• Title/Summary/Keyword: 훈련개선

Search Result 882, Processing Time 0.023 seconds

Comparison of Semantic Segmentation Performance of U-Net according to the Ratio of Small Objects for Nuclear Activity Monitoring (핵활동 모니터링을 위한 소형객체 비율에 따른 U-Net의 의미론적 분할 성능 비교)

  • Lee, Jinmin;Kim, Taeheon;Lee, Changhui;Lee, Hyunjin;Song, Ahram;Han, Youkyung
    • Korean Journal of Remote Sensing
    • /
    • v.38 no.6_4
    • /
    • pp.1925-1934
    • /
    • 2022
  • Monitoring nuclear activity for inaccessible areas using remote sensing technology is essential for nuclear non-proliferation. In recent years, deep learning has been actively used to detect nuclear-activity-related small objects. However, high-resolution satellite imagery containing small objects can result in class imbalance. As a result, there is a performance degradation problem in detecting small objects. Therefore, this study aims to improve detection accuracy by analyzing the effect of the ratio of small objects related to nuclear activity in the input data for the performance of the deep learning model. To this end, six case datasets with different ratios of small object pixels were generated and a U-Net model was trained for each case. Following that, each trained model was evaluated quantitatively and qualitatively using a test dataset containing various types of small object classes. The results of this study confirm that when the ratio of object pixels in the input image is adjusted, small objects related to nuclear activity can be detected efficiently. This study suggests that the performance of deep learning can be improved by adjusting the object pixel ratio of input data in the training dataset.

A Grounded Theory Approach to Person Centered Communication between People Living with Dementia and Their Caregivers (사람중심 치매커뮤니케이션에 대한 근거 이론적 연구)

  • Kim, Dong Seon;Shin, Soo Kyung
    • The Journal of the Korea Contents Association
    • /
    • v.22 no.5
    • /
    • pp.746-764
    • /
    • 2022
  • Communication breakdown has been mentioned causing a heavy burden for dementia caregivers. This study aims to inspect and structure the process and results of communication between people with dementia and their caregivers. The impeding/facilitating elements of communication are also extracted. Interviews with 21 of dementia care experts about the direct and indirect experiences of communication with people with dementia were analyzed based on the grounded theory. Results show that combination of the cognitive and communication decline of the people with dementia, confusing environment and caregivers' inappropriate attitude and lack of communication skills leads to communication breakdown and relations severance. Minimal contacts and task-oriented conversation results in conflicts and people with dementia's increasing agitation, anxiety and violent behaviors while understanding of individuality and listening with heart lead to recovered lucidity in the state of serious dementia, recovered pleasure and voluntary participation in the daily activities for people with dementia. Core paradigm was defined as 'Person Centered Care through relation formation'. There are 4 types of communication with people with dementia : partnering, patronizing, conflicting, avoiding types. Researchers suggest that Person Centered based communication skills be educated and trained for dementia caregivers.

Effect of Swiss Ball Exercise Combined with Taping on Pain, Disability, and Quality of Life in Women with Pregnancy-Related Low Back Pain (테이핑과 병행한 스위스볼 운동이 임신성 요통 환자의 통증과 기능장애 및 삶의 질에 미치는 효과)

  • Jung, Kyoung-Sim;In, Tae-Sung
    • Journal of Korea Entertainment Industry Association
    • /
    • v.14 no.6
    • /
    • pp.301-309
    • /
    • 2020
  • The purpose of this study was to determine whether swiss ball exercise combined with taping would improve low back pain, disability and quality of life in women with pregnancy-related Low Back Pain (PR-LBP). Sixteen patients with PR-LBP were recruited and were randomly divided into two groups: taping and swiss ball exercise group (n=8) and taping and stretching group (n=8). The taping and swiss ball exercise group was treated with swiss ball exercise with kinesio taping, while the taping and stretching group received only taping. The taping and swiss ball exercise group performed swiss ball exercise for 30 minutes a day, 5 times a week for 4weeks, while the taping and stretching group conducted stretching exercise for the same amount of time. VAS was used to assess pain level of low back. Disability was measured using a Roland Morris Disability Questionnaire(RMDQ). Quality of life were measured by SF-36. The pain intensity of low back in the taping and swiss ball exercise group improved significantly greater than the taping and stretching group (p<0.05). Significant improvement in the disability was observed in the taping and swiss ball exercise group compared to the taping and stretching group (p<0.05). The SF 36 in the taping and swiss ball exercise group improved significantly greater than the taping and stretching group (p<0.05). Our findings indicate that swiss ball exercise combined with taping is beneficial and effective to improve low back health and quality of life in women with PR-LBP.

Effects on the Respiratory Function, Lower Extremity Muscle Activity and Balance for the Wellness of Stroke Patients - Focused on Whole Body Vibration Exercise Combined with Breathing Exercise - (뇌졸중 환자의 웰니스를 위한 호흡기능, 하지근활성도 및 균형에 미치는 효과 - 호흡운동을 결합한 전신진동운동을 중심으로 -)

  • Kang, Jeong-Il;Yang, Sang-Hoon;Jeong, Dae-Keun
    • 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.

A Korean menu-ordering sentence text-to-speech system using conformer-based FastSpeech2 (콘포머 기반 FastSpeech2를 이용한 한국어 음식 주문 문장 음성합성기)

  • Choi, Yerin;Jang, JaeHoo;Koo, Myoung-Wan
    • 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.

Changes of The Epidemiologic Competences after Introductory Course of The Korea - Field Epidemiologist Training Program(K-FETP) in Epidemiologic Intelligence Servise(EIS) Officers (한국 역학조사관 기본교육(K-FETP) 전후 역량 평가)

  • Kim, Eun-Young;Lee, Moo-Sik;Lee, Tae-Jun;Lee, Kwan;Nam, Hae-Sung;Lee, Ju-Hyoung;Kim, Hong-Bin;Chun, Byung-Chul;Lee, Sang-Won;Lee, Dong-Han;Kim, Hee-Jung;Kwon, Sung-Whe;Yoon, Na-Bi;Shin, Moon-Chul;Lim, Mee-Jee
    • 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.

Analysis of Evacuation Time According to Variation of Evacuation Stairs' Width in Large-Scale Goshiwons (대규모 고시원의 피난계단 폭의 변화에 따른 피난소요시간 분석)

  • Oh, Su-cheol;Kong, Ha-Sung
    • 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.

An Analysis of Research Trends in Military education: Focusing on Domestic Academic Papers Since 2000 (군인 교육 연구동향 분석: 2000년 이후 국내 학술논문을 중심으로)

  • Ji-young Nam;Kyung-ok Jeong;Chong-soo Cheung
    • 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.

A Study on Falling Detection of Workers in the Underground Utility Tunnel using Dual Deep Learning Techniques (이중 딥러닝 기법을 활용한 지하공동구 작업자의 쓰러짐 검출 연구)

  • Jeongsoo Kim;Sangmi Park;Changhee Hong
    • 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

An Acoustic Event Detection Method in Tunnels Using Non-negative Tensor Factorization and Hidden Markov Model (비음수 텐서 분해와 은닉 마코프 모델을 이용한 터널 환경에서의 음향 사고 검지 방법)

  • Kim, Nam Kyun;Jeon, Kwang Myung;Kim, Hong Kook
    • 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.