Japanese Society for Horticultural Science
Acta Medica Okayama
2189-0102
91
3
2022
Deep Learning Predicts Rapid Over-softening and Shelf Life in Persimmon Fruits
EN
Maria
Suzuki
Graduate School of Environmental and Life Science, Okayama University
Kanae
Masuda
Graduate School of Environmental and Life Science, Okayama University
Hideaki
Asakuma
Fukuoka Agriculture and Forestry Research Center
Kouki
Takeshita
Department of Advanced Information Technology, Kyushu University
Kohei
Baba
Department of Advanced Information Technology, Kyushu University
Yasutaka
Kubo
Graduate School of Environmental and Life Science, Okayama University
Koichiro
Ushijima
Graduate School of Environmental and Life Science, Okayama University
Seiichi
Uchida
Department of Advanced Information Technology, Kyushu University
Takashi
Akagi
Graduate School of Environmental and Life Science, Okayama University
In contrast to the progress in the research on physiological disorders relating to shelf life in fruit crops, it has been difficult to non-destructively predict their occurrence. Recent high-tech instruments have gradually enabled non-destructive predictions for various disorders in some crops, while there are still issues in terms of efficiency and costs. Here, we propose application of a deep neural network (or simply deep learning) to simple RGB images to predict a severe fruit disorder in persimmon, rapid over-softening. With 1,080 RGB images of eSoshuf persimmon fruits, three convolutional neural networks (CNN) were examined to predict rapid over-softened fruits with a binary classification and the date to fruit softening. All of the examined CNN models worked successfully for binary classification of the rapid over-softened fruits and the controls with > 80% accuracy using multiple criteria. Furthermore, the prediction values (or confidence) in the binary classification were correlated to the date to fruit softening. Although the features for classification by deep learning have been thought to be in a black box by conventional standards, recent feature visualization methods (or gexplainableh deep learning) has allowed identification of the relevant regions in the original images. We applied Grad-CAM, Guided backpropagation, and layer-wise relevance propagation (LRP), to find early symptoms for CNNs classification of rapid over-softened fruits. The focus on the relevant regions tended to be on color unevenness on the surface of the fruit, especially in the peripheral regions. These results suggest that deep learning frameworks could potentially provide new insights into early physiological symptoms of which researchers are unaware.
No potential conflict of interest relevant to this article was reported.
Japanese Society for Horticultural Science
Acta Medica Okayama
2189-0102
91
1
2022
Fasciation in Strawberry Floral Organs and Possible Implications for Floral Transition
58
67
EN
Nguyen
Thi Cam
Graduate School of Environmental and Life Sciences, Okayama University
Naomichi
Sunagawa
Graduate School of Environmental and Life Sciences, Okayama University
Miho
Sesumi
Graduate School of Environmental and Life Sciences, Okayama University
Yoshikuni
Kitamura
Graduate School of Environmental and Life Sciences, Okayama University
Yoshiyuki
Tanaka
Graduate School of Agriculture, Kyoto University
Tanjuro
Goto
Graduate School of Environmental and Life Sciences, Okayama University
Ken-ichiro
Yasuba
Graduate School of Environmental and Life Sciences, Okayama University
Yuichi
Yoshida
Graduate School of Environmental and Life Sciences, Okayama University
Fasciation in strawberry is characterized by an enlarged and flattened receptacle, clustering of flowers, and altered inflorescence architecture. However, the developmental process of fasciated flowers remains obscure. In this study, the fasciation incidence and developmental process in the primary fruit and inflorescence architecture were evaluated and compared for the non-susceptible cultivars, eNyohof and eSagahonokaf and one of the most susceptible cultivars, eAi-Berryf. The severity and frequency of flower and inflorescence fasciation was clearly greater in the vigorously growing large plants of eAi-Berryf compared to small plants and large plants of the other two cultivars. In eAi-Berryf, the deformation of the large shoot apical meristem (SAM) into an oval shape was the initial symptom observed before and during floral transition. Such oval-shaped SAMs often differentiated two or more leaf primordia almost at the same time, which then developed into divided multiple vegetative SAMs before floral transition and linearly-fasciated SAMs during floral transition, respectively. The development of fasciation symptoms was observed after downregulation of FaTFL1. Although inflorescence or receptacle fasciation could be controlled when early and rapid floral induction was achieved by intermittent low-temperature treatment, severe fasciation was observed in late-flowered plants which were either not responsive or not subjected to this treatment. These results indicate that fasciation of floral organs may be triggered and develop during floral transition and that temperature fluctuations around boundary values between floral inhibition to induction may cause a half-finished or slowly processed floral transition and finally result in severe fasciation in vigorously growing eAi-Berryf plants.
No potential conflict of interest relevant to this article was reported.
Japanese Society for Horticultural Science
Acta Medica Okayama
21890102
88
1
2019
Publication of the first special issue of The Horticulture Journal Preface
1
EN
Yuichi
Yoshida
Okayama University
No potential conflict of interest relevant to this article was reported.