A Method of Filter Implementation Using Heterogeneous Computing System for Driver Health Monitoring

Research in any field of study requires analysis and comparisons or real-time predictions to extract useful information. To prove that the results have practical potential, various filtering techniques and methodologies should be designed and implemented. Filters being a class of signal processing helps innovate new technologies with various kinds of outcomes, using filters there are always various methods to solve a problem. Considering the current COVID-19 situation, researchers are working on sequencing the novel coronavirus and the genomes of people afflicted with COVID-19 using CPUs and GPUs along with various filtering techniques. In this paper we are using a method of filter implementation to collect raw heart rate data samples from fingertip and ear lobe and process those results on CPUs and GPUs. Our method of implementation to collect raw heart rate data is using a photoplethysmography method. We all know that the moving average filtering technique is the most commonly usedfor averaging an array of sampled data but in this paper we reconstructed the entire moving average filter with a slightly different averaging method where we will prove how our filter technique is better than the traditional moving average filter. This filtering technique is implemented and compared on both GPUs and CPUs. However, the filters on GPUs are slightly altered as per the GPU framework and CUDA programming techniques to optimize and output challenging results. We will also conduct Human trials for this concept and talk about how the heart rate changes while driving and also considering environmental conditions and scenarios. The findings of this work are also compared with apple watch heart rate data as it is the most accurate heart rate sensing device in the market with less than 2% error rate.