• Proceedings of the KSR Conference
• /
• 2004.10a
• /
• pp.1101-1106
• /
• 2004

Rainfall induced landslides are disasters causing sever damage on the human life and the infrastructures. In this paper, a simplified procedure to evaluate the slope stability problems induced by rainfall by modifying the Iverson's pressure head dispersion model. The proposed approach extends the applicability of the Iverson's model in to the cases of higher rainfall intensity than the permeability of the soil by incorporating the existence of overland flow. In addition, the Manning equation is applied to calculated the depth of overland flow. From the calculated depth of overland flow, shear stress acting on the surface is included for the driving component triggering the landslides. From the analysis of a case study, the long term rainfall alters the stability of slope.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.17 no.2 s.105
• /
• pp.207-212
• /
• 2006

A variety of wireless devices are commercially available now. Most of studies, however, have been directed to the biological effects of mobile-phone EMF. In this paper, dosimetric analysis for wireless devices of head-mounted display type and a wristwatch type were made to investigate possible biological effects of these devices. SAR(Specific Absorption Rate) distributions were calculated using FDTD(Finite Difference Time Domain) method, for adult human models such as standard Korean human model and VHP(Visible Human Project) model, as well as scaled child models. Measurements were also performed for SAM phantom wearing a simplified prototype for a wireless device for validation of the simulation results. It has been found that children are more vulnerable to such exposure, and these devices could cause some biological effects even for relatively lower power compared to conventional mobile pones.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.413-415
• /
• 2022

Since human joints can be used as useful information for analyzing human behavior as a component of the human body, many studies have been conducted on human action recognition using joint information. However, it is a very complex problem to recognize human action that changes every moment using only each independent joint information. Therefore, an additional information extraction method to be used for learning and an algorithm that considers the current state based on the past state are needed. In this paper, we propose a human action recognition technique considering the positional relationship of connected joints and the change of the position of each joint over time. Using the pre-trained joint extraction model, position information of each joint is obtained, and bone information is extracted using the difference vector between the connected joints. In addition, a simplified neural network is constructed according to the two types of inputs, and spatio-temporal features are extracted by adding LSTM. As a result of the experiment using a dataset consisting of 9 behaviors, it was confirmed that when the action recognition accuracy was measured considering the temporal and spatial relationship features of each joint, it showed superior performance compared to the result using only single joint information.

• Korean Journal of Remote Sensing
• /
• v.19 no.1
• /
• pp.61-70
• /
• 2003

This paper proposes an autonomous approach to localize the center of fiducial marks included in aerial photographs without precise geometric information and human interactions. For this localization, we present a conceptual model based on two assumptions representing symmetric characteristics of fiducial area and fiducial mark. The model makes it possible to locate exact center of a fiducial mark by checking the symmetric characteristics of pixel value distribution around the mark. The proposed approach is composed of three steps: (a) determining the symmetric center of fiducial area, (b) finding the center of a fiducial mark with unit pixel accuracy, and finally (c) localizing the exact center up to sub-pixel accuracy. The symmetric center of the mark is calculated tv successively applying three geometric filters: simplified ${\nabla}^2$G (Laplacian of Gaussian) filter, symmetry enhancement filter, and high pass filter. By introducing a self-diagnosis function based on the self-similarity measurement, a way of rejecting unreliable cases of center calculation is proposed, as well. The experiments were done with respect to 284 samples of fiducial marks composed of RMK- and RC-style ones extracted from 51 scanned aerial photographs. It was evaluated in the visual inspection that the proposed approach had resulted the erroneous identification with respect to only one mark. Although the proposed approach is based on weak constraints, being free from the exact geometric model of the fiducial marks, experimental results showed that the proposed approach is sufficiently robust and reliable.

• Journal of the Korean Society of Safety
• /
• v.22 no.2 s.80
• /
• pp.59-66
• /
• 2007

As the need of handling heavy materials increases, various cranes are used in industries. However, the effectiveness of crane also entails industrial accidents such as falling, constriction etc. In fact, the number of fatal accidents caused by crane is still high in Korea. To find out the causes of the accidents in terms of human error, we developed a man-machine system model that consists of two axes; human information processing and crane life cycle. In the human information processing dimension, we simplified it as five functions; sensing and perception, decision making and memory, response etc. In the crane life cycle dimension, we divided it into nine phases; design, production, operation etc. For the 152 fatal accident records during 1999-2006 years, we classified them into 45 cells made by two axes. Then we identified the preceding causes of the classified crane accident based on performance shaping factors. As the results of statistical analysis, the overall trend of crane fatal accidents was described. For the cause analysis, wrong decision making in work plan phase shows the highest frequency. Next, the poor information input in crane operation followed in accident frequency. In ergonomics view, the problems of interface design in displays and controls made 11.8% of fatal accidents. Following the analysis, several ergonomic design guidelines to prevent crane accidents were suggested.

• Anxiety and mood
• /
• v.1 no.1
• /
• pp.14-17
• /
• 2005

By the influence of the descriptive approach of DSM-III, the anxiety became the same thing as the anxiety disorder to the clinicians. This unfortunate result sacrificed psychodynamic model of symptom formations and simplified the anxiety as one of the disease entity not as the overdetermined symptoms. These phenomenon awakened the psychoanalytic interest which was in sleep. Freud was the first major articulator of the basic significance of anxiety in human behavior. He attributed the particular quality of the anxiety experience to the trauma of birth, and subsequently to the fear of castration. Such classification of the anxiety according to the psychosexual development is helpful for the clinicians in understanding the origin of anxiety which the patient shows during the psychotherapy. The other analytical view of interpersonal psychoanalysis came from Sullivan. A large part of his therapy is taken up with recognizing and correcting parataxic distortions that interfere with realistic self-appraisal of events and of oneself in relation to others. Perhaps no explanation is the 'most basic' explanation for human anxiety. Anxiety is a multifaceted entity consisting of aspects of realm of discourse. Existential anxiety is inescapable in Western culture but it can be transcended by the cultivation of mind in Eastern culture. The analysts need to stay attuned to their own propensities for anxiety and must permit their own experiences with anxiety to be the grist for the psychotherapeutic mill.

• Journal of Korea Society of Industrial Information Systems
• /
• v.5 no.1
• /
• pp.47-52
• /
• 2000

This study objectively in examines materials related to factory rationalization of D Corp., a regionally based enterprise. One reason that previous factory rationalizations have not been all that effective is that each firm has not used strategies specially designed for it Despite the fact that each firm has a different culture, and different human and physical resources, the application of rationalization without any modifications has produced many problems. In order to stabilize the production system and reduce the capacity of the factory, D Corp. changed the basic 5 S's and stimulated the factory atmosphere through computer education. Rationalization stabilized and standardized the factory, and organized the physical resources and each area of the factory according to their place in the process of production. It also made improvements that verified the party responsible for the flow of the complex production system, and simplified analysis supervision of production, and ex post management. We think that the successful example of D Corp. can serve as a real, tangible model for small and medium regionally-based firms to follow.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.385-398
• /
• 2021

The complexity of deep learning models affects the real-time performance of gesture recognition, thereby limiting the application of gesture recognition algorithms in actual scenarios. Hence, a residual learning neural network based on a deep convolutional neural network is proposed. First, small convolution kernels are used to extract the local details of gesture images. Subsequently, a shallow residual structure is built to share weights, thereby avoiding gradient disappearance or gradient explosion as the network layer deepens; consequently, the difficulty of model optimisation is simplified. Additional convolutional neural networks are used to accelerate the refinement of deep abstract features based on the spatial importance of the gesture feature distribution. Finally, a fully connected cascade softmax classifier is used to complete the gesture recognition. Compared with the dense connection multiplexing feature information network, the proposed algorithm is optimised in feature multiplexing to avoid performance fluctuations caused by feature redundancy. Experimental results from the ISOGD gesture dataset and Gesture dataset prove that the proposed algorithm affords a fast convergence speed and high accuracy.

• Earthquakes and Structures
• /
• v.24 no.2
• /
• pp.111-126
• /
• 2023

Highly reliable and versatile methods artificial intelligence (AI) have found multiple application in the different fields of science, engineering and health care system. In the present study, we aim to utilize AI method to investigated vibrations in the human leg bone. In this regard, the bone geometry is simplified as a thick cylindrical shell structure. The deep neural network (DNN) is selected for prediction of natural frequency and critical buckling load of the bone cylindrical model. Training of the network is conducted with results of the numerical solution of the governing equations of the bone structure. A suitable optimization algorithm is selected for minimizing the loss function of the DNN. Generalized differential quadrature method (GDQM), and Hamilton's principle are used for solving and obtaining the governing equations of the system. As well as this, in the results section, with the aid of AI some predictions for improving the behaviors of the various sport systems will be given in detail.

• Journal of Korean Society of Transportation
• /
• v.15 no.4
• /
• pp.143-163
• /
• 1997

Incident management is significant far the traffic management systems. The management of incidents determines the smoothness of freeway operations. The dynamic nature of incidents and the uncertainty associated with them require solutions based on the incident operator's judgment. Fuzz systems attempt to adapt such human expertise and are designed to replicate the decision making capability of on operator. Fuzzy systems process complex traffic information, and transmit it in a simplified, understandable form to human traffic operators. In this study, fuzzy rules were developed based on data from real incidents on Santa Monica Freeway in LosAngeles. The fuzzy rules ail linguistic based, and hence, user-friendly. A comparison of the results from the linguistic model with the real incident durations indicate that the outputs from the model reliably correspond to real incident durations conditions. The model reliably predicts the freeway incident duration. The modes can thus be used as an effective management tool for freeway incident response systems. The approach could be applied to other problems regarding dispatch systems in transportation.