• The Journal of the Acoustical Society of Korea
• /
• v.14 no.2
• /
• pp.101-112
• /
• 1995

In order to construct a feature map-based phoneme classification system for speech recognition, two procedures are usually required. One is clustering and the other is labeling. In this paper, we present a phoneme classification system based on the Kohonen's Self-Organizing Feature Map (SOFM) for clusterer and labeler. It is known that the SOFM performs self-organizing process by which optimal local topographical mapping of the signal space and yields a reasonably high accuracy in recognition tasks. Consequently, SOFM can effectively be applied to the recognition of phonemes. Besides to improve the performance of the phoneme classification system, we propose the learning algorithm combined with the classical K-mans clustering algorithm in fine-tuning stage. In order to evaluate the performance of the proposed phoneme classification algorithm, we first use totaly 43 phonemes which construct six intra-class feature maps for six different phoneme classes. From the speaker-dependent phoneme classification tests using these six feature maps, we obtain recognition rate of $87.2\%$ and confirm that the proposed algorithm is an efficient method for improvement of recognition performance and convergence speed.

• Korean Journal of Construction Engineering and Management
• /
• v.22 no.5
• /
• pp.73-85
• /
• 2021

This study proposes an efficient management direction for Korean construction accident cases through a deep learning-based text data classification model. A deep learning model was developed, which categorizes five categories of construction accidents: fall, electric shock, flying object, collapse, and narrowness, which are representative accident types of KOSHA. After initial model tests, the classification accuracy of fall disasters was relatively high, while other types were classified as fall disasters. Through these results, it was analyzed that 1) specific accident-causing behavior, 2) similar sentence structure, and 3) complex accidents corresponding to multiple types affect the results. Two accuracy improvement experiments were then conducted: 1) reclassification, 2) elimination. As a result, the classification performance improved with 185.7% when eliminating complex accidents. Through this, the multicollinearity of complex accidents, including the contents of multiple accident types, was resolved. In conclusion, this study suggests the necessity to independently manage complex accidents while preparing a system to describe the situation of future accidents in detail.

• Korean Journal of Radiology
• /
• v.25 no.1
• /
• pp.103-112
• /
• 2024

Objective: To investigate the association of ultrasound (US) features of follicular thyroid carcinoma (FTC) with tumor invasiveness and prognosis based on the World Health Organization (WHO) classification and telomerase reverse transcriptase (TERT) promoter mutations. Materials and Methods: This retrospective study included 54 surgically confirmed FTC patients with US images and TERT promoter mutations (41 females and 13 males; median age [interquartile range], 40 years [30-51 years]). The WHO classification consisted of minimally invasive (MI), encapsulated angioinvasive (EA), and widely invasive (WI) FTCs. Alternative classifications included Group 1 (MI-FTC and EA-FTC with wild type TERT), Group 2 (WI-FTC with wild type TERT), and Group 3 (EA-FTC and WI-FTC with mutant TERT). Each nodule was categorized according to the US patterns of the Korean Thyroid Imaging Reporting and Data System (K-TIRADS) and American College of Radiology-TIRADS (ACR-TIRADS). The Jonckheere-Terpstra and Cochran-Armitage tests were used for statistical analysis. Results: Among 54 patients, 29 (53.7%) had MI-FTC, 16 (29.6%) had EA-FTC, and nine (16.7%) had WI-FTC. In both the classifications, lobulation, irregular margins, and final assessment categories showed significant differences (all Ps ≤ 0.04). Furthermore, the incidences of lobulation, irregular margin, and high suspicion category tended to increase with increasing tumor invasiveness and worse prognosis (all Ps for trend ≤ 0.006). In the WHO groups, hypoechogenicity differed significantly among the groups (P = 0.01) and tended to increase in proportion as tumor invasiveness increased (P for trend = 0.02). In the alternative group, punctate echogenic foci were associated with prognosis (P = 0.03, P for trend = 0.03). Conclusion: Increasing tumor invasiveness and worsening prognosis in FTC based on the WHO classification and TERT promoter mutation results were positively correlated with US features that indicate malignant probability according to both K-TIRADS and ACR-TIRADS.

• Economic and Environmental Geology
• /
• v.37 no.3
• /
• pp.355-364
• /
• 2004

A study on the weathering grade classification has been performed for granite and granite gneiss in Korea. The qualitative classification criteria of weathering were reviewed and then modified with field studies for the weathered rock masses. The thin section observations and XRD analyses for the different weathering grades rock samples showed the petrographical and petrophysical difference with respect to the weathering : the proportion of weathering-resistant minerals suck at quartz and orthoclase has a tendency to increase with the development of weathering, but that of weathering-sensible minerals such as anorthite and biotite is decreased. The ranges of physical and mechanical rock properties for different weathering grades were obtained from the laboratory rock tests and field tests for the studied rocks. And then, along with $RDI_{sq}$(Fookes et al., 1988), the weathering index $I_{a}$, (Woo, 2003) has been developed in this study to demarcate the weathering grade. Those two indices rely mainly on the water absorption ratio of rock and on the different rock strength. The range of these weathering indices have been determined with the physical and mechanical rock properties that can be obtained from simple field or laboratory tests in 4 grades $I_{a}$＞ 7 for F, 3.5 ＜ $I_{a}$ ＜ 10 for SW, 1.0 $I_{a}$＜ 6.0 for MW and $I_{a}$＜ 2.5 for HW. Consequently, the weathering index could be utilized to classify quantitatively the rock weathering grade, especially for the studied granites and the granite gneiss in Korea.

• Journal of Korean Society of Steel Construction
• /
• v.10 no.2 s.35
• /
• pp.211-219
• /
• 1998

The objective of this study is to investigate the structural behavior of Concrete-Filled Tubular Column H-Beam End-Plate Connections with Penetrated HT-Bolts under monotonic load. Simple bending tests are carried out with 5 kinds of specimens including beam specimen. The parameters of these tests are the thickness (T=22, 26. 30mm) of End-plates and the diameter (M=20, 22mm) of bolts. From the tests, the increasing values of yielding strength and initial stiffness of each specimen were gained as the thickness of End-plates and diameter of bolts are increasing. And the application of Bjorhovde et al and Eurocode 3 classification method by non-dimensional moment-rotation curves to the connections showed that all of them are included in rigid region as far as initial stiffness is concerned and all of them are also rigid as far as ultimate strength.

• Korean Journal of Veterinary Research
• /
• v.53 no.1
• /
• pp.19-23
• /
• 2013

This study was carried out to evaluate the diagnosis of acute clinical mastitis (ACM) which was based on the vital signs and complete blood count (CBC) tests in dairy cows. Twenty eight dairy cows diagnosed with ACM, were selected for the study between Jan 2003 and July 2006 in the National Institute of Animal Science. Based on their vital signs (rectal temperature, depression, rumen contraction and, dehydration status), ACM was divided into three different classes; mild, moderate and severe forms. In addition, ACM cows were subjected to CBC tests for further diagnosis of ACM. Of the 27 dairy cows diagnosed with ACM, 3 cows were determined to have a mild form, while moderate and sever forms were each observed in twelve cows. Among of them, 4 cows died, 5 cows were culled and 18 cows were recovered. In the mild form, all haematological parameters were comparable with normal values. However, leukopenia, due to neutropenia and lymphocytopenia, appeared characteristically in the moderate and severe forms. Using the observation of vital signs in conjunction with CBC tests, the diagnosis of ACM is more accurate, and is helpful in making decisions of whether treatment or culling of dairy cows infected with ACM is most appropriate.

• Journal of Pharmaceutical Investigation
• /
• v.34 no.3
• /
• pp.229-254
• /
• 2004

The objective of this study was to scrutinize the rationale of SUPAC-MR and its application in processing postapproval changes to modified release solid oral dosage forms. The types of postapproval changes that were primarily covered with SUPAC-MR included variations in the components and composition, the site of manufacturing, batch size, manufacturing equipment, and manufacturing process. SUPAC-MR defined levels of postapproval changes that the industry might make. Classification of such categories was based on the likelihood of risk occurrence and potential impact of changes upon the safety and efficacy of approved drug products. In most cases, the changes could be classified into 3 levels. It described what chemistry, manufacturing, and control tests should be conducted for each change level. The important tests specified in SUPAC-MR were batch release, stability, in vitro dissolution, and in vivo bioequivalence tests. It then suggested what type of a filing report should be submitted to the FDA for each change level. In general, level 1 changes could be reported in an annual report, whereas level 2 and/or 3 changes could be submitted in changes-being-effected or prior approval supplements. It could be understood that the purpose of SUPAC-MR was to maintain the safety and quality of approved modified release solid oral dosage forms undergoing certain changes. At the same time, it contributed to providing a less burdensome regulatory process with the manufacturers when they wanted to make postapproval changes. European regulatory agencies also implemented SUPAC-like regulations in handling such changes to drug products. Therefore, in this study a recommendation was made for KFDA and the Korean industry to evaluate thoroughly the usefulness of these guidances and regulations in dealing with postapproval changes to modified release solid oral dosage forms.

• Journal of Oral Medicine and Pain
• /
• v.43 no.2
• /
• pp.41-51
• /
• 2018

Purpose: The aim of this study was to evaluate the possibility of utilizing blood tests for the diagnosis of temporomandibular disorders (TMDs) by investigating the hematologic characteristics of TMD patients according to the main source and level of TMD pain and analyzing their interrelationship. Methods: Clinical examination following the research diagnostic criteria for TMD and hematological and psychological evaluations were conducted in 357 TMD patients. Patients were divided into groups according to the main source of pain (myogenous, arthrogenous, and combined pain) and the degree of pain according to the graded chronic pain scale (GCPS). Hematological differences among the groups were statistically analyzed. Results: The C-reactive protein (CRP) level was significantly higher in the arthrogenous pain group compared to the combined pain group (p=0.032). There was no significant difference according to the GCPS classification. There were significant correlations between some of the TMD pain indices and the hematologic indices, and also between the psychological indices and the hematologic indices. Conclusions: This study suggests the possibility of applying blood tests to the diagnosis, treatment and prevention of TMD. Further research should be conducted focusing on the role of CRP in TMD pain with more refined methodology and a longitudinal study design.

• Journal of Families and Better Life
• /
• v.20 no.6
• /
• pp.151-162
• /
• 2002

The instability in the current financial market caused consumers a lot of difficulties in their financial decision making. The purpose of this study is to classify the changes in household portfolios during the economic crisis under IMF-trusteeship (IMF Crisis hereafter), and to examine the characteristics of the households according to the types of household portfolio changes. The data were taken from 1996 and 1999 Korean Household Panel Studies, and 1,293 households were selected for the final analysis. Methods of analysis included frequencies, percentages, Chi-square tests, F-tests, and t-tests. Major findings are as follows: 1. In the midst of the financial market changes during the period of the IMF crisis, consumers tended to manage their household portfolio differently according to their household characteristics. 2. The changes of household portfolio can be classified into two different types: the changed type (44.4%) and the unchanged type(55.6%). There are significant differences in the level of wealth, family life cycle stage, housing tenure, and the household head's job, between the changed type and the unchanged type. The family members of the unchanged type are more likely to be older and relatively wealthy compared with the families in the changed type. 3. The changes of household portfolio can be further classified into six different types: the unchanged-liquidity type (21%), the unchanged-multiplication type (24.6%), the unchanged-insurance type (9.8%), the changed-to-liquidity type (13.9%), the changed-to-multiplication type (13.0%), and the changed-to-insurance type (17.5%). There are significant differences in income level, wealth level, family life cycle stage, housing tenure, and the job of household head among the six types of changes.

• International Journal of Computer Science & Network Security
• /
• v.21 no.9
• /
• pp.19-30
• /
• 2021

Diabetes Mellitus (DM) is one of common chronic diseases leading to severe health complications that may cause death. The disease influences individuals, community, and the government due to the continuous monitoring, lifelong commitment, and the cost of treatment. The World Health Organization (WHO) considers Saudi Arabia as one of the top 10 countries in diabetes prevalence across the world. Since most of the medical services are provided by the government, the cost of the treatment in terms of hospitals and clinical visits and lab tests represents a real burden due to the large scale of the disease. The ability to predict the diabetic status of a patient without the laboratory tests by performing screening based on some personal features can lessen the health and economic burden caused by diabetes alone. The goal of this paper is to investigate the prediction of diabetic and prediabetic patients by considering factors other than the laboratory tests, as required by physicians in general. With the data obtained from local hospitals, medical records were processed to obtain a dataset that classified patients into three classes: diabetic, prediabetic, and non-diabetic. After applying three machine learning algorithms, we established good performance for accuracy, precision, and recall of the models on the dataset. Further analysis was performed on the data to identify important non-laboratory variables related to the patients for diabetes classification. The importance of five variables (gender, physical activity level, hypertension, BMI, and age) from the person's basic health data were investigated to find their contribution to the state of a patient being diabetic, prediabetic or normal. Our analysis presented great agreement with the risk factors of diabetes and prediabetes stated by the American Diabetes Association (ADA) and other health institutions worldwide. We conclude that by performing class-specific analysis of the disease, important factors specific to Saudi population can be identified, whose management can result in controlling the disease. We also provide some recommendations learnt from this research.