• Journal of the Korean Data and Information Science Society
• /
• v.24 no.1
• /
• pp.13-22
• /
• 2013

Smartphone addiction has become more serious than internet addiction since people can download and run numerous applications with smartphones even without internet connection. However, smartphone addiction is not sufficiently dealt with in current studies. The S-scale method developed by Korea National Information Society Agency involves so many questions that respondents are likely to avoid the diagnosis itself. Moreover, since S-scale is determined by the total score of responded items without taking into account of demographic variables, it is difficult to get an accurate result. Therefore, in this paper, we have extracted important factors from all data, which affect smartphone addiction, including demographic variables. Then we classified the selected items with a neural network. The result of a comparative analysis with backpropagation learning algorithm and multiclass support vector machine shows that learning rate is slightly higher in multiclass SVM. Since multiclass SVM suggested in this paper is highly adaptable to rapid changes of data, we expect that it will lead to a more accurate self-diagnosis of smartphone addiction.

• The Monthly Diabetes
• /
• s.134
• /
• pp.46-47
• /
• 2001

• The Korea Swine Journal
• /
• v.20 no.3 s.223
• /
• pp.146-151
• /
• 1998

• Monthly Duck's Village
• /
• s.209
• /
• pp.18-47
• /
• 2020

• Journal of the Korean Society for Nondestructive Testing
• /
• v.27 no.2
• /
• pp.115-123
• /
• 2007

For investigating self-diagnosis applicability, a method based on monitoring the changes in the electrical resistance of carbon fiber reinforced concrete has been tested. Then after examining change in the value of electrical resistance at each flexural weight-stage of carbon fiber in CFGFRP (carbon fiber and glass fiber reinforcing plastic) with new type rib and carbon sheet for concrete reinforcing, the correlations of electrical resistance and load as a function of strain, deflection were analyzed. As the results, it is clarified that when carbon fiber rod, rib and sheet fracture, the electrical resistance of it increase largely, and specially in case of CFGFRP, afterwards glass fiber tows can be resist the load due to the presence of the hybrid (carbon and glass) reinforced fiber. Therefore, it can be recognized that reinforcing bar and new type rib of CFGFRP and sheet of CF could be applied for self-diagnosis of fracture in reinforced FRP concrete.

• Journal of the Korea Concrete Institute
• /
• v.18 no.3 s.93
• /
• pp.439-445
• /
• 2006

For investigating self-diagnosis applicability, a method based on monitoring the changes in the electrical resistance of hybrid FRP(having electrical property) reinforced concrete has been tested. Then after examining change in the value of electrical resistance of carbon fiber in CFRP(non-hybrid type), CFGFRP and CFAFRP(hybrid type) before and after the occurrence of cracks and fracture in non-hybrid and hybrid FRP reinforced concrete at each flexural weight-stage, the correlations of each factors(the changes in electrical resistance and load as a function of strain, deflection) were analyzed. As the results, it is clarified that when the carbon fiber tows fracture, the electrical resistance of it increase largely, and afterwards hybrid FRP composites can be resist the load due to the presence of the reinforced fiber, for example, glass fiber or aramid fiber tows. Therefore, it can be recognized that hybrid FRP(including carbon fiber) reinforcing bar could be applied for self-diagnosis of fracture in reinforced FRP concrete fracture.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.491-493
• /
• 2017

본 논문에서는 PCM 알고리즘을 적용하여 한국인 고유의 신체적 특성에 맞는 한의학 기반의 한방 자가 진단 시스템을 제안한다. 제안된 방법은 사용자로부터 입력받은 각 증상들에 가중치를 설정한다. 입력받은 증상의 개수가 많아질 경우에는 해당되지 않는 질병이 도출되기 때문에 각 증상 클러스터의 가중치를 낮게 설정하여 적은 입출력 변화에도 전체 결과의 신뢰도에 영향을 주지 않도록 한다. 입력 데이터와 가중치를 기반으로 하여 이미 학습된 질병의 증상과 비교한 후, 유사도가 높은 상위 5개의 질병을 도출한다. 도출된 상위 5개의 질병과 도출된 질병의 원인과 민간요법을 제공한다. 질병과 증상에 대한 데이터베이스는 여러 한의학 서적을 통해 구축한 후, 한의학 전문의의 검증을 거쳐 구현하였다. 제안된 한방 자가 진단 시스템은 진료 기록을 바탕으로 증상을 학습함으로써 기존의 질병 진단 시스템 보다 다양한 증상에 대한 질병 정보를 제공할 수 있는 것으로 확인되었다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2012.05a
• /
• pp.224-225
• /
• 2012

본 연구에서는 기존의 한국정보화진흥원의 인터넷 중독진단 척도인 K-척도와 2012년 새롭게 발표된 성인 인터넷 중독 자가진단 간략형 척도인 KS-A를 비교함으로써 성인 인터넷 중독진단의 현황과 문제점을 확인한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.315-317
• /
• 2015

Due to ageing society, health care has become a major concern. So information service for disease prevention is very important to us. Through this application, therefore, check their status after self-diagnosis such as doctor's diagnosis. With the result, it is an object to develop a function for provision of information to the precautionary.

• The Korean Journal of Blood Transfusion
• /
• v.29 no.3
• /
• pp.320-327
• /
• 2018

A 72-year-old man with general weakness visited the outpatient clinic of the hematology department. The patient had been treated under the diagnosis of autoimmune hemolytic anemia for 2 years. His hemoglobin level at the time of the visit was 6.3 g/dL, and a blood transfusion was requested to treat his anemia. The patient's blood type was A, RhD positive. Antibody screening and identification test showed agglutination in all reagent cells with a positive reaction to autologous red blood cells (RBCs). He had a prior transfusion history with three least incompatible RBCs. The patient returned home after receiving one unit of leukoreduced filtered RBC, which was the least incompatible blood in the crossmatching test. After approximately five hours, however, fever, chills, dyspnea, abdominal pain, and hematuria appeared and the patient returned to the emergency room next day after the transfusion. The $anti-Fy^a$ antibody, which was masked by the autoantibody, was identified after autoadsorption using polyethylene glycol. He was diagnosed with an acute hemolytic transfusion reaction due to $anti-Fy^a$ that had not been detected before the transfusion. In this setting, it is necessary to consider the identification of coexisting alloantibodies in patients with autoantibodies and to become more familiar with the method of autoantibody adsorption.