• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.1
• /
• pp.57-64
• /
• 2024

In the industrial field, robots are used to increase productivity by replacing labors with dangerous, difficult, and hard tasks. However, failures of individual industrial robots in the entire production process may cause product defects or malfunctions, and may cause dangerous disasters in the case of manufacturing parts used in automobiles and aircrafts. Although requirements for early diagnosis of industrial robot failures are steadily increasing, there are many limitations in early detection. This paper introduces methods for diagnosing robot failures using sound-based data and deep learning. This paper also analyzes, compares, and evaluates the performance of failure diagnosis using various deep learning technologies. Furthermore, in order to improve the performance of the fault diagnosis system using deep learning technology, we propose a method to increase the accuracy of fault diagnosis based on an inference window. When adopting the inference window of deep learning, the accuracy of the failure diagnosis was increased up to 94%.

• Journal of the Korea Convergence Society
• /
• v.8 no.12
• /
• pp.49-53
• /
• 2017

Breast cancer is the sccond most female cancer patient in the entire female cancer patient, and has emerged as the highest contributor to female cancer deaths. If breast cancer id detected early, the cure rate is 92 percent. However, if early detection fails, breast cancer has a very high rate of metastasis. The transition from cancer to cancer has become more successful as cancer progresses. Early diagnosis of cancer is an important factor in improving quality of life. Examples of breast cancer include Mammograph, ultrasound, and Momotome. Mommography is not only painful for the examiner, but also for easy access to breast cancer exam inations. In this paper, breast cancer diagnosis data mammograph data was used. In addition, the Neural Network were classified for early diagnosis of breast cancer early using NEWFM. After learning of data using NEWFM, the accuracy of the breast cancer data classification was 84.4391%.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.7
• /
• pp.3003-3007
• /
• 2015

Objective: To explore the application of multiplex nested methylated specific polymerase chain reaction (PCR) in the early diagnosis of epithelial ovarian carcinoma (EOC). Materials and Methods: Serum and fresh tissue samples were collected from 114 EOC patients. RUNX3, TFPI2 and OPCML served as target genes. Methylation levels of tissues were assessed by multiplex nested methylated specific PCR, the results being compared with those for carcinoma antigen 125 (CA125). Results: The serum free deoxyribose nucleic acid (DNA) methylation spectrum of EOC patients was completely contained in the DNA spectrum of cancer tissues, providing an accurate reflection of tumor DNA methylation conditions. Serum levels of CA125 and free DNA methylation in the EOC group were evidently higher than those in benign lesion and control groups (p<0.05). Patients with early EOC had markedly lower serum CA125 than those with advanced EOC (p<0.05), but there was no significant difference in free DNA methylation (p>0.05). The sensitivity, specificity and positive predicative value (PPV) of multiplex nested methylated specific PCR were significantly higher for detection of all patients and those with early EOC than those for CA125 (p<0.05). In the detection of patients with advanced EOC, the PPV of CA125 detection was obviously lower than that of multiplex nested methylated specific PCR (p>0.05), but there was no significant difference in sensitivity (p>0.05). Conclusions: Serum free DNA methylation can be used as a biological marker for EOC and multiplex nested methylated specific PCR should be considered for early diagnosis since it can accurately determine tumor methylation conditions.

• Physical Therapy Korea
• /
• v.6 no.1
• /
• pp.47-61
• /
• 1999

The purpose of this study was to investigate factors influencing on the early treatment of children with developmental disability. Data was collected from 102 mothers of children with developmental disability who were treated at 4 rehabilitation facilities in Kyunggi-Do and Kangwon-Do. The results were as follows: 1) Of a total of 102, 63 children began to receive rehabilitation therapy during the period 0~12 months (early treatment group), 38 children after 1 year of age (delayed early treatment group). 2) There were statistically significant differences between the early treatment group and delayed early treatment group for prematurity, low birth weight, the time to discover developmental abnormalities, the time of first diagnosis, and first treatment (p<0.05). 3) There were no statistically significant differences in the two groups for level of education, economic status, risk factors (except prematurity and birth weight), home care, family's cooperation and commuting time (p>0.05). Based on this study, the important factors for early treatment were early detection, early diagnosis and constant follow-up for high-risk babies.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.4
• /
• pp.873-878
• /
• 2004

An expert system for stroke diagnosis was designed in this study. The causes of stroke in the central nervous systems are very diverse, symptoms may not appear in the early stage, so diagnosis ran be difficult. Also, doctors who treats patients with stroke must have expert knowledge for the quick and correct impending diagnosis. Therefore, an expert system for assisting the impending diagnosis of stroke has needed to be developed. In addition, the diagnosis system can be used as an simulator for medical students who study neurology. In this study, and diagnosis expert system was developed. It serves a pathological data bus provided by an interface. An inference engine makes an impending diagnosis of stroke possible. We implemented the system using Windows2000 Server, IIS5.0 and ASP.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2001.11a
• /
• pp.139-144
• /
• 2001

Insulation aging diagnosis system provides early warning regarding electrical equipment defect. Early warning is very important in that it can avoid great losses resulting from unexpected shutdown of the production line. Since relations of insulation aging and partial discharge dynamics are non-linear, it is very difficult to provide early warning in an electrical equipment. In this paper, we propose the design method of insulation aging diagnosis system that use a magnetic wave and acoustic signal to diagnoses an electrical equipment. Proposed system measures the partial discharge on-line from DAS(Data Acquisition System) and acquires 2D patterns from analyzing it. For filtering the noise contained in sensor signals we used ICA algorithms. Using this data, design of the neuro-fuzzy model that diagnoses an electrical equipment is investigated. Validity of the new method is asserted by numerical simulation.

• Clinical and Experimental Pediatrics
• /
• v.61 no.4
• /
• pp.101-107
• /
• 2018

Recent advances in genetics have determined that a number of epilepsy syndromes that occur in the first year of life are associated with genetic etiologies. These syndromes range from benign familial epilepsy syndromes to early-onset epileptic encephalopathies that lead to poor prognoses and severe psychomotor retardation. An early genetic diagnosis can save time and overall cost by reducing the amount of time and resources expended to reach a diagnosis. Furthermore, a genetic diagnosis can provide accurate prognostic information and, in certain cases, enable targeted therapy. Here, several early infantile epilepsy syndromes with strong genetic associations are briefly reviewed, and their genotype-phenotype correlations are summarized. Because the clinical presentations of these disorders frequently overlap and have heterogeneous genetic causes, next-generation sequencing (NGS)-based gene panel testing represents a more powerful diagnostic tool than single gene testing. As genetic information accumulates, genetic testing will likely play an increasingly important role in diagnosing pediatric epilepsy. However, the efforts of clinicians to classify phenotypes in nondiagnosed patients and improve their ability to interpret genetic variants remain important in the NGS era.

• Proceedings of the ESK Conference
• /
• 1996.04a
• /
• pp.160-167
• /
• 1996

The early diagnosis has an very important role in curing dementia. But there was not an effective method to diagnose it until now. In this paper we analyzed the EEG in Alzheimer's disease and normal control groups to compare by nonlinear parameter such as the largest Lyapunov exponent $L_{1}$. We found that patients with Alzheimer's disease have significantly lower$L_{1}$ than normal groups. And we propose the nonlinear analysis of EEG as a useful tool for the early diagnosis of Alzheimer's disease.

• The Journal of the Korean dental association
• /
• v.18 no.1 s.130
• /
• pp.59-64
• /
• 1980

In modern orthodontics, the most emphasized problems are, as Bjork said in his literature, how to control entirely the growth and development and conservation of teeth: how to diminish the damages of orthodontic treament to the teeth. As a solution of these problems Bjork introduced the method of early orthodontic diagnosis. The study of occlusion of primary dentition has two main purposes: 1. To observe the change of occlusion as age increases. 2. To predict the change of occlusion to make early diagnosis possible. From early nineteeth century, Bogue (1908) started the study of occlusion of primary dentition, followed by Bonnar (1956-1960), Kisling (1973-1976), Ravn 1975), Foster (1969), Moyer (1969), etc. These studies have been used in the diagnosis of preventive orthodontics. In Korea, the study of occlusion of primary dentition was started in 1977. The second study was reported in 1978. Through the third report in 1979, author will introduce sagittal relation in the canine and incisor regions of Korean children.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.19 no.39
• /
• pp.129-142
• /
• 1996

The early diagnosis has an very important role in curing dementia. But there was not the effective method to diagnose it until now. In this paper we analyzed the EEG of Alzheimer's disease patients and normal groups by nonlinear methods. In the analysis we calculated the correlation dimensions $D_2$ and the largest Lyapunov exponent $L_1$. We found that patients with Alzheimer's disease have significantly lower $D_2$ and TEX>$L_1$ than normal groups. It means that brains injured by Alzheimer's disease have electrophysiological inactive elements and have decreased chaotic behaviour. We propose the nonlinear analysis of the EEG as a useful tool for the early diagnosis of Alzheimer's disease.