• Journal of Advanced Marine Engineering and Technology
• /
• v.39 no.3
• /
• pp.326-333
• /
• 2015

A tidal sandshoal, called 'Puldeung' in the Daeijackdo Marine Protected Area(DMPA), is facing erosion due to sand mining in the nearby coastal region. To monitor the morphologic change and erosion of Puldeung, a camera monitoring system was established at the top of Song-Ee Mountain in Daeijack Island. The system consists of 2 Cannon digital cameras, Eye-fi memory card/Long-Term Evolution wireless network, and solar power supply. The acquired camera images were analyzed to obtain the area of Puldeung by the following methods: geometric correction of image, identification of shoreline, areal measurement of Puldeung and its error estimation. To compare the Puldeung area with previously measured area of 1.79 km2 at tidal height of 137 cm in 2008 and of 1.59 km2 at tidal height of 148 cm in 2010, we selected images with same tidal heights. The Puldeung area was 1.37 and 1.23 km2 at the tidal height of 137 and 148 cm, respectively. The erosion at DMPA is very severe and thus it is imperative to initiate the morphodynamical study on the seasonal variation and long-term evolution of Puldeung as well as the causes and measures of Puldeung erosion.

• Management & Information Systems Review
• /
• v.35 no.2
• /
• pp.45-66
• /
• 2016

Firms can make scale of economy and scope of economy by internalizing and using new advanced technology and knowledge from technology cooperation network, decrease risk and cost with partner firm of technology cooperation network, and increase market advantage of product & strengthen firms' position in the market. Due to the advantages of technology cooperation network, the related studies have focused on the positive effect of technology cooperation network. However, the related studies investigating the relationship between technology cooperation network and firm performance have only examined the role of technology cooperation network. Safeguarding mechanism, relationship learning, and relationship performance are categorized into the process of technology cooperation network, and this categorization is applied as resources, capability, and performance by resource based view. The empirical results are reported as belows. First, relationship specific investment and relationship capital positively affect on relationship learning as capability. Second, information sharing, common information understanding, and relationship specific memory development positively affect on long-term orientation, but information sharing has no impact on efficiency and effectiveness. Third, relationship specific investment positively affects on relationship capital and efficiency and effectiveness have positive effects on long-term orientation. Applying technology cooperation network in asymmetric technology dependency with resource based theory, this study suggested the importance of both safeguarding and relationship learning by investigating the relationship among safeguarding, relationship learning, and relationship performance. And it is worthy that this study investigated how firms' behavior change affects relationship performance in the relationship of technology cooperation partner.

• Journal of Digital Contents Society
• /
• v.19 no.6
• /
• pp.1161-1167
• /
• 2018

The development of machine learning has enabled machines to perform delicate tasks that only humans could do, and thus many companies have introduced machine learning based translators. Existing translators have good performances but they have problems in number translation. The translators often mistranslate numbers when the input sentence includes a large number. Furthermore, the output sentence structure completely changes even if only one number in the input sentence changes. In this paper, first, we optimized a neural machine translation model architecture that uses bidirectional RNN, LSTM, and the attention mechanism through data cleansing and changing the dictionary size. Then, we implemented a number-processing algorithm specialized in number translation and applied it to the neural machine translation model to solve the problems above. The paper includes the data cleansing method, an optimal dictionary size and the number-processing algorithm, as well as experiment results for translation performance based on the BLEU score.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.6
• /
• pp.622-628
• /
• 2020

This paper proposes a music generation technique that automatically generates trot music using a Generative Adversarial Network (GAN) model composed of a Recurrent Neural Network (RNN). The proposed method uses a method of creating a chord as a skeleton of the music, creating a melody and bass in stages based on the chord progression made, and attaching it to the corresponding chord to complete the structured piece. Also, a new chorus chord progression is created from the verse chord progression by applying the characteristics of a trot song that repeats the structure divided into an individual section, such as intro, verse, and chorus. And it extends the length of the created trot. The quality of the generated music was specified using subjective evaluation and objective evaluation methods. It was confirmed that the generated music has similar characteristics to the existing trot.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.3
• /
• pp.28-37
• /
• 2020

This study developed a deep learning model that predicts rental demand for public bicycles. For this, public bicycle rental data, weather data, and subway usage data were collected. After building an exponential smoothing model, ARIMA model and LSTM-based deep learning model, forecasting errors were compared and evaluated using MSE and MAE evaluation indicators. Based on the analysis results, MSE 348.74 and MAE 14.15 were calculated using the exponential smoothing model. The ARIMA model produced MSE 170.10 and MAE 9.30 values. In addition, MSE 120.22 and MAE 6.76 values were calculated using the deep learning model. Compared to the value of the exponential smoothing model, the MSE of the ARIMA model decreased by 51% and the MAE by 34%. In addition, the MSE of the deep learning model decreased by 66% and the MAE by 52%, which was found to have the least error in the deep learning model. These results show that the prediction error in public bicycle rental demand forecasting can be greatly reduced by applying the deep learning model.

• The Journal of the Acoustical Society of Korea
• /
• v.36 no.2
• /
• pp.136-143
• /
• 2017

In this paper, we propose a method for restoring damaged audio files using deep neural network. It is different from the conventional file carving based restoration. The purpose of our method is to infer lost information which can not be restored by existing techniques such as the file carving. We have devised methods that can automate the tasks which are essential for the restoring but are inappropriate for humans. As a result of this study it has been shown that it is possible to restore the damaged files, which the conventional file carving method could not, by using tasks such as speech or nonspeech decision and speech encoder recognizer using a deep neural network.

• Journal of KIISE
• /
• v.44 no.3
• /
• pp.306-313
• /
• 2017

Named entity recognition (NER) seeks to locate and classify named entities in text into pre-defined categories such as names of persons, organizations, locations, expressions of times, etc. Recently, many state-of-the-art NER systems have been implemented with bidirectional LSTM CRFs. Deep learning models based on long short-term memory (LSTM) generally depend on word representations as input. In this paper, we propose an approach to expand word representation by using pre-trained word embedding, part of speech (POS) tag embedding, syllable embedding and named entity dictionary feature vectors. Our experiments show that the proposed approach creates useful word representations as an input of bidirectional LSTM CRFs. Our final presentation shows its efficacy to be 8.05%p higher than baseline NERs with only the pre-trained word embedding vector.

• Research in Community and Public Health Nursing
• /
• v.9 no.2
• /
• pp.336-349
• /
• 1998

The purpose of this study was to test the effects of music therapy on cognitive function and depression in demented old adults. This study was made with one -group in a pre- and post-test design. The subjects were seven demented old adults over, sixty-five years and with mild to moderate cognitive impairment, residing at a nursing home. Music therapy was given by one researcher and one research assistant for thirty to forty minutes twice a week for 4 months. Music therapy was conducted with the subjects both listening and singing with a cassette player and a double-handed drum. In order to evaluate the effects of music, we measured the level of cognitive function and depression at the beginning and at the end of the music therapy session by means of an MMSE- K developed by Kwon and Park and the Depression Inventory developed by Chon. The Data were analyzed using descriptive statistics and a paired t - test analysis using a SPSS PC package. The results are as follows: 1) The subjects of the music therapy showed improvement in cognitive function. The MMSE-K score was significantly increased after music therapy. Especially, memory recall was very significantly. 2) The subjects of the music therapy showed a slight decrease in depression. However, there was no significant difference in the degree of depression between mean scores measured before and after music therapy. The results suggest that music therapy is effective in improving and maintaining cognitive function in demented old adults. And we suggest that long-term music therapy will be required to improve depression in demented old adults. These findings are encouraging the idea that music therapy may improve cognitive impairment.

• Journal of Korea Multimedia Society
• /
• v.23 no.5
• /
• pp.641-649
• /
• 2020

As the usage of mobile devices extremely increases, malicious mobile apps(applications) that target mobile users are also increasing. It is challenging to detect these malicious apps using traditional malware detection techniques due to intelligence of today's attack mechanisms. Deep learning (DL) is an alternative technique of traditional signature and rule-based anomaly detection techniques and thus have actively been used in numerous recent studies on malware detection. In order to develop DL-based defense mechanisms against intelligent malicious apps, feeding recent datasets into DL models is important. In this paper, we develop a DL-based model for detecting intelligent malicious apps using KU-CISC 2018-Android, the most up-to-date dataset consisting of benign and malicious Android apps. This dataset has hardly been addressed in other studies so far. We extract OPcode sequences from the Android apps and preprocess the OPcode sequences using an N-gram model. We then feed the preprocessed data into LSTM and apply the concept of Information Gain to improve performance of detecting malicious apps. Furthermore, we evaluate our model with numerous scenarios in order to verify the model's design and performance.

• Journal of Korean Academy of Nursing
• /
• v.47 no.1
• /
• pp.1-13
• /
• 2017

Purpose: The purpose of this study was to examine the effects of a cognitive training program on neurocognitive task performance and activities of daily living (ADL) in patients who had a stroke. Methods: The research design for this study was a nonequivalent control group non-synchronized design. Patients were assigned to the experimental (n=21) or control group (n=21). The experimental group received a 4-week cognitive training program and usual care (i.e., rehabilitation service), while the control was received usual care only. Cognitive function was measured with a standardized neurocognitive test battery and ADL was assessed at baseline and one and two months after completion of the intervention. Repeated measures ANOVA was used to determine changes in cognitive function and ADL over 2 months. Results: The interaction of group and time was significant indicating that the experimental group showed improvement in attention, visuospatial function, verbal memory, and executive function compared to the control group which had a sustained or gradual decrease in test performance. A significant group by time interaction in instrumental ADL was also found between the experimental group with gradual improvement and the control group showing no noticeable change. Conclusion: Findings show that the cognitive training program developed in this study is beneficial in restoring cognitive function and improving ADL in patients following a stroke. Further study is needed to investigate the long-term relationship between cognitive training participation and cognitive improvement and effective functioning in daily living.