Abstract-Band - Fakultät für Informatik, TU Wien - Technische ...
Abstract-Band - Fakultät für Informatik, TU Wien - Technische ...
Abstract-Band - Fakultät für Informatik, TU Wien - Technische ...
Sie wollen auch ein ePaper? Erhöhen Sie die Reichweite Ihrer Titel.
YUMPU macht aus Druck-PDFs automatisch weboptimierte ePaper, die Google liebt.
Paul Staroch<br />
A Weather Ontology for Predictive Control in Smart Homes<br />
Studium: Masterstudium Software Engineering & Internet Computing<br />
BetreuerIn: Ao.Univ.Prof. Dr. Wolfgang Kastner<br />
In the past few years, the idea of creating smart homes has gained popularity.<br />
A smart home possesses some kind of intelligence that allows it to support its<br />
inhabitants. The overall goal is to increase the inhabitants' comfort while<br />
energy use and costs are reduced as well. In the context of a project aimed at<br />
building smart home systems, this thesis aims at constructing an OWL ontology<br />
for weather information, containing data about both current conditions and<br />
weather forecasts. The data described by this ontology will enable smart home<br />
systems to make decisions based on current and future weather conditions. At<br />
first, the thesis will determine in which particular ways weather data can be<br />
used within smart homes. Furthermore, possible sources for weather data will<br />
be analysed. Primary sources will be weather services that are that are accessible<br />
via Internet. Optionally, local weather stations will be able to provide<br />
further data about current weather conditions. A set of Internet-based sources<br />
for weather data will be reviewed for their suitability for use within smart<br />
homes. Afterwards, existing ontologies will be reviewed for their structure,<br />
advantages, and disadvantages in order to acquire ideas being suitable to be<br />
re-used. Several well-known approaches for building new ontologies from<br />
scratch will be discussed in detail. The thesis will follow METHONTOLOGY, the<br />
best-fitting of these approaches, to build Smart-HomeWeather, an OWL<br />
ontology that covers both the weather data being available and the concepts<br />
required to perform weather-related tasks within smart homes while always<br />
keeping the possibility of simple and efficient OWL reasoning in mind. Eventually,<br />
Weather Importer, a Java application, will be developed that gathers<br />
data from weather services and local weather stations and transforms it to<br />
comply with the SmartHomeWeather ontology.<br />
Martin Stütz<br />
Detecting Illicit Content in Picture Streams<br />
Studium: Masterstudium Information & Knowledge Management<br />
BetreuerIn: Ao.Univ.Prof. Dr. Wolfgang Kastner<br />
18<br />
Diese Arbeit beschreibt einen Algorithmus zur Erkennung von Farbbildern mit<br />
pornographischen oder gänzlich illegalen Inhalten. Dazu kann der Algorithmus<br />
eine Altersklassifizierung anhand von gesichtsbasierter Geometrie durchführen.<br />
Der Algorithmus erweitert den Algorithm for Nudity Detection von Rigan Apapid<br />
durch die Verwendung von Support Vector Machines und Methoden zur<br />
Eliminierung von Fehlalarmen. Die Nacktheits- und Pornographieerkennung<br />
basiert auf Hauterkennung. Mithilfe von Hauterkennung können Hautflächen in<br />
Bildern lokalisiert werden. Größen, Formen und Distanzen der erkannten Hautflächen<br />
zueinander werden als Features zur Beschreibung der Inhalte von<br />
Bildern verwendet. Basierend auf diesen Features und dem Gesamtanteil von