• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.18 no.9
• /
• pp.29-35
• /
• 2019

The structure of the machinery industry due to the 4th industrial revolution is changing from precision and durability to intelligent and smart machinery through sensing and interconnection(IoT). There is a growing need for research on prognostics and health management(PHM) that can prevent abnormalities in processing machines and accurately predict and diagnose conditions. PHM is a technology that monitors the condition of a mechanical system, diagnoses signs of failure, and predicts the remaining life of the object. In this study, the vibration generated during machining is measured and a classification algorithm for normal and fault signals is developed. Arbitrary fault signal is collected by changing the conditions of un stable supply cutting oil and fixing jig. The signal processing is performed to apply the measured signal to the learning model. The sampling rate is changed for high speed operation and performed machine learning using raw signal without FFT. The fault classification algorithm for 1D convolution neural network composed of 2 convolution layers is developed.

• Journal of dental hygiene science
• /
• v.20 no.4
• /
• pp.206-212
• /
• 2020

Background: A Teachable Machine is a kind of machine learning web-based tool for general persons. In this paper, the feasibility of Google's Teachable Machine (ver. 2.0) was studied in the diagnosis of the tooth-marked tongue. Methods: For machine learning of tooth-marked tongue diagnosis, a total of 1,250 tongue images were used on Kaggle's web site. Ninety percent of the images were used for the training data set, and the remaining 10% were used for the test data set. Using Google's Teachable Machine (ver. 2.0), machine learning was performed using separated images. To optimize the machine learning parameters, I measured the diagnosis accuracies according to the value of epoch, batch size, and learning rate. After hyper-parameter tuning, the ROC (receiver operating characteristic) analysis method determined the sensitivity (true positive rate, TPR) and specificity (false positive rate, FPR) of the machine learning model to diagnose the tooth-marked tongue. Results: To evaluate the usefulness of the Teachable Machine in clinical application, I used 634 tooth-marked tongue images and 491 no-marked tongue images for machine learning. When the epoch, batch size, and learning rate as hyper-parameters were 75, 0.0001, and 128, respectively, the accuracy of the tooth-marked tongue's diagnosis was best. The accuracies for the tooth-marked tongue and the no-marked tongue were 92.1% and 72.6%, respectively. And, the sensitivity (TPR) and specificity (FPR) were 0.92 and 0.28, respectively. Conclusion: These results are more accurate than Li's experimental results calculated with convolution neural network. Google's Teachable Machines show good performance by hyper-parameters tuning in the diagnosis of the tooth-marked tongue. We confirmed that the tool is useful for several clinical applications.

• International Journal of Computer Science & Network Security
• /
• v.22 no.4
• /
• pp.420-426
• /
• 2022

Breast cancer is among the cancers that may be healed as the disease diagnosed at early times before it is distributed through all the areas of the body. The Automatic Analysis of Diagnostic Tests (AAT) is an automated assistance for physicians that can deliver reliable findings to analyze the critically endangered diseases. Deep learning, a family of machine learning methods, has grown at an astonishing pace in recent years. It is used to search and render diagnoses in fields from banking to medicine to machine learning. We attempt to create a deep learning algorithm that can reliably diagnose the breast cancer in the mammogram. We want the algorithm to identify it as cancer, or this image is not cancer, allowing use of a full testing dataset of either strong clinical annotations in training data or the cancer status only, in which a few images of either cancers or noncancer were annotated. Even with this technique, the photographs would be annotated with the condition; an optional portion of the annotated image will then act as the mark. The final stage of the suggested system doesn't need any based labels to be accessible during model training. Furthermore, the results of the review process suggest that deep learning approaches have surpassed the extent of the level of state-of-of-the-the-the-art in tumor identification, feature extraction, and classification. in these three ways, the paper explains why learning algorithms were applied: train the network from scratch, transplanting certain deep learning concepts and constraints into a network, and (another way) reducing the amount of parameters in the trained nets, are two functions that help expand the scope of the networks. Researchers in economically developing countries have applied deep learning imaging devices to cancer detection; on the other hand, cancer chances have gone through the roof in Africa. Convolutional Neural Network (CNN) is a sort of deep learning that can aid you with a variety of other activities, such as speech recognition, image recognition, and classification. To accomplish this goal in this article, we will use CNN to categorize and identify breast cancer photographs from the available databases from the US Centers for Disease Control and Prevention.

• Journal of Advanced Navigation Technology
• /
• v.27 no.1
• /
• pp.111-118
• /
• 2023

For the implementation of a smart factory, it is necessary to collect data by connecting various sensors and devices in the manufacturing environment and to diagnose or predict failures in production facilities through data analysis. In this paper, to predict the residual useful lifetime of milling insert used for machining products in CNC machine, weight k-NN algorithm, Decision Tree, SVR, XGBoost, Random forest, 1D-CNN, and frequency spectrum based on vibration signal are investigated. As the results of the paper, the frequency spectrum does not provide a reliable criterion for an accurate prediction of the residual useful lifetime of an insert. And the weighted k-nearest neighbor algorithm performed best with an MAE of 0.0013, MSE of 0.004, and RMSE of 0.0192. This is an error of 0.001 seconds of the remaining useful lifetime of the insert predicted by the weighted-nearest neighbor algorithm, and it is considered to be a level that can be applied to actual industrial sites.

• International Journal of Computer Science & Network Security
• /
• v.23 no.5
• /
• pp.148-162
• /
• 2023

Classification systems can significantly assist the medical sector by allowing for the precise and quick diagnosis of diseases. As a result, both doctors and patients will save time. A possible way for identifying risk variables is to use machine learning algorithms. Non-surgical technologies, such as machine learning, are trustworthy and effective in categorizing healthy and heart-disease patients, and they save time and effort. The goal of this study is to create a medical intelligent decision support system based on machine learning for the diagnosis of heart disease. We have used a mixed feature creation (MFC) technique to generate new features from the UCI Cleveland Cardiology dataset. We select the most suitable features by using Least Absolute Shrinkage and Selection Operator (LASSO), Recursive Feature Elimination with Random Forest feature selection (RFE-RF) and the best features of both LASSO RFE-RF (BLR) techniques. Cross-validated and grid-search methods are used to optimize the parameters of the estimator used in applying these algorithms. and classifier performance assessment metrics including classification accuracy, specificity, sensitivity, precision, and F1-Score, of each classification model, along with execution time and RMSE the results are presented independently for comparison. Our proposed work finds the best potential outcome across all available prediction models and improves the system's performance, allowing physicians to diagnose heart patients more accurately.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.727-730
• /
• 2023

The operation of electric automatic windows is used in harsh environments, and the energy density decreases as charging and discharging are repeated, and as soundness deteriorates due to damage to the internal separator, the vehicle's mileage decreases and the charging speed slows down, so about 5 to 10 Batteries that have been used for about a year are classified as waste batteries, and for this reason, as the risk of battery fire and explosion increases, it is essential to diagnose batteries and estimate SOH. Estimation of current battery SOH is a very important content, and it evaluates the state of the battery by measuring the time, temperature, and voltage required while repeatedly charging and discharging the battery. There are disadvantages. In this paper, measurement of discharge capacity (C-rate) using a waste battery of a Tesla car in order to predict SOH estimation of a lithium-ion battery. A Support Vector Machine (SVM), one of the machine models, was applied using the data measured from the waste battery.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.6
• /
• pp.1-10
• /
• 2023

The nuclear power plant(NPP)'s Instrumentation and Control(I&C) system periodically conducts integrity checks for the maintenance of self-diagnostic function during normal operation. Additionally, it performs functionality and performance checks during planned preventive maintenance periods. However, there is a need for technological development to diagnose failures and prevent accidents in advance. In this paper, we studied methods for estimating the reliability function by utilizing environmental data and self-diagnostic data of the I&C equipment. To obtain failure data, we assumed probability distributions for component features of the I&C equipment and generated virtual failure data. Using this failure data, we estimated the reliability function using representative artificial intelligence(AI) models used in survival analysis(DeepSurve, DeepHit). And we also estimated the reliability function through the Cox regression model of the traditional semi-parametric method. We confirmed the feasibility through the residual lifetime calculations based on environmental and diagnostic data.

• Journal of Korean Society of Transportation
• /
• v.19 no.4
• /
• pp.7-18
• /
• 2001

This study represents a first attempt in Korea to develop the simultaneous freight supply-demand model which considers the relationship between freight supply and demand. As the existing study was limited in one area, or the supply and the demand was separated and assumed not to affect each other, this study take it into consideration the fact that the demand affects supply and simultaneously vice versa. This approach allows us to diagnose a policy carried on and helps us to make a resonable alternative for the effectiveness of freight transportation system. To find a relationship between them, we use a method of econometrics. a structural equation theory and two stage least-squares(2SLS) estimation technique, to get rid of bias which involves two successive applications of OLS. Based on the domestic freight data, this study consider as explanatory variables a number of population(P), industry(IN), the amount of production of the mining and manufacturing industries(MMI), the rate of the effectiveness of freight capacity(LE) and the distance of an empty carriage operation(VC). This study describes well the simultaneous process of freight supply-demand system in that the increase of VC from the decrease of VC raises the cargo capacity and cargo capacity also augments VC. By the way. it is analyzed that the increment of VC due to the increase of the cargo capacity is larger than the reduction of VC owing to the increase of the quantify of goods. Therefore an alternative policy is needed in a short and long run point of view. That is to say, to promote the effectiveness of the freight transportation system, a short term supply control and a long run logistic infrastructure are urgent based on the restoration of market economy by successive deregulation. So we are able to conclude that gradual deregulation is more desirable to build effective freight market.

• Korean Journal of Health Education and Promotion
• /
• v.18 no.1
• /
• pp.35-47
• /
• 2001

As the complexity of the our environment is further complicated by advancements in industry and increase in vehicle traffic flow, the incidents of injury causing accidents are on the rise. Consequently, there is increasing emphasis on the importance of systematic and continual safety education for injury preventive behaviors. This study investigates safety related problems of elementary school students based on the PRECEDE model, proposed by Green et al.(1980 Green), to comprehensively identify the requirements of school safety education. The identified requirements were used to diagnose the current state of elementary school safety education through the analysis of multidimensional factors. A questionnaire survey was conducted on 594 sixth grade students from randomly selected 4 schools in Seoul to examine their injury preventive behaviors and to determine the educational diagnosis variables that affect it. The duration of the survey was 3 weeks starting from April 12, 1999 to May 8, 1999. A summary of the survey results are presented below; 1. Situations in which accidents have occurred were, in their order of frequency, ‘during play or sports activities within the school grounds’ was most frequent at 59.6％, ‘during play on local streets’ at 49.5％, and ‘traffic accidents’ at 41.6％. 2. Categorization of the injury preventive behavior showed that ‘not playing at high traffic flow locations such as streets and construction sites’ had the higher level of observance, while ‘wearing of helmets and joint protection devices during playing’ was least observed. 3. Considering injury preventive behaviors in relation to educational diagnosis variables indicated, for predisposing factors, lower ‘perception to injury accidents’ (p〈0.001) combined with higher ‘concerns for injury accidents’(p〈0.001), ‘practice of preventive behavior’(p〈0.001), and ‘the level of safety knowledge’(p〈0.001) resulted in significantly higher observance of injury preventive behaviors. For enabling factors, higher ‘perceived level of the school safety education’ (p〈0.001) and ‘availability of safety education resources’(p〈0.01) indicated significantly higher observance of injury preventive behaviors. For the reinforcing factor, frequent exposure to ‘safety education brochure’ (p〈0.01) and ‘audio-visual material for safety education’(p〈0.01) combined with more ‘regional safety education’ (p〈0.01), ‘home safety education’ (p〈0.01), ‘school safety education’(p〈0.001), and, ‘parents’ observance of preventive behaviors' (p〈0.001) showed significantly higher observance of injury preventive behaviors. 4. An analysis of the factors that affect injury preventive behaviors showed that the enabling factor ‘awareness of school safety education’ had the highest correlation with injury preventive behaviors followed by factors, in their order of significance, ‘practice of preventive behavior’, ‘perception to injury accidents’, ‘level of safety knowledge’, ‘parents’ observances of preventive behaviors', and ‘concerns for injury accidents.’

• Atmosphere
• /
• v.29 no.3
• /
• pp.257-267
• /
• 2019

This study is to assess the applicability of the Extreme Forecast Index (EFI) algorithm of the ECMWF seasonal forecast system to the Global Seasonal Forecasting System version 5 (GloSea5), operational seasonal forecast system of the Korea Meteorological Administration (KMA). The EFI is based on the difference between Cumulative Distribution Function (CDF) curves of the model's climate data and the current ensemble forecast distribution, which is essential to diagnose the predictability in the extreme cases. To investigate its applicability, the experiment was conducted during the heat-wave cases (the year of 1994 and 2003) and compared GloSea5 hindcast data based EFI with anomaly data of ERA-Interim. The data also used to determine quantitative estimates of Probability Of Detection (POD), False Alarm Ratio (FAR), and spatial pattern correlation. The results showed that the area of ERA-Interim indicating above 4-degree temperature corresponded to the area of EFI 0.8 and above. POD showed high ratio (0.7 and 0.9, respectively), when ERA-Interim anomaly data were the highest (on Jul. 11, 1994 (> $5^{\circ}C$) and Aug. 8, 2003 (> $7^{\circ}C$), respectively). The spatial pattern showed a high correlation in the range of 0.5~0.9. However, the correlation decreased as the lead time increased. Furthermore, the case of Korea heat wave in 2018 was conducted using GloSea5 forecast data to validate EFI showed successful prediction for two to three weeks lead time. As a result, the EFI forecasts can be used to predict the probability that an extreme weather event of interest might occur. Overall, we expected these results to be available for extreme weather forecasting.