hahsler.netMichael Hahsler - Home Page

Michael Hahsler Home Teaching Research Publications Talks -- Software Lab -- CV -- Michael Hahsler Dept. of Computer Science -- Bobby B. Lyle School of Engineering, SMU P. O. Box 750122, Dallas, TX 75275 e-mail: mhahsler (at) smu.edu office: Caruth Hall, suite 400 office hours: Zoom ID 801 345 349 : by appointment (prior email necessary) I am a Clinical Associate Professor of Computer Science and of Engineering Management, Information, and Systems (EMIS) at the Bobby B. Lyle School of Engineering, SMU. I also hold an adjunct appointment with the Department of Clinical Sciences, UT Southwestern Medical Center, and I am a member of the SMU Artificial Intelligence Laboratory . I serve as an associate editor of the Journal of Statistical Software and the INFORMS Journal on Computing . several conferences and workshops, including PAKDD, ECDM, Data Analytics, BICOB, and QIMIE. -- Department of Information Systems and Operations and a core researcher at the Research Institute for Computational Methods, both at the Vienna University of Economics and Business, Austria. -- My research interests lie in the intersection of computer science, statistical methods, and combinatorial optimization with applications in artificial intelligence, machine learning, data mining, and data science. One important goal is to support reproducible research by publishing high-quality software (see Software section ) along with all theoretical results. My research team maintains more than 15 widely used R packages, including arules , dbscan , seriation , and recommenderlab. symbolic sequence analysis of massive data streams with applications to meteorology ( hurricane intensity prediction ), bioinformatics ( genomics ), healthcare, and simulation data analytics. -- > Read a short Bio or the full academic CV. -- News NIST releases an update with the title "A Responder's Critical Path" to discuss our project. (January 2021) I joined the INFORMS Journal on Computing as an associate editor in the software tools area. (January 2021) I held the first workshop with the title Introduction to R Programming in the new Data Science Workshop Series sponsored by OIT and the SMU Librariew (February 2020). The D Magazine reports on our project in "SMU Research Could Change the Way Diabetes is Treated" (January 2020). I served as the mentor for Matthew Piekenbrock's Google Summer of Code project Estimating the Empirical Cluster Tree. R-package clustertree (Summer 2017). NIST announces our project titled "SAFE-NET: An Integrated Connected Vehicle and Computing Platform for Public Safety Applications" as part of the Public Safety Innovation Accelerator Program (PSIAP) in the press release NIST Awards $38.5 Million to Accelerate Public Safety Communications Technologies (June 2017). The arules package was announced by The Data Incubator as one of the top 10 R packages for machine learning (April 2017). I taught an invited short course on Recommendation Tools at the IESEG School of Management in Lille, France (May 23-26, 2016). I presented an invited talk with the title "Recommender Systems: Harnessing the Power of Personalization" at the Southwest Airlines EDGe Analyst Community Meeting on November 18, 2015. I presented a tutorial with the title "Association Rule Mining: Introduction to the R package arules" at the 2015 March meeting of the Dallas R Users Group in Dallas, Texas ( slides and code ). I co-organize the Data Mining stream at the 2015 INFORMS Computing Society Conference (ICS). Submission deadline is September 15 ( more information ). We are running real-time hurricane intensity predictions for the 2014 Atlantic hurricane season using an advanced data stream modeling technique. Please visit the 2014 real-time prediction page. A team of student from IDA@SMU (under my supervision) wins IBM's 2014 The Great Mind Challenge - Watson Edition, a national data mining competition with 62 participating teams. Teaching and Service Courses for Spring 2021 Hahsler, M., DS/EMIS 1300: A Practical Introduction to Data Science, Lyle School of Engineering, SMU. Hahsler, M., CS 5/7320: Artificial Intelligence, Lyle School of Engineering, SMU. Hahsler, M., CS/EMIS 5/7331: Data Mining, Lyle School of Engineering, SMU. Lecture notes for all my courses Information for current students IDA@SMU Poster Templates: rectangular, square Learn R on your own How to decipher my handwriting. Service to the scientific community (meeting organization, reviewer, etc.) Research My current research interests are focused on methods used in the interdisciplinary field of Data Science including: Artificial Intelligence/Machine Learning/Data Mining: association rule mining, Data stream mining (focus on clustering), sequence mining, recommender systems, reinforcement learning (MDP/POMDP), data visualization. Combinatorial Optimization: Traveling Salesman Problem , seriation , optimal ordering and scheduling problems, density and graph-based clustering . Application Areas: bioinformatics , healthcare analytics, quantitative marketing, earth sciences, manufacturing, and engineering problems. Research Software Development: see Software Section below. Publications Talks Research lab Intelligent Data Analysis Lab (IDA@SMU) List of graduated student researchers with topics and theses. Recent research projects SAFE-NET: An Integrated Connected Vehicle and Computing Platform for Public Safety Applications funded by NIST (60NANB17D180, 2017-2020). Read the press release. QuasiAlign: Position Sensitive P-Mer Frequency Clustering with Application to Classification and Differentiation funded by NIH ( R21HG005912 , 2011-2014). TRACDS: Temporal Relationships Among Clusters in Data Streams funded by NSF ( IIS-0948893 , 2009-2013). Our research on hurricane intensity prediction was featured in the article “Discovery: New Forecasting Algorithm Helps Predict Hurricane Intensity and Wind Speed” (Dec. 5, 2011) by the National Science Foundation and in “Weatherwatch: Can the intensity of a hurricane be predicted?” (Oct. 12, 2011) by The Guardian. Patents US20140344195A1: System and method for machine learning and classifying data Former research topics Digital information management: Digital and virtual libraries Software engineering: Reuse and design patterns Software I am the lead developer and maintainer of several extension packages for the R software environment for statistical computing and graphics. R has been consistently voted one of the most important tools for data mining and analytics and being able to work with R is one of the highest paying analytics skills. Development versions of our software are available on GitHub. Association Rule Mining arules : Provides the infrastructure for representing, manipulating and analyzing transaction data and patterns (frequent itemsets and association rules). Also provides C implementations of the association mining algorithms Apriori and Eclat. Hahsler, Gruen and Hornik (2005) < doi:10.18637/jss.v014.i15 >. arulesViz : Description: Extends package arules with various visualization techniques for association rules and itemsets. The package also includes several interactive visualizations for rule exploration. Michael Hahsler (2017) < doi:10.32614/RJ-2017-047 >. arulesSequences : Add-on package to handle and mine frequent sequences (lead developer: Christian Buchta). arulesCBA : Provides the infrastructure for association rule-based classification including the algorithms CBA, CMAR, CPAR, C4.5 FOIL, PART, PRM, RCAR, and RIPPER to build associative classifiers. (developed with Ian Johnson ). arulesNBMiner : NBMiner is an implementation of the model-based mining algorithm for mining NB-frequent itemsets and NB-precise rules. Michael Hahsler (2006) . < doi: 10.1007/s10618-005-0026-2 > ( preprint ). Bioinformatics rRDP : Seamlessly interfaces the Ribosomal Database Project (RDP) classifier (version 2.9) which implements a Naive Bayesian Classifier (NBC) for biological sequences. [ intr...