Christina Andersson

Approaches to Building a Detection Model for Water Quality: A Case Study

Predicting failure or success of an event or value is a problem that has recently been addressed using data mining techniques. By using the information we have from the past and the information of the present, we can increase the chance to take the best decision on a future event. In this paper, we evaluate some popular classification algorithms to model a water quality detection system. The experiment is carried out using data gathered from Thuringer Fernwasserversorgung water company. We briefly introduce baseline steps we followed in order to achieve a descent model for this binary classification problem. We describe the algorithms we have used, and the purpose of using each algorithm, and in the end we come up with a final best model. Representative models are compared using the F1 score, as a performance measurement. Finding the best model allows for early recognition of undesirable changes in the drinking water quality and enables the water supply companies to counteract in time.

Deployment of a blended learning module in statistics for engineering and computer science students

Teaching a statistics course for undergraduate computer science students can be extremely challenging: As statistics teachers we are usually faced with problems ranging from a complete disinterest in the subject to lack of basic knowledge in mathematics and anxiety for failing the exam, since statistics has the reputation of having high failure rates. In our case, we additionally struggle with difficulties in the timing of the lectures as well as often occurring absence of the students due to spare-time jobs or a long traveling time to the university. This paper reveals how these issues can be addressed by the introduction of a blended learning module in statistics. In the following, we describe an e-learning development process used to implement time- and location-independent learning in statistics. The study focuses on a six-step-approach for developing the blended learning module. In addition, the teaching framework for the blended module is presented, including suggestions for increasing the interest in learning the course. Furthermore, the first experimental in-class-usage has been completed and the outcome is discussed.

Using a Modified Jigsaw Technique in E-Learning Laboratory Classes for Engineering Students

In this paper, we discuss the use of the jigsaw technique in e-learning laboratory classes for mechanical engineering undergraduate students. The program Mechanical Engineering Online at Frankfurt University of Applied Sciences (FRA-UAS) makes it possible for students to combine studying for a university degree with work and family life. The main part of the tuition of the program takes place as web conferences, preferably in the evenings. Only 20% of the teaching requires the students to be present at the university, mostly during weekends. However, one common problem in the teaching of e-learning based courses is the high risk that the students who start the course will drop out. Some important factors influencing the dropout rate are, among many other factors, how actively the students are contributing to the learning process and how much responsibility they assume during the course. This paper describes how we can apply a modified version of the jigsaw cooperative learning technique in order to make the students actively and with a high level of responsibility participate in web conference based laboratory work in a course in basic natural sciences. The current study focuses on the settings and implementation of the web-based laboratory work. Furthermore, the first experimental in-class-usage has been completed and the outcome is discussed.