IS 709/809: Computational Methods for IS Research — Fall 2020
Times: Tuesday 4:30pm – 7:00pm
Location: Online
Instructor: Nirmalya Roy
Instructor’s Office Location and Hours: Online, Thursday 10:00 am – 11:00 am, or by appointment
Instructor’s Email: nroy at umbc dot edu
Course Description and Rationale: Computational methods are inevitable tools for many facets of information systems research. These methodologies are used as fundamental tools and techniques in research and advanced practice in information systems, with particular focus on networking hardware and software technologies that deal with data and systems. Data becomes useful when it provides meaningful information through data analysis and mining, pattern recognition and learning, information extraction and visualization. System becomes useful when it meets the required end performance metrics through the governing policies and procedures and underlying models and simulations. Sophisticated data analysis and system performance measurements require a mixture of skills ranging from algorithmic foundation, data mining, machine learning, computational modeling, and information systems performance evaluation. This course covers the mixture of these skills with the goal of providing information science graduate and masters students with the ability to employ them in future research. The course is project- based, allowing students to understand the use of computational methods to pursue research objectives and interests.
Course Objectives: The purpose of this course is to provide a comprehensive foundation to apply computational research methods in solving problems in Information Systems. This course should enhance students’ reasoning, problem-solving and modeling abilities, particularly in dealing with algorithmic problems. More specifically, the course has the following objectives:
Familiarize students with the concepts and applications of computational techniques (machine learning, data science, graph theory, computational complexity, information and communication technology, operational managements etc) to solve computational problems.
Teach students how to think and formalize problems algorithmically and experimentally.
We will not assume any background beyond high school level mathematics and familiarity with programming concepts. However, students are expected to spend time in learning the concepts in this course, many of which will be covered in detail.
Course Topics:
Algorithmic Complexity
System Modeling and Performance Measurement
Computational Techniques for Cyber-Physical Systems
Computational Techniques for Smart Service Systems
Information and Communication Technology
Applications
Prerequisites: IS 698 (Smart Home Health Analytics) or IS 733 (Data Mining) or consent of the instructor.
Instructional Methods: Classroom Lectures
Recommended Textbooks (Optional):
Data Structures and Algorithm Analysis in C++ (4th Edition) by Mark Allen Weiss, Addison- Wesley, 2013 (Amazon.com)
Fundamentals of Queueing Theory, 4th Ed., by Donald Gross & John F. Shortle & James M. Thompson & Carl M. Harris. John Wiley & Sons, Inc, 2008 (Amazon.com)
Week
Date
Topic
Handout/ Assignment
Due
Notes
1
9/1
Course overview, logistics, etc.
Introduction to Algorithm Analysis and System Modeling
2
9/8
Math Review for Computational Methods and Algorithm Analysis
Research Reflection (Smart Service Systems, CPS, FW discussions)
3
9/15
Computational Complexity
Research Reflection (Smart Service Systems + CPS + FW)
4
9/22
Computational Complexity
Research Reflection (Smart Service Systems + CPS + FW)
5
9/29
Computational Complexity (Contd.)
Research Reflection Schedule Arjun, Josh, Sahara, Masud
6
10/6
Research Reflection Schedule Tobi, Ali, Tashnim, Zahid, Jeanette
HW 2
7
10/13
Research Reflection (Contd.) Xiangyang, Pretam, Debvrat
Sorting Algorithm Analysis [Insertion sort, Selection sort, Shellsort, Mergesort, Quicksort, Decision trees, Counting Sort, External sorting (Multiway Merge) etc.]
Research Paper Presentations Zahid Hasan
8
10/20
Sorting Algorithm Analysis (Contd.)
Research Paper Presentations Jeanette Huang, Tobi Odunsi, Pretom Roy Ovi
9
10/27
Research Paper Presentations Josh Bolton, Sahara Ali, Masud Ahmed, Xiangyang Meng, Tashnim Chowdhury, Ali Alsarhan
Research Proposal
Research Proposal
10
11/3
Introduction to Graph Algorithms, Topological Sort, Shortest Paths, Network Flow; Minimum Spanning Tree Applications (Prim’s and Kruskal’s Algorithms)
Research Paper Presentations Debvrat Varshney, Arjun Pandya
11
11/10
Introduction to Graph Algorithms (Contd.)
Smart Service or Cyber-Physical Systems Performance Evaluation: Queueing Theory, Erlang Concept, Basic Model & Notation, Little’s Theorem
MST (Textbook DSAA: Chapter 9, Section 9.3, 9.4, 9.5)
12
11/17
Poisson process & Exponential distribution, Markovian Property, Memorylessness, Stochastic Process, Markov Process, Birth & Death process, Markovian Systems
Research project progress pitch [5-minutes oral presentation]
HW 3
Intro Queueing Theory (Textbook FQT: Chapter 1, Sections 1.1, 1.2, 1.3, 1.4, 1.5, 1.7, 1.8, and 1.9)
13
11/24
Single Server system: M/M/1-Queue; steady state probabilities, M/M/1 performance measures
Exam Review
Simple Queueing Model (Textbook FQT: Chapter 2, Sections 2.1 and 2.2)
14
12/1
Exam
HW 4
15
12/8
Final Research & Development Project Presentation
Research Paper Presentation Schedule:
(See above)
Research Papers:
In this course we will be discussing various papers recently published in ACM/IEEE UBICOMP (IMWUT) / ISWC 2020. Please check the following link.
https://ubicomp.org/ubicomp2020/program/agenda/
IMWUT 2019-2020
A Multisensor Person-Centered Approach to Understand the Role of Daily Activities in Job Performance with Organizational Personas, Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous TechnologiesDecember 2019
Cross-Dataset Activity Recognition via Adaptive Spatial-Temporal Transfer Learning, Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies December 2019 Yue (Jeanette) Huang
"He Is Just Like me”: A Study of the Long-Term Use of Smart Speakers by Parents and Children, ACM Interact. Mob. Wearable Ubiquitous Technol., Vol. 4, No. 1, 2020 Ali Alsarhan
Investigating Users' Preferences and Expectations for Always-Listening Voice Assistants, Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, December 2019
A wearable magnetic field based proximity sensing system for monitoring COVID-19 social distancing, ISWC '20: Proceedings of the 2020 International Symposium on Wearable Computers, September 2020 Tashnim Chowdhury
AuraRing: Precise Electromagnetic Finger Tracking, Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, December 2019
Towards the Design of a Ring Sensor-based mHealth System to Achieve Optimal Motor Function in Stroke Survivors, Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, December 2019 Debvrat Varshney
Machine Learning for Phone-Based Relationship Estimation: The Need to Consider Population Heterogeneity, Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, December 2019 Xiangyang Meng
Intermittent Learning: On-Device Machine Learning on Intermittently Powered System, Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, December 2019 Tobi Odunsi
Conversational Technologies for In-home Learning: Using Co-Design to Understand Children’s and Parents’ Perspectives, ACM CHI 2020
Privacy Adversarial Network: Representation Learning for Mobile Data Privacy, Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, December 2019 Zahid Hasan
Personalized HeartSteps: A Reinforcement Learning Algorithm for Optimizing Physical Activity, Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, March 2020 Josh Bolton
Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagation, CVPR 2020 Masud Ahmed
Graph Neural Networks for Social Recommendation, World Wide Web Conference, 2019 Pretom Roy Ovi
Oct 13 Presentations:
Oct 20 Presentations:
Tobi Odunsi: Intermittent Learning: On-Device Machine Learning on Intermittently Powered System
Jeanette Huang: Cross-Dataset Activity Recognition via Adaptive Spatial-Temporal Transfer Learning
Pretom Roy Ovi: Graph Neural Networks for Social Recommendation
Oct 27 Presentations:
Josh Bolton: Personalized HeartSteps: A Reinforcement Learning Algorithm for Optimizing Physical Activity
Sahara Ali: Multimodal Deep Learning Based Crop Classification Using Multispectral and Multitemporal Satellite Imagery
Masud Ahmed: Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagation
Xiangyang Meng: Machine Learning for Phone-Based Relationship Estimation: The Need to Consider Population Heterogeneity
Tashnim Chowdhury: A wearable magnetic field based proximity sensing system for monitoring COVID-19 social distancing
Ali Alsarhan: "He Is Just Like me”: A Study of the Long-Term Use of Smart Speakers by Parents and Children
Nov 3 Presentations:
Debvrat Varshney: Towards the Design of a Ring Sensor-based mHealth System to Achieve Optimal Motor Function in Stroke Survivors
Arjun Pandya: Machine Learning for Phone-Based Relationship Estimation: The Need to Consider Population Heterogeneity
Sample Research Project Reports:
David Welsh and Nirmalya Roy. Smartphone-based Mobile Gunshot Detection, In Proceedings of the 13th Workshop on Context and Activity Modeling and Recognition (CoMoRea’17), co-located with PerCom, March 2017. [pdf]
H M Sajjad Hossain, Md Abdullah Al Hafiz Khan, and Nirmalya Roy. SoccerMate: A Personal Soccer Attribute Profiler using Wearables, in Proceedings of the 1st IEEE PerCom International Workshop on Behavioral Implications of Contextual Analytics (BICA), co-located with PerCom, March 2017. [pdf]
Abu Zaher Md Faridee, Sreenivasan Ramasamy Ramamurthy, H M Sajjad Hossain, and Nirmalya Roy. HappyFeet: Recognizing and Assessing Dance on the Floor, in Proceedings of the ACM 19th International Workshop on Mobile Computing Systems and Applications (HotMobile), Feb. 2018 [pdf]
Varun Mandalapu, Lavanya Elluri and Nirmalya Roy. Developing Machine Learning based Predictive Models for Smart Policing, in Proceedings of the 1st IEEE International Students Workshop on Smart Computing (SmartStudents), co-located with SmartComp, pp. 1-6, Washington D.C., June 2019
Research Projects:
Team No
Team Members
Topic/Title
Devices/ Datasets
1
Debvrat Varshney & Tashnim Chowdhury
Semantic segmentation on medical images to detect COVID-19
2
Zahid Hasan
Contactless Heart Rate Sensing using Camera on Edge
MERL rPPG, UBFC-rPPG, & in-house rPPG
3
Yue Huang & Xiangyang Meng
Anomaly Detection for Spatio-temporal Taxi Trip
NYC Yellow Cab Trip Record 2016
4
Arjun Pandya & Tobi Odunsi
Energy consumption forecasts on multivariant time series
Engie Wind Farm & U.S. Energy Information Administration
5
Sahara Ali & Pretom Roy Ovi
Tracking Wildfires based on Satellite Data and Aerial Imagery
Fire-smoke dataset (DeepQuestAI), FIRM’s Active Fire Data (MODIS C6)
6
Ali Alsarhan & Josh Bolton
Students' Performance Prediction
Student Performance Dataset, University of Minho, Portugal
7
Masud Ahmed
Debris tracking and classification
In-house datasets collected by Drone
8
9
10