• Journal of Korea Entertainment Industry Association
• /
• v.14 no.8
• /
• pp.397-405
• /
• 2020

The purpose of study was to compare respiratory function and quadriceps muscle activity in stroke patients by applying inspiratory muscle training combined with whole body vibration. In addition, the purpose of study is to present an exercise method for improving the respiratory function of stroke patients and the function of the lower limb muscles of stroke patients. Totally, 21 patients with Stroke patients were randomly assigned to two groups through clinical sampling. 11 patients who applied whole body vibration combined with respiratory exercise were randomly assigned to Experiment Group I, and 10 patients who applied placebo exercise combined with breathing exercise were randomly assigned to Experiment Group II. And for 5 weeks, 4 days/week, 1 time/day, 4 sets/1 time intervention program was implemented. Before intervention, the respiratory function was measured with a maximum inspiratory pressure meter, the lower extremity muscle activity was measured using the surface EMG, and the balance ability was measured using a bug balance test. And after 5 weeks, the post-test was re-measured and analyzed in the same way as the pre-test. In the comparison of changes within the group of experimental group I, there were significant differences in the activity and balance of the respiratory muscle strength, the biceps femoris, and the anterior tibialis muscle (p<.05). In the comparison of the changes in the experimental group I, there was a significant difference in respiratory strength and balance (p<.05). In the comparison of changes between groups, there was a significant difference in the activity of the biceps femoris and anterior tibialis (p<.01). In the future, research on protocols for respiratory exercise and whole body vibration to improve neuromuscular function is considered to be necessary.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.359-366
• /
• 2022

In this paper, we present the Korean menu-ordering Sentence Text-to-Speech (TTS) system using conformer-based FastSpeech2. Conformer is the convolution-augmented transformer, which was originally proposed in Speech Recognition. Combining two different structures, the Conformer extracts better local and global features. It comprises two half Feed Forward module at the front and the end, sandwiching the Multi-Head Self-Attention module and Convolution module. We introduce the Conformer in Korean TTS, as we know it works well in Korean Speech Recognition. For comparison between transformer-based TTS model and Conformer-based one, we train FastSpeech2 and Conformer-based FastSpeech2. We collected a phoneme-balanced data set and used this for training our models. This corpus comprises not only general conversation, but also menu-ordering conversation consisting mainly of loanwords. This data set is the solution to the current Korean TTS model's degradation in loanwords. As a result of generating a synthesized sound using ParallelWave Gan, the Conformer-based FastSpeech2 achieved superior performance of MOS 4.04. We confirm that the model performance improved when the same structure was changed from transformer to Conformer in the Korean TTS.

• Journal of agricultural medicine and community health
• /
• v.47 no.2
• /
• pp.78-89
• /
• 2022

목적: 이 연구는 2019학년도 역학조사관 입문교육 과정에 참여한 29명의 수습과정생에게 참여형 자기주도 학습 역학조사관 연수 프로그램(FETP)의 효과와 만족도 등 역량 변화를 분석해 그 결과를 향후 과정 개발의 참고 자료로 활용하고자 하였다. 방법: 교육 프로그램의 만족도와 교육 후 모듈에 대한 역량 변화를 평가하는 연구가 수행되었다. 만족도와 역량의 차이 비교는 크루스칼 왈리스 검정(Kruskal-Wallis test)를 실시하였고, 역량의 차이는 윌콕슨 부호순위검정(Wilcoxon signed rank test)에 의해 이루어 졌다. 결과: 2019년 FETP에 참여한 역학조사관 중 여성은 48.3% 였으며, 40세 미만은 9.4% 였다. 역학조사관 입문교육과정 모듈(역학조사, 보건통계 및 정보통계, 감염병 국가 체계, 감염병 질환 감시 체계, 진단 및 실험실 검사, 생물 안전 및 관리, 주요 감염성질환 관리와 조사, 커뮤니케이션, 협동과 리더십, 일반과정)별 만족도는 실무적 도움, 전문성, 기능, 태도 등에서 4점(5점 만점)을 초과하였고, 전체 4.2±0.21(5점 만점)점으로 높은 수준이였다, 모듈의 교육훈련 전후 평균 점수는 2.25±0.91, 3.68±0.63점 등으로 유의한 향상이 있었으며, 모든 모듈 및 하위 주제들도 유의한 향상이 있었다(p<0.001). 그 중에서 현장역학조사 경험이 가장 높은 변화가 있었고, 표본 수집과 실무가 가장 낮은 역량 변화가 있었다. 결론: 2019년 진행된 입문교육 과정은 수료 후 학생들의 역량은 개선되었고, 만족도는 높은 편이었다. 참여형 자기주도학습의 촉진은 역량을 향상시킬 뿐만 아니라 보건 종사자들의 자신감을 높일 수 있었다.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.5
• /
• pp.641-651
• /
• 2022

This research compares and analyzes evacuation time depending on the change in stair width in case of fire at Goshiwons. For this, a simulation has been conducted based on possible evacuation time according to the calculation method for the number of people admittable to a specific target for fire fighting equipped with accommodation. Currently, Gosiwon, which is classified as an accommodation facility (a total floor area of 500 m² or more), uses blind spots prescribed by the Fire Services Act, Building Act, and Parking Act to build a high-rise building on a small area of land, and most Gosiwon is transformed into a modified accommodation. This is in line with the owner's operating profit, so it is expected to show a continuous increase. Securing the golden time of Gosiwon evacuation time is the last bastion of Gosiwon residents who belong to the economically disadvantaged in our society, and we hope this study will serve as a starting point for discussions on revising related laws and regulations to establish a social safety net As a result of the evacuation simulation analysis, the evacuation time was the least when the width of the group and the evacuation stairs were expanded to 200cm, and the evacuation time of the existing building was reduced by up to 166.3 seconds by comparing 648.4 seconds and scenario 6. This analysis can be meaningful, in that the width of the evacuation stairs revision of related laws and regulations for the safety of multiplex available premises.

• Journal of the Society of Disaster Information
• /
• v.19 no.3
• /
• pp.471-480
• /
• 2023

Purpose: This study intends to present a future research direction for military education by identifying and analyzing research trends in the field of education related to soldiers in academic research published in Korea. Method: In domestic academic papers published from 2000 to 2022, 269 final papers were selected from among the papers conducted on the subjects of 'soldiers' and 'education'. The final selected literature was analyzed by categorizing it into year, research subject, research method type, number of researchers, research topic, and research content. Result: First, since 2010, the number of studies has gradually increased, and 31 articles were published in 2021, with the largest number of studies. Second, the largest number of studies were conducted on the entire military, followed by the Army and Nursing Officers. Third, qualitative research methods were used a little more in research methods. Fourth, the number of researchers with two or more researchers was steadily increasing. Fifth, most of the research topics were development, design, and improvement. Sixth, in terms of detailed research contents, most of the studies were related to soldiers' spirit(mental force) education and military education and training. Conclusion: Through this study, it was confirmed that military education was studied in various subjects. The direction of future research should be in-depth research from various perspectives with a lot of interest in military education and safety.

• Journal of the Society of Disaster Information
• /
• v.19 no.3
• /
• pp.498-509
• /
• 2023

Purpose: This paper proposes a method detecting the falling of a maintenance worker in the underground utility tunnel, by applying deep learning techniques using CCTV video, and evaluates the applicability of the proposed method to the worker monitoring of the utility tunnel. Method: Each rule was designed to detect the falling of a maintenance worker by using the inference results from pre-trained YOLOv5 and OpenPose models, respectively. The rules were then integrally applied to detect worker falls within the utility tunnel. Result: Although the worker presence and falling were detected by the proposed model, the inference results were dependent on both the distance between the worker and CCTV and the falling direction of the worker. Additionally, the falling detection system using YOLOv5 shows superior performance, due to its lower dependence on distance and fall direction, compared to the OpenPose-based. Consequently, results from the fall detection using the integrated dual deep learning model were dependent on the YOLOv5 detection performance. Conclusion: The proposed hybrid model shows detecting an abnormal worker in the utility tunnel but the improvement of the model was meaningless compared to the single model based YOLOv5 due to severe differences in detection performance between each deep learning model

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.9
• /
• pp.265-273
• /
• 2018

In this paper, we propose an acoustic event detection method in tunnels using non-negative tensor factorization (NTF) and hidden Markov model (HMM) applied to multi-channel audio signals. Incidents in tunnel are inherent to the system and occur unavoidably with known probability. Incidents can easily happen minor accidents and extend right through to major disaster. Most incident detection systems deploy visual incident detection (VID) systems that often cause false alarms due to various constraints such as night obstacles and a limit of viewing angle. To this end, the proposed method first tries to separate and detect every acoustic event, which is assumed to be an in-tunnel incident, from noisy acoustic signals by using an NTF technique. Then, maximum likelihood estimation using Gaussian mixture model (GMM)-HMMs is carried out to verify whether or not each detected event is an actual incident. Performance evaluation shows that the proposed method operates in real time and achieves high detection accuracy under simulated tunnel conditions.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.241-265
• /
• 2023

A corporate insolvency prediction model serves as a vital tool for objectively monitoring the financial condition of companies. It enables timely warnings, facilitates responsive actions, and supports the formulation of effective management strategies to mitigate bankruptcy risks and enhance performance. Investors and financial institutions utilize default prediction models to minimize financial losses. As the interest in utilizing artificial intelligence (AI) technology for corporate insolvency prediction grows, extensive research has been conducted in this domain. However, there is an increasing demand for explainable AI models in corporate insolvency prediction, emphasizing interpretability and reliability. The SHAP (SHapley Additive exPlanations) technique has gained significant popularity and has demonstrated strong performance in various applications. Nonetheless, it has limitations such as computational cost, processing time, and scalability concerns based on the number of variables. This study introduces a novel approach to variable selection that reduces the number of variables by averaging SHAP values from bootstrapped data subsets instead of using the entire dataset. This technique aims to improve computational efficiency while maintaining excellent predictive performance. To obtain classification results, we aim to train random forest, XGBoost, and C5.0 models using carefully selected variables with high interpretability. The classification accuracy of the ensemble model, generated through soft voting as the goal of high-performance model design, is compared with the individual models. The study leverages data from 1,698 Korean light industrial companies and employs bootstrapping to create distinct data groups. Logistic Regression is employed to calculate SHAP values for each data group, and their averages are computed to derive the final SHAP values. The proposed model enhances interpretability and aims to achieve superior predictive performance.

• Journal of Music and Human Behavior
• /
• v.19 no.2
• /
• pp.81-103
• /
• 2022

The effects of therapeutic instrumental music performance (TIMP) using a ukulele were examined in adults with central nervous system damage and impaired hand functions. The participants were three adults with neurological damage who participated in 30-min sessions twice a week over 6 weeks. Changes in hand function was measured by the Box and Block Test (BBT), the 9-Hole Peg Test (9-HPT), and the Jebsen-Taylor Hand Function Test (JTHFT). Following the intervention, all three participants showed increases in the BBT and 9-HPT scores, indicating positive changes in fine motor coordination and dexterity. In terms of the JTHFT, all three participants showed increases in the "writing" and "card flipping" subtask scores, indicating that the intervention was effective in improving more coordinated finger movements. All participants reported the satisfaction with the intervention. They also pointed out that they were motivated to play the ukulele and that following the intervention used their affected hand more frequently in daily activities. These findings suggest that TIMP with a ukulele for patients with central nervous system damage can have positive effects on their functional hand movements and motivate these patients to practice their rehabilitation exercises.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.444-444
• /
• 2021

하천의 오염부하량 관리 계획은 지속적인 모니터링을 통한 자료 구축과 모형을 이용한 예측결과를 기반으로 수립된다. 하천의 모니터링과 예측 분석은 많은 예산과 인력 등이 필요하나, 정부의 담당 공무원 수는 극히 부족한 상황이 일반적이다. 이에 정부는 전문가에게 관련 용역을 의뢰하지만, 한국과 같이 지형이 복잡한 지역에서의 오염부하량 배출 특성은 각각 다르게 나타나기 때문에 많은 예산 소모가 발생 된다. 이를 개선하고자, 본 연구는 합성곱 신경망 (convolution neural network)과 수문학적 이미지 (hydrological image)를 이용하여 강우 발생시 BOD 및 총인의 부하량 예측 모형을 개발하였다. 합성곱 신경망의 입력자료는 일반적으로 RGB (red, green, bule) 사진을 이용하는데, 이를 그래도 오염부하량 예측에 활용하는 것은 경험적 모형의 전제(독립변수와 종속변수의 관계)를 무너뜨리는 결과를 초래할 수 있다. 이에, 본 연구에서는 오염부하량이 수문학적 조건과 토지이용 등의 변수에 의해 결정된다는 인과관계를 만족시키고자 수문학적 속성이 내재된 수문학적 이미지를 합성곱 신경망의 훈련자료로 사용하였다. 수문학적 이미지는 임의의 유역에 대해 2차원 공간에서 무차원의 수문학적 속성을 갖는 grid의 집합으로 정의되는데, 여기서 각 grid의 수문학적 속성은 SCS 토양보존국(soil conservation service, SCS)에서 발표한 수문학적 토양피복형수 (curve number, CN)를 이용하여 산출한다. 합성곱 신경망의 구조는 2개의 Convolution Layer와 1개의 Pulling Layer가 5회 반복하는 구조로 설정하고, 1개의 Flatten Layer, 3개의 Dense Layer, 1개의 Batch Normalization Layer를 배열하고, 마지막으로 1개의 Dense Layer가 연결되는 구조로 설계하였다. 이와 함께, 각 층의 활성화 함수는 정규화 선형함수 (ReLu)로, 마지막 Dense Layer의 활성화 함수는 연속변수가 도출될 수 있도록 회귀모형에서 자주 사용되는 Linear 함수로 설정하였다. 연구의 대상지역은 경기도 가평군 조종천 유역으로 선정하였고, 연구기간은 2010년 1월 1일부터 2019년 12월 31일까지로, 2010년부터 2016년까지의 자료는 모형의 학습에, 2017년부터 2019년까지의 자료는 모형의 성능평가에 활용하였다. 모형의 예측 성능은 모형효율계수 (NSE), 평균제곱근오차(RMSE) 및 평균절대백분율오차(MAPE)를 이용하여 평가하였다. 그 결과, BOD 부하량에 대한 NSE는 0.9, RMSE는 1031.1 kg/day, MAPE는 11.5%로 나타났으며, 총인 부하량에 대한 NSE는 0.9, RMSE는 53.6 kg/day, MAPE는 17.9%로 나타나 본 연구의 모형은 우수(good)한 것으로 판단하였다. 이에, 본 연구의 모형은 일반 ANN 모형을 이용한 선행연구와는 달리 2차원 공간정보를 반영하여 오염부하량 모의가 가능했으며, 제한적인 입력자료를 이용하여 간편한 모델링이 가능하다는 장점을 나타냈다. 이를 통해 정부의 물관리 정책을 위한 의사결정 및 부족한 물관리 분야의 행정력에 도움이 될 것으로 생각된다.