Skip to content Skip to navigation

Graduate Seminar Courses

Spring 2017

16:198:675/01:198:442

COCOON: Computational Coupling of Citizen Science and Smart Environments

The advent of new sensors, distributed networks and related analytics has enabled the introduction of novel technologies that promise to create a revolution in the design of smart environments that will improve the quality of lives of citizens. The application of such technologies on the design of smart cities has involved so far improving building design, vehicular traffic autonomy, air pollution and pedestrian safety. The focus has been on integrating computation, sensing and intelligence towards environmental entities, however, the behavioral aspects of intelligent citizens that inhabit these elements are frequently disregarded. The next generation of smart and connected environments must harness the tremendous potential of smart citizens, where environments and their informed occupants co-exist in a unified computational framework and dynamically adapt to each other’s needs and requirements. To achieve this dynamically evolving coupled interaction between the citizens and their environments of the future, a novel scientific approach is needed in terms of both computational methods and technology. Citizen science has existed as a separate field focusing on environmental and physical phenomena, and it is time to augment this approach with an interconnected urban information infrastructure. Towards this goal, this class will explore how novel computational methods can enable this coupling between Citizen Science and Smart Environments. In particular, we will explore how recent advancements in computer vision, machine learning, artificial intelligence, and computer simulations can be applied to develop solutions for the next generation of citizen-centric smart environments.

Instructor: Mubbasir Kapadia
Location: LIV BRR1071
Time: Monday 3:20 - 6:20 pm

Class prerequisites: Demonstrable proficiency in one or more of the following topics:

  • Computer Vision
  • Machine Learning
  • Artificial Intelligence
  • Robotics
  • Simulation / Graphics
  • Cognitive / Behavioral Science
  • Urban Planning / Architectural Design

 

Spring 2017

16:198:671

Data-Driven Cyber-Physical Systems for Smart Cities

The Department of Computer Science at Rutgers will offer a new graduate level seminar course 16:198:671 Data-Driven Cyber-Physical Systems for Smart Cities. This class is ideal for graduate students (or high-level undergrads) who want to learn various research topics about Data Science, Internet of Things, and Cyber-Physical Systems with applications on Smart Cities based on real-world systems and data.

Some topics covered include:

Large-Scale Urban Systems as Complex Internet of Things: e.g., cellphone, Wi-Fi, taxi, bus, subway, bike, electric vehicles, smart grid, and finance systems;

Urban Data Collection, Management, Processing, and Visualization: e.g., participatory/opportunistic sensing; stream, trajectory, and graph data management for heterogeneous urban data, streaming data processing, interactive visualization;

Spatial-Temporal Data Analytics: e.g., data fusion, visual analytics, data-driven predictive modeling, interdependency analyses;

Data Predictive Control in Smart Cities;

Human-in-the-Loop in Smart Cities;

Privacy and Security in Smart Cities;

Case Studies in Three Urban Domains: Telecommunication, Transportation, and Energy. Prerequisites: Preliminary knowledge on Calculus, Linear Algebra, and Probability is required. For non-CS students, basic skills for high-level programing languages (e.g., C++, Java, R, Python or SAS) are required. Grading: No exams, and all grades are based on class participation and a semester-long project.

Please contact Prof. Desheng Zhang at d.z@rutgers.edu if you have any questions about the course. More about the research topics related to urban systems and data can be found at https://www.cs.rutgers.edu/~dz220/research.html

 

Spring 2017  (To become CS524 in Fall 2017)

 

16:198:672

 

DIVA: Data Interaction and Visual Analytics

 

Schedule M, Th 10:20 am – 11:40 pm in Tillet 257 (Livingston Campus); First Meeting Tu Jan 17

 

Instructor : James Abello abelloj@cs.rutgers.edu, Teaching Assistant : TBA

 

Prerequisites : CS512 or CS513 (Algorithms), CS539(Data Bases or equivalent). A class on Computer Graphics and Vision (CS428 or equivalent) may be useful but it is not required.

 

Useful Languages to know: C/C++, Java, JavaScript, Python

 

Goal: To become proficient on the current major techniques and systems for algorithmic data analysis, exploration, visual interaction, and summarization. Students will complete a competitive group project that will incorporate all the facets of a software product development, namely: Conceptualization, Data collection, Algorithm identification and Implementation, User Interface, and Evaluation.

Projects can be chosen from the attached Capstone Faculty Project List or from one of the suggested DIVA Sample Project Categories below.

*Projects will be judged by a faculty panel and interested industry sponsors.

Guiding evaluation principles will be: the “value” of the extracted information from the chosen data set, the methods and models used, and the final application Interactivity.

 

Grading (600 Points) Individual Project Draft (Week 3: 10%); Working Group Project Code (Week 10: 60%);

Final Project Demo (Week 13: 20%); Documentation: Final Report and Video (Week 14: 10%).

 

DIVA Sample Project Categories (A Non Exhaustive Guide)

a. Similarity Search, Recommender Systems and Collaborative Filtering

b. Data Retrieval and Topic Waves

c. Prediction and Verification

d. Transaction Driven Data

e. Medical Imaging

f. Computer Aided Manufacturing

g. Apps for: Data Erasure, Nameless File Systems, Password Boxes, Phonetic Lyrics Search, Sentence Completion, Digital Signatures, …

 

Data Sets Students will choose a Data set of their interest and devise representation methods that are conducive to efficient Interactive algorithmic Exploration, Visualization, Analysis, Summarization and Sense making. The data sets used may be real or artificial. Some typical data sets that may be considered include: data feeds from Tweeter, YouTube, news streams, stocks, financial transactions, joke collections, movies, songs, Image Repositories, Transaction Ledgers, Online Encyclopedias (Ex: OEIS, Algorithm and Software repositories ), transportation schedules, data analytics blogs, funding agencies, startups, computer science educational materials, internet of things, …

Reference Materials

a. VisMaster-book

 

http://www.vismaster.eu/wp-content/uploads/2010/11/VisMaster-book-lowres...

b. Computational Social Science, Edited by R. Michael Alvarez, Cambridge University Press, 2016

c. Semiology of Graphics, Jacques Bertin, Translated by William J. Berg, ESRI Press, 2010

d. Selected papers from the literature on Algorithmic Analytics, Visualization and Computer Human Interaction.

 

Topics: Visual Analytics History, building blocks and inherent scientific challenges, Data Management for Visual Analytics, Data with Spatial and Temporal Components; Infra Structural and Language Issues(Hadoop, MapReduce, R, Python) ; Evaluation Methodologies and Challenges.

 

Time Line Phase 1(Background - Week 1 and 2). During the first two weeks students will be exposed to the fundamental principles of Data Analytics and Visual interaction as described in the

 

VisMaster-book. Selected topics from reference materials b. and c. and d. will be used as guides for projects selection.

 

Phase 2(FUN Project Selection - Week 3). During week 3, each student will present to the class and faculty a project conceptualization with a feasible plan of completion. One third of the projects will be selected for continuation. Those students whose projects get selected will become the project leaders. Student Leaders will select two non-leader partners that are willing to commit to the successful project completion. Faculty will choose those Feasible, Useful, and Novel projects they are willing to supervise and sponsor.

 

Phase 3(Project Prototype Progress Report- Week 4 -5 -6). Development and Evaluation of an operational Prototype. Faculty will evaluate project progress and assess the feasibility of project completion by the end of the semester. Only those projects judged as feasible will be allowed to move forward. Those students whose projects do not get selected will be assigned to become testers and project writers of those projects moving forward.

 

Phase 4(Pre Final Defense- Week 7, 8, 9, 10) Faculty sponsors will meet alternatively every week with sponsored projects to monitor their progress. During week 10 each project will have a pre final defense presentation. One third of the projects will be chosen for a final gala presentation (on week 14) in front of the class and a faculty/industry jury.

 

Phase 5(Gala Presentation- Week 14) The best five projects will be selected, project DIVA awards will be distributed, and formally recorded in the planned MSCS Wall of Fame.

 

.