Abstract: In this study, a multivariate analysis of potato spectroscopic data was presented to detect the presence of brown rot disease or not. Near-Infrared (NIR) spectroscopy (1,350-2,500 nm) combined with multivariate analysis was used as a rapid, non-destructive technique for the detection of brown rot disease in potatoes. Spectral measurements were performed in 565 samples, which were chosen randomly at the infection place in the potato slice. In this study, 254 infected and 311 uninfected (brown rot-free) samples were analyzed using different advanced statistical analysis techniques. The discrimination performance of different multivariate analysis techniques, including classification, pre-processing, and dimension reduction, were compared. Applying a random forest algorithm classifier with different pre-processing techniques to raw spectra had the best performance as the total classification accuracy of 98.7% was achieved in discriminating infected potatoes from control.
Abstract: We have been grouping and developing various kinds
of practical, promising sensing applied systems concerning
agricultural advancement and technical tradition (guidance). These
include advanced devices to secure real-time data related to worker
motion, and we analyze by methods of various advanced statistics and
human dynamics (e.g. primary component analysis, Ward system
based cluster analysis, and mapping). What is more, we have been
considering worker daily health and safety issues. Targeted fields are
mainly common farms, meadows, and gardens. After then, we
observed and discussed time-line style, changing data. And, we made
some suggestions. The entire plan makes it possible to improve both
the aforementioned applied systems and farms.