Browsing by Author "Ranaweera, L"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    item: Conference-Abstract
    Anomaly detection in complex trading systems
    (2017) Ranaweera, L; Vithanage, R; Dissanayake, A; Prabodha, C; Ranathunga, S; classification; feature selection; trading systems
    System availability is one of the major requirements expected from systems in the trading domain. In order to prevent system outages that can deteriorate system availability, anomaly detection must be able to assess the status of the system and detect anomalies that can lead to failures on a real-time basis. This paper presents a framework for anomaly detection for complex trading systems based on supervised learning approaches. Multiple feature reduction techniques were experimented with, in order to eliminate the noisy features that were initially derived from the system parameters. A classification technique based on Radial Basis Function (RBF) kernel Support Vector Machine (SVM) along with a feature selection technique built on a tree-based ensemble displayed the most promising results.
  • Thumbnail Image
    item: Conference-Full-text
    Fill in the blanks
    (Department of Computer Science and Engineering, University of Moratuwa., 2016-12) Ranaweera, L; Perera, I; Meedeniya, D
    With the increasing number of utilities provided by touchscreen devices, the process of designing user interfaces is of utmost importance. In the search for UI design decisions, it is necessary to have access to current data related to user behaviour relating to touchscreen inputs. As such, the technique of crowdsourcing has been used to create a game to collect data related to drag and drop, rotate, pinch zoom in and out gestures in the project discussed in this paper. The major design decisions encountered in the project were creating an intriguing gameplay that involves all the touch gestures mentioned above and devising a mechanism to collect and store data related to such movements. The final outcome of the project is a game designed for Android devices that can be distributed via the Google Play Store, which will collect and transfer data to a remote location to be analyzed by UI designers.