The development of food image detection and recognition model of Korean food for mobile dietary management

BACKGROUND/OBJECTIVES: The aim of this study was to develop Korean food image detection and recognition model for use in mobile devices for accurate estimation of dietary intake. SUBJECTS/METHODS: We collected food images by taking pictures or by searching web images and built an image dataset for use in training a complex recognition model for Korean food. Augmentation techniques were performed in order to increase the dataset size. The dataset for training contained more than 92,000 images categorized into 23 groups of Korean food. All images were down-sampled to a fixed resolution of 150 × 150 and then randomly divided into training and testing groups at a ratio of 3:1, resulting in 69,000 training images and 23,000 test images. We used a Deep Convolutional Neural Network (DCNN) for the complex recognition model and compared the results with those of other networks: AlexNet, GoogLeNet, Very Deep Convolutional Neural Network, VGG and ResNet, for large-scale image recognition. RESULTS: Our complex food recognition model, K-foodNet, had higher test accuracy (91.3%) and faster recognition time (0.4 ms) than those of the other networks. CONCLUSION: The results showed that K-foodNet achieved better performance in detecting and recognizing Korean food compared to other state-of-the-art models.

Health Status of Migrant Workers in Korea / 산업간호학회지

PURPOSE: The purpose of the study is to investigate health problems of migrant workers in Korea. METHODS: The data were collected from the records of the medical history of 2,233 migrant workers who visited the community health clinic in Ansan city, Gyeonggi province from Jan. 2005 to Jan. 2007. The data were analyzed by SPSS. RESULTS: Men accounted for 56.4% of the total who participated in the study. Most of them were Chinese, Russian, and Bangladesh people. The 590 people out of all the migrant workers were employed in manufacturing industries and they comprised the largest percentage. The most commonly complained health problems were musculoskeletal (31.7%), digestive (20.7%), respiratory (12.5%), dermatologic (6.5%), cardiovascular (5.5%) and dental disorder (5.2%). The 1,853 (36.0%) workers were assumed to have hypertensive disorder and 1310 (11.1%) workers ,some diseases due to high cholesterol level. CONCLUSIONS: It is necessary to establish a public health care system to improve health and welfare of migrant workers. Furthermore, the communities need to draw their attention to this matter. And it is also necessary to make accurate research on their health and medical service.

A Study of Depression, Anxiety, Stress Response and Self-care by Gender in Diabetic Patients / 재활간호학회지

PURPOSE: The purpose of this study was to investigate the depression, anxiety, stress response and self-care, to analyze the correlation among depression, anxiety, stress response and self-care by gender, and to determine factors associated with self-care in diabetic patients. METHOD: The subjects of this study were 103 participants with diabetes mellitus. Data were analyzed by chi-square test, t-test, Pearson correlation coefficient and multiple regression analysis by using SAS program. RESULT: Items for self-care evaluation by gender were significant differences in hospital visit, hypoglycemia preparation, proper hygiene, taking a rest, foot injury check, drinking, and smoking. The female patients are more likely to have higher self-care score than the male patients. However, there were no differences in depression, anxiety and stress response by gender. In male patients, there were positive correlations between the degree of depression and stress response, the degree of anxiety and stress response. In female patients, there were positive correlations between the degree of depression and stress response, the degree of anxiety and stress response. In multiple regression analysis, gender and experienced admission is associated with self-care. CONCLUSION: We should consider integrated approaches for psychological problems in the management of diabetic patients.

Study on the Factors Affecting the Sleep Disorder of Hemodialysis Patients / 재활간호학회지

PURPOSE: The purpose of this study is to investigate the degree of sleep disorder and its related factors in hemodialysis patients. METHOD: The subjects of this study consisted of 210 hemodialysis patients. Data were analyzed by descriptive statistics, t-test, ANOVA, pearson's correlation coefficient, or stepwise multiple regression analysis by using SPSS/PC+ program. RESULT: Sleep disorder degree averaged 2.24. Stress of hemodialysis patients averaged 2.52. Depression degree of hemodialysis patients averaged 1.14. There was significant difference in sleep disorder according to age, marriage status, education, family income and help-givers. Sleep disorder was significantly associated with stress and depression. Stress, depression and marriage status explained 31.3% of the variance in the sleep disorder. CONCLUSION: In conclusion, the sleep disorder of hemodialysis patients is the nursing problem. The sleep disorder degree relates with stress, depression. Especially, it is strongly affected by stress among them.