No abstract

No abstract

Contamination is a critical issue that affects food consumption adversely. Therefore, efficient detection and classification of food contaminants are essential to ensure food safety. This study applied a visible and near-infrared (VNIR) hyperspectral imaging technique to detect and classify organic residues on the metallic surfaces of food processing machinery. The experimental analysis was performed by diluting both potato and spinach juices to six different concentration levels using distilled water. The 3D hypercube data were acquired in the range of 400–1000 nm using a line-scan VNIR hyperspectral imaging system. Each diluted residue in the spectral domain was detected and classified using six classification methods, including a 1D convolutional neural network (CNN-1D) and five pre-processing methods. Among them, CNN-1D exhibited the highest classification accuracy, with a 0.99 and 0.98 calibration result and a 0.94 validation result for both spinach and potato residues. Therefore, in comparison with the validation accuracy of the support vector machine classifier (0.9 and 0.92 for spinach and potato, respectively), the CNN-1D technique demonstrated improved performance. Hence, the VNIR hyperspectral imaging technique with deep learning can potentially afford rapid and non-destructive detection and classification of organic residues in food facilities.

With the recent accelerated policy-making and interests in new renewable energy, plans to develop and supply the new renewable energy have been devised across multiple regions in Korea. Solar energy, in particular, is being applied to small-scale power supply in provincial areas, as solar cells are used to convert solar energy into electric energy to produce electric power. Nonetheless, in the case of solar power plants, the need for a large stretch of land and considerable sum of financial support implies that the planning step should take into consideration the most suitable meteorological and geographical factors. In this study, the proxy variables of meteorological and geographical factors associated with solar energy were considered in analyzing the vulnerable areas regarding the photovoltaic power generation facility across the nation. GIS was used in the spatial analysis to develop a map for assessing the optimal location for photovoltaic power generation facility. The final vulnerability map developed in this study did not reveal any areas that exhibit vulnerability level 5 (very high) or 1 (very low). Jeollanam-do showed the largest value of vulnerability level 4 (high), while a large value of vulnerability level 3 (moderate) was shown by several administrative districts including Gwangju metropolitan city, Jeollabuk-do, Chungcheongbuk-do, and Gangwon-do. A value of vulnerability level 2 (low) was shown by the metropolitan cities including Daegu, Ulsan, and Incheon. When the 30 currently operating solar power plants were compared and reviewed, most were found to be in an area of vulnerability level 2 or 3, indicating that the locations were relatively suitable for solar energy. However, the limited data quantity for solar power plants, which is the limitation of this study, prevents the accuracy of the findings to be clearly established. Nevertheless, the significance of this study lies in that an attempt has been made to assess the vulnerability map for photovoltaic power generation facility targeting various regions across the nation, through the use of the GIS-based spatial analysis technique that takes into account the diverse meteorological and geographical factors. Furthermore, by presenting the data obtained for all regions across the nation, the findings of this study are likely to prove useful as the basic data in fields related to the photovoltaic power generation.

No abstract