• Journal of the Korea Society of Computer and Information
• /
• v.3 no.1
• /
• pp.95-112
• /
• 1998

The Error Backpropagation algorithm is widely used in various areas such as associative memory, speech recognition, pattern recognition, robotics and so on. However, if and when a new leaning pattern has to be added in order to drill, it will have to accomplish a new learning with all previous learning pattern and added pattern from the very beginning. Somehow, it brings about a result which is that the more it increases the number of pattern, the longer it geometrically progress the time required by leaning. Therefore, a so-called Incremental Learning Method has to be solved the point at issue all by means in case of situation which is periodically and additionally learned by numerous data. In this study, not only the existing neural network construction is still remained, but it also suggests a method which means executing through added leaning by a model pattern. Eventually, for a efficiency of suggested technique, both Monk's data and Iris data are applied to make use of benchmark on machine learning field.

• Physical Therapy Korea
• /
• v.11 no.1
• /
• pp.19-25
• /
• 2004

The purpose of this study was to investigate the effects of backrests of varying degrees ($90^{\circ}$, $100^{\circ}$, $110^{\circ}$) on three abdominal muscles (upper rectus abdominis, external oblique, internal oblique) and back extensor activation during lower extremity exercise. The three different conditions during bilateral knee extention exercise were: (1) leaning on a chair with a $90^{\circ}$ backrest, (2) leaning on a chair with a $100^{\circ}$ backrest, (3) leaning on a chair with a $110^{\circ}$ backrest. Fifteen healthy muscle subjects (mean age=24.2 years [SD=2.96], mean height=175.6 cm [SD=7.46], mean weight=69.1 kg [SD=7.36]) with no history of neuromusculoskeletal disease voluntarily participated in this study. Electromyography was used to collect muscle activation, and the muscle activation was expressed as a percentage of maximal voluntary isometric contraction (%MVIC). Repeated one-way analysis of variance (ANOVA) was used to determine the statistical significance. The results were as follows: (1) upper rectus abdominis, external oblique, internal oblique activation measured significantly lower. (2) measured significantly lower when lower degree.

• Journal of Korean Physical Therapy Science
• /
• v.13 no.3
• /
• pp.15-25
• /
• 2006

The purpose of this study was to investigate effects of different chair type (with backrest chair and without backrest chair) and pelvic position (anterior pelvic tilting and posterior pelvic tilting) on three abdominal muscles (upper rectus abdominis, external oblique, internal oblique) and back extensor activation during lower extremity exercise. The four different conditions during bilateral knee extension exercise were: (1) leaning on backrest chair with anterior pelvic tilting, (2) leaning on backrest chair with posterior pelvic tilting, (3) anterior pelvic tilting without backrest chair, and (4) posterior pelvic tilting without backrest chair. Fifteen healthy male subjects with no history of neuromusculoskeletal disease voluntarily participated in this study. Electromyography (EMG) was used to collect muscle activation data, and muscle activation data was expressed as a percentage of maximal voluntary isometric contraction (%MVIC). One-way repeated analysis of variance (ANOVA) was used to determine the statistical significance, and Bonferroni comparison was used as a post hoc test. The results of this study were the following: (1) Erector spinae activation was significantly lower in posterior pelvic tilting without backrest compared with that in leaning on backrest chair with anterior pelvic tilting. (2) Upper rectus abdominis activation was significantly lower than erector spinae in all four different chair type and pelvic tilting conditions.

• Korean Journal of Applied Biomechanics
• /
• v.19 no.1
• /
• pp.87-98
• /
• 2009

This study was conducted to compare biomechanical differences in throwing movement between skilled and unskilled high school students using three-dimensional analysis system with a force platform. The findings indicated that skilled students showed shorter throwing time, faster horizontal speed of (1) the center of mass at heel contact of left foot, (2) the forearm throughout swing phase, (3) the hand after heel contact while unskilled students showed faster horizontal speed of, (1) the center of mass after heel contact and (2) the hand at heel contact of left foot. Skilled students showed greater (1) shoulder angle during throwing, (2) elbow angle after take off of foot, (3) peak vertical ground reaction force during throwing and (4) peak anterior-posterior ground reaction force at heel contact of right foot. While skilled students showed leaning backward of the trunk during throwing, unskilled students showed leaning forward during release phase with leaning backward before release.

• Journal of Biomedical Engineering Research
• /
• v.21 no.4
• /
• pp.385-390
• /
• 2000

The alignment of the prosthetics is very important in an amputee's gait. In the present study. a static prosthesis-alignment device was developed. It consisted of a force plate with four load cells, a laser beam controlled by a step motor, and a control part programmed by PCBASIC. Using the static prosthesis-alignment device, we measured the distance between the load line and various joints of 24 normal volunteers in three standing postures. such as neutral, forward leaning, and backward leaning. Only neutral postures were evaluated on four trans-tibial amputees. The load line for the normal person's neutral position located anterior to the ankle, the knee, and the greater trochanter, but posterior to the shoulder joint. Forward and backward leaning of the normal person resulted in a significant anterior and posterior movements of the load line, respectively. The load line for the amputated side of the trans-tibial amputee also located anterior to the ankle, the extremity prostheses, providing a good relative locations of the load line with respect to various joints.

• Electronics and Telecommunications Trends
• /
• v.34 no.4
• /
• pp.15-22
• /
• 2019

Recent technological advances in three-dimensional (3D) sensing devices and machine learning such as deep leaning has enabled data-driven 3D applications. Research on artificial intelligence has developed for the past few years and 3D deep learning has been introduced. This is the result of the availability of high-quality big data, increases in computing power, and development of new algorithms; before the introduction of 3D deep leaning, the main targets for deep learning were one-dimensional (1D) audio files and two-dimensional (2D) images. The research field of deep leaning has extended from discriminative models such as classification/segmentation/reconstruction models to generative models such as those including style transfer and generation of non-existing data. Unlike 2D learning, it is not easy to acquire 3D learning data. Although low-cost 3D data acquisition sensors have become increasingly popular owing to advances in 3D vision technology, the generation/acquisition of 3D data is still very difficult. Even if 3D data can be acquired, post-processing remains a significant problem. Moreover, it is not easy to directly apply existing network models such as convolution networks owing to the various ways in which 3D data is represented. In this paper, we summarize technological trends in AI-based 3D content generation.

• Journal of Gifted/Talented Education
• /
• v.21 no.1
• /
• pp.175-191
• /
• 2011

This study is to investigate the creative thinking style and it's leaning that normal students and scientifically gifted students use mainly at processing information. Right Brain vs Left Brain Creativity Test(R/LCT) and Brain Preference Indicator(BPI) is taken to investigate the creative thinking style of normal students(N=144) and scientifically gifted students(N=97). In the R/LCT, the normal students responded that they prefer to use right-brain thinking rather than left-brain thinking. But the scientifically gifted students prefer to left-brain thinking. The normal students showed most preference for Holistic Processing of right side brain and they did most avoiding for Verbal Processing of left side brain. The scientifically gifted students showed most preference for Logical Processing of left side brain. And they did most avoiding for Random Processing of right side brain. There was a meaningful difference between left side brain preference group and right side brain preference group on Sequential, Symbolic, Logical, Verbal, Random, Intuitive, Fantasy-oriented Processing of normal Students. But the scientifically gifted students showed a meaningful difference in right side brain processing mainly. In other word, all the scientifically gifted students took an lean processing in Logical, Symbolic, Linear Processing, etc. In sum, the scientifically gifted students are unequal in at processing information against the normal students. So it is required more appropriate teaching-learning method based on the creative thinking style and it's leaning for effective gifted education.

• Journal of the Korea Convergence Society
• /
• v.10 no.6
• /
• pp.95-101
• /
• 2019

The purpose of this study was to determine whether PNF respiratory convergence exercise increases the pulmonary function of normal adults by $45^{\circ}$ leaning sitting position. Twenty normal adults in their 20s were randomly assigned to an experimental group (n=10) or control group (n=10). Over the course of four weeks, the experimental group participated in PNF respiration exercises by $45^{\circ}$ leaning position for 30 minutes three per week. And the control group participated in PNF respiration exercises by supine position for 30 minutes three times per week. Subjects were assessed pre-test and post-test by measurement of pulmonary function. Our findings show that the experimental group had significant improvements in expiratoy reserve volume and vital capacity, maximal voluntary volume. In this study, the experimental group showed greater improvement in pulmonary function than the control group, which indicates that the PNF respiratory exercise by $45^{\circ}$ leaning sitting position is effective at increasing the pulmonary function of normal adults.

• 제어로봇시스템학회:학술대회논문집
• /
• 1988.10a
• /
• pp.326-331
• /
• 1988

In this paper, an iterative leaning control algorithm for the linear discrete system is proposed. Based upon the parameter estimation method, the learning for good tracking control is acqured through a sequence of repetitive operations. A series of simulation are performed to show the validity of this algorithm.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.13 no.4
• /
• pp.81-90
• /
• 2017

This paper presents a smart seat for correction of driver posture while driving. We introduce good postures with seat height, seat angle, head height, back of knees, distances of foot pedals, tilt of seat, etc. There have been some studies on correction of good posture while driving, effects of driving environment on driver's posture, sitting strategies based on seating pressure distribution, estimation of driver's standard postures, and others. However, there are a few studies on guide of good postures while driving for problem of driver's posture using machine leaning. Therefore, we suggest a smart seat for correction of driver's posture based on machine leaning, 1) developed the system to get postures by 10 piezoelectric effect element, 2) collect piezoelectric values from 37 drivers and 28 types of cars, 3) suggest 4 types of good postures while driving, 4) analyze test postures by kNN. As the results, we can guide good postures for bad or problems of postures while driving.