이 연구에서는 Inception V3, SqueezeNet(local), VGG-16, Painters 및 DeepLoc의 다섯 가지 인공지능(AI) 모 델을 사용하여 차나무 잎의 병해를 분류하였다. 여덟 가지 이미지 카테고리를 사용하였는데, healthy, algal leaf spot, anthracnose, bird’s eye spot, brown blight, gray blight, red leaf spot, and white spot였다. 이 연구에서 사용한 소프트웨 어는 데이터 시각적 프로그래밍을 위한 파이썬 라이브러리로 작동하는 Orange3였다. 이는 데이터를 시각적으로 조작하여 분석하기 위한 워크플로를 생성하는 인터페이스를 통해 작동되었다. 각 AI 모델의 정확도로 최적의 AI 모 델을 선택하였다. 모든 모델은 Adam 최적화, ReLU 활성화 함수, 은닉 레이어에 100개의 뉴런, 신경망의 최대 반복 횟수가 200회, 그리고 0.0001 정규화를 사용하여 훈련되었다. Orange3 기능을 확장하기 위해 새로운 이미지 분석 Add-on을 설치하였다. 훈련 모델에서는 이미지 가져오기(import image), 이미지 임베딩(image embedding), 신경망 (neural network), 테스트 및 점수(test and score), 혼동 행렬(confusion matrix) 위젯이 사용되었으며, 예측에는 이미 지 가져오기(import image), 이미지 임베딩(image embedding), 예측(prediction) 및 이미지 뷰어(image viewer) 위젯 이 사용되었다. 다섯 AI 모델[Inception V3, SqueezeNet(로컬), VGG-16, Painters 및 DeepLoc]의 신경망 정밀도는 각 각 0.807, 0.901, 0.780, 0.800 및 0.771이었다. 결론적으로 SqueezeNet(local) 모델이 차나무 잎 이미지를 사용하여 차 병해 탐색을 위한 최적 AI 모델로 선택되었으며, 정확도와 혼동 행렬을 통해 뛰어난 성능을 보였다.

Celiac disease (CD) is classified as an autoimmune disease of small intestine and occurred with people with the human leucocyte antigen (HLA) DQ2(8) cells. The gluten commonly called for the gliadins and glutenins from wheat and related proteins from barley and rye is significant cause of celiac disease. There are many sequences that recognized by T-cell according to species and different types of gliadins. In ω-gliadin, two sort of epitopes were figured out that consisting of some proline(P) and glutamine(Q) scattered in gliadin sequence. All registered ω-gliadin sequences deposited in NCBI database were downloaded and collected. In order to classify groups depending on sequence difference, sequence similarity and their closeness were analyzed by phylogenetic trees using by MEGA (ver.6.06). Chinese spring genome sequence database offered by URGI (Unité de Recherche Génomique Info) is used for sequence assembly. Primers to validate presence of epitopes were designed by two different type from conserved and specific region. Primer pair from consensus region were designed in conserved domain of ω-gliadin sequences from public database by sequence alignment. And, sequence-specific primers of ω-gliadin were designed from the unique region of each ω-gliadin sequence comparing ω-gliadin sequences from NCBI database with draft sequence of Chinese spring in URGI. The two known epitopes of ω-gliadin were located on same site, approximately from the 315th nucleotide to the 348th nucleotide in CDS. Candidate epitopes present in ω-gliadin were divided into three categories based on analysis of sequence similarity. This categorization shows similar pattern with groups that were previously reported by sequence motifs such as SRLL, AREL, ARQL and KELQ. However, sequence which has AREL motif and sequence ARQL motif were not distinguished obviously in ω-gliadin based on sequence alignment.