• The Journal of the Acoustical Society of Korea
• /
• v.22 no.3
• /
• pp.175-181
• /
• 2003

Because a word of Korean digits is a syllable and deeply coarticulatied in connected digits, some recognition models based on demisyllables have been proposed by researchers. However, they could not show an excellent recognition results yet. This paper proposes a recognition model based on extended and context-dependent demisyllables, such as a tri-demisyllable like a tri-phone, for the Korean 4-connected digits recognition. For experiments, we use a toolkit of HTK 3.0 for building this model of continuous HMMs using training Korean connected digits from SiTEC database and for recognizing unknown ones. The results show that the recognition rate is 92% and this model has an ability to improve the recognition performance of Korean connected digits.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.7
• /
• pp.19-26
• /
• 2018

This paper presents a structuring process of unstructured social network service (SNS) messages on rail services. We crawl messages about rail services posted on SNS and extract keywords indicating date and time, rail operating company, station name, direction, and rail service types from each message. Among them, the rail service types are classified by machine learning according to predefined rail service types, and the rest are extracted by regular expressions. Words are converted into vector representations using Word2Vec and a conventional Convolutional Neural Network (CNN) is used for training and classification. For performance measurement, our experimental results show a comparison with a TF-IDF and Support Vector Machine (SVM) approach. This structured information in the database and can be easily used for services for railway users.

• International Journal of Concrete Structures and Materials
• /
• v.1 no.1
• /
• pp.63-73
• /
• 2007

Optimum multi-layered feed-forward neural network (NN) models using a resilient back-propagation algorithm and early stopping technique are built to predict the shear capacity of reinforced concrete deep and slender beams. The input layer neurons represent geometrical and material properties of reinforced concrete beams and the output layer produces the beam shear capacity. Training, validation and testing of the developed neural network have been achieved using 50%, 25%, and 25%, respectively, of a comprehensive database compiled from 631 deep and 549 slender beam specimens. The predictions obtained from the developed neural network models are in much better agreement with test results than those determined from shear provisions of different codes, such as KBCS, ACI 318-05, and EC2. The mean and standard deviation of the ratio between predicted using the neural network models and measured shear capacities are 1.02 and 0.18, respectively, for deep beams, and 1.04 and 0.17, respectively, for slender beams. In addition, the influence of different parameters on the shear capacity of reinforced concrete beams predicted by the developed neural network shows consistent agreement with those experimentally observed.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.14 no.1
• /
• pp.71-76
• /
• 2008

The main ports of Korean south sea are exposed to intensive danger as 58.1% of total vessel in Korea waters and 62.9% of total dangerous cargo ships. Therefore, it is required to establish fundamental database to solve numerous issues at the main ports cf the south sea as studying amount of the vessel traffic and their flows into the main ports, and evaluating degree of danger by traffics environmental stress model as analyzing relationships among degree of danger, maritime accident, and number of vessel arriving or departing in the main ports.

• Korean Journal of Adult Nursing
• /
• v.29 no.1
• /
• pp.51-62
• /
• 2017

Purpose: The purpose of this study was to provide data about the risk factors related to falls among elderly patients with dementia using meta-analysis. Methods: Key words used for search through electronic database (CINAHL, PubMed, Ovid-MEDLINE, RISS, KISS, DBPIA, National Assembly Library) included 'dementia', 'Alzheimer', 'fall'. Twenty studies met the inclusion criteria for the meta-analysis and 'R' version 3.2.2 was used to analyze the correlated effect size. Results: Study results showed that risk factors related to falls were identified as the demographic (age, gender, education), dementia-related (disease duration, cognition), physical (body mass index, walking, balance, activity of daily living, use of walking aids, number of medications including psychotropic drugs, musculoskeletal problems, parkinsonism, comorbidity), psychological (neuropsychiatric symptom, depression), environmental (Physical environment), and fall-related (fall history, high risk group of fall) factors. The effect size of risk factors such as high risk group of fall (r=.35), use of walking aids (r=.33), depression (r=.31), psychotropic drugs (r=.27), Musculoskeletal problems (r=.25) were higher than the other risk factors. Conclusion: Based on the findings of this study, strategies to improve elderly patient's depression, intensive care for high risk group of fall, and adequate training with walking aids are needed for prevention of falls in elderly patients with dementia.

• Journal of IKEEE
• /
• v.17 no.3
• /
• pp.254-259
• /
• 2013

The choice of labeled data in semi-supervised learning algorithm can result in effects on the performance of the resultant classifier. In order to select labeled data required for the training of a semi-supervised learning algorithm, VCNN(Vector Centroid Neural Network) is proposed in this paper. The proposed selection method of label data is evaluated on UCI dataset and caltech dataset. Experiments and results show that the proposed selection method outperforms conventional methods in terms of classification accuracy and minimum error rate.

• Journal of Korean Academy of Nursing Administration
• /
• v.18 no.2
• /
• pp.202-212
• /
• 2012

Purpose: As Evidence-Based Practice (EBP) has increasingly been proven as a means of cost-effective and higher-quality healthcare, its successful implementing are challenging. This study done to identify EBP beliefs, knowledge and performance among nurses experienced as a preceptor. Method: A descriptive cross-sectional survey was conducted with a convenience sample of 249 preceptor nurses working in 9 general hospitals in Korea. Reliable and valid questionnaires (EBP beliefs scale, Evidence Based Practice Questionnaire, Research-related activities) were used and the data were analyzed using SPSS win 17.0. Result: Perceived beliefs on EBP were relatively positive (mean score 3.57 out of 5), and the level of knowledge was moderate (4.21 out of 7). However, performance of EBP was low (3.82 out of 7). Regularity in reading research journals and searching evidences using core web-database were rarely conducted. Statistically significant correlations were found between beliefs, knowledge and performance of EBP (all p<.05). Conclusions: This result indicates that education and training programs to facilitate EBP performance are needed among preceptor nurses.

• The KIPS Transactions:PartD
• /
• v.12D no.1 s.97
• /
• pp.159-164
• /
• 2005

In a computing environment connected pan-based computers and a server by Internet, This paper describes a language learning system evaluating the quality of a handwriting string. For the purpose of the system, this paper explains how to retrieve reference data from a database, how to evaluate the quality of a handwriting string using global and local features. The Proposed system can evaluate the qualify of a handwriting string as well as a handwriting character. The qualify can be computed in the case of different language between reference and input. Therefore, we expect that the system is very useful not only for training on handwriting but also learning a language.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.384-386
• /
• 1998

The use of hand gesture provides an attractive alternative to cumbersome interface devices for human-computer interaction(HCI). Many methods hand gesture recognition using visual analysis have been proposed such as syntactical analysis, neural network(NN), Hidden Markov Model(HMM) and so on. In our research, a HMMs is proposed for alphabetical hand gesture recognition. In the preprocessing stage, the proposed approach consists of three different procedures for hand localization, hand tracking and gesture spotting. The hand location procedure detects the candidated regions on the basis of skin-color and motion in an image by using a color histogram matching and time-varying edge difference techniques. The hand tracking algorithm finds the centroid of a moving hand region, connect those centroids, and thus, produces a trajectory. The spotting a feature database, the proposed approach use the mesh feature code for codebook of HMM. In our experiments, 1300 alphabetical and 1300 untrained gestures are used for training and testing, respectively. Those experimental results demonstrate that the proposed approach yields a higher and satisfying recognition rate for the images with different sizes, shapes and skew angles.

• Journal of KIISE:Software and Applications
• /
• v.34 no.5
• /
• pp.455-464
• /
• 2007

The construction of a fingerprint database is important to evaluate the performance of an automatic fingerprint recognition system. Due to the cost of collecting fingerprints, there are only few benchmark databases available. Since it is hard to evaluate how robust the system is in various environments with the databases, this paper proposes a novel method that generates fingerprint images automatically from only a few training samples by using the genetic algorithm. Fingerprints generated by the proposed method include similar characteristics of those collected from the corresponding real environment. The proposed method has been verified by comparing with real fingerprint images, showing the usefulness of the method.