This meeting will be held partly as a joint meeting with the DIMACS workshop on
Clustering Problems in Biological Networks May 9 - 11, 2006.
The CSNA meeting is co-sponsored by The Institute of Mathematical Statistics.
Wednesday, May 10, 2006
1:00 - 5:00 Tutorials. - Room 431
1:00 - 2:45 Tutorial A: Introduction to Data Mining
Tutorial slides
David Banks, Duke University
3:15 - 5:00 Tutorial B: Cluster Analysis for Data Mining: A Survey
of Algorithms, and a Deeper Look at Input Data Coding, and
Computational Efficiency
Tutorial slides
Fionn Murtagh, Royal Holloway, University of London
6:30 - 8:30 Reception at Holiday Inn
Thursday, May 11, 2006
8:00 - 8:35 Breakfast and registration
8:35 - 8:45 Opening welcome
Fred Roberts, DIMACS Director
8:45 - 10:15 Session T1. Invited Talks - 1st Floor Lecture Hall
Session chair: Melvin Janowitz
8:45 - 9:25 Data Mining and Network Models of Massive Datasets
Panos Pardalos, University of Florida
9:30 - 10:10 Multi-class protein classification using
string kernels and adaptive codes
Christina Leslie, Columbia University
10:15 - 10:45 Break
10:45 - 12:15 Session T2. Invited Session - 1st Floor Lecture Hall
Session organizer: Paul Kantor, Rutgers University
Author Identification
10:45 - 11:15 Identifying Authors and Authors' Styles
David Hoover, NYU
11:15 - 11:45 Simulated Entity Resolution: DIMACS Work on the
KDD Challenge of 2005
Aynur Dayanik, Dmitriy Fradkin, Paul Kantor, David Lewis,
David Madigan,and Fred Roberts, Rutgers University
11:45 - 12:15 The Words of Our Lives: Analyzing Age-and Sex-Linked
Language Variation in the Blogosphere
Shlomo Argamon, Moshe Koppel, James W. Pennebaker, and Jonathan Schler,
Illinois Institute of Technology
10:45 - 12:15 Sessiom T3. Contributed Papers - Room 431
Chair: Bernie Harris
10:45 - 11:15 Comparison of Classification Methods to Predict Complications to Liver Surgery
Leah Ben-Porat, Memorial Sloan-Kettering Cancer Center
11:15 - 11:45 Self-Organizing Maps for Brain Electrical Activity Classification
Wei Zeng, Rutgers University
11:45 - 12:15 Using Scan Statistics for Anomaly Detection in Genetic Networks
Christopher Overall, George Mason University
12:15 - 1:30 Lunch
1:30 - 3:30 Session T4 Joint Session from Dimacs Workshop on Biological Networks
Session chair: Claudia Perlich
1:30 - 2:00 Protein Cluster Analysis via Directed Diffusion
Yosi Keller, Yale University
2:00 - 2:30 Learning and Classification in Biological Data
Sofus Macskassy, Fetch Technologies, Inc.
2:30 - 3:00 Information-Based Clustering
Gurinder Singh Atwal, Princeton University
3:00 - 3:30 Classification vs Clustering, Analyzing Gene Functionality
Claudia Perlich, IBM T.J. Watson Research Center
3:30 - 3:45 Break
3:45 - 4:45 Session T5. Contributed Papers- 1st Floor Lecture Hall
Session chair: Panos Paradalos
3:45 - 4:15 Using Cluster Analysis to Relate Subjective and Objective
Pharmacovigilance Association Measures
Ronald Pearson, ProSanos Corporation
4:15 - 4:45 Distance Based Probabilistic Clustering of Data
Cem Iyigun, Rutgers University
6:00 CSNA Executive Board
Friday, May 12, 2006
8:00 - 8:50 Breakfast and registration
8:50 - 9:00 Opening remarks
Melvin Janowitz, DIMACS Associate Director
9:00 - 10:25 Session F1 Invited Talks - 1st Floor Lecture Hall
Session chair: Fionn Murtagh
9:00 - 9:40 Unsupervised anomaly detection in computer security
Sal Stolfo, Columbia University
9:45 - 10:25 Incorporation of extra-data sources in predictive modeling
David Madigan, Rutgers University
10:30 - 11:00 break
11:00 - 12:30 Session F2 Invited paper session - 1st Floor Lecture Hall
Session organizer: Rebecka Jornsten, Rutgers University
Clustering and classification in computational biology
11:00 - 11:30 Predicting and analyzing protein interaction networks
Mona Singh, Princeton University
11:30 - 12:00 Nonparametric Pathway-Based Regression Models for
Analysis of Genomic Data
Hongze Li, University of Pennsylvania
12:00 - 12:30 Clustering and classification in computational biology
Rebecka Jornsten, Rutgers University
11:00 - 12:30 Session F3 Contributed paper session- Room 431
Session chair: Art Kendall
11:00 - 11:30 Using Data Mining Tools in an Urban Development Study
Chamont Wang, The College of New Jersey, and
Pin-Shuo Liu, William Paterson University
11:30 - 12:00 Graphical Modeling of Coded Text Data:
Modeling and Measurement of Empathy
Carolyn J. Anderson, University of Illinois
12:00 - 12:30 An application of combinatorial methods introduced
for verification of cluster analyses
Bernie Harris, Process Automation Controls, Corp.
12:30 - 1:40 Lunch
1:40 - 2:20 Session F4 Invited Talk - 1st Floor Lecture Hall
Session chair: David Banks
1:40 - 2:20 Active learning of linear separators
Sanjoy Dasgupta, UCSD
2:20 - 2:45 Break
2:45 - 4:45 Session F5 Invited paper session - 1st Floor Lecture Hall
Session organizer: Stanley Wasserman, Indiana University
Networks and Classification
2:45 - 3:15 Computational Framework for Analysis of Dynamic Social Networks
Tanya Berger-Wolf, University of Illinois - Chicago
3:15 - 3:45 Path-based Sampling and Inference in the Internet:
Implications of Network Structure
Eric Kolaczyk, Boston University
3:45 - 4:15 Clusterwise p* regression for social networks
Douglas Steinley, University of Missouri
4:15 - 4:45 Goodness of fit of social network models
David Hunter, Penn State University
2:45 - 4:45 Session F6 Contributed paper session - Room 431
Session chair: Carolyn Anderson
2:45 - 3:15 Dimension Reduction Problem: A Version of PARAMAP
Extended to Deal With Large Data Sets
Ulas Akkucuk, Bogazici University, Istanbul, Turkey and
J. Douglas Carroll, Rutgers Business School
3:15 - 3:45 Analyzing the Supreme Court Justice Decisions using Multidimensional
Scaling (MDS) and Parametric Mapping (PARAMAP)
Stephen France and J Douglas Carroll, Rutgers University
3:45 - 4:15 Comparison of One Heuristic and One Globally Optimal
Unidimensional Scaling Technique
Leslie Rutkowski, University of Illinois at Urbana-Champaign
4:15 - 4:45 Cluster Analysis using Different Correlation Coefficients
Jong-Min Kim, University of Minesota at Morris
7:00 - 9:30 Banquet at Holiday Inn
Saturday, May 13, 2006
8:00 - 8:50 Breakfast and registration
8:50 - 9:00 Opening remarks
Melvin Janowitz, DIMACS Associate Director
9:00 - 10:25 Session S1. Invited talks - 1st Floor Lecture Hall
Session chair: Jim Rohlf
9:00 - 9:40 Finding relations between social network
invariants with AutoGraphiX
Pierre Hansen, GERAD, Montreal, Canada
9:45 - 10:25 Clustering and Machine Learning over
Genomic Databases with Underlying
(Network or Tree) Structure
Casimir Kulikowski, Akshay Vashisht, Ilya Muchnik, Rutgers University
10:30 - 11:00 break
11:00 - 12:30 Session S2. Invited paper session - 1st Floor Lecture Hall
Session Organizer: Jon Kettenring, Drew University
Weights and Metrics for Cluster Analysis
11:00 - 11:30 A New Variable Weighting and Selection
Procedure for K-means Cluster Analysis
Douglas Steinley, University of Missouri-Columbia
11:30 - 12:00 Strategies for Scaling and Weighting
Variables in Cluster Analysis
Srinivas Maloor, Rutgers University
12:00 - 12:30 An Improved Distance Measure Between the Expression Profiles
Linking Co-Expression and Co-Regulation in Mice
Ryung S. Kim, Harvard Medical School
11:00 - 12:30 Session S3. Contributed paper session - Room 431
Session chair: David Dubin
11:00 - 11:30 Learning and Classification in Networked Data
Sofus A. Macskassy, Fetch Technologies, Inc.
11:30 - 12:00 Distibuted Least-Squares Classification in Wireless Sensor Networks
Joel Predd, Princeton University
12:00 - 12:30 ACA Similarity Analysis Re-examined
David Dubin, University of Illinois at Urbana-Champaign
12:30 - 1:00 CSNA membership meeting
12:30 - 2:00 Lunch
2:00 - 2:40 Session S4. Invited Talk - 1st Floor Lecture Hall
Session chair: Melvin Janowitz
Fionn Murtagh, University of London
Identifying and exploiting ultrametricity
2:40 - 3:00 break
3:00 - 4:30 Session S5. Contributed paper session - 1st Floor Lecture Hall
Session chair: William D. Shannon
3:00 - 3:30 Standard Errors, Prediction Error and Model Tests in Additive Trees
Willem J. Heiser, Leiden University, The Netherlands
3:30 - 4:00 A Likelihood Approach for Determining Cluster Number
William D. Shannon, Washington University in St. Louis School of Medicine
4:00 - 4:30 Fitting Directed Tree Graphs to Asymmetric Proximities
James E. Corter, Teachers College, Columbia University
Publishers booths offering conference discounts on books: Springer, Taylor & Francis
Previous: Participation
Workshop Index
DIMACS Homepage