检索结果-内蒙古大学图书馆

Motor Imagery EEG Classification using Wavelet Common Spatial Boosting Pattern

学校读者我要写书评

暂无评论

Motor Imagery EEG Classification using Wavelet Common Spatia...

2017 5th International Conference on Advanced computer science Applications and Technologies(ACSAT 2017)

作者： Shaobo Liu Fuchun Sun Wenchang Zhang Chuanqi Tan Department of Computer Science and Technology Tsinghua UniversityState Key Lab. of Intelligent Technology and SystemsTsinghua National Laboratory for Information Science and Technology (TNList)

Feature Extraction is one of the most important steps in brain-computer interface(BCI) systems. In particular, the common spatial patterns(CSP) is one of the most successful solutions which has been widely used in MI-BCIs. However, studies have reported that the performance of CSP heavily depends on its channels configuration. To the best of our current knowledge, it is not available to obtain the active channels related to brain activities of stroke patients in advance. Hence, we usually set a relatively broad channels or try to select a subject-specific channels when applying CSP to stroke patients. In this paper, we present a novel approach which employs wavelet transform and boosting algorithm to improve accuracy and robustness of the conventional CSP. In our proposed approach, the channel configurations are initially divided into multiple preconditions. Then, the informative features of the predefined channels are obtained using the Wavelet Common Spatial Pattern(W-CSP) algorithm that provided high-temporal-spectral resolution. Eventually, we train weak classifiers on the obtained features and combine these weak classifiers to a weighted combinational model using boosting strategy. Extensive experiments have been performed on datasets from the famous BCI competition III and IV. The results demonstrate its superior performance.

关键词： Common Spatial Pattern Wavelet Transform Brain-computer Interface(BCI)

On-line memorry defragmentation for NVM-based persistent heaps 6

学校读者我要写书评

暂无评论

On-line memorry defragmentation for NVM-based persistent hea...

6th IEEE Non-Volatile Memory Systems and Applications Symposium, NVMSA 2017

作者： Li, Lin Jiang, Wei Pan, Rui Zhan, Jinyu Shao, Zili Xiong, Xiankui School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Department of Computing Hong Kong Polytechnic University Hong Kong Hong Kong Zhongxing Telecommunication Equipment Corporation Nanjing China State Key Lab of Mathematical Engineering and Advanced Computing Wuxi China

ISBN: (纸本)9781538617687

Due to the durability of NVM, we are facing the great challenge of performing efficient memory defragmentation on persistent heaps. To address the problem, we propose an Online Persistent Memory Defragmentation (OPMD) method to manage persistent heaps. Employing two segment trees to track memory allocation and deallocation operations, our method can amortize the cost of global scan, and determine the most valuable objects needed to be moved in logarithmic time. OPMD adopts software transactional memory to move objects and updates object references in constant time using object metadata. We conduct extensive experiments to test the impact of OPMD on the throughput of the operations of linked list and hash table. © 2017 IEEE.

关键词： Resource management Metadata Nonvolatile memory Memory management Tracking Throughput Random access memory

Privacy preserving distributed permutation test 16

学校读者我要写书评

暂无评论

Privacy preserving distributed permutation test

4th ACM International Workshop on Security in Cloud Computing, SCC 2016

作者： Mao, Yunlong Zhang, Yuan State Key Laboratory for Novel Software Technology Nanjing University Computer Science and Technology Department Nanjing210046 China

ISBN: (纸本)9781450342858

In this paper, we propose a privacy-preserving algorithm for two-party distributed permutation test for the difference of means. Our algorithm allows two parties to jointly perform a permutation test on the union of their data without revealing their data to each other. Our algorithm is useful especially in areas where the testing data often contains private information e.g. clinic trial and biomedical research. We have proved the security of our algorithm and used experiment to show its efficiency. To the best of our knowledge, we are the first to address the privacy issues in permutation tests. © 2016 ACM.

关键词： Bioinformatics

Improving interpretability of deep neural networks with semantic information

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Dong, Yinpeng Su, Hang Zhu, Jun Zhang, Bo Tsinghua National Lab for Information Science and Technology State Key Lab of Intelligent Technology and Systems Center for Bio-Inspired Computing Research Department of Computer Science and Technology Tsinghua University

Interpretability of deep neural networks (DNNs) is essential since it enables users to understand the overall strengths and weaknesses of the models, conveys an understanding of how the models will behave in the future, and how to diagnose and correct potential problems. However, it is challenging to reason about what a DNN actually does due to its opaque or black-box nature. To address this issue, we propose a novel technique to improve the interpretability of DNNs by leveraging the rich semantic information embedded in human descriptions. By concentrating on the video captioning task, we first extract a set of semantically meaningful topics from the human descriptions that cover a wide range of visual concepts, and integrate them into the model with an interpretive loss. We then propose a prediction difference maximization algorithm to interpret the learned features of each neuron. Experimental results demonstrate its effectiveness in video captioning using the interpretable features, which can also be transferred to video action recognition. By clearly understanding the learned features, users can easily revise false predictions via a human-in-the-loop procedure. Copyright © 2017, The Authors. All rights reserved.

关键词： Deep neural networks

DoesWilliam Shakespeare REALLY write hamlet? knowledge representation learning with confidence

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Xie, Ruobing Liu, Zhiyuan Lin, Fen Lin, Leyu Department of Computer Science and Technology State Key Lab on Intelligent Technology and Systems National Lab for Information Science and Technology Tsinghua University Search Product Center WeChat Search Application Department Tencent

Knowledge graphs (KGs), which could provide essential relational information between entities, have been widely utilized in various knowledge-driven applications. Since the overall human knowledge is innumerable that still grows explosively and changes frequently, knowledge construction and update inevitably involve automatic mechanisms with less human supervision, which usually bring in plenty of noises and conflicts to KGs. However, most conventional knowledge representation learning methods assume that all triple facts in existing KGs share the same significance without any noises. To address this problem, we propose a novel confidence-aware knowledge representation learning framework (CKRL), which detects possible noises in KGs while learning knowledge representations with confidence simultaneously. Specifically, we introduce the triple confidence to conventional translation-based methods for knowledge representation learning. To make triple confidence more flexible and universal, we only utilize the internal structural information in KGs, and propose three kinds of triple confidences considering both local and global structural information. In experiments, We evaluate our models on knowledge graph noise detection, knowledge graph completion and triple classification. Experimental results demonstrate that our confidence-aware models achieve significant and consistent improvements on all tasks, which confirms the capability of CKRL modeling confidence with structural information in both KG noise detection and knowledge representation learning. Copyright © 2017, The Authors. All rights reserved.

关键词： Knowledge graph

Counting hypergraph matchings up to uniqueness threshold 19

学校读者我要写书评

暂无评论

Counting hypergraph matchings up to uniqueness threshold

19th International Workshop on Approximation Algorithms for Combinatorial Optimization Problems, APPROX 2016 and the 20th International Workshop on Randomization and Computation, RANDOM 2016

作者： Song, Renjie Yin, Yitong Zhao, Jinman Department of Computer Science and Technology Nanjing University China State Key Lab for Novel Software Technology Nanjing University China Department of Computer Science University of Wisconsin-Madison United States

ISBN: (纸本)9783959770187

We study the problem of approximately counting matchings in hypergraphs of bounded maximum degree and maximum size of hyperedges. With an activity parameter λ, each matching M is assigned a weight λ|M|. The counting problem is formulated as computing a partition function that gives the sum of the weights of all matchings in a hypergraph. This problem unifies two extensively studied statistical physics models in approximate counting: The hardcore model (graph independent sets) and the monomer-dimer model (graph matchings). For this model, the critical activity λc = dd k(d-1)d+1 is the threshold for the uniqueness of Gibbs measures on the infinite (d + 1)-uniform (k + 1)-regular hypertree. Consider hypergraphs of maximum degree at most k+1 and maximum size of hyperedges at most d+1. We show that when λ c, there is an FPTAS for computing the partition function;and when λ = λc, there is a PTAS for computing the log-partition function. These algorithms are based on the decay of correlation (strong spatial mixing) property of Gibbs distributions. When λ > 2λc, there is no PRAS for the partition function or the log-partition function unless NP=RP. Towards obtaining a sharp transition of computational complexity of approximate counting, we study the local convergence from a sequence of finite hypergraphs to the infinite lattice with specified symmetry. We show a surprising connection between the local convergence and the reversibility of a natural random walk. This leads us to a barrier for the hardness result: The non-uniqueness of infinite Gibbs measure is not realizable by any finite gadgets.

关键词： Statistical Physics

Testing as an investment

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Xu, Xiaoran Fang, Chunrong Chen, Zhenyu State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Software Institute Nanjing University Nanjing China Computer Science Department Rice University HoustonTX United States

software testing is an expensive and important task. Plenty of researches and industrial efforts have been invested on improving software testing techniques, including criteria, tools, etc. These studies can provide guidelines to select suitable test techniques for software engineers. However, in some engineering projects, business issues may be more important than technical ones, hence we need to lobby non-technical members to support our decisions. In this paper, a well-known investment model, Nelson-Siegel model, is introduced to evaluate and forecast the processes of testing with different testing criteria. Through this model, we provide a new perspective to understand short-term, medium-term, and long-term returns of investments throughout the process of testing. A preliminary experiment is conducted to investigate three testing criteria from the viewpoint of investments. The results show that statement-coverage criterion performs best in gaining long-term yields;the short-term and medium-term yields of testing depend on the scale of programs and the number of faults they contain. Copyright © 2017, The Authors. All rights reserved.

关键词： Investments

Launch of the NSFC Excellent Young Scholars Forum

学校读者我要写书评

暂无评论

Frontiers of computer science 2016年第1期10卷 1-1页

作者： Zhi-Hua ZHOU National Key Laboratory for Novel Software Technology Department of Computer Science & Technology Nanjing University Nanjing 210023 China

In 2012, the national Natural science Foundation of China （NSFC） launched the Excellent Young Scholars （EYS） Pro- gram. As its name suggests, this program aims to recognize and support excellent young scholars in the fields of science and engineering. This program is similar to the NSF Career Award in the United States, and the competition is very tough： only a very limited number of applicants can get through. Each awardee will receive a fund of one million CNY for a three-year *** such generous support, awardees are expected to do more excellent research and grow up quickly as distinguished young scholars.

关键词： NSFC Excellent Young Scholars

Empirical risk minimization for stochastic convex optimization: O(1/n)- and O(1/n2)-type of Risk Bounds

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Zhang, Lijun Yang, Tianbao Jin, Rong National Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China Department of Computer Science University of Iowa Iowa CityIA52242 United States Alibaba Group Seattle United States

Although there exist plentiful theories of empirical risk minimization (ERM) for supervised learning, current theoretical understandings of ERM for a related problem—stochastic convex optimization (SCO), are limited. In this work, we strengthen the realm of ERM for SCO by exploiting smoothness and strong convexity conditions to improve the risk bounds. First, we establish an Oe(d/n + pF∗/n) risk bound when the random function is nonnegative, convex and smooth, and the expected function is Lipschitz continuous, where d is the dimensionality of the problem, n is the number of samples, and F∗ is the minimal risk. Thus, when F∗ is small we obtain an Oe(d/n) risk bound, which is analogous to the Oe(1/n) optimistic rate of ERM for supervised learning. Second, if the objective function is also λ-strongly convex, we prove an Oe(d/n + κF∗/n) risk bound where κ is the condition number, and improve it to O(1/[λn2] + κF∗/n) when n = Ω(e κd). As a result, we obtain an O(κ/n2) risk bound under the condition that n is large and F∗ is small, which to the best of our knowledge, is the first O(1/n2)-type of risk bound of ERM. Third, we stress that the above results are established in a unified framework, which allows us to derive new risk bounds under weaker conditions, e.g., without convexity of the random function and Lipschitz continuity of the expected function. Finally, we demonstrate that to achieve an O(1/[λn2] + κF∗/n) risk bound for supervised learning, the Ω(e κd) requirement on n can be replaced with Ω(κ2), which is dimensionality-independent. Copyright © 2017, The Authors. All rights reserved.

关键词： Convex optimization