• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.12
• /
• pp.1652-1662
• /
• 1995

In this paper, a hybrid neural network is proposed to improve the learning ability of a neural network. The union of the characteristics of a Self-Organizing Neural Network model and of multi-layer perceptron model using the backpropagation learning method gives us the advantage of reduction of the learning error and the learning time. In learning process, the proposed hybrid neural network reduces the number of nodes in hidden layers to reduce the calculation time. And this proposed neural network uses the fuzzy feedback values, when it updates the responding region of each node in the hidden layer. To show the effectiveness of this proposed hybrid neural network, the boolean function(XOR, 3Bit Parity) and the solution of inverse kinematics are used. Finally, this proposed hybrid neural network is applied to the visual tracking control of a PUMA560 robot, and the result data is presented.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.8 no.3
• /
• pp.228-234
• /
• 2016

Recent icebreaking ships need to be designed to enhance not only icebreaking capability but also turning ability. For the evaluation of ice resistance induced by an icebreaking hull form, HHI (Hyundai Heavy Industries) has developed the hybrid empirical formulas (Park et al., 2015) by considering the geometrical hull shape features, such as waterline and underwater sections. However, the empirical formulas have inherent limits to the precise estimation of the icebreaking and turning ability because the breaking process and the resulting pattern are ignored. For this reason, numerical calculation in time domain is performed to predict the icebreaking process and pattern. In the simulation, varying crushing stress according to velocity vectors and contact areas between hull and ice is newly introduced. Moreover, the simulation results were verified by comparing them with the model test results for three different bow-first icebreaking models.

• Proceedings of the KIEE Conference
• /
• 2003.07a
• /
• pp.366-368
• /
• 2003

In this paper, a parametric evaluation method of protection ability is proposed. The adequacy of every parameter is evaluated for the setting rules. Then the results are combined to give protection level of a whole protective system. The setting rules are categorized into three groups for hierarchical calculation. The proposed scheme is applied to a location problem of a new protective device to show its effectiveness.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.157.6-157
• /
• 2001

We estimated various neuron functions to construct of engineering neurons, which are the combination of sigmoid, linear, sine, quadric, double/single bended, soft max/minimum functions. These combinations are estimated by the property on the potential surface between the learning points, calculation speed, and learning convergence; because the surface depends on the inference ability of a neuron system; and speed and convergence are depend on the efficiency on the points of engineering applications. After the evaluating discussions, we can select more appropriate combination than original sigmoid function´s, which is single bended function and linear one. The combination ...

• 제어로봇시스템학회:학술대회논문집
• /
• 1987.10b
• /
• pp.101-104
• /
• 1987

This paper shows the robot-vision system which consists of robot, vision system, single board computer and IBM-PC. IBM-PC based system has a great flexibility in expansion for a vision system interfacing. Easy human interfacing and great calculation ability are the benefits of this system. It was carried to interface between each component. The calibration between two coordinate systems is studied. The robot language for robot-vision system was written in "C" language. User also can write job program in "C" language in which the robot and vision related functions reside in the library.side in the library.

• Proceedings of the IEEK Conference
• /
• 2001.06a
• /
• pp.289-292
• /
• 2001

This paper investigates a RBF equalizer (RBFE) reducing a center Estimating Speed. One of method for RBF center estimation is using k-means clustering. The performance of RBFE is depends on the estimation ability of the RBF center. We Propose a RBF Equalizer using modified k-means clustering algorithm (MKMC) to speed up channel estimation and to reduce complexity of calculation. Computer simulations are included to illustrate the analytical results. It is shown that a discussed method improves about 1 dB via less training data.

• Journal of the Ergonomics Society of Korea
• /
• v.1 no.2
• /
• pp.11-15
• /
• 1982

There is the possibility that human error during testing and maintenance brings about the failure of the system, the reliability of which depends on mechanical failure and human error. This paper deals with the calculation of the reliability of the redundant system with the dependent hunman error through Karnaugh Map. Two cases are considered. One is the reli- ability of the system neglecting the test interval of each component and the other is that considering the test interval of each component.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.49.4-49
• /
• 2001

Digit recognition based on backpropagation neural networks, as an important application of pattern recognition, was attracted much attention. Although it has the advantages of parallel calculation, high error-tolerance, and learning capability, better recognition effects can only be achieved with some specific fixed format input of the digit image. Therefore, digit image preprocessing ability directly affects the accuracy of recognition. Here using Matlab software, the digit image was enhanced by resizing and neutral-rotating the extracted digit image, which improved the digit recognition capability of the backpropagation neural network under practical conditions. This method may also be helpful for recognition of other patterns with backpropagation neural networks.

• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.16 no.2
• /
• pp.158-164
• /
• 2005

Melody intonation therepy (MIT) is to improve the linguistic aspects of the verbal utterance for aphasic patients utilizing the intact right brain. It is applied to the aphasic patients with good comprehension, poor fluency, and little available speech are thought to be ideal candidates. The purpose of the study was to investigate the effects of Korean Melody intonation therapy (kMIT) in patients with non-fluent aphasia. Five male non-fluent aphasic patients were participated in this study. Average ages were 49.9 years old. Each therapy took 45-50minutes once a week for six months. Aphasic Screen lest (RISS) was used to assess language parameter such as Auditory comprehension, oral expression, reading, writing and calculation ability before and after kMIT. Mean of Length Utterance, verbal intelligibility and articulation disorder were assessed also. Computerized Speech Lab was used to assess the acoustic characteristics of aphasic patients before and after kMIT. The results are as follows : 1) Auditory comprehension, oral expression, reading, writing and calculation ability of the subjects increased after UH'. However, only oral expression showed significant difference (p<0.05). 2) Mean of Length Utterance of five patients generally increased after Un. 3) After kMIT, verbal intelligibility increased and showed significant difference (p<0.05). 4) Misarticulation rate generally decreased after m. 5) Voice Onset Time of the alveolar lenis /t/ and velar lenis /k/ gradually decreased after kMIT. 6) However, intonation pattern were increased gradually in yes'no question after kMIT.

• Journal of Preventive Medicine and Public Health
• /
• v.55 no.1
• /
• pp.106-113
• /
• 2022

Objectives: Previous studies have found that the oral health of seniors can affect their physical nutrition and quality of life (QoL). Additionally, poor oral health can lead to the development of dementia, which is associated with decreased cognitive function. This study aimed to examine the impact of geriatric oral health (GOH) on the QoL of Korean seniors and the mediating effects of cognitive function. Methods: We used data from the seventh Korean Longitudinal Study of Aging conducted in 2018. In total, 4049 seniors were included in our study. We analyzed the impact of GOH on QoL according to 5 mediating domains of cognitive function and control variables. To examine each path of mediating effects, bootstrapping with 5000 iterations was performed with 95% confidence intervals. Results: Our findings revealed that good GOH had a positive effect on the QoL of seniors. Also, better GOH corresponded to a higher degree of cognitive function within all 5 domains: orientation, memory registration, attention/calculation, memory recall, and language and visuospatial ability. In addition, 3 domains of the 5 domains (attention/calculation, memory recall, and language and visuospatial ability) had significant mediating effects on the relationship between GOH and QoL. Conclusions: This study suggests that adequate management of GOH is crucial for promoting a better QoL and a high degree of cognitive function among seniors. To prevent cognitive impairment, such as dementia, future studies should take a more targeted approach by examining data according to each cognitive domain and various socio-demographic factors.