• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.1726-1748
• /
• 2024

Trajectory planning is vital for autonomous systems like robotics and UAVs, as it determines optimal, safe paths considering physical limitations, environmental factors, and agent interactions. Recent advancements in trajectory planning and future location prediction stem from rapid progress in machine learning and optimization algorithms. In this paper, we proposed a novel framework for Spatial-temporal transformer-based feed-forward neural networks (STTFFNs). From the traffic flow local area point of view, skip-gram model is trained on trajectory data to generate embeddings that capture the high-level features of different trajectories. These embeddings can then be used as input to a transformer-based trajectory planning model, which can generate trajectories for new objects based on the embeddings of similar trajectories in the training data. In the next step, distant regions, we embedded feedforward network is responsible for generating the distant trajectories by taking as input a set of features that represent the object's current state and historical data. One advantage of using feedforward networks for distant trajectory planning is their ability to capture long-term dependencies in the data. In the final step of forecasting for future locations, the encoder and decoder are crucial parts of the proposed technique. Spatial destinations are encoded utilizing location-based social networks(LBSN) based on visiting semantic locations. The model has been specially trained to forecast future locations using precise longitude and latitude values. Following rigorous testing on two real-world datasets, Porto and Manhattan, it was discovered that the model outperformed a prediction accuracy of 8.7% previous state-of-the-art methods.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2002.04a
• /
• pp.179-183
• /
• 2002

This paper presents a new approach to the calibration of a SCARA robot orientation with a camera modeling that accounts for major sources of camera distortion, namely, radial, decentering, and thin prism distortion. radial distortion causes an inward or outward displacement of a given Image point from its ideal location. Actual optical systems are subject to various degrees of decentering, that is, the optical centers of lens elements are not strictly collinear. Thin prism distortion arises from imperfection in lens design and manufacturing as well as camera assembly It is our purpose to develop the vision system for the pattern recognition and the automatic test of parts and to apply the line of manufacturing.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1997.10a
• /
• pp.65-69
• /
• 1997

This paper presents a new approach to the calibration of a SCARA robot orientation with a camera modeling that accounts for major sources of camera distortion, namely, radial, decentering, and thin prism distortion. Radial distortion causes an inward or outward displacement of a given image point from its ideal location. Actual optical systems are subject to various degrees of decentering, that is, the optical centers of lens elements are not strictly collinear. Thin prism distortion arises from imperfection in lens design and manufacturing as well as camera assembly. It is our purpose to develop the vision system for the pattern recognition and the automatic test of parts and to apply the line of manufacturing.

• Tunnel and Underground Space
• /
• v.7 no.4
• /
• pp.334-340
• /
• 1997

Alpha center theory which was first proposed by Stefanescu has been proved to be effective for the detection of the location of the conductive orebody. A numerical forward modeling was conducted to verify the effectiveness of this method. Field works were carried out along the three profiles in two different areas for the purpose of finding fractured zone which might be accompanied with the presence of the groundwater. And the results were modeled by alpha center method, which was later testified by wellproven 2-dimensional finite difference inversion scheme. Field data could be successfully modeled with this alpha center algorithm, especially for the smooth-varying resistivity models. For the abrupt change of the resistivity values, the alpha center coefficients have a tendency to be negative to simulate the steep resistivity gradients. This method is quite simple and easy for the future applications. The numerical calculation can be performed very quickly with the personal computers.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2001.10a
• /
• pp.117-121
• /
• 2001

This paper presents a new approach to the calibration of a SCARA robot orientation with a camera modeling that accounts for major sources of camera distortion, namely, radial, decentering, and thin prism distortion. Radial distortion causes an inward or outward displacement of a given image point from its ideal location. Actual optical systems are subject to various degrees of decentering, that is, the optical centers of lens elements are not strictly collinear. Thin prism distortion arises from imperfection in lens design and manufacturing as well as camera assembly. It is our purpose to develop the vision system for the pattern recognition and the automatic test of parts and to apply the line of manufacturing.

• Journal of Korean Institute of Industrial Engineers
• /
• v.30 no.3
• /
• pp.224-240
• /
• 2004

Supply chain management(SCM) has been recognized as a major strategy in today's market place. A growing number of researchers have begun to realize the strategic importance of model construction, planning, controlling and operation for SCM. Also various researches of supply chain model building are going on. In this paper, we synthesis key elements of supply chain model such as performance factors, decision variables and constraints. We have reviewed past and present supply chain models and then analyzed those in view of environment factors, operations, solution approaches.

• Structural Engineering and Mechanics
• /
• v.25 no.2
• /
• pp.131-146
• /
• 2007

This paper presents the results of a study to show how the development of a crack alters the structural behavior of I-shaped steel beams and how this can be used to evaluate nondestructive evaluation techniques. The approach is based on changes in the dynamic behavior. An approximate finite element model for a cracked beam with I-shaped cross-section is developed based on a simplified fracture model. The model is then used to review different damage cases. Damage detection techniques are studied to determine their ability to identify the existence of the crack and to identify its location. The techniques studied are the coordinate modal assurance criterion, the modal flexibility, and the state and the slope arrays.

• Computational Structural Engineering
• /
• v.8 no.2
• /
• pp.73-84
• /
• 1995

The study summarized in this paper is concerned with the buckling of longitudinal bars in reinforced concrete columns with numerical analysis method. The objectives of this study are (1) to investigate the stress transfer mechanism between concrete and reinforcement and (2) to propose a modeling equation. The results give an acceptable agreement between the proposed modeling equation and published computer packages as follows; (1) the proposed equation is a possible of strain softening of concrete and buckling of reinforcement. (2) the buckling of longitudinal bar is mainly influenced by spacing of hoop and location of the bar

• Wind and Structures
• /
• v.22 no.4
• /
• pp.393-408
• /
• 2016

Weibull distribution is a suitable distribution to use in modeling the life time data. It has been found to be a exact fit for the empirical distribution of the wind speed measurement samples. In brief this paper consist of important properties and characters of Weibull distribution. Also we discuss the application of Weibull distribution to wind speed measurements and derive an expression for the probability distribution of the power produced by a wind turbine at a fixed location, so that the modeling problem reduces to collecting data to estimate the three parameters of the Weibull distribution using Maximum likelihood Method.

• Journal of KIBIM
• /
• v.2 no.2
• /
• pp.17-26
• /
• 2012

This paper presents the results of a theoretical energy analysis of a research test bed called the Zero Net Energy Test House (ZNETH) in Omaha, Nebraska in U.S.A. The ZNETH project is being designed and built with the goal of consuming a negligible amount of energy by offsetting remaining usage after energy conservation. The theoretically consumed and generated energy levels were analyzed using energy modeling software programs. By integrating a highly graphical and intuitive analysis with a Building Information Model(BIM) of the house, this investigation introduces strategies to include sustainable materials and systems to predict energy generation with a case study of ZNETH. In addition, this paper introduces parametric analyses for better envelope design and construction material selection by analyzing simulated energy consumption with various parametric inputs, e.g., material types, location, and size. It was found that the current design of ZNETH does not meet its goal of zero net energy. Sugeestions are presented to assist ZHETH in meeting its net zero energy goal.