Admission requirements
Recommended prior knowledge
Programming experience with Python;
Machine learning and data mining;
Deep Learning (have already taken the course or taking it parallel);
Statistics.
Description
Urban computing, as an interdisciplinary field, is the science of using computing technology in solving urban and environmental challenges such as traffic, and pollution. This course provides a comprehensive introduction to this topic. Throughout the course, students will get familiar with data acquisitions, integration, and modeling skills required for urban computing research.
Spatio-temporal data is the data collected as a result of movement of mobile objects, such as cars and people, over space. Spatio-temporal data mining is the core to most urban computing research projects. Most previously designed machine learning algorithms do not consider the specific characteristics of spatio-temporal data. In this course, we will talk about how different classes of machine learning algorithms have been designed so far to perform on such data. We will also learn how additional data sources can be fused and integrated with spatio-temporal data. The concepts throughout the course are explained using examples extracted from the state of the art research literature. Students will put the knowledge of spatio-temporal data mining they acquire in this course into practice, using different assignments and a final project. Topics to be addressed are:
Acquiring data for urban computing research
Processing time-series data
Processing spatial data
Processing spatio-temporal data
Visualization techniques for spatio-temporal data
Machine learning algorithms for urban computing research
Deep learning for urban computing research
Course objectives
This course aims at providing knowledge for students to design machine learning algorithms for spatio-temporal data. While reviewing the theoretical concepts we greatly focus on how environmental and urban applications can be addressed with such methods. Notably, we discuss and see examples of various data sources (Earth observations, GPS sensors, open data), their imperfections and peculiarities and design algorithmic solutions for them. After this course students are able to:
categorize and compare existing machine learning approaches for handling spatio-temporal and time-series data;
collect and employ existing spatio-temporal data, evaluate and analyze their properties and imperfections;
identify new research problems based on spatio-temporal data sources and design a methodology to address it;
develop new algorithms tailored to spatio-temporal data and design an evaluation approach based on the properties of the available data;
present and communicate their result results (i.e., the relevance of the research questions, methods, evaluation and conclusions).
Timetable
The most recent timetable can be found at the Computer Science (MSc) student website.
You will find the timetables for all courses and degree programmes of Leiden University in the tool MyTimetable (login). Any teaching activities that you have sucessfully registered for in MyStudyMap will automatically be displayed in MyTimeTable. Any timetables that you add manually, will be saved and automatically displayed the next time you sign in.
MyTimetable allows you to integrate your timetable with your calendar apps such as Outlook, Google Calendar, Apple Calendar and other calendar apps on your smartphone. Any timetable changes will be automatically synced with your calendar. If you wish, you can also receive an email notification of the change. You can turn notifications on in ‘Settings’ (after login).
For more information, watch the video or go the the 'help-page' in MyTimetable. Please note: Joint Degree students Leiden/Delft have to merge their two different timetables into one. This video explains how to do this.
Mode of instruction
Interactive lectures
Seminar presentations
Assignments
Paper
Presentation
Course load
Total hours of study: 168 hrs. (= 6 EC)
Lecture hours (lectures + presentations): 24 hrs.
Practical assignments: 40 hrs.
Final project: 104 hrs.
Assessment method
The final score of the course is composed of:
Assignments (35%)
Presentation (15 %)
Project (40%)
Project peer review (10%)
It is possible to resit assignments and the project. However, the resit of assignments gets a maximum grade of 7. To pass the course the course combined grade, project grade and each assignments grade should be over 5.5. No resit option is available for presentations. Submitting a project proposal is compulsory (no submission implies deduction of 20% of the project grade).
Reading list
- Extra reading material composed of recent papers will become available through Brightspace.
Registration
From the academic year 2022-2023 on every student has to register for courses with the new enrollment tool MyStudyMap. There are two registration periods per year: registration for the fall semester opens in July and registration for the spring semester opens in December. Please see this page for more information.
Please note that it is compulsory to both preregister and confirm your participation for every exam and retake. Not being registered for a course means that you are not allowed to participate in the final exam of the course. Confirming your exam participation is possible until ten days before the exam.
Extensive FAQ's on MyStudymap can be found here.
Contact
Lecturer: dr. M. Baratchi