To perform mechanical recycling of massive amounts of waste plastics, we developed an identifier oriented on industrial use and based on Raman spectroscopy. For the purpose of designing a practical classification technique that is accurate, fast, and robust against external noise, a simple comparison of spectroscopic peak intensities is considered to be more useful than a complicated multivariate analysis. However, such peak choosing is carried out empirically so far based on expert spectroscopic knowledges. In this report, we successfully demonstrate the classification of three kind plastics using only two peaks that are selected based on support vector machine (SVM) of machine learning; three types of plastic, polypropylene (PP), polystyrene (PS), and acrylonitrilebutadienestyrene copolymer (ABS), are categorized well even in the case of the large artificially generated noise conditions. We could choose automatically a set of two peaks among six sets of four peaks that become candidates in the Raman spectra. Margin values in SVM allow obtaining the decisive information on how to select the peaks in the spectra quantitatively, for distinguishing different types of plastics.
Inadequate lighting conditions can harm the accuracy of blink detection systems, which play a crucial role in fatigue detection technology, transportation and security applications. While some video capture devices are now equipped with flashlight technology to enhance lighting, users occasionally need to remember to activate this feature, resulting in slightly darker videos. Consequently, there is a pressing need to improve the performance of blink detection systems to detect eye accurately blinks in low light videos. This research proposes developing a machine learning-based blink detection system to see flashes in low-light videos. The Confusion matrix was conducted to evaluate the effectiveness of the proposed blink detection system. These tests involved 31 videos ranging from 5 to 10 seconds in duration. Involving male and female test subjects aged between 20 and 22. The accuracy of the proposed blink detection system was measured using the confusion matrix method. The results indicate that by leveraging a machine learning approach, the blink detection system achieved a remarkable accuracy of 100% in detecting blinks within low-light videos. However, this research necessitates further development to account for more complex and diverse real-life situations. Future studies could focus on developing more sophisticated algorithms and expanding the test subjects to improve the performance of the blink detection system in low light conditions. Such advancements would contribute to the practical application of the system in a broader range of scenarios, ultimately enhancing its effectiveness in fatigue detection technology.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.