http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Design and Implementation of a Body Fat Classification Model using Human Body Size Data
Taejun Lee,Hakseong Kim,Hoekyung Jung The Korea Institute of Information and Commucation 2023 Journal of information and communication convergen Vol.21 No.2
Recently, as various examples of machine learning have been applied in the healthcare field, deep learning technology has been applied to various tasks, such as electrocardiogram examination and body composition analysis using wearable devices such as smart watches. To utilize deep learning, securing data is the most important procedure, where human intervention, such as data classification, is required. In this study, we propose a model that uses a clustering algorithm, namely, the K-means clustering, to label body fat according to gender and age considering body size aspects, such as chest circumference and waist circumference, and classifies body fat into five groups from high risk to low risk using a convolutional neural network (CNN). As a result of model validation, accuracy, precision, and recall results of more than 95% were obtained. Thus, rational decision making can be made in the field of healthcare or obesity analysis using the proposed method.
Malignant Granular Cell Tumor of the Upper Thoracic Spine: A Case Report
Taejun Hwang,Sang Joon Park,Jungsoo Kim,Yongjae Yoo,Jee Youn Moon 대한통증연구학회 2023 International Journal of Pain Vol.14 No.2
Granular cell tumors (GCTs) are uncommon soft tissue tumors usually originating from the nerve sheath, affecting any body part but rarely the spinal region. Only 2% of GCTs are malignant, which is associated with a very poor prognosis. They occur most frequently in middle-aged females. Clinical symptoms of GCTs from the spine origin depend on their location. Radical resection is the treatment of choice for GCTs, followed by radiotherapy and chemotherapy if it turns out malignancy or complete resection is impossible. Herewith, we report a case of malignant GCTs of the upper thoracic spine with pleural metastasis. Although the initial upper extremity MRI showed a small thoracic paravertebral mass, it was missed, resulting in a delayed diagnosis of malignancy. From the case, we can learn that vigilant suspicion to rule out any malignancy is essential if aggravation of symptoms is observed even under active pain management.
Taejun Yoo,Byeongjin Ye,Jung-Il Kim,Siwoo Park 대한직업환경의학회 2016 대한직업환경의학회지 Vol.28 No.-
Objective: The present study analyzed relationship of workplace violence and perpetrators of violence on sleep disturbance among wage workers in Korea. Methods: The present study used data from the 4th Korean Working Conditions Survey (KWCS) of 2014 in selecting a total of 25,138wage workers as the study population, which excluded those who failed or refused to respond to questions required for the present study. The workplace violence experience group included people who satisfied at least one of six relevant criteria (verbal abuse, unwanted sexual attention, threatening or humiliating behavior, physical violence, bullying/harassment, and sexual harassment) and the group was divided according to whether the perpetrator of violence was a client or colleague. Presence of sleep disturbance was determined based on subjective symptoms felt within the past 12 months by each individual. A multiple logistic regression analysis was performed to identify the effects on sleep distance according to general, occupational, and psychosocial characteristics, as well as the types of workplace violence and perpetrators of violence. Results: Workplace violence was found as a factor affecting sleep disturbance (OR = 3.773, 95 % CI = 3.058–4.655), and with respect to perpetrators of violence, complaint of sleep disturbance symptoms was higher when the perpetrator was a colleague or boss (OR = 5.688, 95 % CI 4.189–7.723) than a client (OR = 2.992, 95 % CI 2.301–3.890). Conclusion: Workplace violence had an effect on occurrence of sleep disturbance and when the perpetrators of violence was a boss or colleague at work, the risk for symptoms such as sleep disturbance increased, which indicated the need for appropriate intervention from a workplace healthcare perspective, including preventive education of workplace violence among employees.
Population Aging in Korea: Macroeconomic Impacts and Financing National Health Insurance
( Taejun Lim ) 한국경제학회 2016 The Korean Economic Review Vol.32 No.2
We provided a quantitative model to analyze the impacts of population aging on the Korean economy and National Health Insurance (NHI). We found that the NHI premium rate for workers should be increased by 3.7 percentage points between 2015 and 2060 to finance the augmented burden of the NHI program as a result of the aging population. Within the same period, the aggregate labor would be decreased by 30.9 percent despite the increase in employment ratio by 2.2 percentage points while the aggregate output was decreased by 18.3 percent. To make distinction between the population aging effect and the effect from the increased NHI premium rate, we conducted an experiment where the NHI premium rate for workers was held constant at the level of 2015 along the transition path. The experiment showed that the distortion effect of the increased NHI premium rate would be only minor compared to the direct effect of population aging.