• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 한국해양정보통신학회 2007년도 춘계종합학술대회
• /
• pp.887-890
• /
• 2007

Today, many universities are progressing research of ubiquitous campus for discrimination and the part universities constructed ubiquitous campus with telecommunication company. It is applied with campus service. But, Currently ubiquitous campus environment has two weakness. First one is Non-practicality cause of Not enough supplying related device for using service to student. And the other one is that can't support Student Oriented Service. In this paper, We studied on model that tan analysis ubiquitous utilization of student and can be Student Oriented Service. To resolve this, we realized practical service via analysis of User IT Infra.

• Journal of the military operations research society of Korea
• /
• 제37권1호
• /
• pp.1-9
• /
• 2011

The contractor management is one of the important factors for the modem defense acquisition program. The occurrence of unlawful company causes the reason in which defense acquisition program is unable to be reasonably fulfilled and setback to the deployment of defense weapon system. In this paper, we propose the Artificial Neural Network to develop a prediction model for the discrimination of unlawful company in defense procurement. The data which are used in analysis, are obtained targeting domestic small & medium manufacture enterprises. It is expected that our model can be used to improve the program management capability for defense acquisition and contribute to the establishment of efficient procurement procedure through entry of the reliable domestic manufacturer.

• BMB Reports
• /
• 제41권1호
• /
• pp.23-28
• /
• 2008

The altered amino acid (AA) levels as neurotransmitter closely correlate to neurodegenerative conditions including Alzheimer's disease (AD). Target profiling analysis of nineteen AAs in brain cortex samples from three Tg2576 mice as AD model and three littermate mice as control model was achieved as their N(O,S)-ethoxycarbonyl/tert-butyldimethylsilyl derivatives by gas chromatography. Subsequently, star pattern recognition analysis was performed on the brain AA levels of AD mice after normalization to the corresponding control median values. As compared to control mice, $\gamma$-aminobutyric acid among ten AAs found in brain samples was significantly reduced (P < 0.01) while leucine was significantly elevated (P < 0.02) in AD mice. The normalized AA levels of the three AD mice were transformed into distorted star patterns which was different from the decagonal shape of control median. The present method allowed visual discrimination of the three AD mice from the controls based on the ten normalized AA levels.

• Korean journal of food and cookery science
• /
• 제20권3호
• /
• pp.247-255
• /
• 2004

The foodservice industry is changing more and more from on-site foodservice management to contract foodservice management. However there are differences according to the level of management and operation of contract foodservice management company (CFMC). The necessity of certification on CFMC is increasing to enable fair discrimination of CFMC among most clients that want to contract with CFMC. This study was performed to identify the foodservice operation evaluation model's criteria items for certifying CFMC. The analysis research methods included literature review, content analysis, individual interview, Delphi technique, and brain storming. First, the following infrastructure items were prepared in the contractor's viewpoint: procurement, transparency of operation, menu development and operation system, nutrition service system, professional employee education, sanitation andsafety management system, customer satisfaction system, facility system, management information system (MIS), business and economics. Second, the evaluation criteria required by the contractor on the client's view point was similar to school foodservice, hospitalfoodservice, and business andindustry foodservice except extraordinary items of field. Third, evaluation criteria and detail categories and items were identified such as financial focus, customer focus, process focus, human focus, and renewal and development by grafting on intellectual capital evaluation methodology for CFMC.

• International journal of advanced smart convergence
• /
• 제9권2호
• /
• pp.20-27
• /
• 2020

Sound event detection in real-world environments suffers from the interference of non-stationary and time-varying noise. This paper presents an adaptive noise reduction method for sound event detection based on non-negative matrix factorization (NMF). In this paper, we proposed a deep learning model that integrates Convolution Neural Network (CNN) with Non-Negative Matrix Factorization (NMF). To improve the separation quality of the NMF, it includes noise update technique that learns and adapts the characteristics of the current noise in real time. The noise update technique analyzes the sparsity and activity of the noise bias at the present time and decides the update training based on the noise candidate group obtained every frame in the previous noise reduction stage. Noise bias ranks selected as candidates for update training are updated in real time with discrimination NMF training. This NMF was applied to CNN and Hidden Markov Model(HMM) to achieve improvement for performance of sound event detection. Since CNN has a more obvious performance improvement effect, it can be widely used in sound source based CNN algorithm.

• Journal of the Korean Society of Physical Medicine
• /
• 제13권2호
• /
• pp.21-31
• /
• 2018

PURPOSE: This study examined the differences between male and female workers by investigating the various factors that affected the workers' abilities to return to work according to the International Classification of Functioning standards. METHODS: We analyzed the personal factor, environmental factor, work performance and participation factor related to ICF according to worker's gender. For this purpose data from the third Worker's Compensation Insurance panel survey conducted by the Korea Workers' Compensation & Welfare Service were analyzed. In order to verify the research model, we used frequency analysis, cross analysis to compare the differences between male and female workers according to personal, environmental, work performance, and participation factors and hierarchical regression analysis to identify significant factors affecting job performance. RESULTS: The results, indicate that the level of education, license status, working period, socioeconomic status and employment type of female workers were lower than those of male workers. Factors that have the greatest influence on job performance are grade of disability, status of disability, economic activity status, and instrumental activities of daily living (p<.05). CONCLUSION: It is necessary to provide socially stable employment support and social policy support without discrimination to allow disabled female workers to return to work and maintain their jobs and to study factors influencing job performance further.

• ETRI Journal
• /
• 제36권4호
• /
• pp.662-672
• /
• 2014

Human action recognition is used in areas such as surveillance, entertainment, and healthcare. This paper proposes a system to recognize both single and continuous human actions from monocular video sequences, based on 3D human modeling and cyclic hidden Markov models (CHMMs). First, for each frame in a monocular video sequence, the 3D coordinates of joints belonging to a human object, through actions of multiple cycles, are extracted using 3D human modeling techniques. The 3D coordinates are then converted into a set of geometrical relational features (GRFs) for dimensionality reduction and discrimination increase. For further dimensionality reduction, k-means clustering is applied to the GRFs to generate clustered feature vectors. These vectors are used to train CHMMs separately for different types of actions, based on the Baum-Welch re-estimation algorithm. For recognition of continuous actions that are concatenated from several distinct types of actions, a designed graphical model is used to systematically concatenate different separately trained CHMMs. The experimental results show the effective performance of our proposed system in both single and continuous action recognition problems.

• Journal of KIISE:Software and Applications
• /
• 제30권9호
• /
• pp.867-875
• /
• 2003

This paper concerns continuous density HMM topology optimization. There have been several researches for HMM topology optimization. BIC (Bayesian Information Criterion) is one of the well known optimization criteria, which assumes statistically well behaved homogeneous model parameters. HMMs, however, are composed of several different kind of parameters to accommodate complex topology, thus BIC's assumption does not hold true for HMMs. Even though BIC reduced the total number of parameters of HMMs, it could not improve the recognition rates. In this paper, we proposed two new model selection criteria, HBIC (HMM-oriented BIC) and BIC_Anti. The former is proposed to improve BIC by estimating model priors separately. The latter is to combine BIC and anti-likelihood to accelerate discrimination power of HMMs. We performed some comparative research on couple of model selection criteria for online handwriting data recognition. We got better recognition results with fewer number of parameters.

• Journal of Preventive Medicine and Public Health
• /
• 제32권4호
• /
• pp.538-545
• /
• 1999

Objective : To compare the predictive power of International Classification of Diseases 10th Edition(ICD-10) based International Classification of Diseases based Injury Severity Score(ICISS) with Trauma and Injury Severity Score(TRISS) and International Classification of Diseases 9th Edition Clinical Modification(ICD-9CM) based ICISS in the injury severity measure. Methods : ICD-10 version of Survival Risk Ratios(SRRs) was derived from 47,750 trauma patients from 35 Emergency Centers for 1 year. The predictive power of TRISS, the ICD-9CM based ICISS and ICD-10 based ICISS were compared in a group of 367 severely injured patients admitted to two university hospitals. The predictive power was compared by using the measures of discrimination(disparity, sensitivity, specificity, misclassification rates, and ROC curve analysis) and calibration(Hosmer-Lemeshow goodness-of-fit statistics), all calculated by logistic regression procedure. Results : ICD-10 based ICISS showed a lower performance than TRISS and ICD-9CM based ICISS. When age and Revised Trauma Score(RTS) were incorporated into the survival probability model, however, ICD-10 based ICISS full model showed a similar predictive power compared with TRISS and ICD-9CM based ICISS full model. ICD-10 based ICISS had some disadvantages in predicting outcomes among patients with intracranial injuries. However, such weakness was largely compensated by incorporating age and RTS in the model. Conclusions : The ICISS methodology can be extended to ICD-10 horizon as a standard injury severity measure in the place of TRISS, especially when age and RTS were incorporated in the model. In patients with intracranial injuries, the predictive power of ICD-10 based ICISS was relatively low because of differences in the classifying system between ICD-10 and ICD-9CM.

• Journal of Korean Society of Forest Science
• /
• 제90권3호
• /
• pp.324-330
• /
• 2001

This study was carried out to develop prediction model for fill slope failure of forest road in igneous rock area using fuzzy theory which is non-linear model. The results were summarized as follows. The importance weight of factors on fill slope failure was ranked in the order of fill slope length, fill slope gradient, soil type, aspect, road position and longitudinal slope form. The degree of potential slope failure was high mainly under the such conditions as fill slope length greater than 8m, fill slope gradients steeper than $40^{\circ}$, constituent material with weathered rock, aspect of NE and road on ridge position. The optimal prediction model was developed with 0.15 of optimal coefficient(c) and 3.1165 of ${\lambda}$-value when fuzzy integral value of slope failure possibility is more than 0.5. And the discriminant accuracy was 86.8%, which shows the high availability for discrimination.