• Journal of Korean Society of Steel Construction
• /
• v.17 no.1 s.74
• /
• pp.1-11
• /
• 2005

A bi-level damage detection algorithm that utilizes the dynamic responses of the structure as input and neural network (NN) as pattern classifier is presented. Signal anomaly index (SAI) is proposed to express the amount of changes in the shape of frequency response functions (FRF) or strain frequency response function (SFRF). SAI is calculated using the acceleration and dynamic strain responses acquired from intact and damaged states of the structure. In a bi-level damage identification algorithm, the presence of damage is first identified from the magnitude of the SAI value, then the location of the damage is identified using the pattern recognition capability of NN. The proposed algorithm is applied to an experimental model bridge to demonstrate the feasibility of the algorithm. Numerically simulated signals are used for training the NN, and experimentally-acquired signals are used to test the NN. The results of this example application suggest that the SAI-based pattern recognition approach may be applied to the structural health monitoring system for a real bridge.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.2
• /
• pp.100-109
• /
• 2007

Object recognition of service robots is very important for most of services such as delivery, and errand. Conventional methods are based on the geometric models in static industrial environments, but they have limitations in indoor environments where the condition is changable and the movement of service robots occur because the interesting object can be occluded or small in the image according to their location. For solving these uncertain situations, in this paper, we propose the method that exploits observed objects as context information for predicting interesting one. For this, we propose the method for modeling domain knowledge in probabilistic frame by adopting Bayesian networks and ontology together, and creating knowledge model dynamically to extend reasoning models. We verify the performance of our method through the experiments and show the merit of inductive reasoning in the probabilistic model

• Journal of Electrical Engineering and Technology
• /
• v.6 no.6
• /
• pp.806-816
• /
• 2011

Interest about social security has recently increased in favor of safety for infrastructure. In addition, advances in computer vision and pattern recognition research are leading to video-based surveillance systems with improved scene analysis capabilities. However, such video surveillance systems, which are controlled by human operators, cannot actively cope with dynamic and anomalous events, such as having an invader in the corporate, commercial, or public sectors. For this reason, intelligent surveillance systems are increasingly needed to provide active social security services. In this study, we propose a core technique for intelligent surveillance system that is based on swarm robot technology. We present techniques for invader enclosing using swarm robots based on multiple distributed object environment. The proposed methods are composed of three main stages: location estimation of the object, specified object tracking, and decision of the cooperative behavior of the swarm robots. By using particle filter, object tracking and location estimation procedures are performed and a specified enclosing point for the swarm robots is located on the interactive positions in their coordinate system. Furthermore, the cooperative behaviors of the swarm robots are determined via the result of path navigation based on the combination of potential field and wall-following methods. The results of each stage are combined into the swarm robot-based invader-enclosing technique on multiple distributed object environments. Finally, several simulation results are provided to further discuss and verify the accuracy and effectiveness of the proposed techniques.

• International Journal of Control, Automation, and Systems
• /
• v.3 no.4
• /
• pp.509-523
• /
• 2005

We are developing a novel framework, PRIDE (PRediction In Dynamic Environments), to perform moving object prediction (MOP) for autonomous ground vehicles. The underlying concept is based upon a multi-resolutional, hierarchical approach which incorporates multiple prediction algorithms into a single, unifying framework. The lower levels of the framework utilize estimation-theoretic short-term predictions while the upper levels utilize a probabilistic prediction approach based on situation recognition with an underlying cost model. The estimation-theoretic short-term prediction is via an extended Kalman filter-based algorithm using sensor data to predict the future location of moving objects with an associated confidence measure. The proposed estimation-theoretic approach does not incorporate a priori knowledge such as road networks and traffic signage and assumes uninfluenced constant trajectory and is thus suited for short-term prediction in both on-road and off-road driving. In this article, we analyze the complementary role played by vehicle kinematic models in such short-term prediction of moving objects. In particular, the importance of vehicle process models and their effect on predicting the positions and orientations of moving objects for autonomous ground vehicle navigation are examined. We present results using field data obtained from different autonomous ground vehicles operating in outdoor environments.

• The Journal of Korea Robotics Society
• /
• v.11 no.4
• /
• pp.205-216
• /
• 2016

The localization of the robot is one of the most important factors of navigating mobile robots. The use of featured information of landmarks is one approach to estimate the location of the robot. This approach can be classified into two categories: the natural-landmark-based and artificial-landmark-based approach. Natural landmarks are suitable for any environment, but they may not be sufficient for localization in the less featured or dynamic environment. On the other hand, artificial landmarks may generate shaded areas due to space constraints. In order to improve these disadvantages, this paper presents a novel development of the localization system by using artificial and natural-landmarks-based approach on a topological map. The proposed localization system can recognize far or near landmarks without any distortion by using landmark tracking system based on top-view image transform. The camera is rotated by distance of landmark. The experiment shows a result of performing position recognition without shading section by applying the proposed system with a small number of artificial landmarks in the mobile robot.

• Atmosphere
• /
• v.24 no.2
• /
• pp.189-196
• /
• 2014

The definition of onset date of Changma is revisited in this study using a quality controlled Ieodo ocean research station data. The Ieodo station has great importance in terms of its southwest location from Korean Peninsula and, hence, makes it possible to predict Changma period in advance with less impact of continents. The onset date of Changma using the Ieodo station data is defined by the time that meridional wind direction changes and maintains from northerly to southerly, and then the zonal wind changes from easterly to westerly after first June. This definition comes from a recognition that the establishment and movement of the western North Pacific subtropical high (WNPSH) cause Changma through southwesterly flow. The onset data of Changma has been determined by large-scale dynamic-thermodynamic characteristics or various meteorological station data. However, even the definition based on circulation data at the Ieodo station has a potential for the improved prediction skill of the onset date of Changma. The differences between before and after Changma, defined as Ieodo station data, are also found in synoptic chart. The convective instability and conspicuous circulations, corresponding low-level southwesterly flow related to WNPSH and strong upper-level zonal wind, are represented during Changma.

• KIISE Transactions on Computing Practices
• /
• v.22 no.11
• /
• pp.619-624
• /
• 2016

Social-aware video displays not only the relationships between characters but also diverse information on topics such as economics, politics and culture as a story unfolds. Particularly, the speaking habits and behavioral patterns of people in different situations are very important for the analysis of social relationships. However, when dealing with this dynamic multi-modal data, it is difficult for a computer to analyze the drama data effectively. To solve this problem, previous studies employed the deep concept hierarchy (DCH) model to automatically construct and analyze social networks in a TV drama. Nevertheless, since location knowledge was not included, they can only analyze the social network as a whole in stories. In this research, we include location knowledge and analyze the social relations in different locations. We adopt data from approximately 4400 minutes of a TV drama Friends as our dataset. We process face recognition on the characters by using a convolutional- recursive neural networks model and utilize a bag of features model to classify scenes. Then, in different scenes, we establish the social network between the characters by using a deep concept hierarchy model and analyze the change in the social network while the stories unfold.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.1
• /
• pp.85-95
• /
• 2019

This work shows how to design a robot structure and to control to overcome obstacles while traveling through ducts of various diameters and shapes by three-legged robot. Circuits are centered in the body to connect the three wheel bodies that are driven around the center body with the 4-section slider link structure. Also, the springs are used to contract and expand the robot legs so that it can be caparable of various environments. Geared motor, spring, and belt were selected based on the static and dynamic calculation to be suitable to horizontal and vertical travels. The center body is equipped with a camera and the distance sensors, and a control algorithms are implemented so that it can be successfully performed in L-type and T-type ducts. Using UWB modules and trilateration algorithm, the location of the duct-cleaning robot inside the duct could be identified successfully.