Navigation To modulepage
Display language

Data Engineering

6

English

#61041 / #4

SoSe 2020 - WS 2020/21

Fakultät VI

No information

Institut für Bauingenieurwesen

36312400 FG Systemtechnik baulicher Anlagen

Hartmann, Timo

Hartmann, Timo

timo.hartmann@tu-berlin.de

POS-Nummer PORD-Nummer Modultitel
38271 Fehler in der Verknüpfung: Nicht gefunden

Learning Outcomes

More and more data is becoming available in the area of civil engineering that engineers need to make sense of and integrate into their design work. Examples of such data sources are ranging from sensor based measurements of infrastructure and buildings, to measurements of the environment (weather, water flows), to openly available geographic data. Lately civil engineers even have started to analyse sentiment data users have left on social media platforms such as Facebook or Twitter about their experience while using civil engineered products. At the end of this class, students will know about the basics of data engineering analysis - the art of asking the right questions for drawing insights from any of these data- sets to support sustainable civil engineering tasks. After finalizing the module students will be able to apply the most common data mining and machine learning methods to data sets from the wider civil engineering field. Students will also have a good knowledge of how to assess the performance and quality of models and how to evaluate their applicability for prediction and sustainable decision making. Students will also develop first thoughts on the ethical ramifications of analyzing data with respect to for example, accounting for minorities that might not be well represented in a data set, but also with respect to potential biases that are introduced by the analysis methods.

Content

The module will teach the following methods: - data mining patterns and sequences - semantic text mining - regression analysis - correlation - Bayesian classification - decision trees and rule based classification - black-box methods - neural networks and support vector machines - unsupervised learning - evaluation of predictive models - data visualization: plotting and 3D

Module Components

Pflichtgruppe:

All Courses are mandatory.

Course Name Type Number Cycle Language SWS
Data Engineering VL 3631 L 9034 SS English 2
Data Engineering PJ 3631 L 9035 SS English 2

Workload and Credit Points

Data Engineering (VL):

Workload description Multiplier Hours Total
Präsenzzeit 15.0 2.0h 30.0h
Vor-/Nachbereitung 15.0 4.0h 60.0h
90.0h(~3 LP)

Data Engineering (PJ):

Workload description Multiplier Hours Total
Project work (weekly) 15.0 6.0h 90.0h
90.0h(~3 LP)
The Workload of the module sums up to 180.0 Hours. Therefore the module contains 6 Credits.

Description of Teaching and Learning Methods

- Read and comment on selected texts to acquire the fundamental knowledge about data engineering techniques - Reflection and discussion of the techniques based on the texts; practice and application examples during lectures - Project work: application of the techniques on a number of selected data sets from the civil engineering domain

Requirements for participation and examination

Desirable prerequisites for participation in the courses:

The module can be completed without any specific prior knowledge. Ideally students have followed Systemtechnik I or a similar module teaching an introduction to stochastic. Some basic skills with R will also be helpful.

Mandatory requirements for the module test application:

No information

Module completion

Grading

graded

Type of exam

Portfolio examination

Type of portfolio examination

100 points in total

Language

English

Test elements

Name Points Categorie Duration/Extent
comments on literature 40 written ca. 10 texts
Final data analytics challenge (group work) 20 practical report of 5000 words
data engineering project assignments 40 practical ca. 7 assignments of around 900 words

Grading scale

1.01.31.72.02.32.73.03.33.74.0
95.092.089.086.083.080.077.074.071.068.0

Test description (Module completion)

comments on literature data engineering project assignments The final data analytics challenge will require students to work in groups to analyze a real world data set under consideration of practical questions. Students will vote on the winner of this final challenge.

Duration of the Module

This module can be completed in one semester.

Maximum Number of Participants

This module is not limited to a number of students.

Registration Procedures

Qispos

Recommended reading, Lecture notes

Lecture notes

Availability:  unavailable

Electronical lecture notes

Availability:  unavailable

Literature

Recommended literature
No recommended literature given.

Assigned Degree Programs

This module is used in the following Degree Programs (new System):

Verwendungen (2)
Studiengänge: 2 Stupos: 2 Erstes Semester: SoSe 2020 Letztes Semester: WS 2020/21

This moduleversion is used in the following modulelists:

Students of other degrees can participate in this module without capacity testing.

Miscellaneous

No information