• ETRI Journal
• /
• v.33 no.6
• /
• pp.871-879
• /
• 2011

Because a wide variety of multimedia services are provided through personal wireless communication devices, the demand for efficient bandwidth utilization becomes stronger. This demand naturally results in the introduction of the variable bitrate speech coding concept. One exemplary work is the selectable mode vocoder (SMV) that supports speech/music classification. However, because it has severe limitations in its classification performance, a couple of works to improve speech/music classification by introducing support vector machines (SVMs) have been proposed. While these approaches significantly improved classification accuracy, they did not consider correlations commonly found in speech and music frames. In this paper, we propose a novel and orthogonal approach to improve the speech/music classification of SMV codec by adaptively tuning SVMs based on interframe correlations. According to the experimental results, the proposed algorithm yields improved results in classifying speech and music within the SMV framework.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2005.07a
• /
• pp.566-567
• /
• 2005

Until now variable pattern classification methods have been introduced. So, variable methods in PD source classification were applied. NN(neural network) the most used scheme as a PD(partial discharge) source classification. But in recent year another method were developed. These methods is present superior to NN in the field of image and signal process function of classification. In this paper, it is show classification result in PD source using three methods; that is, BP(back-propagation), ANFIS(adaptive neuro-fuzzy inference system), PCA-LDA(principle component analysis-linear discriminant analysis).

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.12
• /
• pp.11-19
• /
• 2013

This paper proposes an algorithm using vibration signals and texture analysis for mechanical fault diagnosis of an induction motor. We analyze characteristics of contrast and pattern of an image converted from vibration signal and extract three texture features using gray-level co-occurrence model(GLCM). Then, the extracted features are used as inputs of a multi-level support vector machine(MLSVM) which utilizes the radial basis function(RBF) kernel function to classify each fault type. In addition, we evaluate the classification performance with varying the parameter from 0.3 to 1.0 for the RBF kernel function of MLSVM, and the proposed algorithm achieved 100% classification accuracy with the parameter of the RBF from 0.3 to 1.0. Moreover, the proposed algorithm achieved about 98% classification accuracy with 15dB and 20dB noise inserted vibration signals.

• Asian Spine Journal
• /
• v.12 no.6
• /
• pp.981-986
• /
• 2018

Study Design: Retrospective case series. Purpose: Cauda equina syndrome (CES) is associated with etiologies such as lumbar disc herniation (LDH) and lumbar canal stenosis (LCS). CES has a prevalence of 2% among patients with LDH and exhibits variable outcomes, even with early surgery. Few studies have explored the factors influencing the prognosis in terms of bladder function. Therefore, we aimed to assess the factors contributing to bladder recovery and propose a simplified bladder recovery classification. Overview of Literature: Few reports have described the prognostic clinical factors for bladder recovery following CES. Moreover, limited data are available regarding a meaningful bladder recovery status classification useful in clinical settings. Methods: A single-center retrospective study was conducted (April 2012 to April 2015). Patients with CES secondary to LDH or LCS were included. The retrieved data were evaluated for variables such as demographics, symptom duration, neurological symptoms, bladder symptoms, and surgery duration. The variable bladder function outcome during discharge and at follow-up was recorded. All subjects were followed up for at least 2 years. A simplified bladder recovery classification was proposed. Statistical analyses were performed to study the correlation between patient variables and bladder function outcome. Results: Overall, 39 patients were included in the study. Majority of the subjects were males (79.8%) with an average age of 44.4 years. CES secondary to LDH was most commonly seen (89.7%). Perianal sensation (PAS) showed a significant correlation with neurological recovery. In the absence of PAS, bladder function did not recover. Voluntary anal contraction (VAC) was affected in all study subjects. Conclusions: Intactness of PAS was the only significant prognostic variable. Decreased or absent VAC was the most sensitive diagnostic marker of CES. We also proposed a simplified bladder recovery classification for recovery prognosis.

• The Journal of the Korea Contents Association
• /
• v.9 no.5
• /
• pp.182-188
• /
• 2009

The purpose of this study was to investigate the effect of self-care training based on ICF(International Classification of functioning, Disability and Health) on functional independence in the young children with spastic cerebral palsy. Total of 43 young children(male=25, female=18; age range from 36month to 72month) with spastic cerebral palsy, classified at GMFCS(Gross Motor Function Classification System) levels III-IV. Total of 32sessions of a self-care training (eating, grooming, bathing, toileting) were given 4 times a week for 30minutes from August 1th to September 30th of 2008. Changes in the functional independence after the training obtained by Wee-FIM(Functional Independence Measure for Children). Results were as follows: Functional independence was significantly increased after the training. As a result, a self-care training should be applied as an effective intervention to improve the functional independence in the young children with spastic cerebral palsy.

• Journal of Korean Society of Archives and Records Management
• /
• v.13 no.2
• /
• pp.179-199
• /
• 2013

This study is analyzed by examining the records management systems that are built to use comfortably and manage the records of universities efficiently. This paper analyzed the current status of the records in Chonnam National University (CNU), unit task, function, and organization. As a result, CNU has 127 sections that treat 1,625 unit tasks. The unit task involved in education accounts for 85.91%. The problem is that unit tasks are not organized unequally. It can seem to include some problems in classification and analysis of work when unit tasks are even, more or less, in a particular area. Functional classification in universities are also unequally organized. In universities, functional classification in the field of administration is detailed, while functional classification in the field of research is small in quantity. A more efficient records management will be done if work and function about organization are formed appropriately.

• The Journal of Korean Physical Therapy
• /
• v.20 no.1
• /
• pp.49-56
• /
• 2008

Purpose: Lack of a valid prognosis of gross motor development in children with cerebral palsy (CP) and the absence of longitudinal data on which to base an opinion in Korea have made it difficult to plan treatment and counsel prognosis issues accurately. The purposes of this study were to examine whether the Gross Motor Function Classification System (GMFCS) is valuable to prognostication about gross motor progress in children with CP in Korea. Methods: Medical records of 61 patients were retrospectively reviewed that visited outpatient department and were diagnosed as CP. Various information was surveyed including CP type, visual acuity, cognitive function, motor acquisition age, ambulatory status, development curves of Gross Motor Function Measure (GMFM) according to each of the 5 level of GMFCS. All of them were compared with other studies. Also the gross motor development curves and the maximum GMFM score derived from this study were compared with the Palisano's report and the Rosenbaum's report. Results: Based on a total of 494 GMFM assessments provided by this study, the 5 distinct motor development curves and the maximum GMFM score were created. These observations is corresponding with the Palisano's and the Rosenbaum`s Development curves. Conclusion: The 5 distinct motor development curves (GMFCS) that were created by Palisano's and Rosenbaum's study is useful in Korea, providing parents and clinicians with a means to plan interventions and to judge progress over time.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.6
• /
• pp.107-111
• /
• 2010

The damage of tire by damage material classification method is researched as used ultrasonic wave signal to occur at a tire during vehicle driving. Auto-correlation function after having passed through an envelope detecting preprocess is used for detecting periodicity because of occurring periodic ultrasonic waves signal with tire revolution. One revolution cycle time of a damaged tire and period that calculated auto-correlation function appeared equally in experiment. The result that can classification whether or not there was a tire damage is established.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.6
• /
• pp.799-803
• /
• 2007

In this paper, we propose a new fuzzy membership function for FSVM(Fuzzy Support Vector Machines). We apply a fuzzy membership to each input point of SVM and reformulate SVM into fuzzy SVM (FSVM) such that different input points can make different contributions to the learning of decision surface. The proposed method enhances the SVM in reducing the effect of outliers and noises in data points. This paper compares classification and estimated performance of SVM, FSVM(1), and FSVM(2) model that are getting into the spotlight in time series prediction.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.1
• /
• pp.18-20
• /
• 2017

In this paper, we propose a new classification method to complement a $na{\ddot{i}}ve$ Bayesian classifier. This classifier assumes data distribution to be Gaussian, finds the discriminant function, and derives the decision curve. However, this method does not investigate finding the decision curve in much detail, and there are some minor problems that arise in finding an accurate discriminant function. Our findings also show that this method could produce errors when finding the decision curve. The aim of this study has therefore been to investigate existing problems and suggest a more reliable classification method. To do this, we utilize the gradient to find the decision curve. We then compare/analyze our algorithm with the $na{\ddot{i}}ve$ Bayesian method. Performance evaluation indicates that the average accuracy of our classification method is about 10% higher than $na{\ddot{i}}ve$ Bayes.