• The Journal of the Acoustical Society of Korea
• /
• v.13 no.3
• /
• pp.25-32
• /
• 1994

This paper presents the Korean digit recognition method under noise environment using the spectral mapping training based on static supervised adaptation algorithm. In the presented recognition method, as a result of spectral mapping from one space of noisy speech spectrum to another space of speech spectrum without noise, spectral distortion of noisy speech is improved, and the recognition rate is higher than that of the conventional method using VQ (vector quatization) and DTW(dynamic time warping) without noise processing, and even when SNR level is 0dB, the recognition rate is 10 times of that using the conventional method. It has been confirmed that the spectral mapping training has an ability to improve the recognition performance for speech in noise environment.

• ETRI Journal
• /
• v.17 no.1
• /
• pp.11-22
• /
• 1995

This paper proposes a modified error function to improve the error back-propagation (EBP) algorithm for multi-Layer perceptrons (MLPs) which suffers from slow learning speed. It can also suppress over-specialization for training patterns that occurs in an algorithm based on a cross-entropy cost function which markedly reduces learning time. In the similar way as the cross-entropy function, our new function accelerates the learning speed of the EBP algorithm by allowing the output node of the MLP to generate a strong error signal when the output node is far from the desired value. Moreover, it prevents the overspecialization of learning for training patterns by letting the output node, whose value is close to the desired value, generate a weak error signal. In a simulation study to classify handwritten digits in the CEDAR [1] database, the proposed method attained 100% correct classification for the training patterns after only 50 sweeps of learning, while the original EBP attained only 98.8% after 500 sweeps. Also, our method shows mean-squared error of 0.627 for the test patterns, which is superior to the error 0.667 in the cross-entropy method. These results demonstrate that our new method excels others in learning speed as well as in generalization.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.15 no.1
• /
• pp.36-45
• /
• 2012

In this thesis, we propose an integrated simulation method of virtual tank simulators and an entity-based constructive simulation model for small unit tactical training. To do this, we first identify requirements for virtual-constructive integrated simulation in a synthetic environment. We then propose a virtual and constructive interoperation method where individual combat entities of virtual-constructive models are interacting with each others. We develop a method of aggregating individual combat entities into a larger combat unit and disaggregating an unit into entities from time to time. We also present a way of sharing synthetic environment information between the models. Finally, we suggest that for more effective interoperability, virtual and constructive models should be developed by using common combat object models. The proposed interoperation method can be extended to further live-virtual-constructive models.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.12
• /
• pp.29-38
• /
• 2019

A path prediction method using lifelog requires a large amount of training data for accurate path prediction, and the path prediction performance is degraded when the training data is insufficient. The lack of training data can be solved using data of other users having similar user movement patterns. Therefore, this paper proposes a path prediction algorithm based on user similarity. The proposed algorithm learns the path in a triple grid pattern and measures the similarity between users using the cosine similarity technique. Then, it predicts the path with applying measured similarity to the learned model. For the evaluation, we measure and compare the path prediction accuracy of proposed method with the existing algorithms. As a result, the proposed method has 66.6% accuracy, and it is evaluated that its accuracy is 1.8% higher than other methods.

• Journal of Korea Multimedia Society
• /
• v.25 no.6
• /
• pp.886-893
• /
• 2022

Outlier detection refers to the task of detecting data that deviate significantly from the normal data distribution. Most outlier detection methods compute an outlier score which indicates the degree to which a data sample deviates from normal. However, setting a threshold for an outlier score to determine if a data sample is outlier or normal is not trivial. In this paper, we propose a binary prediction method for outlier detection based on spectral clustering and one-class SVM ensemble. Given training data consisting of normal data samples, a clustering method is performed to find clusters in the training data, and the ensemble of one-class SVM models trained on each cluster finds the boundaries of the normal data. We show how to obtain a threshold for transforming outlier scores computed from the ensemble of one-class SVM models into binary predictive values. Experimental results with high dimensional text data show that the proposed method can be effectively applied to high dimensional data, especially when the normal training data consists of different shapes and densities of clusters.

• Geophysics and Geophysical Exploration
• /
• v.26 no.2
• /
• pp.62-76
• /
• 2023

Recently, machine learning (ML) techniques have been actively applied for seismic trace interpolation. However, because most research is based on training-inference strategies that treat missing trace gather data as a 2D image with a blank area, a sufficient number of fully sampled data are required for training. This study proposes trace interpolation using ML, which uses only irregularly sampled field data, both in training and inference, by modifying the training-inference strategies of trace-based interpolation techniques. In this study, we describe a method for constructing networks that vary depending on the maximum number of consecutive gaps in seismic field data and the training method. To verify the applicability of the proposed method to field data, we applied our method to time-migrated seismic data acquired from the Vincent oilfield in the Exmouth Sub-basin area of Western Australia and compared the results with those of the conventional trace interpolation method. Both methods showed high interpolation performance, as confirmed by quantitative indicators, and the interpolation performance was uniformly good at all frequencies.

• Physical Therapy Rehabilitation Science
• /
• v.6 no.3
• /
• pp.120-126
• /
• 2017

Objective: The purpose of this study was to investigate the effects of backward treadmill gait training between underwater and ground environments on strength, proprioception, and walking ability in persons with stroke. Design: Randomized control trial. Methods: Twenty eight subjects participated in the study in which they were randomly assigned to either the underwater backward treadmill training (UBTT) group (n=13) or the BTT group (n=15). In both groups, forward gait training was performed for 20 minutes on the ground treadmill. The UBTT group performed backward gait on an underwater treadmill for 20 minutes while the BTT group performed backward gait on a ground treadmill for 20 minutes. The gait training in each group was performed twice a week for a total of six weeks. Muscle strength, proprioception, and gait ability was assessed using a digital power meter, joint angle recurrence method using the smartphone protractor application, the Figure-of-Eight walk test (F8W) and the functional gait assessment (FGA) respectively. Results: Both groups showed significant improvement in strength, F8W and FGA scores after training (p<0.05). However, there was no statistically significant difference between the two groups. Both groups showed significant improvement in proprioception after training (p<0.05). In the comparison between the two groups, there was a greater significant change in the UBTT group for joint proprioception (p<0.05). Conclusions: In this study, it was found that both backward treadmill gait training programs were effective on strength, proprioception, and gait ability, and that underwater training was particularly effective on proprioception compared to ground training.

• Journal of The Korean Society of Integrative Medicine
• /
• v.1 no.1
• /
• pp.1-9
• /
• 2013

Purpose : The purpose of this study is to investigate the impact on the ability to walk, balance after side walking training of hemiplegic patients caused by stroke. Method : The subjects were training before stroke onset whether more than one year elapsed 15 patients with chronic stroke patients, and Berg balance scale(BBS) and Timed up and go test(TUG), Functional reaching test(FRT), 20m walking time 200m walking time were measured and recorded. Training period, a total of three weeks, and training frequency circuit training times 10 minutes per training, 5-minute break, the 10-minute training total 25-minute training was conducted. Gait line of 3m to be based on the patient's side walking, and the risk of falling compared to the presence of the experimenter trained under was carried out. Result : 1. TUG, 2. 20m walking time, 3. 200m walking time 4. FRT, 5. All showed significant improvement in BBS. Judging from the results, the side walking training conducted three weeks due to chronic stroke hemiplegic patient's ability to balance and showed a positive effect on the improvement of walking ability. Conclusion : Accordingly, it was more effective to train hemiplegic patients with chronic stroke on side walking.

• Journal of Labour Economics
• /
• v.24 no.3
• /
• pp.83-117
• /
• 2001

This study intends to analyze the status and efficiency of education-training in Korean firm. A study on the education-training in firm is very important nowadays, but the study level on this issue in Korea is low. The study method of this paper is the case study on a high-level Korean firm in the education-training status. This study first attempted to analyze the concept and size of the education-training in firm. And then this study figured out factors that determine the efficiency of education-training. Finally, I analyzed the status and efficiency of education-training in this case firm. Unfortunately, the efficiency level of my case firm in the education-training was low, in spite of a high-level firm in the education-training status. To upgrade the efficiency level of this firm in the education-training, this firm has to resolve many tasks.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.4
• /
• pp.51-56
• /
• 2012

Nowadays, For that reason, the tactical training system that were applied to recruit training center and police training, a real-life survivor game place is a drill using conventional training methods that there is no special training system at open terrain and field, there is no training accomplishment in conformity with battlefield situation portrayal. Therefore, this paper developed the tactical training evaluation system and real-time monitoring system that is compensated the defect and controlled sensing, interlock with PC as wireless a way of GUI using PCB mounted MICOM. This system evaluate drill that regulate sensor control module, tactical training system remotely according to what they should do, is installed to fit the occasion as to be reflected or transmission choosingly and is a 24V H/W drive module.