检索结果-内蒙古大学图书馆

Application traffic classification at the early stage by characterizing application rounds

INFORMATION SCIENCES 2013年 232卷 130-142页

作者： Huang, Nen-Fu Jai, Gin-Yuan Chao, Han-Chieh Tzang, Yih-Jou Chang, Hong-Yi Natl Tsing Hua Univ Dept Comp Sci Hsinchu 30013 Taiwan Natl Ilan Univ Inst Comp Sci & Informat Engn Ilan 260 Taiwan Hsing Wu Univ Sci & Technol Dept Informat Management New Taipei City 244 Taiwan Natl Chiayi Univ Dept Management Informat Syst Chiayi 60054 Taiwan

This article proposes a machine learning-based high-accuracy algorithm called "APPlication Round method (APPR)" to identify network application traffic at the early stage. For each TCP/UDP flow, discriminators available at the early stage are determined to support high-accuracy and real-time traffic classification. Such discriminators characterize the possible negotiation behaviors of each flow from an application layer perspective. The ability of flow attributes is tested using several machine learning algorithms. By contrast, this study also compares the level of accuracy of the proposed method with those reported by machine learning-based application traffic classification methods that have addressed real-time application traffic classification problems based on identical sample traffic sets. By applying a pruned C4.5 tree machine learning algorithm to real traffic traces, the proposed method offers a maximal 99.21%, with an average overall accuracy of 92.88% for all traffic samples. Compared to other machine learning algorithms, the proposed algorithm not only provides a minimal accuracy improvement of approximately 7-8% for normal ratio data sets and more than 15-30% improvement of overall accuracy for fixed ratio data samples, but is also suitable for on-line identification because of the low-flow test duration. Furthermore, the proposed method is also appropriate for identifying encrypted protocols because it demonstrates high accuracy, classifies encryption-based protocols, and supports real-time classification. (C) 2013 Elsevier Inc. All rights reserved.

关键词： P2P Traffic identification/classification machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

A cross-validation scheme for machine learning algorithms in shotgun proteomics

引用

BMC BIOINFORMATICS 2012年第Sup16期13卷 S3-S3页

作者： Granholm, Viktor Noble, William Stafford Kall, Lukas KTH Royal Inst Technol Sch Biotechnol Sci Life Lab Solna Sweden Stockholm Univ Dept Biochem & Biophys Sci Life Lab Solna Sweden Univ Washington Dept Genome Sci Seattle WA 98195 USA Univ Washington Dept Comp Sci & Engn Seattle WA 98195 USA

Peptides are routinely identified from mass spectrometry-based proteomics experiments by matching observed spectra to peptides derived from protein databases. The error rates of these identifications can be estimated by target-decoy analysis, which involves matching spectra to shuffled or reversed peptides. Besides estimating error rates, decoy searches can be used by semi-supervised machine learning algorithms to increase the number of confidently identified peptides. As for all machine learning algorithms, however, the results must be validated to avoid issues such as overfitting or biased learning, which would produce unreliable peptide identifications. Here, we discuss how the target-decoy method is employed in machine learning for shotgun proteomics, focusing on how the results can be validated by cross-validation, a frequently used validation scheme in machine learning. We also use simulated data to demonstrate the proposed cross-validation scheme's ability to detect overfitting.

关键词： machine learning algorithm Shotgun Proteomics Decoy Database Estimate Error Rate Incorrect Match

来源：评论

学校读者我要写书评

暂无评论

Comparative study on classification performance between support vector machine and logistic regression

引用

INTERNATIONAL JOURNAL OF machine learning AND CYBERNETICS 2013年第1期4卷 13-24页

作者： Musa, Abdallah Bashir Univ Gezira Fac Math Sci & Comp Wad Madani 20 Sudan

Support vector machine (SVM) is a comparatively new machine learning algorithm for classification, while logistic regression (LR) is an old standard statistical classification method. Although there have been many comprehensive studies comparing SVM and LR, since they were made, there have been many new improvements applied to them such as bagging and ensemble. Recently, bagging and ensemble learning have become hot topics, widely used to improve the generalization performance of single learning algorithm. Therefore, comparing classification performance between SVM and LR using bagging and ensemble is an interesting issue. The average of estimated probabilities' strategy was used for combining classifiers in this paper. Different evaluation metrics assess different characteristics of machine learning algorithm. It is possible for a learning method to perform well on one metric, but be suboptimal on other metrics. Therefore this study includes a variety of criteria to evaluate the classification performance of the learning methods: accuracy, sensitivity, specificity, precision, F-score and the area under the receiver operating characteristic curve. This has not been included in previous studies of SVM, owing to the fact that it did not support estimated probabilities at that time. Other metrics used in medical diagnosis, such as, Youden's index (gamma), positive and negative likelihoods (rho+, rho-) and diagnostic odds ratio were evaluated to convey and compare the qualities of the two algorithms. This study is distinct by its inclusion of a comprehensive statistical analysis for the results of the SVM and LR algorithms on various data sets.

关键词： Support vector machine (SVM) Logistic regression (LR) machine learning algorithm Bagging Ensemble Statistical analysis

来源：评论

学校读者我要写书评

暂无评论

THREE DIFFERENTIAL EMOTION CLASSIFICATION BY machine learning algorithmS USING PHYSIOLOGICAL SIGNALS

THREE DIFFERENTIAL EMOTION CLASSIFICATION BY MACHINE LEARNIN...

引用

4th International Conference on Agents and Artificial Intelligence

作者： Jang, Eun-Hye Park, Byoung-Jun Kim, Sang-Hyeob Sohn, Jin-Hun Elect & Telecommun Res Inst BT Convergence Technol Res Dept Taejon 305606 South Korea

ISBN: (纸本)9789898425959

In HCI researches, human emotion classification has done by machine learning algorithms based on physiological signals. The aim of this study is to classify three different emotional states (boredom, pain, and surprise) by 5 machine teaming algorithms using features extracted from physiological signals. 200 college students participated in this experiment The audio-visual film clips Were used to provoke emotions and were tested their appropriateness and effectiveness. EDA ECG.. PPG, and SKT as physiological signals,, were acquired for 1 minute before each emotional state as baseline and for 1-1.5 minutes timing emotional state and were analyzed for 30 seconds from the baseline and the emotional stitte. 23 parameters were extracted from these signals: SCL NSCR, mean SCR, mean SET, maxinmm SET, sum of negative SET, and sum of positive SET, mean FPG, mean RR interval. standard deviation RR interval, mean BPM, RMSSD, NN50, percenet of NN50, SD1, SD2, CSI, CVI, IF HF nLF nHF, and LF/HF ratio. For emotion classification, the difference values of each feature subtracting baseline from the emotional state were used I or analysis using 5 machine learning algorithms. The result showed that an accuracy of emotion classification by SOM was lowest and SVM was highest. This could help emotion recognition studies lead to better chance to recognize various human emotions by using physiological signals. Also, it is able to be applied on human-computer interaction system for emotion detection.

关键词： Emotion classification machine learning algorithm Physiological signal

来源：评论

学校读者我要写书评

暂无评论

An intelligent integrative assistive system for dyslexic learners

引用

JOURNAL OF ASSISTIVE TECHNOLOGIES 2013年第3期7卷 172-187页

作者： Ndombo, Daniel Mpia Ojo, Sunday Osunmakinde, Isaac O. Tshwane Univ Technol Dept Comp Sci Pretoria South Africa ICT Pretoria South Africa Univ South Africa Coll Sci Engn & Technol Sch Comp Semant Comp Grp Pretoria South Africa

Purpose - The objective of this paper is to present a comprehensive literature survey on dyslexic learners and to propose a model for integrated assistive technology of dyslexic learners. Design/methodology/approach - The use of the proposed model through real-life scenarios categorized as "phonological, reading and writing scenarios". We have also surveyed some systems for use with dyslexic learners currently in use and have compared them on the basis of number of barriers, technological innovation, age group and fostering. Findings - Dyslexic learners are characterized by slow learning, poor handwriting, poor spelling skills and difficulties in planning, organizing, revising and editing texts;technology plays a major role in the educational environment;it has become crucial in impacting knowledge across the globe;and open research issues and challenges that have to be addressed in the design of the current dyslexic system have been presented in detail. Research limitations/implications - Full implementation of the proposed model and its application in developing countries. Practical implications - The system improves the phonological awareness, reading and writing skills of dyslexic learners and it provides a solution for children as well as adults with dyslexia. Social implications - This survey can be used as a reference guide to understand learning barriers and intelligent systems for dyslexic learners and to promote the use of these in schools for those with learning disabilities who need assistive technologies. Originality/value - Development of a newly proposed integrated intelligent assistive system for dyslexic learners;knowledge generation as a reference guide to understand dyslexic learning ability in general and an intelligent assistive dyslexic system in particular;and survey of open research issues and challenges to further research in intelligent dyslexic systems.

关键词： Dyslexia Assistive intelligent model machine learning algorithm Game theory and visualization concepts learning

来源：评论

学校读者我要写书评

暂无评论

Applying Correlation Threshold on Apriori algorithm

Applying Correlation Threshold on Apriori Algorithm

引用

IEEE International Conference on Emerging Trends in Computing, Communication and Nanotechnology (ICECCN)

作者： Anand, H. S. Vinodchandra, S. S. Coll Engn Dept Comp Sci Trivandrum Kerala India Univ Kerala Ctr Comp Trivandrum Kerala India

ISBN: (纸本)9781467350372;9781467350365;9781467350358

Ever growing size of information and database has always demanded the scientific world for very efficient rule mining algorithm. This paper gives an extension to the Apriori algorithm, a classical rule mining algorithm. Apriori finds its application in areas of data mining, finding association between attributes and in prediction systems. Even though Apriori suits in various applications it possesses various disadvantages. To increase the efficiency of the present Apriori algorithm a method for incorporating a new correlation factor (threshold) is being introduced. First part of the paper provides a quick summary of basic Apriori algorithm and second half details the implementation of correlation threshold. Performance of the redesigned algorithm is evaluated and is compared with the traditional Apriori algorithm. The evaluation shows a peak improvement in the mining result. We reduce the time complexity of the newly designed algorithm into O (n). In an application level, qualitative content analysis of water was also conducted to affirm the results.

关键词： apriori algorithm datamining itemsets correlation threshold association rule mining machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Automated Color Model-Based Concrete Detection in Construction-Site Images by Using machine learning algorithms

引用

JOURNAL OF COMPUTING IN CIVIL ENGINEERING 2012年第3期26卷 421-433页

作者： Son, Hyojoo Kim, Changmin Kim, Changwan Chung Ang Univ Dept Architectural Engn Seoul 156756 South Korea

Concrete structural component detection in color images is a key pre-process in various applications such as construction progress measurement, structural health monitoring, and three-dimensional as-built modeling. The goal of this research was to identify an automated color model-based concrete detection method that (by using a machine learning algorithm) can detect concrete structural components in color images with a high level of accuracy. A data set consisting of more than 87 million pixels was generated from 108 images of concrete surfaces with a variety of surfaces. Transformations from the RGB color space to non-RGB color spaces were performed to increase separability between concrete and background classes and to achieve robustness to changes in illumination. To find the optimal combination of color space and machine learning algorithm, the performance of three machine learning algorithms (e.g., a Gaussian mixture model, an artificial neural network model, and a support vector machine model) in two non-RGB color spaces (e.g., HSI and normalized RGB) was comparatively analyzed. The comparison showed that the combination of the support vector machine algorithm and the HSI color space is superior in detecting concrete structural components in color images, compared with the other five algorithm-color space combinations. Performance was validated by experiments run on various images of actual construction-site scenes. DOI: 10.1061/(ASCE)CP.1943-5487.0000141. (C) 2012 American Society of Civil Engineers.

关键词： Color-space transformation Concrete structural component Artificial neural networks Gaussian mixture models Support vector machines machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Potential responders to FOLFOX therapy for colorectal cancer by Random Forests analysis

引用

BRITISH JOURNAL OF CANCER 2012年第1期106卷 126-132页

作者： Tsuji, S. Midorikawa, Y. Takahashi, T. Yagi, K. Takayama, T. Yoshida, K. Sugiyama, Y. Aburatani, H. Teikyo Univ Sch Med Univ Hosp Dept Surg Kawasaki Kanagawa Japan Univ Tokyo Adv Sci & Technol Res Ctr Genome Sci Div Tokyo Japan Nihon Univ Sch Med Dept Digest Surg Tokyo Japan Gifu Univ Dept Surg Oncol Gifu Japan

BACKGROUND: Molecular characterisation using gene-expression profiling will undoubtedly improve the prediction of treatment responses, and ultimately, the clinical outcome of cancer patients. METHODS: To establish the procedures to identify responders to FOLFOX therapy, 83 colorectal cancer (CRC) patients including 42 responders and 41 non-responders were divided into training (54 patients) and test (29 patients) sets. Using Random Forests (RF) algorithm in the training set, predictor genes for FOLFOX therapy were identified, which were applied to test samples and sensitivity, specificity, and out-of-bag classification accuracy were calculated. RESULTS: In the training set, 22 of 27 responders (81.4% sensitivity) and 23 of 27 non-responders (85.1% specificity) were correctly classified. To improve the prediction model, we removed the outliers determined by RF, and the model could correctly classify 21 of 23 responders (91.3%) and 22 of 23 non-responders (95.6%) in the training set, and 80.0% sensitivity and 92.8% specificity, with an accuracy of 69.2% in 29 independent test samples. CONCLUSION: Random Forests on gene-expression data for CRC patients was effectively able to stratify responders to FOLFOX therapy with high accuracy, and use of pharmacogenomics in anticancer therapy is the first step in planning personalised therapy. British Journal of Cancer (2012) 106, 126-132. doi:10.1038/bjc.2011.505 *** Published online 17 November 2011 (C) 2012 Cancer Research UK

关键词： colorectal cancer FOLFOX therapy machine learning algorithm class predictor personalised therapy

来源：评论

学校读者我要写书评

暂无评论

Effects of meteorological forcing on coastal eutrophication: Modeling with model trees

引用

ESTUARINE COASTAL AND SHELF SCIENCE 2012年 115卷 210-217页

作者： Tamvakis, Androniki Miritzis, John Tsirtsis, George Spyropoulou, Alexandra Spatharis, Sofie Univ Aegean Dept Marine Sci Mitilini 81100 Greece

The exploration of processes leading to coastal eutrophication is a major challenge in ecological research, particularly in light of important new policies such as the European Water Framework Directive. In the present study primary production (in terms of chlorophyll alpha - chl alpha) is modeled based on a number of abiotic parameters using model trees (MTs), a machine learning (ML) approach whereby linear regressions are induced within homogeneous subsets of samples (tree leaves). Standardized regression was applied to determine the relative weight of abiotic parameters in the MT tree leaves whereas the efficiency of the MT method in chl alpha prediction was tested against neural networks (NNs) which is the most frequently used ML approach, and the classical multiple linear regression (MLR). To assess the efficiency of models to describe eutrophication-related responses under different environmental conditions, the methods were applied on a coastal ecosystem affected by terrestrial runoff for two meteorologically contrasting annual cycles: a typical dry ('04-'05) and a typical wet ('09-'10). MTs showed increased predictive power in chl alpha prediction attributed to the discrimination of input data space into tree leaves, instead of using a uniform space as in NNs and MLR. By grouping samples of each tested annual cycle (wet and dry) on a seasonal basis into discrete groups/leaves, MTs offer a much more explanatory description of ecosystem status than NNs and MLR. The discriminating variables forming tree leaves and the weighing coefficients of Linear Models (LMs) in each leaf provided a useful scaling of abiotic parameters driving chl alpha dynamics. The MT method is thus proposed as an efficient tool for obtaining insights into ecosystem processes leading to eutrophication events in coastal ecosystems and a useful component in integrated coastal zone management. (C) 2012 Elsevier Ltd. All rights reserved.

关键词： process-based modeling linear regression machine learning algorithm model tree dynamics eutrophication

来源：评论

学校读者我要写书评

暂无评论

NgLOC: Software and web server for predicting protein subcellular localization in prokaryotes and eukaryotes

引用

BMC Research Notes 2012年第1期5卷 1-7页

作者： King, Brian R. Vural, Suleyman Pandey, Sanjit Barteau, Alex Guda, Chittibabu Department of Computer Science Bucknell University Lewisburg PA 17837 One Dent Drive United States Department of Genetics Cell Biology and Anatomy University of Nebraska Medical Center Omaha NE 68198 United States Center for Bioinformatics and Systems Biology University of Nebraska Medical Center Omaha NE 68198 United States

Background: Understanding protein subcellular localization is a necessary component toward understanding the overall function of a protein. Numerous computational methods have been published over the past decade, with varying degrees of success. Despite the large number of published methods in this area, only a small fraction of them are available for researchers to use in their own studies. Of those that are available, many are limited by predicting only a small number of organelles in the cell. Additionally, the majority of methods predict only a single location for a sequence, even though it is known that a large fraction of the proteins in eukaryotic species shuttle between locations to carry out their function. Findings. We present a software package and a web server for predicting the subcellular localization of protein sequences based on the ngLOC method. ngLOC is an n-gram-based Bayesian classifier that predicts subcellular localization of proteins both in prokaryotes and eukaryotes. The overall prediction accuracy varies from 89.8% to 91.4% across species. This program can predict 11 distinct locations each in plant and animal species. ngLOC also predicts 4 and 5 distinct locations on gram-positive and gram-negative bacterial datasets, respectively. Conclusions: ngLOC is a generic method that can be trained by data from a variety of species or classes for predicting protein subcellular localization. The standalone software is freely available for academic use under GNU GPL, and the ngLOC web server is also accessible at. © 2012 King et al.;licensee BioMed Central Ltd.

关键词： Bayesian method machine learning algorithm N-gram-based approach ngLOC Protein sequence classification Protein subcellular localization prediction

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：