Data Science Research Lab (DSRL)

DSRL is led by Dr. Cyril S. Ku in the Department of Computer Science. It is a multi-disciplinary, inter-departmental, and inter-institutional research lab. Data science encompasses data collection, transformation, data mining, as well as data visualization. Various technologies of data science, including big data analytics, natural language processing, data/text mining, and machine learning are being conducted at DSRL by faculty and students.

NSF ACCESS Award: DSRL is supported by the NSF ACCESS Program. Dr. Ku is the Principal Investigator for the project titled: “High-Performance Computing Capability for the Data Science Research Lab at William Paterson University (Award Number: CIS230163)”. The ACCESS (Advanced Cyberinfrastructure Coordination Ecosystem: Services & Support) Program offers new advances in innovative cyberinfrastructure. Researchers associated with DSRL can access over fifteen supercomputing facilities nationwide.

The following four projects are being conducted using the resources at DSRL.

• Project HEAL Evaluation: Project HEAL is the hospital-based violence intervention program established at Jersey Shore University Medical Center. Dr. Sheetal Ranjan is the Founder of the Healthcare Approaches to Justice Collaborative at Montclair State University which establishes community-based violence prevention and intervention programs. One of the projects in the Collaborative is to partner with Project HEAL to provide violence prevention and intervention program evaluation and related support, as well as develop policies, protocols, and data collection instruments that facilitate evaluation efforts over time. Dr. Ku is a Research Scientist for the Healthcare Approaches to Justice Collaborative. He provides research and technical assistance through DSRL on various qualitative and quantitative tools and techniques (including data/text mining and machine learning) for the assessment efforts.

• Healthcare Informatics: Healthcare informatics allows a hospital to evaluate, improve, and communicate its quality of patient care, and develop better policies and procedures for healthcare management. Big data analytics is the key driver of how hospitals make decisions to provide quality healthcare and how physicians assess the effectiveness of medicines, treatment methods, as well as clinical procedures. Dr. Ku collaborates with Dr. Morgan R. Peltier, Dr. Daniel Weiner, Dr. Meera Wells, and Andrew Huang - MS4, from the Hackensack Meridian School of Medicine on using artificial intelligence technologies that automate the knowledge discovery process (neural networks and deep learning) for qualitative and quantitative analyses.

• Social Media Big Data Analytics: Big data is key to inductive reasoning as the more quantity in data, the more accurate the prediction or evidence there is to validate or invalidate a hypothesis. Large data gathered from social media platforms contain interesting and important information for researchers and practitioners alike. Dr. Ku collaborates with Dr. Jin-A Choi from the School of Communication and Media at Montclair State University on exploring various approaches to analyzing unstructured textual data.

• Data Science and Software Engineering: Dr. Ku collaborates with Dr. Thomas J. Marlowe (Professor Emeritus, Seton Hall University), Dr. Vassilka D. Kirova (Nokia Bell Labs), and Fr. Joseph R. Laracy, S.T.D. (Seton Hall University) on cybernetics, data science, databases, and various topics in software engineering (currently working on the impacts of large language models, e.g., ChatGPT, on software engineering and software engineering education).