• Tunnel and Underground Space
• /
• v.28 no.3
• /
• pp.277-291
• /
• 2018

LSTM (Long Short-Term Memory) algorithm which is a kind of recurrent neural network was used to establish a model to predict the stress-strain curve of an material under uniaxial compression. The model was established from the stress-strain data from uniaxial compression tests of silica-gypsum specimens. After training the model, it can predict the behavior of the material up to the failure state by using an early stage of stress-strain curve whose stress is very low. Because the LSTM neural network predict a value by using the previous state of data and proceed forward step by step, a higher error was found at the prediction of higher stress state due to the accumulation of error. However, this model generally predict the stress-strain curve with high accuracy. The accuracy of both LSTM and tangential prediction models increased with increased length of input data, while a difference in performance between them decreased as the amount of input data increased. LSTM model showed relatively superior performance to the tangential prediction when only few input data was given, which enhanced the necessity for application of the model.

• Journal of KIISE
• /
• v.44 no.6
• /
• pp.607-612
• /
• 2017

This paper presents an attempt to apply Deep Learning technology to solve the problem of forecasting floods in urban areas. We employ Recurrent Neural Networks (RNNs), which are suitable for analyzing time series data, to learn observed data of river water and to predict the water level. To test the model, we use water observation data of a station in the Trinity river, Texas, the U.S., with data from 2013 to 2015 for training and data in 2016 for testing. Input of the neural networks is a 16-record-length sequence of 15-minute-interval time-series data, and output is the predicted value of the water level at the next 30 minutes and 60 minutes. In the experiment, we compare three Deep Learning models including standard RNN, RNN trained with Back Propagation Through Time (RNN-BPTT), and Long Short-Term Memory (LSTM). The prediction quality of LSTM can obtain Nash Efficiency exceeding 0.98, while the standard RNN and RNN-BPTT also provide very high accuracy.

• Journal of KIISE
• /
• v.44 no.7
• /
• pp.674-679
• /
• 2017

In big-data environments wherein large amounts of text documents are produced daily, titles are very important clues that enable a prompt catching of the key ideas in documents; however, titles are absent for numerous document types such as blog articles and social-media messages. In this paper, a title-generation model for which sequence-to-sequence RNNs with attention and copying mechanisms are employed is proposed. For the proposed model, input sentences are encoded based on bi-directional GRU (gated recurrent unit) networks, and the title words are generated through a decoding of the encoded sentences with keywords that are automatically selected from the input sentences. Regarding the experiments with 93631 training-data documents and 500 test-data documents, the attention-mechanism performances are more effective (ROUGE-1: 0.1935, ROUGE-2: 0.0364, ROUGE-L: 0.1555) than those of the copying mechanism; in addition, the qualitative-evaluation radiative performance of the former is higher.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.12 no.2
• /
• pp.121-130
• /
• 2012

This paper proposes an intuitive real-time robot control system using human body movement. Recently, it has been developed that motion generation for humanoid robots with reflecting human body movement, which is measured by a motion capture. However, in the existing studies about robot control system by human body movement, the detailed structure information of a robot, for example, degrees of freedom, the range of motion and forms, must be examined in order to calculate inverse kinematics. In this study, we have proposed Associative Motion Generation as humanoid robot motion generation method which does not need the detailed structure information. The associative motion generation system is composed of two neural networks: nonlinear principal component analysis and Jordan recurrent neural network, and the associative motion is generated with the following three steps. First, the system learns the correspondence relationship between an indication and a motion using training data. Second, associative values are extracted for associating a new motion from an unfamiliar indication using nonlinear principal component analysis. Last, the robot generates a new motion through calculation by Jordan recurrent neural network using the associative values. In this paper, we propose a real-time humanoid robot control system based on Associative Motion Generation, that enables user to control motion intuitively by human body movement. Through the task processing and subjective evaluation experiments, we confirmed the effective usability and affective evaluations of the proposed system.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.6
• /
• pp.165-171
• /
• 2022

Human heart rate can be used to measure exercise intensity as an important indicator. If heart rate can be predicted, exercise can be performed more efficiently by regulating the intensity of exercise in advance. In this paper, a FitRec-based prediction model is proposed for estimating running heart rate for users. Endomondo data is utilized for training the proposed prediction model. The processing algorithms for time-series data, such as LSTM(long short term memory) and GRU(gated recurrent unit), are employed to compare their performance. On the basis of simulation results, it was demonstrated that the proposed model trained with running exercise performed better than the model trained with several cardiac exercises.

• Journal of Korea Water Resources Association
• /
• v.51 no.12
• /
• pp.1217-1227
• /
• 2018

This paper aims to evaluate the applicability of dam inflow prediction model using recurrent neural network theory. To achieve this goal, the Artificial Neural Network (ANN) model and the Elman Recurrent Neural Network(RNN) model were applied to hydro-meteorological data sets for the Soyanggang dam and the Chungju dam basin during dam operation period. For the model training, inflow, rainfall, temperature, sunshine duration, wind speed were used as input data and daily inflow of dam for 10 days were used for output data. The verification was carried out through dam inflow prediction between July, 2016 and June, 2018. The results showed that there was no significant difference in prediction performance between ANN model and the Elman RNN model in the Soyanggang dam basin but the prediction results of the Elman RNN model are comparatively superior to those of the ANN model in the Chungju dam basin. Consequently, the Elman RNN prediction performance is expected to be similar to or better than the ANN model. The prediction performance of Elman RNN was notable during the low dam inflow period. The performance of the multiple hidden layer structure of Elman RNN looks more effective in prediction than that of a single hidden layer structure.

• Korean Journal of Applied Biomechanics
• /
• v.33 no.2
• /
• pp.62-72
• /
• 2023

Objective: Although balance training has been used as an effective ankle injury rehabilitation program to restore neuromuscular deficits in patients with chronic ankle instability, it is not effectively used in terms of motor learning. Attentional focusing can be an effective method for improving ankle kinematics to prevent recurrent ankle injuries. This study aimed to 1) evaluate the effects of attentional focus, including internal and external focus, and 2) determine a more effective focusing method for patients with chronic ankle instability to learn balance tasks. Method: Twenty-four patients with chronic ankle instability were randomly assigned to three groups (external focus, internal focus, and no feedback) and underwent four weeks of progressive balance training. The three-dimensional ankle kinematics of each patient were measured before and after training as the main outcomes. Ensemble curve analysis, discrete point analysis, and post hoc pairwise comparisons were performed to identify interactions between groups and time. Results: The results showed that (1) the external focus group was more dorsiflexed and everted than the internal focus group; (2) the external focus group was more dorsiflexed than the no feedback group; and (3) the no feedback group was more dorsiflexed than the internal focus group. Conclusion: Because dorsiflexion and eversion are ankle motions that oppose the mechanism of lateral ankle sprain, using the external focus method during balance training may be more effective in modifying these motions, thereby reducing the risk of ankle sprain.

• Journal of Practical Engineering Education
• /
• v.8 no.1
• /
• pp.57-62
• /
• 2016

The purpose of this study is to provide the basic data and to construct education system by analizing the case of Japan on the lifelong vocational competency development utilizing the university. Japan has grown by the world leading technology and talented people. In a globalized world, In order to achieve economic growth, It is necessary to connect the Human resource development to the overall growth of the economy. After the law on policy implementation system for the Lifelong Learning Promotion is enacted. University of japan, the newly defined the philosophy of lifelong learning in the Fundamental Law of Education. Then, University of japan has induced people to actively participate in the lifelong vocational competency development. In this paper, we refer to the Shizuoka University in Japan and learning support program and we studied the method for the activation of improvement and field placement of the training capacity of field training using the case of Japan on the lifelong vocational competency development utilizing the university.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.15
• /
• pp.6783-6787
• /
• 2015

Background: Despite consistent pharmacogenetic effects of CYP2D6 on tamoxifen exposure, there is considerable controversy regarding the validity of CYP2D6 as a predictor of tamoxifen outcome. Understanding the current state of evidence in this area and its limitations is important for the care of patients who require endocrine therapy for breast cancer. Materials and Methods: A total of 101 patients with breast cancer who received tamoxifen therapy for at least 3 years, were genotyped for common alleles of the CYP2D6 gene by nested-PCR and restriction fragment length polymorphism PCR. Patients were classified as extensive or poor metabolizers (PM) based on CYP2D6*4 alleles in 3 different groups according to the menopause, Her2-neu status, and stage 3. Results: The mean age of the patients with the disease recurrence was $50.8{\pm}6.4$ and in non recurrent patients was $48.2{\pm}6.8$. In this study 63.3% (n=64) patients were extensive metabolizers and 36.6% (n=37) were poor metabolizers. Sixty four of the 101 patients (63.3%) were Her2-neu positive. For tamoxifen-treated patients, no statistically significant difference in rate of recurrence observed between CYP2D6 metabolic variants in stage 3 and post-menopausal patients. However, there was a significant association between CYP2D6 genotype and recurrence in tamoxifen-treated Her2-neu positive patients. Compared with other women with breast cancer, those with Her2-neu positive breast cancer and extensive metabolizer alleles had a decreased likelihood of recurrence. Conclusions: This study for the first time demonstrated significant effects of CYP2D6 extensive metabolizer alleles on risk of recurrence in Her2-neu positive breast cancer patients receiving adjuvant tamoxifen therapy. Therefore, CYP2D6 metabolism, as measured by genetic variation, can be a predictor of breast cancer outcome in Her2-neu positive women receiving tamoxifen.

• Journal of the Korean Society of Radiology
• /
• v.84 no.5
• /
• pp.1009-1016
• /
• 2023

Radiofrequency ablation (RFA) is a minimally invasive treatment modality used as an alternative to surgery in patients with benign thyroid nodules and recurrent thyroid cancers. In Korea, RFA for thyroid nodules was first performed in 2002, and a large population study was published in 2008. The Task Force Committee of the Korean Society of Thyroid Radiology (KSThR) developed its first recommendations for RFA in 2009, which were revised in 2012 and 2018. The KSThR guideline was the first guideline for RFA of thyroid nodules worldwide and has become a guideline for physicians to perform thyroid RFA in Korea and other countries around the world. These guidelines have contributed significantly to the establishment and widespread use of RFA worldwide. In addition, since 2015, the KSThR has conducted intensive hands-on courses depending on the level of the participants. In this article, the authors introduce the history of eduction for RFA conducted by the KSThR and describe the learning curve of RFA and current training programs in Korea, along with future directions for training programs.