• 한국전문물리치료학회지
• /
• 제30권2호
• /
• pp.128-135
• /
• 2023

Background: Despite the fact that aquatic exercise is one of the most popular alternative treatment methods for children with cerebral palsy (CP), there are few research regarding its effectiveness. Objects: The purpose of this study was to examine the effects of aquatic exercise on upper extremity function and postural control during reaching in children with CP. Methods: Ten participants (eight males and two females; 4-10 years; Gross Motor Function Classification System levels II-IV) with spastic diplegia were recruited to this study. The aquatic exercise program consisted of four modified movements that were selected from the Halliwick 10-point program to enhance upper extremity and trunk movements. The participants attended treatment two times a week for 6 weeks, averaging 35 minutes each session. The Box and Block Test (BBT), transferring pennies in the Bruininks-Oseretsky Test (BOT), and pediatric reaching test (PRT) scores were used as clinical measures. Three-dimensional motion analysis system was used to collect and analyze kinematic data. Differences in BBT and BOT values among pre-treatment, post-treatment, and retention (after 3 weeks) were analyzed using a Friedman test. In addition, the PRT scores and variables (movement time, hand velocity, straightness ratio, and number of movement units) from the three-dimensional motion analysis were tested using a Wilcoxon signed-rank test. The significance level was established at p < 0.05. When the results appeared to be statistically significant, a post-hoc test for multiple comparisons was performed with the Wilcoxon signed-rank test. Results: All clinical measures, which included BBT, transferring pennies of BOT, and PRT, were significantly increased between pre-intervention and post-intervention scores and between pre-intervention and retention scores after treatment (p = 0.001). Three-dimensional motion analysis mostly were significantly improved after treatment (p = 0.001). Conclusion: Aquatic exercise may help to improve body function, activity, and participation in children with varying types of physical disabilities.

• 자원리싸이클링
• /
• 제26권2호
• /
• pp.46-55
• /
• 2017

본 연구에서는 레이저유도붕괴분광(Laser Induced Breakdown Spectroscopy, LIBS)을 이용하여 방사형 기저함수 신경회로망(Radial Basis Function Neural Networks, RBFNNs) 분류기 설계방법론을 개발하고 실제 폐소형가전제품의 플라스틱 분류 시스템에 적용하였다. ABS, PP, PS와 같은 검정색 플라스틱을 구별하기 위해, 지능형 알고리즘 중 하나인 방사형 기저함수 신경회로망 분류기를 설계하였다. 획득한 입력변수는 주성분 분석법(Principal Component Analysis, PCA)을 이용하여 축소시켰으며, 군집화기법 중 하나인 K-means 클러스터링 방법을 이용해 여러 그룹으로 분할하였다. 전체 데이터는 학습 데이터와 테스트 데이터를 4:1의 비율로 나누었으며, 제안된 분류기의 성능 및 신뢰도를 평가하기 위하여 5-FCV(5-Fold Cross Validation) 기법을 사용하였다. 입력변수와 클러스터의 개수가 각각 5개인 경우, 제안된 분류기의 분류 성능은 96.78%로 나타났다. 또한, 제안된 분류기는 다른 분류기들과 비교하였을 경우 분류 성능의 관점에서 우수성을 보여주었다.

• 한국산학기술학회논문지
• /
• 제20권8호
• /
• pp.431-440
• /
• 2019

이 연구는 경직성 뇌성마비 아동을 대상으로 1년간 물리 및 작업치료 후 대동작 기능분류체계에 따라 일상생활동작 변화정도가 차이가 있는지 그리고 소아장애척도지수와 아동용 일상생활 기능독립 측정 중 어떤 평가도구가 일상생활 동작의 변화에 민감하게 반응하는지를 알아보기 위해 시행되었다. 48명의 경직성 뇌성마비 아동이 참여하였고, 대동작 기능분류체계, 아동용 일상생활 기능독립 측정, 그리고 소아장애척도지수를 측정하였다. 연구결과, 대동작 기능분류체계는 소아장애척도지수와 유의한 상관을 보였지만(p<0.05) 아동용 일상생활 기능독립 측정과 유의한 상관을 보이지 않았다. 또한 중재 전과 후 일상생활동작의 변화는 아동용 일상생활 독립측정인 경우 유의한 차이를 보이지 않았지만, 소아장애척도지수인 경우 유의한 차이를 보였다(p<0.05). 대동작 기능분류체계에 따라 일상생활동작의 변화는 유의하게 차이가 있었으며, 기능수준이 높은 경우 일상생활동작이 변화가 유의하게 컸었다(p<0.05). 물리 및 작업치료 후 대동작 기능 분류체계에 따라 일상생활동작의 향상정도는 다르지만 임상적으로 의미 있게 향상되는 것으로 보이며, 소아장애척도지수는 일상생활동작의 변화에 민감하게 반응하므로 임상에서 폭 넓게 활용하는 것이 필요한 것으로 여겨진다.

• The Journal of Korean Physical Therapy
• /
• 제26권3호
• /
• pp.209-215
• /
• 2014

Purpose: The purpose of this study is to examine the effects of postural control training using a horseback riding simulation on the spinal alignment of children with cerebral palsy. Methods: This study was conducted with 30 children with cerebral palsy at levels I~IV in the Gross Motor Function Classification System (GMFCS), and they were randomly divided into a control group and a hippotherapy group. Both the control group and the experimental group received NDT for 30 minutes per session, four times per week for ten weeks, while the experimental group also received hippotherapy 15 minutes per session, four times per week for ten weeks, after the neurodevelopmental treatment (NDT). The horseback riding simulators (JOBA, EU7805, Panasonic) used in this study simulated actual horse movements. Trunk imbalance, pelvic torsion, and pelvic tilt were measured in each group before the exercise and five weeks and ten weeks after the beginning of the exercise using a spinal structure analysis system (ABW Mapper). Results: The Intra-group effects on trunk imbalance, pelvic torsion, and pelvic tilt according to the exercise periods after the hippotherapy were tested, and the results showed significant interaction effects between the groups and the periods (p<0.05). Conclusion: The horseback riding simulation exercise was shown to be effective for the spinal alignment of children with cerebral palsy. Therefore, additional studies should be conducted with more children with CP divided by type.

• 한국정보처리학회논문지
• /
• 제4권9호
• /
• pp.2299-2308
• /
• 1997

대부분의 기계학습 방법들은 특정한 방법을 중심으로 연구되어 왔다. 하지만 두 가지 이상의 기계학습방법을 효과적으로 통합할 수 있는 방법에 대한 요구가 증가하며, 이에 따라 본 논문은 귀납법칙 (rule induction) 방법과 개체위주 학습방법 (instance-based learning)을 통합하는 시스템의 개발을 제시한다. 귀납법칙 단계에서는 엔트로피 함수의 일종인 Hellinger 변량을 사용하여 귀납법칙을 자동 생성하는 방법을 보이고, 개체위주 학습방법에서는 기존의 알고리즘의 단점을 보완한 새로운 개체위주 학습방법을 제시한다. 개발된 시스템은 여러 종류의 데이터에 의해 실험되었으며 다른 기계학습 방법과 비교되었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권8호
• /
• pp.3806-3825
• /
• 2016

This paper brings out a neoteric frame of reference for visual semantic based 3d video search and retrieval applications. Newfangled 3D retrieval application spotlight on shape analysis like object matching, classification and retrieval not only sticking up entirely with video retrieval. In this ambit, we delve into 3D-CBVR (Content Based Video Retrieval) concept for the first time. For this purpose we intent to hitch on BOVW and Mapreduce in 3D framework. Here, we tried to coalesce shape, color and texture for feature extraction. For this purpose, we have used combination of geometric & topological features for shape and 3D co-occurrence matrix for color and texture. After thriving extraction of local descriptors, TB-PCT (Threshold Based- Predictive Clustering Tree) algorithm is used to generate visual codebook. Further, matching is performed using soft weighting scheme with L₂ distance function. As a final step, retrieved results are ranked according to the Index value and produce results .In order to handle prodigious amount of data and Efficacious retrieval, we have incorporated HDFS in our Intellection. Using 3D video dataset, we fiture the performance of our proposed system which can pan out that the proposed work gives meticulous result and also reduce the time intricacy.

• 한국측량학회지
• /
• 제35권5호
• /
• pp.423-430
• /
• 2017

Recently, data analysis research has been carried out using the deep learning technique in various fields such as image interpretation and/or classification. Various types of algorithms are being developed for many applications. In this paper, we propose a precipitation prediction algorithm based on deep learning with high accuracy in order to take care of the possible severe damage caused by climate change. Since the geographical and seasonal characteristics of Korea are clearly distinct, the meteorological factors have repetitive patterns in a time series. Since the LSTM (Long Short-Term Memory) is a powerful algorithm for consecutive data, it was used to predict precipitation in this study. For the numerical test, we calculated the PWV (Precipitable Water Vapor) based on the tropospheric delay of the GNSS (Global Navigation Satellite System) signals, and then applied the deep learning technique to the precipitation prediction. The GNSS data was processed by scientific software with the troposphere model of Saastamoinen and the Niell mapping function. The RMSE (Root Mean Squared Error) of the precipitation prediction based on LSTM performs better than that of ANN (Artificial Neural Network). By adding GNSS-based PWV as a feature, the over-fitting that is a latent problem of deep learning was prevented considerably as discussed in this study.

• 한국응용약물학회:학술대회논문집
• /
• 한국응용약물학회 1997년도 추계학술대회
• /
• pp.57-74
• /
• 1997

To make a proposal for the revision of KGCP, ICH Harmonized Tripartite Guideline for Good Clinical Practice, which is on the stage of worldwide implementation, was compared with current GCPs of tripartite countries of ICH, namely USA, Europe and Japan as well as Korea. On the basis of the classification in ICH GCP, comprehensive comparisons among the corresponding articles of 4 regions or countries were made in the order of IRB / IEC, Investigator, Sponsor and Clinical Trial Protocol. Based on the comparisons of the contents in ICH-GCP with those in current GCPs, major suggestions for the revision of current KGCP can be made as follows. Firstly, the function of IRB / IEC needs to be strengthened for the initiation and continuation of clinical trial. Current 2-step approval system of IRB / IEC and Health Authorities requires to be converted into the system similar to that of developed countries. Secondly, sponsor's obligation needs to be tightened to control and assure the quality of clinical trial. Inspection of regulatory authorities should be made to perform during and / or after clinical trial, when it is necessary. In other words, sponsor should be made to establish written Standard Operating Procedures (SOPs) for all aspects of clinical trial including monitoring to ensure that trials are conducted and data are generated, documented, and reported in compliance with the protocol, GCP, and the applicable regulatory requirement (s). Besides, the provision of ‘Quality Control and Quality Assurance’ should be added to the protocol to establish the credibility of the result of the clinical trial.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2008년도 학술대회 논문집 정보 및 제어부문
• /
• pp.187-192
• /
• 2008

로봇 시스템의 신경망 포화 및 퍼지 데드존 보상기를 제안한다. 퍼지논리 함수의 분류특성과 신경회로망의 함수 근사화 능력은 포화와 데드존에 의해 유발되는 오자를 제거하기 위한 보상기 설계를 가능케 한다. 포화 및 데드존 보상이 적응적이고 추적오차와 파라미터 추정 치가 유계가 되는 신경망 가중치와 퍼지논리 파라미터 동조알리리듬과 안정도 증명을 제시한다. 신경망 포화 및 퍼지 데드존 보상기를 모의실험으로 포화 및 데드존의 해로운 영향을 줄이는 효과를 보여 준다.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2007년도 한국지능정보시스템학회
• /
• pp.309-320
• /
• 2007

The data imbalance problem which can be uncounted in data mining classification problems typically means that there are more or less instances in a class than those in other classes. It causes low prediction accuracy of the minority class because classifiers tend to assign instances to major classes and ignore the minor class to reduce overall misclassification rate. In order to solve the data imbalance problem, there has been proposed a number of techniques based on resampling with replacement, adjusting decision thresholds, and adjusting the cost of the different classes. In this paper, we study the feasibility of the combination usage of the techniques previously proposed to deal with the data imbalance problem, and suggest a combination method using genetic algorithm to find the optimal combination ratio of the techniques. To improve the prediction accuracy of a minority class, we determine the combination ratio based on the F-value of the minority class as the fitness function of genetic algorithm. To compare the performance with those of single techniques and the matrix-style combination of random percentage, we performed experiments using four public datasets which has been generally used to compare the performance of methods for the data imbalance problem. From the results of experiments, we can find the usefulness of the proposed method.