Decision Tree and Random Forest Implementations for Fast Filtering of Sensor Data

摘要: With increasing capabilities of energy efficient systems, computational technology can be deployed, virtually everywhere. Machine learning has proven a valuable tool for extracting meaningful information from measured data and forms one the basic building blocks ubiquitous computing. In high-throughput applications, measurements are rapidly taken to monitor physical processes. This brings modern communication technologies its limits. Therefore, only subset measurements, interesting ones, should further processed possibly communicated other devices. this paper, we investigate architectural characteristics embedded systems filtering high-volume sensor before processing. particular, implementations decision trees random forests classical von-Neumann computing architecture custom circuits by means field programmable gate arrays.