IS 709/809: Computational Methods for IS Research
Spring 2014

Times: Wednesday 4:30 - 7:00pm
Location: ITE 231
Instructor: Nirmalya Roy
Instructor's Office Location and Hours: ITE 421,  Monday 2:00 - 4:00pm, or by appointment
Instructor's Email: nroy at umbc dot edu
Course webpage: http://userpages.umbc.edu/~nroy/courses/spring2014/cmisr/

Course Descriptions: 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, 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 details.

• Each student will be required to present 1 paper in the entire semester. 

• There will be one mid-term exam, and no final exam.

• There will be a development project (programming/testbed development). The main idea is to use real devices to build real systems which help collect data and albeit information latter! Example is developing smart home activity recognition data collection toolkit, or developing a household appliance energy metering system, or sensor based stress monitoring system or a system which keeps an eye on your diet. We will be using off-the-shelf commercially available devices, smart phones, wireless sensors, smart plugs or any other devices as need be for this purpose. The main intuition behind this semester long development project is getting real data for your research project. Energy education related project equipment will be sponsored by Constellation Energy while all other equipment will be provided by the instructor.
  

• The next most important component of the course will be the final research project obviously based on the computational methods you learn in this class. You are expected to do these projects in groups of 2 (preferably). Think about the research project problem early, discuss your ideas with me, read papers in the area, formulate your solution, and finally get the data from your development project and implement, and present it to the class.

Course Prerequisites: IS 650 (Data Communication and Networks) or IS 733 (Data Mining) or consent of the instructor

• Introduction to Machine Learning, Second Edition, by Ethem Alpaydin, MIT Press, 2010 (Amazon.com)

• Fundamentals of Queueing Theory, 4^th Ed., by Donald Gross & John F. Shortle & James M. Thompson & Carl M. Harris. John Wiley & Sons, Inc, 2008 (Amazon.com)

• Data Structures and Algorithm Analysis in C++ (4th Edition) by Mark Allen Weiss, Addison-Wesley, 2013 (Amazon.com)
  

• IEEE ICDM, ICDE, PerCom, ICML,
• ACM KDD, SenSys, IPSN, Ubicomp, MobiSys, BuildSys, CHI
  

ErdOS: Achieving Energy Savings in Mobile OS, Narseo Vallina-Rodriguez, Jon Crowcroft, ACM MobiArch 2011

Extracting a mobility model from real user traces, Minkyong Kim and David Kotz and Songkuk Kim. IEEE Infocom 2006
Activity-Aware Map: Identifying Human Daily Activity Pattern Using Mobile Phone Data, Santi Phithakkitnukoon et. al., HBU 2010
ACE: Exploiting Correlation for Energy-Efficient and Continuous Context Sensing, Suman Nath, ACM MobiSys 2012. Awarded Best Paper
Leveraging Graphical Models to Improve Accuracy and Reduce Privacy Risks of Mobile Sensing, Abhinav Parate et. al., MobiSys 2013

Towards a Zero-Configuration Wireless Sensor Network Architecture for Smart Buildings, Lars Schor, Philipp Sommer, Roger Wattenhofer, ACM BuildSys 2009
Efficient Application Integration in IP-Based Sensor Networks, Dogan Yazar, Adam Dunkels, ACM BuildSys 2009
Distributed Wireless Control for Building Energy Management, Alan Marchiori and Qi Han, ACM BuildSys 2010

SmartAds: Bringing Contextual Ads to Mobile Apps, Suman Nath, Felix Lin, Lenin Ravindranath, and Jitu Padhye, ACM MobiSys 2013
Using Mobile Phones to Write in Air, Sandip Agrawal, Ionut Constandache, Sharavan Gaonkar, Romit Roy Choudhury, ACM MobiSys, June 2011
SurroundSense: Mobile Phone Localization Via Ambience Fingerprinting, Martin Azizyan, Ionut Constandache, Romit Roy Choudhury, ACM MobiCom, September 2009
VUPoints: Collaborative Sensing and Video Recording through Mobile Phones, Xuan Bao, Romit Roy Choudhury, ACM MobiHeld (with ACM Sigcomm) August, 2009 
MicroBlog: Sharing and Querying Content using Mobile Phones and Social Participation, S. Gaonkar, et. al., ACM MobiSys 2008
Sensing Meets Mobile Social Networks: The Design, Implementation and Evaluation of the CenceMe Application, E. Mulizzo, et. al., ACM Sensys 08
Avoiding the Rush Hours: WiFi Energy Management for Mobile Devices, Justin Manweiler, Romit Roy Choudhury, ACM MobiSys, June 2011

The Visage Face Interpretation Engine for Mobile Phone Applications, Xiaochao Yang, Chuang-Wen You, Hong Lu, Mu Lin, Nicholas D. Lane, and Andrew T. Campbell, MobiCase 2012
MobileQueue: An Image-based Queue Card Retrieving System through Augmented Reality Phones, Chuang-Wen You et. al., UbiComp Poster, 2012
CarSafe: A Driver Safety App that Detects Dangerous Driving Behavior using Dual-Cameras on Smartphones, Chuang-Wen You et. al., UbiComp Poster, 2012
BeWell+: Multi-dimensional Wellbeing Monitoring with Community-guided User Feedback and Energy Optimization, Mu Lin et. al., Wireless Health 2012
StressSense: Detecting Stress in Unconstrained Acoustic Environments using Smartphonesn, Hong Lu et. al., ACM UbiComp 2012
WalkSafe: A Pedestrian Safety App for Mobile Phone Users Who Walk and Talk While Crossing Roads, Tianyu Wang et. al., ACM HotMobile 2012
From Smart to Cognitive Phones, Andrew T. Campbell and Tanzeem Choudhury, IEEE Pervasive Computing, June 2012
Cooperative Communities (CoCo): Exploiting Social Networks for Large-scale Modeling of Human Behavior, Nicholas Lane et. al., IEEE Pervasive Computing, 2011
Enabling Large-scale Human Activity Inference on Smartphones using Community Similarity Networks (CSN), Nicholas D. Lane et. al., ACM Ubicomp 2011
Tapping into the Vibe of the City Using VibN, Emiliano Miluzzo et. al., ACM Ubicomp 2011
SpeakerSense: Energy Efficient Unobtrusive Speaker Identification on Mobile Phones, Hong Lu et. al., Pervasive 2011
The Jigsaw Continuous Sensing Engine for Mobile Phone Applications, Hong Lu et. al., SenSys 2010
Darwin Phones: The Evolution of Sensing and Inference on Mobile Phones, Emiliano Miluzzo et. al., MobiSys 2010
MetroTrack: Predictive Tracking of Mobile Events using Mobile Phones, Gahng-Seop Ahn et. al., DCOSS 2010

The Sound of Silence, Wai-Tian Tan (Cisco Systems), Mary Baker (HP Labs), Ramin Samadani (Qualcomm Technologies, Inc.), Bowon Lee (HP Labs); ACM SenSys 2013
ScreenPass: Secure Password Entry on Touchscreen Devices, ACM MobiSys 2013
What's Your Current Stress Level? Detection of Stress Patterns from GSR Sensor Data, J Bakker et. al., ICDM Workshop 2011
Your reactions suggest you liked the movie: automatic content rating via reaction sensing, Xuan Bao et. al., ACM UbiComp 2013
Crowd++: Unsupervised Speaker Count with Smartphones, Chenren Xu et. al., ACM UbiComp 2013
Towards Zero-Shot Learning for Human Activity Recognition Using Semantic Attribute Sequence Model, ACM UbiComp 2013

• Smart Home in a Box (SHiB) (ADL monitoring toolkit in smart homes at large scale)
  
• Tweet-a-Watt (Build a wireless home-power monitoring system)
• Microsoft HomeOS (Enabling Smarter Homes for Community)
• Shimmer GSR/Optical Pulse Development Kit (Stress Detection and Analysis; Affective Computing and Cognitive Factors Research; Emotional Engagement;
  Agitation Detection; Psychological Arousal like Mental Effort, Excitement, Shock etc)
  

• ActiGraph (Sleep and Wellness Assessment)
• Shimmer Sensing Platform (Wearable Sensing: Kinematics, motion, biophysical like cardio, EMG, GSR, Strain Gauge development kits are available)
• Fitbit (Fitness, ADL monitoring)
• Microsoft Lab of Things (Connect devices home & beyond; support HomeOS)
  
• Waspmote from Libelium
  
• Smart Cities (Smart parking, Smart lighting, Traffic congestion, Waste management etc);
  
• Smart Environments (Air pollution, Forest fire detection, Snow level monitoring etc);
• Smart Utility (Water or Gas leakages, Water quality, Energy consumption monitoring etc);
• eHealth (Fall detection, ADL monitoring etc)
• Internet of Things

• Internet of Things
• OpenWSN project: open-source implementations of protocol stacks based on Internet of Things standards
• Mobile Opportunistic and Collaborative Sensing 
• MURI-Opportunistic Sensing Project, 
• Opportunity Project - Activity and Context Recognition with Opportunistic Sensor Configurations
• Smart City 
• Senseable City Lab MIT

• DOE's Max Tech and Beyond design competition (Ultra-low-energy-use appliances and equipment)
  
• The Heritage open mHealth $100K Challenge  (Inspire the development of mobile health applications using an open architecture)
  
• Intel Make it Wearable (Inspire ideas and fuel innovation that will evolve the emerging ubiquitous computing in exciting new ways)
• NSF Innovation Corps (Prepare students to extend their focus beyond the laboratory and broadens the impact of basic-research projects)
• Nokia Sensing XCHALLENGE (Transforming personal health with sensing)
• Qualcomm Tricorder XPRIZE (Bringing healthcare to the palm of your hand)
  

• Queueing System Performance Measurements: QtsPlus
• Weka (www.cs.waikato.ac.nz/~ml/weka)
• Machine learning open-source software (mloss.org)

• UCI ML Repository (archive.ics.uci.edu/ml)
• UCI KDD Repository (kdd.ics.uci.edu)
• Challenges: KDD-Cup, Netflix etc