Results Classification in an RGB LED Based Optical Fiber Sensor System using Python

In this paper, the analysis of sensor results from a light emitting diode (LED) based optical fiber sensor (OFS) system is presented. A tri-color RGB (Red-Green-Blue) LED is used to provide three stimulus colors to stimulate a Surface Plasmon Resonance (SPR) sensor which is optically coupled to the system electronics. Analysis of the sensor results under different light conditions is used to identify a particular chemical under test. In the analysis approach undertaken, a combination of the CURE (Clustering Using REpresentatives) data clustering method (algorithm) and the k-nearest neighbor (kNN) algorithm is used for classifying the chemical under test. The system hardware is based on the field programmable gate array (FPGA) and the classification is undertaken on a personal computer (PC) using the Python open source programming language.