检索结果-内蒙古大学图书馆

Exploring machine learning Object Classification for Interactive Proximity Surfaces 1

4th international conference on Distributed, Ambient and Pervasive Interactions (DAPI) held as part of 18th international conference on Human-Computer Interaction (HCI international)

作者： Braun, Andreas Alekseew, Michael Kuijper, Arjan Fraunhofer Inst Comp Graph Res IGD Darmstadt Germany Tech Univ Darmstadt Darmstadt Germany

ISBN: (数字)9783319398624

ISBN: (纸本)9783319398624;9783319398617

Capacitive proximity sensors are a variety of the sensing technology that drives most finger-controlled touch screens today. However, they work over a larger distance. As they are not disturbed by non-conductive materials, they can be used to track hands above arbitrary surfaces, creating flexible interactive surfaces. Since the resolution is lower compared to many other sensing technologies, it is necessary to use sophisticated data processing methods for object recognition and tracking. In this work we explore machine learning methods for the detection and tracking of hands above an interactive surface created with capacitive proximity sensors. We discuss suitable methods and present our implementation based on Random Decision Forests. the system has been evaluated on a prototype interactive surface - the CapTap. Using a Kinect-based hand tracking system, we collect training data and compare the results of the learning algorithm to actual data.

关键词： Capacitive proximity sensing Interactive surfaces machine learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Task learning for Food Identification and Analysis with Deep Convolutional Neural Networks

引用

Journal of Computer Science & Technology 2016年第3期31卷 489-500页

作者： Xi-Jin Zhang Yi-Fan Lu Song-Hai Zhang Department of Computer Science and Technology Tsinghua University Beijing 100084 China

In this paper, we proposed a multi-task system that can identify dish types, food ingredients, and cooking methods from food images with deep convolutional neural networks. We built up a dataset of 360 classes of different foods with at least 500 images for each class. To reduce the noises of the data, which was collected from the Internet, outlier images were detected and eliminated through a one-class SVM trained with deep convolutional features. We simultaneously trained a dish identifier, a cooking method recognizer, and a multi-label ingredient detector. they share a few low-level layers in the deep network architecture. the proposed framework shows higher accuracy than traditional method with handcrafted features, and the cooking method recognizer and ingredient detector can be applied to dishes which are not included in the training dataset to provide reference information for users.

关键词： multi-task learning convolutional neural network food recognition machine learning

来源：评论

学校读者我要写书评

暂无评论

Function Interface Analysis: A Principled Approach for Function recognition in COTS Binaries

Function Interface Analysis: A Principled Approach for Funct...

引用

international conference on Dependable Systems and Networks (DSN)

作者： Rui Qiao R. Sekar Stony Brook University Stony Brook NY US Stony Brook University

ISBN: (纸本)9781538605431

Function recognition is one of the key tasks in binary analysis, instrumentation and reverse engineering. Previous approaches for this problem have relied on matching code patterns commonly observed at the beginning and end of functions. While early efforts relied on compiler idioms and expert-identified patterns, more recent works have systematized the process using machine-learning techniques. In contrast, we develop a novel static analysis based method in this paper. In particular, we combine a low-level technique for enumerating candidate functions with a novel static analysis for determining if these candidates exhibit the properties associated with a function interface. Both control-flow properties (e.g., returning to the location at the stack top at the function entry point) and data-flow properties (e.g., parameter passing via registers and the stack, and the degree of adherence to application-binary interface conventions) are checked. Our approach achieves an F1-score above 99% across a broad range of programs across multiple languages and compilers. More importantly, it achieves a 4× or higher reduction in error rate over best previous results.

关键词： Optimization Error analysis Instruments Registers Robustness pattern matching

来源：评论

学校读者我要写书评

暂无评论

Efficient Natural Language Pre-processing for Analyzing Large data Sets 4

Efficient Natural Language Pre-processing for Analyzing Larg...

引用

4th IEEE international conference on Big data (Big data)

作者： Billal, Belainine Fonseca, Alexsandro Sadat, Fatiha Univ Quebec Montreal Dept Comp Sci Montreal PQ Canada

ISBN: (纸本)9781467390057

the phenomenon of big data is described using five Vs: Volume, Variety, Velocity, Variability and Veracity. In this paper, we are interested by analyzing and pre-processing tweets for NLP and machine learning applications such as machine translation and classification. Collected contents from twitter (tweets) are considered as unstructured, highly noisy and short (140 characters) texts. Overcoming these complex challenges will help learn from such data and apply traditional NLP and machine learning techniques. In this paper, we propose a pre-processing pipeline for tweets consisting of filtering part-of-speech, named entities recognition, hashtag segmentation and disambiguation. Our proposed approach is also based on the graph theory and group words of tweets using semantic relations of WordNet and the idea of connected components. Evaluations on the task of classification showed promising results when using this proposed preprocessing pipeline, with an increase in the accuracy of the classification up to 87.6%.

关键词： Natural Language Processing big data tweets twitter named entities hashtag segmentation

来源：评论

学校读者我要写书评

暂无评论

Transfer learning Algorithms for Autonomous Reconfiguration of Wearable Systems 4

Transfer Learning Algorithms for Autonomous Reconfiguration ...

引用

4th IEEE international conference on Big data (Big data)

作者： Saeedi, Ramyar Ghasemzadeh, Hassan Gebremedhin, Assefaw H. Washington State Univ Sch Elect Engn & Comp Sci Pullman WA 99164 USA

ISBN: (纸本)9781467390057

Wearables have emerged as a revolutionary technology in many application domains including healthcare and fitness. machine learning algorithms, which form the core intelligence of wearables, traditionally deduce a computational model from a set of training examples to detect events of interest (e.g. activity type). However, in the dynamic environment in which wearables typically operate in, the accuracy of a computational model drops whenever changes in configuration of the system (such as device type and sensor orientation) occur. therefore, there is a need to develop systems which can adapt to the new configuration autonomously. In this paper, using transfer learning as an organizing principle, we develop several algorithms for data mapping. the data mapping algorithms employ effective signal similarity methods and are used to adapt the system to the new configuration. We demonstrate the efficacy of the data mapping algorithms using a publicly available dataset on human activity recognition.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Predicting Statistics of Asynchronous SGD Parameters for a Large-Scale Distributed Deep learning System on GPU Supercomputers 4

Predicting Statistics of Asynchronous SGD Parameters for a L...

引用

4th IEEE international conference on Big data (Big data)

作者： Oyama, Yosuke Nomura, Akihiro Sato, Ikuro Nishimura, Hiroki Tamatsu, Yukimasa Matsuoka, Satoshi Tokyo Inst Technol Tokyo Japan Denso It Lab Inc Tokyo Japan Denso Corp Kariya Aichi Japan

ISBN: (纸本)9781467390057

Many studies have shown that Deep Convolutional Neural Networks (DCNNs) exhibit great accuracies given large training datasets in image recognition tasks. Optimization technique known as asynchronous mini-batch Stochastic Gradient Descent (SGD) is widely used for deep learning because it gives fast training speed and good recognition accuracies, while it may increases generalization error if training parameters are in inappropriate ranges. We propose a performance model of a distributed DCNN training system called SPRINT that uses asynchronous GPU processing based on mini-batch SGD. the model considers the probability distribution of mini-batch size and gradient staleness that are the core parameters of asynchronous SGD training. Our performance model takes DCNN architecture and machine specifications as input parameters, and predicts time to sweep entire dataset, mini-batch size and staleness with 5%, 9% and 19% error in average respectively on several supercomputers with up to thousands of GPUs. Experimental results on two different supercomputers show that our model can steadily choose the fastest machine configuration that nearly meets a target mini-batch size.

关键词： Deep learning Performance modeling Asynchronous stochastic gradient descent

来源：评论

学校读者我要写书评

暂无评论

Analyzing efficiency of pseudo-random number generators using machine learning 16

Analyzing efficiency of pseudo-random number generators usin...

引用

4th international conference on Information and Network Security, ICINS 2016

作者： Kumar, Sumit Cyber Security Schneider Electric India Pvt. Ltd. Bangalore India

ISBN: (纸本)9781450347969

Random numbers are very important components in cyber security. A main application of random numbers is in the field of cryptography. PKI and TLS based encryption uses random numbers extensively. Other areas include session IDs of web applications, passwords and game of chance. A number of cyber security attacks have happened in the past because of using weak random number generators. machine learning has been extensively used in pattern identification in a number of areas, including credit card frauds, genomics and face identification. It utilizes a set of algorithms to detect patterns from in a data to perform tasks like classification, clustering and prediction. In this paper, a fast method to test the randomness of a sequence generated by pseudo-random number generator is proposed which tries to take advantages of the pattern identification of machine learning. © 2016 ACM.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

4th international Workshop on New Frontiers in Mining Complex patterns, NFMCP 2015 and Held in Conjunction with European conference on machine learning and Principles and Practice of Knowledge Discovery in databases, ECML-PKDD 2015

4th International Workshop on New Frontiers in Mining Comple...

引用

4th international Workshop on New Frontiers in Mining Complex patterns, NFMCP 2015 and Held in Conjunction with European conference on machine learning and Principles and Practice of Knowledge Discovery in databases, ECML-PKDD 2015

ISBN: (纸本)9783319393148

the proceedings contain 15 papers. the special focus in this conference is on data Stream Mining, Classification, Mining Complex data and Sequences. the topics include: Adaptive ensembles for evolving data streams;combining block-based and online solutions;comparison of tree-based methods for multi-target regression on data streams;frequent itemsets mining in data streams using reconfigurable hardware;discovering and tracking organizational structures in event logs;intelligent adaptive ensembles for data stream mining;mining periodic changes in complex dynamic data through relational pattern discovery;the usefulness of roughly balanced bagging for complex and high-dimensional imbalanced data;classifying traces of event logs on the basis of security risks;redescription mining with multi-target predictive clustering trees;generalizing patterns for cross-domain analogy;spectral features for audio based vehicle identification;heterogeneous network decomposition and weighting with text mining heuristics;semi-supervised multivariate sequential pattern mining and evaluating a simple string representation for intra-day foreign exchange prediction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pathological Brain Detection Based on Online Sequential Extreme learning machine 4

Pathological Brain Detection Based on Online Sequential Extr...

引用

4th IEEE international conference on Progress in Informatics and Computing (IEEE PIC)

作者： Lu, Siyuan Wang, Hainan Wu, Xueyan Wang, Shuihua Nanjing Normal Univ Sch Comp Sci & Technol Nanjing 210023 Jiangsu Peoples R China Zhejiang Univ State Key Lab CAD & CG Hangzhou 310027 Zhejiang Peoples R China Jilin Univ Minist Educ Key Lab Symbol Computat & Knowledge Engn Changchun 130012 Jilin Peoples R China State Stat Bur Key Lab Stat Informat Technol & Data Min Chengdu 610225 Sichuan Peoples R China CUNY City Coll New York Dept Elect Engn New York NY 10031 USA

ISBN: (纸本)9781509034840

Magnetic resonance imaging (MRI) is a kind of imaging modality, which offers clearer images of soft tissues than computed tomography (CT). It is especially suitable for brain disease detection. It is beneficial to detect diseases automatically and accurately. We proposed a pathological brain detection method based on brain MR images and online sequential extreme learning machine. First, seven wavelet entropies (WE) were extracted from each brain MR image to form the feature vector. then, an online sequential extreme learning machine (OS-ELM) was trained to differentiate pathological brains from the healthy controls. the experiment results over 132 brain MRIs showed that the proposed approach achieved a sensitivity of 93.51%, a specificity of 92.22%, and an overall accuracy of 93.33%, which suggested that our method is effective.

关键词： magnetic resonance imaging wavelet entropy online sequential extreme learning machine Classification pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Analysis of Images, Social Networks and Texts: 4th international conference, AIST 2015, Yekaterinburg, Russia, April 9-11, 2015

引用

2016年

作者： Mikhail Yu Khachay Natalia Konstantinova Alexander Panchenko Dmitry I. Ignatov Valeri G Labunets

ISBN: (纸本)9783319261225

this book constitutes the proceedings of the Fourth international conference on Analysis of Images, Social Networks and Texts, AIST 2015, held in Yekaterinburg, Russia, in April *** 24 full and 8 short papers were carefully reviewed and selected from 140 submissions. the papers are organized in topical sections on analysis of images and videos; pattern recognition and machine learning; social network analysis; text mining and natural language processing.

关键词：

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：