• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.6
• /
• pp.285-292
• /
• 2023

With the wide spread of smart farms and the advancements in IoT technology, it is easy to obtain additional data in addition to crop images. Consequently, deep learning-based crop disease diagnosis research utilizing multimodal data has become important. This study proposes a crop disease diagnosis method using multimodal supervised contrastive learning by expanding upon the multimodal self-supervised learning. RandAugment method was used to augment crop image and time series of environment data. These augmented data passed through encoder and projection head for each modality, yielding low-dimensional features. Subsequently, the proposed multimodal supervised contrastive loss helped features from the same class get closer while pushing apart those from different classes. Following this, the pretrained model was fine-tuned for crop disease diagnosis. The visualization of t-SNE result and comparative assessments of crop disease diagnosis performance substantiate that the proposed method has superior performance than multimodal self-supervised learning.

• Journal of information and communication convergence engineering
• /
• v.15 no.2
• /
• pp.85-90
• /
• 2017

Expert systems for health diagnosis are only for medical experts who have deep knowledge in the field but we need a self-checking pre-diagnosis system for preventive public health monitoring. Korea Traditional Medicine is popular in use among Korean public but there exist few available health information systems on the internet. A computerized self-checking diagnosis system is proposed to reduce the social cost by monitoring health status with simple symptom checking procedures especially for Korea Traditional Medicine users. Based on the national reports for disease/symptoms of Korea Traditional Medicine, we build a reliable database and devise an intelligent inference engine using fuzzy c-means clustering. The implemented system gives five most probable diseases a user might have with respect to symptoms given by the user. Inference results are verified by Korea Traditional Medicine doctors as sufficiently accurate and easy to use.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.11
• /
• pp.2150-2157
• /
• 2007

In this paper, we have proposed a self disease diagnosis system for ordinary persons to help the decision of access methods to a specialized medical management, and for medical specialities to discover new diseases and their symptoms easily, using verification of an individual#s health status by a series of processes performed by oneself. In the proposed self disease diagnosis system, illness is decided by 60 kinds of diseases selected using the report called #Diseases that Koreans take seriously# published by Ministry of Health & Welfare and medical contents called #Engel Pharm#, and also using 161 representative symptoms for the 60 kinds of diseases. An individual#s health information is extracted by diagnosis of one#s health status by a clustering of the 60 kinds of diseases using enhanced ART2 algorithm and input vectors from the results of questions for symptoms of each disease.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.328-330
• /
• 2004

In this paper, ECG based cardiac disease diagnosis models are developed. Conventionally, ECG monitoring equipments can only measure and store ECG signals and they always require medical doctor's diagnosis actions which are not desirable for continuous ambulatory monitoring and diagnosis healthcare systems. In this paper, two kinds of neural based self cardiac disease diagnosis engines are developed and tested for four kinds of diseases, sinus bradycardia, sinus tachycardia, left bundle branch block and right bundle branch block. For diagnosis engines, error backpropagation neural network (BP) and probabilistic neural network (PNN) were applied. Five signal features including heart rate, QRS interval, PR interval, QT interval, and T wave types were selected for diagnosis characteristics. To show the validity of proposed diagnosis engine, MIT-BIH database were used to test. Test results showed that BP based diagnosis engine has 71% of diagnosis accuracy which is superior to accuracy of PNN based diagnosis engine. However, PNN based diagnosis engine showed superior diagnosis accuracy for complex-disease diagnoses than BP based diagnosis engine.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.5
• /
• pp.11-18
• /
• 2014

In this paper, we propose a self-diagnosis system that is based on the ART2 algorithm in order to extract more detailed disease information by fuzzy reasoning method especially when the boundary of perceived symptoms are not clearly classified into disease categories. With that modification from previous version of the self health pre-diagnosis system, the proposed one is verified as more effective by field experts' evaluation as an intelligent assistant tool for public users before they consult with medical experts.

• Journal of Korean Public Health Nursing
• /
• v.14 no.2
• /
• pp.342-354
• /
• 2000

This study was conducted to identify the characteristics of activities of daily living(ADU) and its influencing factors in patients with chronic arthritis. The data were obtained from 104 patients with chronic arthritis in one university hospital from May to August. 2000. For analysing data. SAS program was used for t-test. ANOVA, Schefte test. Pearson correlation. and stepwise multiple regression. The results were as follows: 1. The variables which influenced self-efficacy were duration of disease. number of painful joint, quality of sleep and alcohol drinking. 2. The variables which influenced fatigue were diagnosis and number of painful joint. 3. The variables which influenced ADL were age. duration of disease. diagnosis. number of painful joint. number of exercise and alcohol drinking. 4. ADL was positive correlation with self-efficacy and negative correlation with fatigue. And self-efficacy was negative correlation with fatigue. 5. The predictors to explain ADL were self-efficacy. number of painful joint. lupus. duration of disease and religion. These predictors explained $66.01\%$ of the activites of daily living. According to these findings. the most significant influencing factor of ADL was self-efficacy. therefore the development of nursing intervention for enhancing self-efficacy would be needed. Also. it is suggested that an exercise program should be recommended as one of useful and appropriate nursing intervention for reducing fatigue and increasing ADL.

• Pediatric Gastroenterology, Hepatology & Nutrition
• /
• v.24 no.1
• /
• pp.109-117
• /
• 2021

Purpose: Ménétrier disease (MD) was first described in 1888, and 50 cases have been reported until now. We aimed to discuss the etiology, diagnostics, and management of MD in children. Methods: We searched for case reports published from 2014 till 2019 in English using PubMed. Articles were selected using subject headings and key words of interest to the topic. Interesting references of the included articles were also included. Results: The pathophysiology of MD is still uncertain. However, overexpression of transforming growth factor alpha with transformation of the gastric mucosa has been observed, which may be mediated by genetics and provoked by an infectious trigger. Clinically, MD is diagnosed by abdominal pain, vomiting, anorexia, and edema secondary to hypoalbuminemia. A gastroscopy with biopsy is the gold standard for the diagnosis of MD. In children, the disease is self-limiting and only requires supportive treatment. In general, children have a good prognosis and recover spontaneously within a few weeks. Conclusion: Few pediatric cases of MD have been described in recent years, and with all different etiology. Endoscopy with biopsy remains the golden standard for the diagnosis of MD, and in children, the disease is self-limiting.

• Clinical and Experimental Pediatrics
• /
• v.49 no.8
• /
• pp.830-832
• /
• 2006

Immune thrombocytopenic purpura(ITP) is an autoimmune disease characterized by increased peripheral platelet destruction due to antibody to platelet, which results in thrombocytopenia and cutaneous or mucosal bleeding. Bleeding generally occurs when platelet counts fall to less than $20,000/{\mu}L$. Children affected with ITP are usually healthy prior to the onset of the disease and typically present suddenly after a viral infection or insidiously with progressive petechiae, bruising, or purpura. In most cases the disease is self-limited; approximately 80% of children recover by 6 months after diagnosis, with or without treatment. Children with thrombocytopenia persisting for more than 6 months are defined as having chronic ITP. Clinical manifestations, diagnosis, laboratory findings, differential diagnosis and various treatment modalities are reviewed.

• Journal of Pharmacopuncture
• /
• v.14 no.2
• /
• pp.75-80
• /
• 2011

Objectives & Methods: This research may accounts for Self Targeting Therapy (STT) which is a peculiar operation of Mountain Ginseng Pharmacopuncture. The objectives include analysis of its mechanism and reporting of clinical cases. Results: 1. STT of Mountain Ginseng Pharmacopuncture refers to the function of curing and making a diagnosis of the disease by oneself. 2. The mechanism of STT is to pursue the latent illness and make the remedial action by oneself. In this process, the symptom of latent disease is outwardly expressed. 3. The most popular symptom expressed is manifestation of pecular sensation along the specific meridians. Then followed headache, dizziness, powerless and etc. Diverse symptoms can be expressed by a patient. 4. If the revealed symptoms are carefully observed, the cause of the disease or the patient state can be diagnosed easily. Conclusion: The mechanism of STT of Mountain Ginseng Pharmacopuncture can be a great asset in clinical trials. Other studies on STT of Mountain Ginseng Pharmacopuncture should be followed in the future.

• The Korean Journal of Rehabilitation Nursing
• /
• v.7 no.2
• /
• pp.127-139
• /
• 2004

Purpose: This study was to investigate the degree of body image, self esteem and quality of life, to identify general and disease of characteristics on influencing this factors with the intention of providing basal data for developing nursing intervention to promote body image, self esteem and quality of life. Method: Subjects of this study were 91 grown-up congenital heart patients over 18 years in 2 tertiary hospitals. The data on body image, self esteem and quality of life were collected through questionnaire from March to April 2004. The data were analyzed by descriptive statistics, t-test, Pearson's correlation, ANOVA and tukey test using SAS for Windows 8.1 program. Result: 1) The mean scores of body image, self esteem and quality of life were 63.01, 25.29 and 496.79. 2) Body image was correlated with age(p=.0239), educational level(p=.0182), diagnosis(p=.0066), number of operation(p=.0148), cyanosis(p<.0001), complication(p=.0096) and NYHA level(p=.0378). 3) Self esteem was correlated with education level(p=.0026), economic level(p=.0240), number of operation(p=.0113) and cyanosis (p=.0006). 4) Quality of life was correlated with age(p=.0432) and diagnosis(p=.0020), number of operation (p=.0063), duration of last operation(p=.0225), cyanosis(p<.0001), complication(p=.0090) and NYHA level(p<.0001). 5) There was significantly positive relationship between body image, self esteem and quality of life. Subjects with more positive body image had higher self esteem(r=.7897, p<.05) and subjects with higher self esteem had higher quality of life(r=.6091, p<.05).