Recently, transfer learning techniques with a base convolutional neural network (CNN) model have widely gained acceptance in early detection and classification of crop diseases to increase agricultural productivity with reducing disease spread. The transfer learning techniques based classifiers generally achieve over 90% of classification accuracy for crop diseases using dataset of crop leaf images (e.g., PlantVillage dataset), but they have ability to classify only the pre-trained diseases. This paper provides with an evaluation scheme on selecting an effective base CNN model for crop disease transfer learning with regard to the accuracy of trained target crops as well as of untrained target crops. First, we present transfer learning models called CDC (crop disease classification) architecture including widely used base (pre-trained) CNN models. We evaluate each performance of seven base CNN models for four untrained crops. The results of performance evaluation show that the DenseNet201 is one of the best base CNN models.

Cockles(Tegillarca granosa) species that found throughout the Indo-Pacific region and this study was conducted in Yeosu from November 2015 through April 2016. Antioxidant activities (lipid peroxidation, DPPH radical scavenging, superoxide anion radical scavenging, reducing power, and iron chelating assays) were studied at different stages during the processing. The results showed that all cockle samples were related to antioxidant activities, they also possessed effective abilities as free radical scavengers, reducing agents, and iron chelators in most cases. Seasonal variations in antioxidant activities were also observed, characterized by high activity values in April, spring season, a period where phytoplankton is their primary food source which propagates considerably. Moreover, the harvested cockles exhibited the higher radical scavenging activities than marketed cockles by compared in the similar concentration and the activities increased with increasing concentration. The results also showed the useful in the assessment of the cockle potential for the development of functional foods, food ingredients or pharmaceuticals. Moreover, keeping the freshness of the cockle during processing chain is pivotal for keeping its antioxidant activities.

\멍게껍질에 함유된 기능성 물질을 효소 및 열수로 추출하여 면역활성 및 항암 효과를 평가하였다. 세포독성을 검정하기 위하여 RAW 264.7 세포주에 추출물을 10∼200 ㎍/㎖ 농도로 처리한 결과 독성을 나타내지 않았다. 따라서 다양한 농도에서 효소 및 열수 추출물의 생리기능성을 평가하기 위하여 NO생성량을 측정한 결과 열수 추출물과 효소 추출물은 높은 NO 생성량을 보였다(123.0~161.7%). 위암 및 대장암 억제효과를 파악하기 위하여 다양한 농도에서 평가하였지만 최대 200 ㎍/㎖ 농도에서도 위암세포 AGS와 대장암세포 HT-29의 세포생장 억제에는 영향을 미치지 못하였다.