• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.8
• /
• pp.3748-3759
• /
• 2013

The purpose of this study was to examine the classification accuracies of ML, MAP, and EAP methods under DINA model. For this purpose, this study examined the classification accuracies of the classification methods under the various conditions: the number of attributes, the ability distribution of examinees, and test length. To accomplish this purpose, this study used a simulation method. For the simulation study, data was simulated under the various simulation conditions including the number of attributes (K= 5, 7), the ability distribution of examinees (high, middle, low), and test length (J= 15, 30, 45). Additionally, the percent of agreements between true skill patterns(true ${\alpha}$) and skill patterns estimated by the ML, MAP, and EAP methods were calculated. The summary of the main results of this study is as follows: First, When the number of attributes was 5 and 7, the EAP method showed relatively higher average in the percent of exact agreement than the ML and MAP methods. Second, under the same conditions, as the number of attributes increased, the average percent of exact agreement decreased in ML, MAP, and EAP methods. Third, when the prior distribution of examinees ability was different from low to high under the conditions of the same test length, the EAP method showed relatively higher average in the percent of exact agreement than those of the ML and MAP methods. Fourth, the average percent of exact agreement increased in all methods, ML, MAP, and EAP when the test length increased from 15 to 30 and 45 under the conditions of the same the ability distribution of examinees.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.3
• /
• pp.1-9
• /
• 2021

This research examines deep learning based image recognition models for beef sirloin classification. The sirloin of beef can be classified as the upper sirloin, the lower sirloin, and the ribeye, whereas during the distribution process they are often simply unified into the sirloin region. In this work, for detailed classification of beef sirloin regions we develop a model that can learn image information in a reasonable computation time using the MobileNet algorithm. In addition, to increase the accuracy of the model we introduce data augmentation methods as well, which amplifies the image data collected during the distribution process. This data augmentation enables to consider a larger size of training data set by which the accuracy of the model can be significantly improved. The data generated during the data proliferation process was tested using the MobileNet algorithm, where the test data set was obtained from the distribution processes in the real-world practice. Through the computational experiences we confirm that the accuracy of the suggested model is up to 83%. We expect that the classification model of this study can contribute to providing a more accurate and detailed information exchange between suppliers and consumers during the distribution process of beef sirloin.

• Journal of Korea Multimedia Society
• /
• v.22 no.12
• /
• pp.1491-1499
• /
• 2019

Insufficient sleep time and bad sleep quality causes many illnesses and it's research became more and more important. The most common method for measuring sleep quality is the polysomnography(PSG). The PSG is a test used to diagnose sleep disorders. The most common PSG data is obtained from the examiner, which attaches several sensors on a body and takes sleep overnight. However, most of the sleep stage classification in PSG are low accuracy of the classification. In this paper, we have studied algorithm for sleep level classification based on machine learning which can replace PSG. EEG, EOG, and EMG channel signals are studied and tested by using CNN algorithm. In order to compensate the performance, a mixed model using both CNN and DNN models is designed and tested for performance.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.33 no.2
• /
• pp.1-16
• /
• 2008

The purpose of this paper is to propose a new binary classification method for predicting corporate failure based on genetic algorithm, and to validate its prediction power through empirical analysis. Establishing virtual companies representing bankrupt companies and non-bankrupt ones respectively, the proposed method measures the similarity between the virtual companies and the subject for prediction, and classifies the subject into either bankrupt or non-bankrupt one. The values of the classification variables of the virtual companies and the weights of the variables are determined by the proper model to maximize the hit ratio of training data set using genetic algorithm. In order to test the validity of the proposed method, we compare its prediction accuracy with ones of other existing methods such as multi-discriminant analysis, logistic regression, decision tree, and artificial neural network, and it is shown that the binary classification method we propose in this paper can serve as a premising alternative to the existing methods for bankruptcy prediction.

• Journal of Information Processing Systems
• /
• v.18 no.5
• /
• pp.599-613
• /
• 2022

Non-proliferative diabetic retinopathy is a representative complication of diabetic patients and is known to be a major cause of impaired vision and blindness. There has been ongoing research on automatic detection of diabetic retinopathy, however, there is also a growing need for research on an automatic severity classification system. This study proposes an automatic detection system for pathological symptoms of diabetic retinopathy such as microaneurysms, retinal hemorrhage, and hard exudate by applying the Faster R-CNN technique. An automatic severity classification system was devised by training and testing a Random Forest classifier based on the data obtained through preprocessing of detected features. An experiment of classifying 228 test fundus images with the proposed classification system showed 97.8% accuracy.

• Journal of Korean Society for Geospatial Information Science
• /
• v.19 no.1
• /
• pp.105-113
• /
• 2011

Since existing thematic maps have been made with medium- to low-resolution satellite images, they have several shortcomings including low positional accuracy and low precision of presented thematic information. Digital aerial photo image taken recently can express panchromatic and color bands as well as NIR (Near Infrared) bands which can be used in interpreting forest areas. High resolution images are also available, so it would be possible to conduct precision land cover classification. In this context, this paper implemented object-based land cover classification by using digital aerial photos with 0.12m GSD (Ground Sample Distance) resolution and IKONOS satellite images with 1m GSD resolution, both of which were taken on the same area, and also executed qualitative analysis with ortho images and existing land cover maps to check the possibility of object-based land cover classification using digital aerial photos and to present usability of digital aerial photos. Also, the accuracy of such classification was analyzed by generating TTA(Training and Test Area) masks and also analyzed their accuracy through comparison of classified areas using screen digitizing. The result showed that it was possible to make a land cover map with digital aerial photos, which allows more detailed classification compared to satellite images.

• Proceedings of the Safety Management and Science Conference
• /
• 2011.11a
• /
• pp.551-556
• /
• 2011

This research presents an implementation strategy of Process Capability Index (PCI) according to the types of process characteristics. The types of process feature are classified as four perspectives of variation range, time period, error position, and process stage. The paper examines short-term or long-term PCI, within or between variation, position of precision or accuracy, and inclusion of measurement or calibration stage. Moreover, the study proposes normality test of unilateral PCI.

• Journal of the Korean Society of Radiology
• /
• v.14 no.1
• /
• pp.39-44
• /
• 2020

The purpose of this study was learning about chest X-ray image classification and accuracy research through Deep Learning using big data technology with Convolution Neural Network. Normal 1,583 and Pneumonia 4,289 were used in chest X-ray images. The data were classified as train (88.8%), validation (0.2%) and test (11%). Constructed as Convolution Layer, Max pooling layer size 2×2, Flatten layer, and Image Data Generator. The number of filters, filter size, drop out, epoch, batch size, and loss function values were set when the Convolution layer were 3 and 4 respectively. The test data verification results showed that the predicted accuracy was 94.67% when the number of filters was 64-128-128-128, filter size 3×3, drop out 0.25, epoch 5, batch size 15, and loss function RMSprop was 4. In this study, the classification of chest X-ray Normal and Pneumonia was predictable with high accuracy, and it is believed to be of great help not only to chest X-ray images but also to other medical images.

• The korean journal of orthodontics
• /
• v.52 no.1
• /
• pp.3-19
• /
• 2022

Objective: The purpose of this study was to investigate the accuracy of one-step automated orthodontic diagnosis of skeletodental discrepancies using a convolutional neural network (CNN) and lateral cephalogram images with different qualities from nationwide multi-hospitals. Methods: Among 2,174 lateral cephalograms, 1,993 cephalograms from two hospitals were used for training and internal test sets and 181 cephalograms from eight other hospitals were used for an external test set. They were divided into three classification groups according to anteroposterior skeletal discrepancies (Class I, II, and III), vertical skeletal discrepancies (normodivergent, hypodivergent, and hyperdivergent patterns), and vertical dental discrepancies (normal overbite, deep bite, and open bite) as a gold standard. Pre-trained DenseNet-169 was used as a CNN classifier model. Diagnostic performance was evaluated by receiver operating characteristic (ROC) analysis, t-stochastic neighbor embedding (t-SNE), and gradient-weighted class activation mapping (Grad-CAM). Results: In the ROC analysis, the mean area under the curve and the mean accuracy of all classifications were high with both internal and external test sets (all, > 0.89 and > 0.80). In the t-SNE analysis, our model succeeded in creating good separation between three classification groups. Grad-CAM figures showed differences in the location and size of the focus areas between three classification groups in each diagnosis. Conclusions: Since the accuracy of our model was validated with both internal and external test sets, it shows the possible usefulness of a one-step automated orthodontic diagnosis tool using a CNN model. However, it still needs technical improvement in terms of classifying vertical dental discrepancies.

• Physical Therapy Korea
• /
• v.27 no.2
• /
• pp.140-148
• /
• 2020

Background: Scapular winging (SW) could be caused by tightness or weakness of the periscapular muscles. Although data mining techniques are useful in classifying or predicting risk of musculoskeletal disorder, predictive models for risk of musculoskeletal disorder using the results of clinical test or quantitative data are scarce. Objects: This study aimed to (1) investigate the difference between young women with and without SW, (2) establish a predictive model for presence of SW, and (3) determine the cutoff value of each variable for predicting the risk of SW using the decision tree method. Methods: Fifty young female subjects participated in this study. To classify the presence of SW as the outcome variable, scapular protractor strength, elbow flexor strength, shoulder internal rotation, and whether the scapula is in the dominant or nondominant side were determined. Results: The classification tree selected scapular protractor strength, shoulder internal rotation range of motion, and whether the scapula is in the dominant or nondominant side as predictor variables. The classification tree model correctly classified 78.79% (p = 0.02) of the training data set. The accuracy obtained by the classification tree on the test data set was 82.35% (p = 0.04). Conclusion: The classification tree showed acceptable accuracy (82.35%) and high specificity (95.65%) but low sensitivity (54.55%). Based on the predictive model in this study, we suggested that 20% of body weight in scapular protractor strength is a meaningful cutoff value for presence of SW.