University Institute of Information Science Beijing Jiaotong University National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of Sciences Key Laboratory of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of Sciences Department of Computer Science and Technology Xi'an Jiaotong University School of Electronics Engineering and Computer Science Peking University

Cross-media analysis and reasoning is an active research area in computer science, and a promising direction for artificial intelligence. However, to the best of our knowledge, no existing work has summarized the state-of-the-art methods for cross-media analysis and reasoning or presented advances, challenges, and future directions for the field. To address these issues, we provide an overview as follows：（1） theory and model for cross-media uniform representation; （2） cross-media correlation understanding and deep mining; （3） cross-media knowledge graph construction and learning methodologies; （4） cross-media knowledge evolution and reasoning; （5） cross-media description and generation; （6） cross-media intelligent engines; and （7） cross-media intelligent applications. By presenting approaches, advances, and future directions in cross-media analysis and reasoning, our goal is not only to draw more attention to the state-of-the-art advances in the field, but also to provide technical insights by discussing the challenges and research directions in these areas.

关键词： Cross-media analysis Cross-media reasoning Cross-media applications

Non-rigid 3D models retrieval based on hierarchical matching

学校读者我要写书评

暂无评论

Computer Aided Drafting,Design and Manufacturing 2017年第1期27卷 39-47页

作者： Liu Yujie Li Wei Song Yang Gong Weiqing Li Zongmin Li Hua Department of Computer & Communication Engineering China University of Petroleum ChinaPetro (Karamay) Data Center Sinopec Exploration & Production Research Institute (PEPRIS) Key Lab of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of Sciences

In 3D models retrieval, feature description and retrieval of non-rigid model face more complex problems due to the isometry transformation of itself. We introduce the hierarchical combination matching into the feature comparison, and build a map between the divided regions of two models, and then achieve accurate feature matching based on patch-by-patch, which successfully introduces the spatial information into feature matching. Verified by experiment, the 3D model retrieval method proposed in this paper based on hierarchical combination matching can make sure more accurate feature matching, so as to enhance the precision of retrieval.

关键词： non-rigid 3D model shape descriptor spatial distribution hierarchical combination matching