• Korean Journal of Remote Sensing
• /
• 제39권2호
• /
• pp.183-192
• /
• 2023

The remotely sensed data, such as satellite imagery and aerial photos, can be used to extract and detect some objects in the image through image interpretation and processing techniques. Significantly, the possibility for utilizing digital map updating and land monitoring has been increased through automatic object detection since spatial resolution of remotely sensed data has improved and technologies about deep learning have been developed. In this paper, we tried to extract plastic greenhouses into aerial orthophotos by using fully convolutional densely connected convolutional network (FC-DenseNet), one of the representative deep learning models for semantic segmentation. Then, a quantitative analysis of extraction results had performed. Using the farm map of the Ministry of Agriculture, Food and Rural Affairsin Korea, training data was generated by labeling plastic greenhouses into Damyang and Miryang areas. And then, FC-DenseNet was trained through a training dataset. To apply the deep learning model in the remotely sensed imagery, instance norm, which can maintain the spectral characteristics of bands, was used as normalization. In addition, optimal weights for each band were determined by adding attention modules in the deep learning model. In the experiments, it was found that a deep learning model can extract plastic greenhouses. These results can be applied to digital map updating of Farm-map and landcover maps.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• 제16권6호
• /
• pp.392-399
• /
• 2023

This paper proposes a deep learning model to determine the region and depth of cabbage cores for robotic automation of the cabbage core removal process during the kimchi manufacturing process. In addition, rather than predicting the depth of the measured cabbage, a model was presented that simultaneously detects and classifies the area by converting it into a discrete class. For deep learning model learning and verification, RGB images of the harvested cabbage 522 were obtained. The core region and depth labeling and data augmentation techniques from the acquired images was processed. MAP, IoU, acuity, sensitivity, specificity, and F1-score were selected to evaluate the performance of the proposed YOLO-v4 deep learning model-based cabbage core area detection and classification model. As a result, the mAP and IoU values were 0.97 and 0.91, respectively, and the acuity and F1-score values were 96.2% and 95.5% for depth classification, respectively. Through the results of this study, it was confirmed that the depth information of cabbage can be classified, and that it can be used in the development of a robot-automation system for the cabbage core removal process in the future.

• Journal of Food Hygiene and Safety
• /
• 제26권4호
• /
• pp.322-329
• /
• 2011

This study was done to analyze the contents of minerals and vitamins to compare the measured values of minerals, vitamins with labeled values of them in food labeling and to investigate the ratio of measured values to labeled values in 437 specimen with minerals and vitamins - fortified commercial beverages and liquid teas. Content of calcium and sodium in samples after microwave digestion was analyzed with an ICP-OES (Inductively Coupled Plasma Optical Emission Spectrometer) and vitamins were determined using by HPLC (High Performance Liquid Chromatography). The measured values of calcium were ranged 80.3~142.6% of the labeled values in 21 samples composed calcium - fortified commercial beverages and liquid teas. In case of sodium, measured values were investigated 33.9~48.5% of the labeled values in 21 sports beverages. The measured values of vitamin C, vitamin $B_2$ and niacin were ranged 99.7~2003.6, 81.1~336.7, 90.7~393.2% of the labeled values in vitamins - fortified commercial beverages and liquid teas, 57, 12, 11 samples. To support achievement of the accurate nutrition label, there must be program and initiatives for better understanding and guidances on food labelling and nutrition for food manufacture.

• Journal of the Korean Society of Food Science and Nutrition
• /
• 제26권1호
• /
• pp.161-174
• /
• 1997

Omega-3 fatty acids have been major research interests in medical and nutritional science relating to life sciences since after the epidemiologic data on Green3and Eskimos reported by several researchers clearly showed fewer per capita deaths from heart diseases and a lower incidence of adult diseases. Linolenic acid(LNA) is an essential fatty acid for human beings as well as linoleic acid(LA) due to the fact that vertebrates lack an enzyme required to incorporate a double bond beyond carbon 9 in the chain. In addition the ratio of omega-6 and 3 fatty acids seems to be important in terms of alleviation of heart diseases since LA and LNA competes for the metabolic pathways of eicosanoids synthesis. High consumption of omega-3 fatty acids in seafoods may control heart diseases by reducing blood cholesterol, triglyceride, VLDL, LDL and increasing HDL and by inhibiting plaque development through the formation of antiaggregatory substances like PGI$_2$, PGI$_3$ and TXA$_3$ metabolized from LNA. Omega 3 fatty acids also play an important role in neuronal developments and visual functioning, in turn influence learning behaviors. Current dietary sources of omega-3 fatty acids are limited mostly to seafoods, leafy vegetables, marine and some seed oils and the most appropriate way to provide omega-3 fatty acids is as a part of the normal dietary regimen. The efforts to enhance the intake of omega-3 fatty acids due to several beneficial effects have been made nowadays by way of food processing technology. Two different ways can be applied: one is add Purified and concentrated omega-3 fatty acids into foods and the other is to produce foods with high amounts of omega-3 fatty acids by raising animals with specially formulated feed best for the transfer of omega-3 fatty acids. Recently, items of manufactured and marketed omega-3 fatty acids fortified foodstuffs are pork, milk, cheese, egg, formula milk and ham. In domestic food market, many of them are distributed already, but problem is that nutritional informations on the amounts of omega-3 fatty acids are not presented on the labeling, which might cause distrust of consumers on those products, result in lower sales volumes. It would be very much wise if we consume natural products, result in lower sales volumes. It would be very much wise if we consume natural products high in omega-3 fatty acids to Promote health related to many types of adult diseases rather than processed foods fortified with omega-3 fatty acids.

• Journal of the Korean Society of Food Science and Nutrition
• /
• 제44권7호
• /
• pp.975-982
• /
• 2015

Piceatannol (trans-3,4,3',5'-trihydroxystilbene), a natural stilbene, is an analogue of resveratrol. In the present study, possible mechanisms by which piceatannol exerts its pro-apoptotic action in cultured human oral cancer YD-15 cells were investigated. To investigate whether or not piceatannol has effects on cancer cell viability, human oral YD-15 cells were treated with piceatannol (0, 50, and $100{\mu}M$). Piceatannol treatment ($100{\mu}M$) showed the strongest inhibition of cell proliferation and reduced cell viability in a dose-dependent manner. Chromatin condensation detected by DAPI staining significantly increased in a concentration-dependent manner, indicating apoptosis. Piceatannol treatment activated initiator Bax (pro-apoptotic) and cPARP in a concentration-dependent manner. Further, piceatannol induced down-regulation of Bcl-2 (anti-apoptotic). We also evaluated the activity of piceatannol against oral cavity cancer tumors in mice. Piceatannol-treated nude mice bearing YD-15 xenograft tumors exhibited significantly reduced tumor volume and weight due to the potent effect of piceatannol on tumor cell apoptosis, as determined by terminal deoxynucleotidyl transferase-mediated dUTP nick end labeling assay. Immunohistochemistry staining showed elevated expression of cleaved-caspase-3 as well as reduced expression of Ki-67 in the piceatannol-treated group. Therefore, piceatannol can be developed as a cancer preventive medicine due to its growth inhibitory effects and induction of apoptosis in human oral cancer cells.

• Journal of the Korean Chemical Society
• /
• 제53권6호
• /
• pp.742-748
• /
• 2009

In the meat industry, correct breed information in food labeling is required to assure meat quality. Genetic markers provide corroborating evidence to identify breed. We described the development of DNA markers to discriminate between Korean beef cattle (Hanwoo), Holstein, and mixed cow beefs. As most breeds are standardized for coat colour, the melanocortin 1 receptor (MC1R) gene, involved in the regulation of eu/pheomelanins synthesis, has been suggested as marker for breed traceability of products of animal origin. We also designed sex-determining region Y (SRY) gene specific primers for Y chromosome detection. In this study, fragments of MC1R gene and SRY gene were amplified by multiplex-PCR and subjected to digestion by MspA1I restriction endonuclease. Reaction products were analysised by denaturing high performance liquid chromatography (DHPLC). As a result, we identified 6 DHPLC peak types from MC1R gene and SRY gene analysis. DHPLC method showed more sensitive than RFLP method for DNA fragments analysis. Therefore, DHPLC method can apply to identify for Hanwoo, Holstein and mixed beef.