• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.2
• /
• pp.84-90
• /
• 2022

Machine tool state monitoring is a process that automatically detects the states of machine. In the manufacturing process, the efficiency of machining and the quality of the product are affected by the condition of the tool. Wear and broken tools can cause more serious problems in process performance and lower product quality. Therefore, it is necessary to develop a system to prevent tool wear and damage during the process so that the tool can be replaced in a timely manner. This paper proposes a method for diagnosing five tool states using a deep learning-based hierarchical convolutional neural network to change tools at the right time. The one-dimensional acoustic signal generated when the machine cuts the workpiece is converted into a frequency-based power spectral density two-dimensional image and use as an input for a convolutional neural network. The learning model diagnoses five tool states through three hierarchical steps. The proposed method showed high accuracy compared to the conventional method. In addition, it will be able to be utilized in a smart factory fault diagnosis system that can monitor various machine tools through real-time connecting.

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.601-609
• /
• 2023

In this paper, we propose an artificial intelligence-based high-speed fault diagnosis method using an FPGA in the event of a ground fault in a DC system. When applying artificial intelligence algorithms to fault diagnosis, a substantial amount of computation and real-time data processing are required. By employing an FPGA with AI-based high-speed fault diagnosis, the DC breaker can operate more rapidly, thereby reducing the breaking capacity of the DC breaker. therefore, in this paper, an intelligent high-speed diagnosis algorithm was implemented by collecting fault data through fault simulation of a DC system using Matlab/Simulink. Subsequently, the proposed intelligent high-speed fault diagnosis algorithm was applied to the FPGA, and performance verification was conducted.

• Journal of the Korean Society of Radiology
• /
• v.84 no.1
• /
• pp.92-109
• /
• 2023

In patients with thyroid nodules, ultrasonography (US) has been established as a primary diagnostic imaging method and is essential for treatment decision. The Korean Thyroid Imaging Reporting and Data System (K-TIRADS) is a pattern-based, US malignancy risk stratification system that can easily diagnose nodules during real-time ultrasound examinations. The 2021 K-TIRADS clarified the US criteria for nodule classification and revised the size thresholds for nodule biopsy, thereby reducing unnecessary biopsies for benign nodules while maintaining the appropriate sensitivity to detect malignant tumors in patients without feature of high risk thyroid cancer. Thyroid radiology practice has an important clinical role in the diagnosis and non-surgical treatment of patients with thyroid nodules, and should be performed according to standard practice guidelines for proper and effective clinical care.

• Journal of Animal Science and Technology
• /
• v.54 no.4
• /
• pp.247-253
• /
• 2012

Ultrasound measures of back fat thickness (UBF), eye muscle area (UEMA) and marbling score (UMS) and carcass measures of carcass weight (CW), backfat thickness (BF), eye muscle area (EMA) and marbling score (MS) were available on 26,129 Hanwoo steers. Statistically significant differences by regions of the farms location and birth years-seasons for the steers taken ultrasound measures and their carcass measures (p<0.01) were found. Steers in Gyeonggi province showed the highest values in ultrasound measures and carcass traits except in BF compared to steers in the other provinces. Comparing between ultrasound and carcass measures, UBF was thicker in general than BF in all regions except in Daejeon city. UEMA was higher than EMA in all regions except in Gyeonggior in Jeju provinces. Especially, the difference in Jeonnam province between UEMA and EMA was $7cm^2$ while the differences between UMS and MS ranged from 0.9 to 2.26 depending on the regions of steers located. Steers born in spring showed greater ultrasound or carcass values than those born in autumn. However, carcass measures of steers born in autumn were greater than those born in spring, 2009 except MS. The pearson and residual correlations were 0.63 and 0.65 between UBF and BF, 0.31 and 0.32 between UEMA and EMA and 0.56 and 0.56 between UMS and MS, respectively.

• Clinical and Experimental Pediatrics
• /
• v.49 no.7
• /
• pp.737-744
• /
• 2006

Purpose : To assess the usefulness of $^{99m}Tc-DISIDA$ scanning in the early evaluation of neonatal cholestasis and to verify the diagnostic value of this test in the differential diagnosis of biliary atresia. Methods : DISIDA scannings were performed and analyzed in 87 children(58 males and 29 females; age, 18-139 days, mean, 59.1 days) with neonatal cholestasis. Five groups according to the final diagnosis and the results of DISIDA scanning were analyzed by scatter plots using the parameters of age and the level of liver function tests(direct bilirubin, AST, ALT, ALP, GGT). The diagnostic sensitivity, specificity and accuracy of DISIDA scanning in the diagnosis of biliary atresia were compared between a higher bilirubin group and a lower bilirubin group(direct bilirubin level >5 mg/dL vs. <5 mg/dL) decided by the pattern of scatter plots. Results : DISIDA scannings in the diagnosis of biliary atresia were analyzed by high sensitivity(100 percent, 16/16) but lower specificity(70.4 percent, 50/71) and accuracy(75.9 percent, 66/87). False positivity(29.6 percent, 21/71) was higher in patients with a higher direct bilirubin level(42.5 percent for >5 mg/dL vs. 9.7 percent for <5 mg/dL, P<0.01). The age and the level of liver function tests(AST, ALT, ALP, GGT) analyzed by scatter plots revealed neither diagnostic value in predicting final diagnosis nor estimated the accuracy rate of DISIDA scanning in the evaluation of neonatal cholestasis. Conclusion : We suggest that DISIDA scannings should not be routinely used in evaluating neonatal cholestasis with elevated direct bilirubin level(>5 mg/dL), especially if it delays early diagnosis and surgical intervention.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.5
• /
• pp.1239-1244
• /
• 2013

In the field of clinical medicine and research, the analysis of such as protein and DNA at the molecular level and even at the cell level are necessary for disease diagnosis and treatment. In many cases, a real time image of samples is needed for the accurate analysis and manipulation of samples since experimental samples are degenerated with time. In this research, a three-dimensional fluorescence microscope device was developed for taking images of protein and DNA inside a single cell and the server-client based image analysis system was made for an integrated management of the real-time images taken from the microscope device. The system consists of a fluorescent measurement device, the associated software and a client program on smartphone. The developed system allows doctors or experimental managers to receive and look at the real-time experimental images taken from the samples of patients anywhere in the emergency, to analyze results and to instantly diagnose the disease and to transfer the results to the patients. As a result, the system is able to be utilized in the implementation of ubiquitous health as well.

• Journal of agricultural medicine and community health
• /
• v.44 no.4
• /
• pp.165-184
• /
• 2019

Objectives: The purpose of this study was to identify and compare the difference and related factors with general characteristic and health behaviors, a experience of diagnosis and treatment of chronic diseases between rural and urban among elderly in Korea. Methods: We used the data of Community Health Survey 2017 which were collected by the Korean Center for Disease Control and Prevention. The study population comprised 67,835 elderly peopled aged 65 years or older who participated in the survey. The chi-square test, univariate and multivariate logistic regression analysis were used to analyze data. Results: We identified many significant difference of health behaviors, an experience of diagnosis and treatment with chronic diseases between rural and urban. Compared to urban elderly, the odds ratios (ORs) (95% confidence interval) of rural elderly were 1.136 (1.092-1.183) for diagnosis of diabetes, 1.278 (1.278-1.386) for diagnosis of dyslipidemia, 0.940 (0.904-0.977) for diagnosis of arthritis, 0.785(0.736-0.837) for treatment of arthritis, 1.159 (1.116-1.203) for diagnosis of cataracts, and 1.285(1.200-1.375) for treatment of cataracts. In the experience of diagnosis and treatment of chronic diseases, various variables were derived as contributing factors for each disease. Especially, there were statistically significant difference in the experience of diabetes diagnosis, arthritis diagnosis, cataract diagnosis and dyslipidemia except for hypertension diagnosis (p <0.01) between urban and rural elderly. There were statistically significant differences in the experience of treatment for arthritis and cataract (p <0.01), but there was no significant difference in the experience of treatment for hypertension, diabetes, dyslipidemia between urban and rural elderly. Conclusion: Therefore, it would be necessary to implement a strategic health management project for diseases that showed significant experience of chronic diseases with diagnosis and treatment, reflecting the related factors of the elderly chronic diseases among the urban and rural areas.

• Journal of KIISE:Software and Applications
• /
• v.28 no.1
• /
• pp.1-13
• /
• 2001

RMO(Region Monitor Object)는 결함전파나 객체군에 주어진 요구사항의 위반에 의해 발생하는 오류를 처리하는 실시간객체로써 여러 실시간객체의 상태를 감시 및 분석하여 오류를 감지하고, 증상을 진단한 후 알맞은 복구 및 재구성을 실행하다, 이를 위하여 RMO는 응용 실시간객체를 감시할 수 있는 권한을 갖는다. RMO의 권한을 지원해주는 구조는 결함허용 중개자를 이용한다. 결함허용 중개자(FTB 또는 Fault Tolerance Broker)는 RMO가 응용 실시간객체를 감시할 때에 응용의 설계와 응용의 위치에 투명하게 수행될 수 있게 중개자 역할을 한다. 제안하는 감시 구조에는 결함허용 중개자가 응용 실사간객체마다 스터브로 붙는 스터브 방식과 각 노드의 커널에 모듈로 존재하는 커널 모듈 방식이 있다. 본 논문은 스터브 방식에서 RMO가 응용 실시간객체를 감시하는 구조를 제시하고 구현한다. 결함허용 중개자 스터브는 응용 실시간객체와 같은 주소 공간에 존재하면서 응용 실시간객체에서 발생하는 메세지를 가로채고 소속자료에 접근한다. RMO는 결함허용 중개자 스터브가 제공하는 인터페이스를 통해서 응용 실시간객체에 대한 감시 정보를 얻는다. 제안한 감시 구조는 실시간객체 모델인 dRTO(dependable RTO) 모델에 기반하여 설계하였고 실시간 커널인 dKernel 상에서 구현 및 실험하였으나 다른 모델이나 커널에도 적용될 수 있다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.8 no.2
• /
• pp.273-279
• /
• 2007

As the number of mobile telephone users increases, technologies fur increasing quality of services between a mobile terminal and the base station transceiver system become more important than ever. The important criteria of quality of service includes minimum interference of base station, the success rate of network access and portability between different mobile companies. Among many factors, the successful rate of network connection between a mobile terminal and the base station is the most important. In this paper, we introduce an analysis system of mobile terminals using RS-232C communication after considering such environments. This application software simulates the communicational signals between and mobile terminals and the base station and shows the results through the graphs. Using this system, the task about testing communication performance of mobile terminals will be easy since it helps to analyze the status of communication.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.4 no.5
• /
• pp.951-961
• /
• 2000

A diagnosis system that provides early warnings regarding machine malfunction is very important for rolling mill so as to avoid great losses resulting from unexpected shutdown of the production line. But it is very difficult to provide early warnings in rolling mill. Because dynamics of rolling mill is non-linear. This Paper proposes a new method for diagnosis of rolling mill using wavelet transform(W) to solve this problem. Proposed method that measures the vibration signals of rolling mill on-line and analyze it using wavelet to acquire pattern data. And we design a fault-diagnosis system that diagnose a rolling mill using this data. Validity of the new method is asserted by real numerical data experiment.