Informatik
Refine
Year of publication
- 2021 (4) (remove)
Document Type
- Master's Thesis (4)
Has Fulltext
- yes (4)
Is part of the Bibliography
- no (4)
Beim Online-Lernen ist es wichtig, angemessenes Feedback zu geben, damit der Schüler aus seinen Fehlern lernen und sich weiterbilden kann. Oft besteht Feedback nur aus ungenügenden Informationen, wie etwa nur aus den Worten „Richtig“ oder „Falsch“, mit denen der Schüler nicht viel anfangen kann und somit nicht aus seinen Fehlern lernen kann. Ein gutes Feedback bei inkorrekten Antworten enthält wichtige Informationen, warum eine Antwort oder Aktion falsch ist und wie sie verbessert werden kann. Bei korrekten Antworten ist ein Lob oder eine Anerkennung der richtigen Antwort ebenfalls fördernd.
In dieser Arbeit wird das Feedback des Systems XData, welches für das Erlernen von SQL (Structured Query Language) genutzt wird, verbessert. Dazu wird das aktuelle System beschrieben, um das aktuelle Feedback bei SQL-Queries beurteilen zu können. Um das aktuelle Feedback angemessen verbessern zu können, wird ein Einblick in die Themen Lernen und Feedback gegeben. Die aus den beiden Themen gewonnen Eindrücke und Erkenntnisse werden bestmöglich für das zu verbessernde Feedback genutzt. Um das System und sein Feedback beurteilen zu können, sowie das verbesserte Feedback bewerten zu können, werden verschiedene SQL-Queries (Abfragen) verwendet. Es wird die Implementierung des Feedbacks durch ein Textbausteinsystem beschrieben und die verschiedenen Feedback-Fälle vorgestellt. Abschließend werden die Resultate beschrieben und beurteilt, sowie über die Ausblicke des Systems diskutiert.
Debugging errors in software applications can be a major challenge. It is not enough to know that a specific error exists, but the cause of it must be found in order to be able to fix it. Finding the source of an error can be time and cost intensive. The general approach is to analyse and debug the presumably erroneous part of the software. The analysis can be accompanied by instrumentation to gather additional information during the program execution. The analysis is made more difficult by the existence of different errors categories. Each category may need to be handled individually. Especially in embedded software applications, which commonly lack features like process or memory isolation, error detection and prevention can be even more challenging. This is the kind of problem this thesis tackles. This thesis tries to support developers during debugging and troubleshooting. The main focus is on errors related to memory management and concurrency. Specific features and properties of Arm Cortex-M processors are used to try to detect errors as well as their causes. For example, the memory protection unit is used to isolate the stack memories of different tasks running in a RTOS. The thesis tries to provide as much information as possible to the developer when reporting errors of any kind. The solution developed in this thesis also contains a custom memory allocator, which can be used to track down errors related to dynamic memory management. Furthermore, a Eclipse plugin has been developed which provides assertions for array accesses to detect and prevent out-of-bound accesses. The resulting solution has been implemented in commercial embedded software applications. This ensures that the developed solution is not only suitable for newly developed applications, but also for the integration into already existing products.
A concept for a recommender system for the information portal swissmom is designed in this work. The challenges posed by the cold start problem and the pregnancy-related temporal interest changes need to be considered in the concept. A state-of-the-art research on recommender systems is conducted to evaluate suitable models for solving both challenges. The explorative data analysis shows that the article's month of pregnancy is an important indicator of how relevant an article is to a user. Neither collaborative filtering, content-based filtering, hybrid models, nor context-aware recommender systems are applicable because the user's pregnancy phase is unknown in the available data. Therefore, the proposed recommender system concept is a case-based model that recommends articles which belong to the same gestation phase as the currently viewed article.
This recommender system requires that the month of pregnancy, in which an article is relevant, is known for each article. However, this information is only available for 31% of all articles about pregnancy. Consequently, this work looks for an approach to predict the month of gestation based on the article text. The challenges with this are that only few training data are available, and the article texts of the various months of pregnancy often contain the same terms, considering all articles are about pregnancy. A keyword-based approach using the TF-IDF model is compared with a context-based approach using the BERT model. The results show that the context-based approach outperforms the keyword-based approach.