2011 10th International Conference on Machine Learning and Applications Workshops

ICMLA 2011 Table of Contents

Volume - 2 Preface - Volume 2........................................................................................................................................................xi Committee Lists - Volume 2.......................................................................................................................................xii Program Committee - Volume 2...............................................................................................................................xiv

Special Session: Machine Learning for Human Behavior Understanding and Assisted Living Error Bounds for Online Predictions of Linear-Chain Conditional Random Fields: Application to Activity Recognition for Users of Rolling Walkers ...............................................................................1 Mathieu Sinn and Pascal Poupart Manifold Learning and Recognition of Human Activity Using Body-Area Sensors .....................................................7 Mi Zhang and Alexander A. Sawchuk

Special Session: Learning in Evolving Environments and Its Application on Real-World Problems Extending k-Means-Based Algorithms for Evolving Data Streams with Variable Number of Clusters .......................................................................................................................................................14 Jonathan de Andrade Silva and Eduardo Raul Hruschka Dynamic Evolving Cluster Models Using On-line Split-and-Merge Operations .........................................................20 Edwin Lughofer The Biased Multi-objective Optimization Using the Reference Point: Toward the Industrial Logistics Network ..................................................................................................................................27 Eriko Azuma, Tomohiro Shimada, Keiki Takadama, Hiroyuki Sato, and Kiyohiko Hattori Role Model of Search in Agents' Parameter-Space ......................................................................................................31 Ondrej Kazík and Roman Neruda A Neural Network Model for Learning Data Stream with Multiple Class Labels .......................................................35 Tomoyasu Takata and Seiichi Ozawa v

Adaptive Time Window Size to Track Concept Drift ..................................................................................................41 Moamar Sayed-Mouchaweh, Janan Zaytoon, and Patrice Billaudel Incremental Learning Based on Growing Gaussian Mixture Models ..........................................................................47 Abdelhamid Bouchachia and Charlie Vanaret

Special Session: Machine Learning for Biomedical Literature Analysis and Text Retrieval Unsupervised Grammar Induction of Clinical Report Sublanguage ............................................................................53 Rohit J. Kate Pattern Learning through Distant Supervision for Extraction of Protein-Residue Associations in the Biomedical Literature ....................................................................................................................59 K.E. Ravikumar, Haibin Liu, Judith D. Cohn, Michael E. Wall, and Karin Verspoor Evaluating Distributional Semantic and Feature Selection for Extracting Relationships from Biological Text ....................................................................................................................................................66 Ehsan Emadzadeh, Siddhartha Jonnalagadda, and Graciela Gonzalez Discriminative Optimization of String Similarity and Its Application to Biomedical Abbreviation Clustering ...............................................................................................................................................72 Atsuko Yamaguchi, Yasunori Yamamoto, Jin-Dong Kim, Toshihisa Takagi, and Akinori Yonezawa The DIEGO Lab Graph Based Gene Normalization System .......................................................................................78 Ryan Sullivan, Robert Leaman, and Graciela Gonzalez Using Published Medical Results and Non-homogenous Data in Rule Learning ........................................................84 Janusz Wojtusiak, Katherine Irvin, Aybike Birerdinc, and Ancha V. Baranova An EM Clustering Algorithm which Produces a Dual Representation ........................................................................90 Sun Kim and W. John Wilbur Comparison of Two Methods for Finding Biomedical Categories in Medline ............................................................96 Lana Yeganova, Won Kim, Donald C. Comeau, and W. John Wilbur Ranking Interactions for a Curation Task ...................................................................................................................100 Simon Clematide and Fabio Rinaldi

Special Session: Machine Learning with Multimedia Data Metric Learning for Music Symbol Recognition .......................................................................................................106 Ana Rebelo, Jakub Tkaczuk, Ricardo Sousa, and Jaime S. Cardoso Looking Beyond Genres: Identifying Meaningful Semantic Layers from Tags in Online Music Collections .......................................................................................................................................112 Rafael Ferrer and Tuomas Eerola Music Similarity Estimation with the Mean-Covariance Restricted Boltzmann Machine ......................................................................................................................................................................118 Jan Schlüter and Christian Osendorfer

vi

Combining Visual and Acoustic Features for Music Genre Classification ................................................................124 Ming-Ju Wu, Zhi-Sheng Chen, Jyh-Shing Roger Jang, Jia-Min Ren, Yi-Hsung Li, and Chun-Hung Lu Mood Classfication from Musical Audio Using User Group-Dependent Models .....................................................130 Kyogu Lee and Minsu Cho The Influence of Chord Duration Modeling on Chord and Local Key Extraction .....................................................136 Johan Pauwels, Jean-Pierre Martens, and Marc Leman Non-Linear Semantic Embedding for Organizing Large Instrument Sample Libraries .............................................142 Eric J. Humphrey, Aron P. Glennon, and Juan Pablo Bello

Special Session: Machine Learning in Medicine Automatic Detection of Excessive Glycemic Variability for Diabetes Management ................................................148 Matthew Wiley, Razvan Bunescu, Cindy Marling, Jay Shubrook, and Frank Schwartz Building an Ensemble of Probabilistic Classifiers for Lung Nodule Interpretation ...................................................155 Dmitriy Zinovev, Jacob Furst, and Daniela Raicu Rule-Based Prediction of Medical Claims’ Payments: A Method and Initial Application to Medicaid Data .....................................................................................................................................162 Janusz Wojtusiak, Che Ngufor, John Shiver, and Ronald Ewald Predicting Patients Likely to Overstay in Hospitals ...................................................................................................168 Rodrigo Vivanco and Dan Roberts Classification of Patients Using Novel Multivariate Time Series Representations of Physiological Data ..................................................................................................................................................172 Patricia Ordóñez, Tom Armstrong, Tim Oates, and Jim Fackler

Special Session: Machine Learning in Bioinformatics and Computational Biology Frequent Substring-Based Sequence Classification with an Ensemble of Support Vector Machines Trained Using Reduced Amino Acid Alphabets ............................................................................180 Charith D. Chitraranjan, Loai Alnemer, Omar Al-Azzam, Saeed Salem, Anne M. Denton, Muhammad J. Iqbal, and Shahryar F. Kianian Charge Prediction of Lipid Fragments in Mass Spectrometry ...................................................................................186 B. Schrom, L. Kangas, B. Ginovska, T. Metz, and J. Miller Predicting “Essential” Genes across Microbial Genomes: A Machine Learning Approach ....................................................................................................................................................................189 Krishnaveni Palaniappan and Sumitra Mukherjee Developing an Appropriate Data Normalization Method ..........................................................................................195 Balemir Uragun and Ramesh Rajan Analysis of Microbiome Data across Inflammatory Bowel Disease Patients ............................................................200 Nuttachat Wisittipanit, Huzefa Rangwala, and Patrick Gillevet

vii

Special Session: Machine Learning Methods in Cancer Diagnosis and Treatment A Kernel Method for Real-Time Respiratory Tumor Motion Estimation Using External Surrogates .....................................................................................................................................................206 Ruijiang Li and Lei Xing 3D Bayesian Tracking with a Single Imager for Real-Time Image Guidance in Prostate Radiation Therapy ......................................................................................................................................................210 Ruijiang Li, Benjamin Fahimian, and Lei Xing Development of a Beam Source Modeling Technique for a Flattening Filter Free (FFF) Beam ...........................................................................................................................................................................215 Woong Cho, Jeong-Hoon Park, Won-Gyun Jung, Tae-Suk Suh, Kayla N. Kielar, Ed Mok, Ruijiang Li, and Lei Xing The Combination of Clinical, Dose-Related and Imaging Features Helps Predict Radiation-Induced Normal-Tissue Toxicity in Lung-cancer Patients—An in-silico Trial Using Machine Learning Techniques ..................................................................................................220 G. Nalbantov, A. Dekker, D. De Ruysscher, P. Lambin, and E.N. Smirnov Regional Normal Liver Tissue Density Changes in Patients Treated with Stereotactic Body Radiation Therapy for Liver Metastases ...........................................................................................................225 Christopher Howells, Quentin Diot, David Westerly, and Moyed Miften

Special Session: Learning on the Web Multiple Kernel Learning on Time Series Data and Social Networks for Stock Price Prediction ....................................................................................................................................................................228 Shangkun Deng, Takashi Mitsubuchi, Kei Shioda, Tatsuro Shimada, and Akito Sakurai An Automatic Multi-domain Thesauri Construction Method Based on LDA ...........................................................235 Na Ni, Kai Liu, and Yaodong Li Using Machine Learning to Detect Cyberbullying .....................................................................................................241 Kelly Reynolds, April Kontostathis, and Lynne Edwards Collaborative Filtering with CCAM ...........................................................................................................................245 Meng-Lun Wu, Chia Hui Chang, and Rui Zhe Liu Learning to Tag from Logic Constraints in Hyperlinked Environments ....................................................................251 Claudio Saccà, Michelangelo Diligenti, Marco Gori, and Marco Maggini Learning to Rank Using Markov Random Fields .......................................................................................................257 Nino Freno, Tiziano Papini, and Michelangelo Diligenti Web Ad-Slot Offline Scheduling Using an Ant Colony Algorithm ..........................................................................263 Vasile Palade and Soumya Banerjee Exploring Structural Features in Predicting Social Network Evolution .....................................................................269 Shu Huang and Dongwon Lee

viii

Special Session: Machine Learning in Energy Application Extraction of Basic Patterns of Household Energy Consumption ..............................................................................275 Haoyang Shen, Hideitsu Hino, Noboru Murata, and Shinji Wakao Performance Analysis of a Hydrofoil with and without Leading Edge Slat ..............................................................281 Tahir Yavuz, Birol Kilkis, Hursit Akpinar, and Özgür Erol A Measure of Credibility of Solar Power Prediction ..................................................................................................286 Haoyang Shen, Hideitsu Hino, Noboru Murata, and Shinji Wakao A New Control Method for dc-dc Converter by Neural Network Predictor with Repetitive Training .............................................................................................................................................292 Fujio Kurokawa, Kimitoshi Ueno, Hidenori Maruta, and Hiroyuki Osuga Comparison of Classification Techniques used in Machine Learning as Applied on Vocational Guidance Data .....................................................................................................................................298 Halil Ibrahim Bülbül and Özkan Ünsal Transient States of the Multiscalar Controlled Double Fed Induction Generator in the Wind Farm ............................................................................................................................................................302 Piotr Kolodziejek An Intelligent Decision Support Tool for a Travelling Wave Ultrasonic Motor Based on k-Nearest Neighbor Algorithm ..............................................................................................................................308 Seref Sagiroglu, H. Tolga Kahraman, Mehmet Yesilbudak, and Ilhami Colak An Intelligent Power Factor Correction Approach Based on Linear Regression and Ridge Regression Methods ..................................................................................................................................313 Ramazan Bayindir, Murat Gök, Ersan Kabalci, and Orhan Kaplan

Workshop: Machine Learning Algorithms, Systems and Applications Energy Efficiency for Unmanned Aerial Vehicles .....................................................................................................316 Balemir Uragun A Resource Entity Model Oriented Mobile Collaboration Environment ...................................................................321 Yuhui Cao, Weihong Wang, Zhiqiang He, Dianyuan Shi, and Liang Li Benefits Analysis of Live Customer Support Chat in E-commerce Websites: Dimensions of a New Success Model for Live Customer Support Chat ....................................................................325 Ahmed Elmorshidy Semi-supervised Feature Extraction Using Independent Factor Analysis .................................................................330 Latifa Oukhellou, Etienne Côme, Patrice Aknin, and Thierry Denoeux Robust FCMdd-based Linear Clustering for Relational Data with Alternative c-Means Criterion .......................................................................................................................................................334 Takeshi Yamamoto, Katsuhiro Honda, Akira Notsu, and Hidetomo Ichihashi SVM Multi-classification of T2D/CVD Patients Using Biomarker Features ............................................................338 Sai Buddi, Thomas Taylor, Chad Borges, and Randall Nelson

ix

Estimation of PSF for a Shaking Blurred Image Using GA .......................................................................................342 Takumi Shimomukai, Michifumi Yoshioka, and Hidekazu Yanagimoto Extended Finite-State Machine Induction Using SAT-Solver ...................................................................................346 Vladimir Ulyantsev and Fedor Tsarev Arabic Text-Dependent Speaker Verification for Mobile Devices Using Artificial Neural Networks .........................................................................................................................................................350 Abdulrahman Alarifi, Issa Alkurtass, and AbdulMalik S. Al-Salman Choosing Best Fitness Function with Reinforcement Learning .................................................................................354 Arina Afanasyeva and Maxim Buzdalov Comparisons of Machine Learning Algorithms for Application Identification of Encrypted Traffic ...................................................................................................................................................358 Yohei Okada, Shingo Ata, Nobuyuki Nakamura, Yoshihiro Nakahira, and Ikuo Oka Combining Corpus-Based Features for Selecting Best Natural Language Sentences ................................................362 Foaad Khosmood and Robert Levinson Implementation of Parameter Space Search for Meta Learning in a Data-Mining Multi-agent System .....................................................................................................................................................366 Ondrej Kazík, Klára Pešková, Martin Pilát, and Roman Neruda An Iris Recognition Approach based on Fuzzy Support Vector Machine .................................................................370 Hongying Gu, Zhiwen Gao, and Cheng Yang Empirical Normalization for Quadratic Discriminant Analysis and Classifying Cancer Subtypes ......................................................................................................................................................................374 Mark A. Kon and Nikolay Nikolaev Street View Challenge: Identification of Commercial Entities in Street View Imagery ............................................380 Amir Roshan Zamir, Alexander Darino, and Mubarak Shah Structured Multivariate Pattern Classification to Detect MRI Markers for an Early Diagnosis of Alzheimer’s Disease ..............................................................................................................................384 Cécilia Damon, Edouard Duchesnay, and Marine Depecker Probabilistic Clustering Based on Langevin Mixture .................................................................................................388 Ola Amayri and Nizar Bouguila Author Index - Volume 2 .........................................................................................................................................392

x