检索结果-内蒙古大学图书馆

2018 International Joint Conference on Neural Networks, IJCNN 2018

作者： Geng, Mingyang Li, Yiying Ding, Bo Wang, And Huaimin National Key Laboratory of Parallel and Distributed Processing College of Computer National University of Defense Technology ChangSha China

ISBN: (纸本)9781509060146

Following trails in the wild is an essential capability of out-door autonomous mobile robots. Recently, deep learningbased approaches have made great advancements in this field. However, the existing research only focuses on the trail following with a single robot. In contrast, many robotic tasks in the reality, such as search and patrolling, are conducted by a group of robots. While these robots are grouped to move in the wild, they can cooperate to significantly promote the trail following accuracy, for example, by sharing images of different view angles or real-time decision fusion. This paper proposes such an approach named DL-Cooper that enables multi-robot visionbased trail following based on deep learning algorithms. It allows each robot to make a decision respectively with deep neural network and then fusion the decisions on the collective level with the support of back-end cloud computing infrastructure. It also takes Quality of Service (QoS) assurance, a very essential property of robotic software, into consideration. By limiting the condition to fusion decisions, the time latency can be minimally sacrificed. Experiments on the real-world dataset show that our approach has significantly improved the accuracy of the singlerobot system. © 2018 IEEE.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Learning-based Depth Estimation aided Visual SLAM Approach

arXiv

引用

arXiv 2019年

作者： Geng, Mingyang Shang, Suning Ding, Bo Wang, Huaimin Zhang, Pengfei Zhang, Lei National Key Laboratory of Parallel and Distributed Processing College of Computer National University of Defense Technology China National Key Laboratory of Integrated Automation of Process Industry Northeastern University China

Existing visual-based SLAM systems mainly utilize the three-dimensional environmental depth information from RGB-D cameras to complete the robotic synchronization localization and map construction task. However, the RGB-D camera maintains a limited range for working and is hard to accurately measure the depth information in a far distance. Besides, the RGB-D camera will easily be influenced by strong lighting and other external factors, which will lead to a poor accuracy on the acquired environmental depth information. Recently, deep learning technologies have achieved great success in the visual SLAM area, which can directly learn high-level features from the visual inputs and improve the estimation accuracy of the depth information. Therefore, deep learning technologies maintain the potential to extend the source of the depth information and improve the performance of the SLAM system. However, the existing deep learning-based methods are mainly supervised and require a large amount of ground-truth depth data, which is hard to acquire because of the realistic constraints. In this paper, we first present an unsupervised learning framework, which not only uses image reconstruction for supervising but also exploits the pose estimation method to enhance the supervised signal and add training constraints for the task of monocular depth and camera motion estimation. Furthermore, we successfully exploit our unsupervised learning framework to assist the traditional ORB-SLAM system when the initialization module of ORB-SLAM method could not match enough features. Qualitative and quantitative experiments have shown that our unsupervised learning framework performs the depth estimation task comparably to the supervised methods and outperforms the previous state-of-the-art approach by 13.5% on KITTI dataset. Besides, our unsupervised learning framework could significantly accelerate the initialization process of ORB-SLAM system and effectively improve the accuracy on environme

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Succinct Representations in Collaborative Filtering: A Case Study using Wavelet Tree on 1,000 Cores

Succinct Representations in Collaborative Filtering: A Case ...

引用

IEEE International Conference on parallel and distributed computing, Applications and Technologies (PDCAT)

作者： Xiangjun Peng Qingfeng Wang Xu Sun Chunye Gong Yaohua Wang User-Centric Computing Group University of Nottingham Ningbo China Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology

ISBN: (数字)9781728126166

ISBN: (纸本)9781728126173

User-Item (U-I) matrix has been used as the dominant data infrastructure of Collaborative Filtering (CF). To reduce space consumption in runtime and storage, caused by data sparsity and growing need to accommodate side information in CF design, one needs to go beyond the U-I Matrix. In this paper, we took a case study of Succinct Representations in Collaborative Filtering, rather than using a U-I Matrix. Our key insight is to introduce Succinct Data Structures as a new infrastructure of CF. Towards this, we implemented a User-based K-Nearest-Neighbor CF prototype via Wavelet Tree, by first designing a Accessible Compressed Documents (ACD) to compress U-I data in Wavelet Tree, which is efficient in both storage and runtime. Then, we showed that ACD can be applied to develop an efficient intersection algorithm without decompression, by taking advantage of ACD's characteristics. We evaluated our design on 1,000 cores of Tianhe-II supercomputer, with one of the largest public data set ml-20m. The results showed that our prototype could achieve 3.7 minutes on average to deliver the results.

关键词： Vegetation Collaboration Filtering Data structures Runtime Indexes Time complexity

来源：评论

学校读者我要写书评

暂无评论

Modeling complex relationship paths for knowledge graph completion

Modeling complex relationship paths for knowledge graph comp...

引用

作者： Zeng, Ping Tan, Qingping Meng, Xiankai Zhang, Haoyu Xu, Jianjun College of Computer National University of Defense Technology Changsha China National Key Laboratory for Parallel and Distributed Processing Changsha China

Determining the validity of knowledge triples and filling in the missing entities or relationships in the knowledge graph are the crucial tasks for large-scale knowledge graph completion. So far, the main solutions use machine learning methods to learn the low-dimensional distributed representations of entities and relationships to complete the knowledge graph. Among them, translationmodels obtain excellent performance. However, the proposed translation models do not adequately consider the indirect relationships among entities, affecting the precision of the representation. Based on the long short-term memory neural network and existing translation models, we propose a multiple-module hybrid neural network model called TransP. By modeling the entity paths and their relationship paths, TransP can effectively excavate the indirect relationships among the entities, and thus, improve the quality of knowledge graph completion tasks. Experimental results show that TransP outperforms state-of-the-art models in the entity prediction task, and achieves the comparable performance with previous models in the relationship prediction task. © 2018 The Institute of Electronics, Information and Communication Engineers.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

GREYONE: data flow sensitive fuzzing 20

GREYONE: data flow sensitive fuzzing

引用

Proceedings of the 29th USENIX Conference on Security Symposium

作者： Shuitao Gan Chao Zhang Peng Chen Bodong Zhao Xiaojun Qin Dong Wu Zuoning Chen State Key Laboratory of Mathematical Engineering and Advanced Computing Institute for Network Science and Cyberspace Tsinghua University and Beijing National Research Center for Information Science and Technology ByteDance AI lab Institute for Network Science and Cyberspace Tsinghua University National Research Center of Parallel Computer Engineering and Technology

ISBN: (纸本)9781939133175

Data flow analysis (e.g., dynamic taint analysis) has proven to be useful for guiding fuzzers to explore hard-to-reach code and find vulnerabilities. However, traditional taint analysis is labor-intensive, inaccurate and slow, affecting the fuzzing efficiency. Apart from taint, few data flow features are *** this paper, we proposed a data flow sensitive fuzzing solution GREYONE. We first utilize the classic feature taint to guide fuzzing. A lightweight and sound fuzzing-driven taint inference (FTI) is adopted to infer taint of variables, by monitoring their value changes while mutating input bytes during fuzzing. With the taint, we propose a novel input prioritization model to determine which branch to explore, which bytes to mutate and how to mutate. Further, we use another data flow feature constraint conformance, i.e., distance of tainted variables to values expected in untouched branches, to tune the evolution direction of *** implemented a prototype of GREYONE and evaluated it on the LAVA data set and 19 real world programs. The results showed that it outperforms various state-of-the-art fuzzers in terms of both code coverage and vulnerability discovery. In the LAVA data set, GREYONE found all listed bugs and 336 more unlisted. In real world programs, GREYONE on average found 2.12X unique program paths and 3.09X unique bugs than state-of-the-art evolutionary fuzzers, including AFL, VUzzer, CollAFL, Angora and Honggfuzz, Moreover, GREYONE on average found 1.2X unique program paths and 1.52X unique bugs than a state-of-the-art symbolic exeuction assisted fuzzer QSYM. In total, it found 105 new security bugs, of which 41 are confirmed by CVE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Attention-based fault-tolerant approach for multi-agent reinforcement learning systems

arXiv

引用

arXiv 2019年

作者： Geng, Mingyang Xu, Kele Li, Yiying Liu, Shuqi Ding, Bo Wang, Huaimin National Key Laboratory of Parallel and Distributed Processing College of Computer National University of Defense Technology Changsha410073 China National Key Laboratory of Big Data Management and Analysis Northeastern University Shenyang110000 China

The aim of multi-agent reinforcement learning systems is to provide interacting agents with the ability to collaboratively learn and adapt to the behavior of other agents. In many real-world applications, the agents can only acquire a partial view of the world. However, in realistic settings, one or more agents that show arbitrarily faulty or malicious behavior may suffice to let the current coordination mechanisms fail. In this paper, we study a practical scenario considering the security issues in the presence of agents with arbitrarily faulty or malicious behavior. Under these circumstances, learning an optimal policy becomes particularly challenging, even in the unrealistic case that an agent's policy can be made conditional upon all other agents' observations. To overcome these difficulties, we present an Attention-based Fault-Tolerant (FT-Attn) algorithm which selects correct and relevant information for each agent at every time-step. The multi-head attention mechanism enables the agents to learn effective communication policies through experience concurrently to the action policies. Empirical results have shown that FT-Attn beats previous state-of-the-art methods in some complex environments and can adapt to various kinds of noisy environments without tuning the complexity of the algorithm. Furthermore, FT-Attn can effectively deal with the complex situation where an agent needs to reach multiple agents' correct observation at the same time. Copyright © 2019, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Mobile Robot Object Recognition in The Internet of Things based on Fog computing

Mobile Robot Object Recognition in The Internet of Things ba...

引用

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

作者： Meixia Fu Songlin Sun Kaili Ni Xiaoying Hou National Engineering Laboratory for Mobile Network Security Beijing University of Posts and Telecommunications Key Laboratory of Trustworthy Distributed Computing and Service (BUPT)

ISBN: (数字)9781728132488

ISBN: (纸本)9781728132495

Mobile robot object recognition has attracted significant attention in the internet of things recently, in which there are many challenging tasks, such as the objects, the communication networks and the computer system. It still needs a large of computation, communication and storage capability for the whole system. In this paper, we propose a scheme of mobile robot object recognition in IOT and use edge nodes to process the data from robot vision instead of cloud computing. Besides, we adopt YOLOv3 as the main algorithm in the edge nodes to process the video data. The video from the camera on the robot is transmitted to the fog node by a Wi-Fi router. The advantages of using edge nodes for computation local robot clusters are reliability, real-time capability and flexibility compared with the cloud. In our experiment, we efficiently train the computer model using COCO database deployed to GPU. The robot using the proposed model could recognize the objects in real-time. We achieve mAP of 31.0% and response time of 52ms that illustrates the state-of-art performance of the proposed framework.

关键词： Object recognition Edge computing Cloud computing Real-time systems Servers Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Towards a uniform architecture for the efficient implementation of 2D and 3D deconvolutional neural networks on FPGAS

arXiv

引用

arXiv 2019年

作者： Wang, Deguang Shen, Junzhong Wen, Mei Zhang, Chunyuan College of Computer National University of Defense Technology Changsha410073 China National Key Laboratory for Parallel Distributed ProcessingNational University of Defense Technology Changsha410073 China

Three-dimensional deconvolution is widely used in many computer vision applications. However, most previous works have only focused on accelerating 2D deconvolutional neural networks (DCNNs) on FPGAs, while the acceleration of 3D DCNNs has not been studied in depth as they have higher computational complexity and sparsity than 2D DCNNs. In this paper, we focus on the acceleration of both 2D and 3D DCNNs on FPGAs by proposing efficient schemes for mapping 2D and 3D DCNNs on a uniform architecture. By implementing our design on the Xilinx VC709 platform for four real-life 2D and 3D DCNNs, we can achieve up to 3.0 TOPS with high hardware efficiency. Comparisons with CPU and GPU solutions demonstrate that we can achieve an improvement of up to 63.3× in throughput relative to a CPU solution and an improvement of up to 8.3× in energy efficiency compared to a GPU solution. Copyright © 2019, The Authors. All rights reserved.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Based Antenna Selection in User-Centric Massive MIMO

Reinforcement Learning Based Antenna Selection in User-Centr...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Xinxin Chai Hui Gao Ji Sun Xin Su Tiejun Lv Jie Zeng Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing University of Posts and Telecommunications Beijing China Ministry of Industry and Information Technology Institute of Telecommunications Beijing China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China

ISBN: (数字)9781728152073

ISBN: (纸本)9781728140537

In this paper, we consider a user-centric massive multiple-input multiple-output (UC-MMIMO) system, wherein the optimal antenna selection (AS) is very complicated, because of the huge number of deployed antennas. Traditional AS algorithms rely heavily on full and perfect channel state information (CSI). Thus, we propose a novel AS algorithm to achieve low-complexity and less CSI reliance for UC-MMIMO. The proposed AS algorithm consists of the selection stage and the adjustment stage. In the selection stage, antennas are selected by a reinforcement learning (RL) based algorithm in which input data are the locations of users. In the adjustment stage, an adjustment mechanism is designed to further improve the performance. Numerical results show that our algorithm achieves better performance with lower complexity compared with related traditional algorithms.

关键词： Loaded antennas Machine learning algorithms Reinforcement learning Antenna arrays Massive MIMO

来源：评论

学校读者我要写书评

暂无评论

Modulation Recognition based on Incremental Deep Learning

Modulation Recognition based on Incremental Deep Learning

引用

International Conference on Mechanical, Control and Computer Engineering (ICMCCE)

作者： Yong Yang Menghan Chen XiaoYa Wang Piming Ma The 54th Research Institute of CETC Shijiazhuang China School of Information Science and Engineering Shandong University Qingdao China School of Information and Communication Engineering National Engineering Laboratory for Mobile Network Security Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications line Beijing China

Incremental learning has emerged to solve the problem of incrementally updating the classification model as the number of data classes grows. There are many challenges in incremental learning such as catastrophic forgetting and learning efficiency. In this paper, we present a method of the modulation recognition based on incremental learning, that allows learning continuously with a class-incremental way. The new classes can be added into the existing model progressively from a sequential data stream. We conduct experiments on the modulation signal dataset characterized by the constellation diagram, the experimental results prove the feasibility of our incremental learning system. Our method performs similarly in classification accuracy compared to common multi-task joint training, but performs better in training efficiency.

关键词： Training Learning systems Deep learning Constellation diagram Memory management Modulation Aerospace electronics

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：