Browsing by Author "Connan, James"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item KernTune: Self-tuning Linux kernel performance using support vector machines(Association for Computing Machinery, 2007) Yi, Long; Connan, JamesSelf-tuning has been an elusive goal for operating systems and is becoming a pressing issue for modern operating systems. Well-trained system administrators are able to tune an operating system to achieve better system performance for a specific system class. Unfortunately, the system class can change when the running applications change. Our model for self-tuning operating system is based on a monitor-classify-adjust loop. The idea of this loop is to continuously monitor certain performance metrics, and whenever these change, the system determines the new system class and dynamically adjusts tuning parameters for this new class. This paper describes KernTune, a prototype tool that identifies the system class and improves system performance automatically. A key aspect of KernTune is the notion of Artificial Intelligence (AI) oriented performance tuning. It uses a support vector machine (SVM) to identify the system class, and tunes the operating system for that specific system class. This paper presents design and implementation details for KernTune. It shows how KernTune identifies a system class and tunes the operating system for improved performance.Item Real-time gesture recognition using eigenvectors(2009) Segers, Vaughn; Connan, JamesThis paper discusses an implementation for gesture recognition using eigenvectors under controlled conditions. This application of eigenvector recognition is trained on a set of defined hand images. Training images are processed using eigen techniques from the OpenCV image processing library. Test images are then compared in real-time. These techniques are outlined below.Item A surface acoustic wave touchscreen-type device using two transducers(2008) Ghaziasgar, Mehrdad; Connan, JamesCurrent wireless human-computer interaction devices such as wireless mice and touchscreens, by and large, incorporate a sophisticated electronic architecture. The sophistication achieves wireless capabilities but carries over a cost overhead. In this paper we lay the foundation for developing a novel human-computer interaction device with reduced hardware sophistication. We developed a surface acoustic wave touchscreen-type device using only two transducers, as opposed to, typically, three or more transducers in conventional surface acoustic wave touchscreens. The transducers are mounted on a glass surface and connected into the line-in of a stereo sound card. User-initiated taps are detected, analysed and located on the surface, and the mouse cursor is moved to the computed screen location.