• 재활간호학회지
• /
• 제19권2호
• /
• pp.108-117
• /
• 2016

Purpose: This study aimed to prove the effects of the net-step exercise (NSE) on gait ability, depression, cognitive function and activities of daily living (ADL) in older adults. Methods: The study employed a non-equivalent control group non-synchronized design. A total of 64 community-dwelling older adults were recruited and divided equally into two groups; 32 subjects for an experimental group and 32 subjects for a control group. In the experimental group, the NSE was applied to an hour, two times per week for 4 weeks. The level of gait ability, depression, cognitive function and ADL were measured before and after NSE. The study conducted from July to August, 2016. Data were analyzed with descriptive statistics, $x^2$ test, Fisher's exact test, t-test, ANCOVA, and Pearson correlation coefficients using SPSS/WIN 22.0 version. Results: Gait ability, depression, cognitive function were significantly better in the experimental group than the control group. However, the difference in ADL was not significant between the two groups. Conclusion: These findings in this study showed that the NSE was an efficient intervention for older adults. Nurses could apply non-pharmacological interventions to avoid pharmacological side-effects.

• 수산해양기술연구
• /
• 제31권1호
• /
• pp.29-44
• /
• 1995

A model experiment on the pair midwater trawl net applicable to 800 PS class Korean pair bottom trawlers was carried out in the special-prepared experimental thank. the tank was prepared as a reverse trapezoid shape in its vertical section by digging out flat soil. The dimension of the tank showed the 9.6 W$\times$43.0 L(m) of the upper fringe and the 4.8 W$\times$38.0 L(m) of the bottom with 3.0m in depth. The depth of water was maintained 2.7m during experiment. The model net was prepared based on the Tauti's similarity law of fishing gear in 1/30 scale considering the dimension of the experimental tank. Mouth performance of the model net during towing were determined by the photographs taken in front of the net mouth with the combinations of towing velocity, warp length and distance between paired boats. The results obtained can be summarized as follows: 1. Vertical opening of the model nets A and B was varied in the range of 0.18~0.88 m and 0.21~0.78 m (which can be converted into 5.4~26.4m and 6.3~23.4 m in the full-scale net) respectively, and was varied predominantly by towing speed. Vertical opening (H which is appendixed m for the model net. f for the full-scale net. A and B for the types of the model net) can be expressed as the function of towing velocity$V_t$as in the model net $V_t$ : m/ sec)$H_{mA}$=1.67$e^{-1.65V_t}$ $H_{mB}$=1.15$e^{-1.13V_t}$, in the full-scale net ($V_t$ : k't) $H_{fA}$=50.27$e^-0.37V_t$ $H_{fB}$=34.46$e^{-0.26Vt}$. 2. Horizontal opening of the model nets An and b was varied in the range of 1.03~1.54m and 1.04~1.55 m (which can be converted into 30.9~46.2 m and 31.2~46.5m in the full-scale net) respectively, and was varied predominantly by distance between paired boats. Horizontal opening (W, appendixes are as same as the former) an be expressed as the function of distance between paired boats $D_b$as in the model net $W_{mA}$=0.69+0.09$D_b$ $W{mB}$=0.73+0.09$D_b$, in the full-scale net $W_{fA}$=20.81+0.09$D_b$ $W_{fB}$=22.11+0.09$D_b$ 3. Net opening area of the model net A and B was varied in the range of 0.28~1.04 $m^2$ and 0.33~0.94$m^2$(which can be converted into 252~936$m^2$ and 297~846$m^2$ in the full-scale net) respectively, and was varied predominantly by towing velocity. Net opening area ($S$, appendixes are as same as the former) van be expressed as the function of towing velocity$V_t$ as in the model net $v_t$ : m/sec) $S_{Ma}$=2.01$e^{-1.54V_T}$ $S_{mA}$=1.40$e^{-1.65V_t}$, in the full-scale net ($V_t$ : k't) $S_{fA}$=1.807$e^-0.35V_t$ $S_{fA}$=1.265$e^{-0.24V_t}$. 4. Filtering volume of the model nets A and B was varied in the range of 0.32~0.55 $m^3$ and 0.37~0.55$m^3$(which can be converted into 8.640~14.850 $m^3$ and 9.990~14.850$m3$in the full~scale net) respectively, and was predominantly varied by towing speed. filtering volume of the model net-A showed the maximum at the towing speed 0.69 m/sec(3 k't in the full-scale net), compared with that of the model net B showed at 0.92 m/sec(4 k't in the full-scale net).

• 스마트미디어저널
• /
• 제13권3호
• /
• pp.27-35
• /
• 2024

본 연구는 GAN(Generative Adversarial Network)을 기반으로 한 Semi Supervised Learning을 활용하여 이미지 생성과 ResNet50을 이용한 이미지 분류를 결합하는 방법에 대해 다루고 있다. 이를 통해 새로운 접근법을 제시하여 이미지 생성과 분류를 통합함으로써 더 정확하고 다양한 결과를 얻을 수 있도록 하였다. 생성자와 판별자를 학습시켜 생성된 이미지와 실제 이미지를 구별하고, ResNet50을 활용하여 이미지 분류를 수행한다. 실험 결과에서는 생성된 이미지의 품질이 epoch에 따라 변화함을 확인할 수 있었으며, 이를 통해 산업재해 예측 정확성을 향상하고자 한다. 또한, GAN과 ResNet50의 결합을 통해 이미지 생성의 품질을 향상시키고 이미지 분류의 정확도를 높이는 효율적인 방법을 제시하고자 한다.

• Journal of Information Processing Systems
• /
• 제14권1호
• /
• pp.205-217
• /
• 2018

Deep learning using convolutional neural networks (CNNs) is being studied in various fields of image recognition and these studies show excellent performance. In this paper, we compare the performance of CNN architectures, KCR-AlexNet and KCR-GoogLeNet. The experimental data used in this paper is obtained from PHD08, a large-scale Korean character database. It has 2,187 samples of each Korean character with 2,350 Korean character classes for a total of 5,139,450 data samples. In the training results, KCR-AlexNet showed an accuracy of over 98% for the top-1 test and KCR-GoogLeNet showed an accuracy of over 99% for the top-1 test after the final training iteration. We made an additional Korean character dataset with fonts that were not in PHD08 to compare the classification success rate with commercial optical character recognition (OCR) programs and ensure the objectivity of the experiment. While the commercial OCR programs showed 66.95% to 83.16% classification success rates, KCR-AlexNet and KCR-GoogLeNet showed average classification success rates of 90.12% and 89.14%, respectively, which are higher than the commercial OCR programs' rates. Considering the time factor, KCR-AlexNet was faster than KCR-GoogLeNet when they were trained using PHD08; otherwise, KCR-GoogLeNet had a faster classification speed.

• 수산해양기술연구
• /
• 제54권4호
• /
• pp.279-286
• /
• 2018

The objective of this study was to quantitatively evaluate the influence of the netting hanging ratio on fishing performance of gillnet. A total of six tests was carried out using three kinds of gillnets with different horizontal hanging ratios (0.3, 0.5 and 0.7) on the basis commercial gillnet of mesh size of 60 mm used in Yeosu Dolsan. As a result of the test fishing operation, catches of the net with hanging ratio 0.3 and the shortest float length was 1.34 times larger than the net with hanging ratio 0.7. The caught species in experimental testes was lager in the net with hanging ratio 0.3 than the net with hanging ratio 0.7. The catch rate per unit area (CPUE) is on the silver croaker with the largest catches in tests as follows. The net with hanging ratio 0.3 net was $89.45g/m^2$, hanging ratio 0.5 net was $41.63g/m^2$, and hanging ratio 0.7 net was $24.50g/m^2$. The net with hanging ratio 0.3 (float line length of 45 m) exhibited the largest CPUE value.

• 스마트미디어저널
• /
• 제11권5호
• /
• pp.26-37
• /
• 2022

본 논문에서는 시설재배 작물 중 딸기의 초기 병해를 방제하고자 이미지를 자동으로 취득하고, EfficientNet 모델을 활용해 병해를 분석하여 농민에게 병해 여부를 알려주고, 전문가를 통한 병해 진단 서비스를 제안한다. 딸기 생육단계의 이미지를 취득하고, 학습된 EfficientNet 모델을 활용해 병해 진단 분석결과를 농민의 애플리케이션으로 전송 후 전문가의 피드백을 신속하게 받을 수 있다. 데이터 세트로는 실제 시설재배를 운영하는 농민을 섭외하여 시스템을 이용해 이미지를 취득하였고, 핸드폰으로 촬영한 이미지의 초안을 활용하여 데이터가 부족한 문제를 해결했다. 실험 결과 EfficientNet B0부터 B7까지의 정확도는 유사하여 추론 속도가 가장 빠른 B0를 채택했다. 성능향상을 위해 ImageNet으로 사전학습 된 모델을 사용해 Fine-tuning 했고, 100 Epoch부터 급격한 성능향상을 확인했다. 제안하는 서비스는 초기 병해를 빠르게 탐지하여 생산량을 증대시킬 것으로 기대한다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1995년도 추계학술대회 논문집
• /
• pp.961-964
• /
• 1995

For geometric accuracy in the net shape machining, the problem of tool deflection should be resolved in some fashion. In particular, this is crucial in finish cut operation where slim tools are used. The purpose of this paper is to verify the validity and effectiveness of the prediction model of the machined surface. Experimental results are presented for the cut of steel material with HSS endmill of diameter 6mm on machining center. The results shows that 1) the machining error due totool deflection is serious even in the low cutting load, 2) by using the mechanistic simulation model with experimental coefficients, the machining error was predicted with maximum prediction error of 10% which was significantly reduced to the desired level by the path modification method.

• Bulletin of the Korean Chemical Society
• /
• 제16권10호
• /
• pp.915-923
• /
• 1995

The parameters for an empirical net atomic charge calculation method, Modified Partial Equalization of Orbital Electronegativity (MPEOE), were determined for the atoms in organosilicon compounds and zeolites. For the organosilicon family, the empirical parameters were determined by introducing both experimental and ab initio observables as constraints, these are the experimental and ab initio dipole moments, and the ab initio electrostatic potential of the organosilicon molecules. The Mulliken population was also introduced though it is not a quantum mechanical observable. For the parameter optimization of the atoms in the aluminosilicates, the dipole moments and the electrostatic potentials which calculated from the 6-31G** ab initio wave function were used as constraints. The empirically calculated atomic charges of the organosilicons could reproduce both the experimental and the ab inito dipole moments well. The empirical atomic charges of the aluminosilicates could reproduce the ab initio electrostatic potentials well also.

• 수산해양기술연구
• /
• 제40권1호
• /
• pp.37-46
• /
• 2004

제주도 연안 정치망 조업 시스템 개량과 개발분야에서 연안해역에서 널리 사용되고 있는 각망어구의 구조개량을 위한 기초연구로서 현재 사용되고 있는 실물망을 1/20로 축소하여 개량된 입구 구조를 갖춘 모형 어구 8종류를 제작하고, 실험 수조에서 고등어 어군을 이용하여 모형 어구에 대한 어군의 입 ${\cdot}$ 출망 행동을 관찰 분석하였는데, 그 결과는 다음과 같다. 1. 원통그물내에서의 어군의 행동 패턴은 원형 모양으로 한쪽 원통그물내에 체류하는 행동과 긴 타원형 모양으로 좌 ${\cdot}$ 우 원통그물내를 왕복 유영하는 행동패턴으로 분류할 수 있었다. 2. 모형 어구 내에서의 고등어 어군의 평균 유영 속도는 원통 그물 중간 부분에서 24.9cm/sec, 오른쪽 원통그물내에서 12.6cm/sec, 입구에서 32.0cm/sec였다. 3. 어군의 입망율은 경과 시간 60초일 때 표준 모형 어구에서는 47%였고, 깔대기 그물이 길이가 35cm 의 모형 어구에서는 40%로 나타났는데, 양자의 차이는 7% 정도로 그다지 크지 않았다. 4. 어군의 출망율은 경과 시간 60초일 때 표준 모형 어구에서는 69%였고, 깔대기 그물의 길이가 35cm 의 모형 어구에서는 10%로 나타났는데, 양자의 차이는 59% 정도로 그 폭이 컸다. 5. 어군의 잔여율은 경과 시간 60초일 때 표준 모형 어구에서는 31%였고, 깔대기 그물의 길이가 35cm의 모형 어구에서는 90%로 나타났는데, 양자의 차이는 59% 정도였다.

• 수산해양기술연구
• /
• 제41권2호
• /
• pp.95-100
• /
• 2005

In order to improve the gill nets for croaker, Miichthys miiuy which is proper to the fishermen's income ans fisheries resource management, we had studied to the net height of present gill nets (mesh size 160mm, 50 mesh in depth), experimental gill nets-I(mesh size 150mm, 68 mesh in depth) and experimental gill nets-II(mesh size 142mm, 75 mesh in depth) in wter using the gill nets design ans analysis simulation system, and then investigated and analyzed the catch efficiency of each gill nets through the field fishing experiments. The net height of emperimental gill nets-I and experimental gill nets-II in water were estimated respectively about 1.5 times and 1.3 times higher than present gill nets which the net height is about 3.5m as the results of simulation considering the current of fishing fields. Total number of croakers which were caught by the persent gill nets was 62(body length 300~1,200mm), total catch weight was 398.7kg (mean 0.6kg/sheet). Total number of croakers which were caught by the experimental gill nets- I was 68(body length 600~1,100mm), total catch weight was 391.6kg (mean 1.2kg/sheet). Total number of croakers which were caught by the experimental gill nets-II was 28(body length 400~900mm), total catch weight was 99.2kg (mean 0.3kg/sheet).