• Journal of Ocean Engineering and Technology
• /
• v.11 no.1
• /
• pp.84-95
• /
• 1997

This paper presents a new approach to the design speed and azimuth control of a mobile robot with drive wheel. The proposed control scheme uses a Gaussian function as a unit function in the fuzzy-neural network, and back propagation algorithm to train the fuzzy-neural network controller in the frmework of the specialized learning architecture. It is proposed a learning controller consisting of two neural network-fuzzy based on independent reasoning and a connection net with fixed weights to simple the neural networks-fuzzy. The performance of the proposed controller is shown by performing the computer simulation for trajectory tracking of the speed and azimuth of a mobile robot driven by two independent wheels.

• Steel and Composite Structures
• /
• v.34 no.6
• /
• pp.795-802
• /
• 2020

The subject of the paper is a circular plate with symmetrically thickness-wise varying mechanical properties. The plate is simply supported and carries a concentrated force located in its centre. The axisymmetric bending problem of the plate with consideration of the shear effect is analytically and numerically studied. A nonlinear function of deformation of the straight line normal to the plate neutral surface is assumed. Two differential equations of equilibrium based on the principle of stationary potential energy are obtained. The system of equations is analytically solved and the maximum deflections and shear coefficients for example plates are derived. Moreover, the maximum deflections of the plates are calculated numerically (FEM), for comparison with the analytical results.

• Journal of the Korean Society for Precision Engineering
• /
• v.28 no.9
• /
• pp.1103-1109
• /
• 2011

This research quantitatively confirmed an acoustical anisotropy that exists in a pure titanium plate from the signal of ultrasonic flow detection and suggested a new way to evaluate the acoustical anisotropy by inputting acquired characteristic of ultrasound signal into the neutral network. Using the fact with the suggested method that the characteristic of ultrasound signal is shown differently depending on the pure titanium plate's rolling direction, the neural network was constructed by extracting the characteristic that can decide each direction of $0^{\circ}$, $45^{\circ}$, and $90^{\circ}$ with waveform analysis program. As a result of inputting the characteristic of ultrasound signal acquired from a random rolling direction into the neural network that was built like this, it showed a pattern recognition rate higher than 95% on directions of $0^{\circ}$, $45^{\circ}$, $90^{\circ}$.

• Journal of Korea Multimedia Society
• /
• v.21 no.10
• /
• pp.1195-1202
• /
• 2018

Artificial neural network is widely used for its excellent performance and implementability. However, traditional neural network needs to learn the system from scratch, with the addition of new input data, the variation of the observation environment, or the change in the form of input/output data. To resolve such a problem, the technique of transfer learning has been proposed. Transfer learning constructs a newly developed target system partially updating existing system and hence provides much more efficient learning process. Until now, transfer learning is mainly studied in the field of image processing and is not yet widely employed in acoustic data processing. In this paper, focusing on the scalability of transfer learning, we apply the concept of transfer learning to the problem of guitar chord classification and evaluate its performance. For this purpose, we build a target system of convolutional neutral network (CNN) based 48 guitar chords classification system by applying the concept of transfer learning to a source system of CNN based 24 guitar chords classification system. We show that the system with transfer learning has performance similar to that of conventional system, but it requires only half the learning time.

• Journal of the Korean association of regional geographers
• /
• v.20 no.1
• /
• pp.30-48
• /
• 2014

Relying on the interaction indices - dominance index, relative strength index and entropy index, this paper analyzes the structural features of urban network in the Seoul metropolitan area with the flows of commuting, business, and freight. Analytical results show that the Seoul metropolitan urban system is vertical, size-dependent, one-way, and the highest city-dominant network rather than horizontal, size-neutral, two-way, complementary one. The network of freight flow is a little bit more symmetrical than the networks of commuting and business. However, the interaction with Seoul is still determinant in all aspects of hierarchical structure, relative strength, and symmetry of flow.

• Proceedings of the Korean Society of Tribologists and Lubrication Engineers Conference
• /
• 1995.06a
• /
• pp.65-71
• /
• 1995

기계 윤활면내에 포함된 마멸입자는 기계시스템의 상태를 잘 대변하여 주므로 마멸입자의 크기분포, 단위체적당 입자수, 구성성분 및 형상 등의 정확한 규명은 기계시스템의 상태진단을 위한 여러 정보를 제공한다. 특히 마멸입자의 형상과 그 크기는 미시적 파괴현상인 마멸과정의 기구를 반영해 주고 있으며, 또한 마멸입자의 표면은 그것이 마찰면 혹은 파단면의 미시적인 형상과 반응 생성물을 포함하고 있는 표본이 된다. 본 연구에서는 마멸분의 형상, 크기, 표면광택 등과 그것이 발생하는 작동조건과의 관계를 인공 신경회로망 해석을 이용하여 기계 윤활면의 마멸분 형태인식에 적용하는 것을 목적으로 하였다.

• 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 housing association
• /
• v.26 no.3
• /
• pp.99-108
• /
• 2015

The purpose of this study was to determine the relationship between subjective happiness and social capital. The data for the analysis were collected via the questionnaire survey method, from October 29 to November 10, 2013. The sample consisted of 338 residents, living in Seoul and Gyeonggi-Do province. Social capital is composed of the social network, social trust and social norms. The social network is composed of the satisfaction of one's social relations, and the degree of social interaction. Social trust is composed of the trust in ones's neighbors and the local community. Social norms are composed of reciprocity, participation and a sense of belonging and solidarity. The findings of this study were as follows: 1) The average for subjective happiness was 3.82 points, over neutral. In particular, the subjective happiness of people over 50 years old was highest. 2) The social network, social trust, and social norms were related to the subjective happiness.

• Steel and Composite Structures
• /
• v.15 no.4
• /
• pp.451-466
• /
• 2013

This paper deals with the multi-objective optimization of tire reinforcement structures such as the tread belt and the carcass path. The multi-objective functions are defined in terms of the discrete-type design variables and approximated by artificial neutral network, and the sensitivity analyses of these functions are replaced with the iterative genetic evolution. The multi-objective optimization algorithm introduced in this paper is not only highly CPU-time-efficient but it can also be applicable to other multi-objective optimization problems in which the objective function, the design variables and the constraints are not continuous but discrete. Through the illustrative numerical experiments, the fiber-reinforced tire belt structure is optimally tailored. The proposed multi-objective optimization algorithm is not limited to the tire reinforcement structure, but it can be applicable to the generalized multi-objective structural optimization problems in various engineering applications.

• Journal of Engineering Education Research
• /
• v.23 no.2
• /
• pp.24-30
• /
• 2020

This paper proposes the approaches to the evaluation of learning using concepts of artificial intelligence. Among various techniques, deep learning algorithm is employed to achieve quantitative results of evaluation. In particular, this paper focuses on the process-based evaluation instead of the result-based one using face expression. The expression is simply acquired by digital camera that records face expression when students solve sample test problems. Face expressions are trained using convolutional neural network (CNN) model followed by classification of expression data into three categories, i.e., easy, neutral, difficult. To substantiate the proposed approach, the simulation results show promising results, and this work is expected to open opportunities for intelligent evaluation system in the future.