Institut für Informatik
Lehr- und Forschungseinheit für Programmier- und Modellierungssprachen
E-Mail: y i n g d i n g . w a n g [at] ifi * lmu * de
Summer Term 2017
- Exercise: "Human Computation"
- Master-Practicum: "Human Computation and Analytics"
- (WS 2016/2017) Exercise: "Human Computation and Analytics"
- (WS 2016/2017) Master-Seminar: "Physiological Data Analysis for Educational Technologies"
- (SS 2016) Softwareentwicklungspraktikum: "Python mit dem Raspberry Pi"
- (WS 2015/2016) Master-Praktikum: "Technology-Enhanced Learning"
- Learning Analytics for Educational Technologies
- Analysis of Physiological Data
- Information Retrieval and Text Mining
- Human Computation and Visual Analytics
- Stress Tracking in Learning Activities (Stila)
Stress is a common problem in our contemporary society, especially among students and professionals. The goal of project Stila is to provide students and professionals with personalized recommendations aiming at improving their learning performances. To achieve this, stress development of learners needs to be monitored during theirs learning activities. A visual feedback on stress level development based on physiological sensor data, shall be provided to learners. A trend analysis of aggregated sensor data over a period time enables further classification of eustress(positive stress) and distress(negative stress) associated with learning activities. Based on the outcome of individual trend analysis of stress development, feedbacks and recommendations for a particular learning activity can be individually provided to each learner.
Project Website: http://stila.pms.ifi.lmu.de/
- Intelligent Recommender of MOOCs (Irom)
Massive Open Online Courses (MOOCs) are emerging online learning offers for university students. Due to the large number of MOOCs provided by different MOOC platforms, it is quite difficult for learners to select the MOOCs best fulfilling their needs. The goal of project Irom is to conceive, develop and test an intelligent MOOCs search engine. To this aim, the MOOCs textual description will be analyzed, for example by clustering the term-document vectors derived from the MOOCs descriptions and by using explicit as well as implicit feedback from the MOOCs search engine users.
Project Website: http://irom.pms.ifi.lmu.de/
- CodeKōan - A Source Code Analysis Platform
Producing faultless, high quality source code is a challenging task, that many programmers strive to excel at performing. Computer science has made great strides in the last decades in developing new techniques for producing better source code. The introduction of programming paradigms -- object oriented, functional and aspect oriented programming -- and technology, such as exceptions and the actor model, has enabled programmers to write the software, which powers our everyday life.
Previous research has contributed algorithms and technology to enable writing better software. The goal of project CodeKōan is to put the focus on the most important part of coding: The Programmers. To fulfill this goal, project CodeKōan contributes a search engine, that finds similarities between pieces of source code and code examples in online resources like Stackoverflow.
Project Website: http://codekoan.org/
- Joseph Birkner, Ranking with neural network derived document vectors
- Christof Schramm, Recognition of Code Patterns from Stackoverflow Answers in Computer Programs
- Benjamin Humpel, Parlance comparison of textual MOOC descriptions -- Applying NLP tools and statistical analysis among different MOOC Platforms
- Patrik Hagen, Eustress and Distress Detection from Physiological Data using Supervised Machine Learning (M.Sc.)
- Kai Wilker, Multidimensional Clustering of MOOC Offers -- Applying unsupervised learning algorithms FCM and SOM to text description (B.Sc.)
- Marcel Heil, Conception and Implementation of a Mobile Application with Fitness Trackers as Supportive Tools for Computed Stress Detection (B.Sc.)