HS2017 | Creative Data Mining

Sep - 18 - 2017

HS2017 | Creative Data Mining

The students examine patterns of crowd-flows in an extraordinary urbanisation phenomena: festivals. Bottom-up urbanization you might recognize also on pictures from slums, (refugee/military/exploratory) camps etc. 
Learn how to simulate the flows of people and how to quantify the (real estate) value of stand locations. Caliente Festival, Zurich, will serve as an example.




The Creative Data Mining course aims to provide aspirants a hands-on experience on machine learning (ML) tools and techniques for data processing and data analysis. Since future technologies increasingly rely upon machine learning, urban systems and architecture shall adopt it and the aspirant should learn creative ways to apply ML to better understand urban systems. The course covers a wider range ML techniques including supervised and unsupervised learning methods for data analysis and pattern recognition that help to better understand urban system for improving urban life.

All methods taught in the course will be applied to a common project to evaluate various dynamics of the urban environment. Students will work with time-series and geo-referenced data including temperature, relative humidity, illuminance, noise, people density, and dust particulate matter. Subjective impression survey data will also be integrated into the student projects to further explore influencing factors of the urban environment on our perceptual experiences. A selected neighborhood in the city of Zurich will be used as the case study and each student will present the findings of their research question in a final project.

Additionally, there are two of non-architectural skills the participants can develop during this course. First is an introduction to programming where at a minimum they can successfully use code-snippets to customize the computational tools presented in the course. Second, how clustering methods like PCA or K-Means could be applied in an architectural context.

Where: HIT H 31.4 (Video wall)
When: Mondays 10:00 - 12:00

2 ECTS

Supervision:

Course Flyer

Sep - 25 - 2017

Lecture 01: Steps of Knowledge Discovery Processes

Slides Lecture 01

Oct - 02 - 2017

Lecture 02: Fundamentals of Supervised Learning

Slides Lecture 02

Exercise 01

Oct - 09 - 2017

Lecture 03: Introduction to python and programming I

Slides Lecture 03

 

Oct - 16 - 2017

LECTURE 04: INTRODUCTION TO PYTHON AND PROGRAMMING II

Slides Lecture 04