• The Journal of Korea Robotics Society
• /
• v.17 no.1
• /
• pp.40-47
• /
• 2022

A reward function suitable for a task is required to manipulate objects through reinforcement learning. However, it is difficult to design the reward function if the ample information of the objects cannot be obtained. In this study, a demonstration-based object manipulation algorithm called stochastic exploration guided by demonstration (SEGD) is proposed to solve the design problem of the reward function. SEGD is a reinforcement learning algorithm in which a sparse reward explorer (SRE) and an interpolated policy using demonstration (IPD) are added to soft actor-critic (SAC). SRE ensures the training of the critic of SAC by collecting prior data and IPD limits the exploration space by making SEGD's action similar to the expert's action. Through these two algorithms, the SEGD can learn only with the sparse reward of the task without designing the reward function. In order to verify the SEGD, experiments were conducted for three tasks. SEGD showed its effectiveness by showing success rates of more than 96.5% in these experiments.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.808-813
• /
• 2022

This study presents the problems of data imbalance, varying difficulties across target objects, and small objects in construction object segmentation for far-field monitoring and utilize compound loss functions to address it. Construction site scenes of assembling scaffolds were analyzed to test the effectiveness of compound loss functions for five construction object classes---workers, hardhats, harnesses, straps, hooks. The challenging problem was mitigated by employing a focal and Jaccard loss terms in the original loss function of LinkNet segmentation model. The findings indicates the importance of the loss function design for model performance on construction site scenes for far-field monitoring.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.19 no.3
• /
• pp.19-27
• /
• 1982

Minimization of total routing and number of cuts has been adopted for the placement problem in LSI and printed wire board as the object function, recently. Although it is considered that in the general situation this object function reflects the final goal which is wiring of 100% of layout, it often seems to be insufficient because it does not exhibit partial wire congestion. This paper introduces a new concept called the wire congestion of segestion to get the partial wire congestion and proposes the object function to minimize the wire congestion of segmests. In order to optimize this object function, an effective heuristic algorithm is also suggestsl Experimental results show that this algorithm sustains its efficiency. The experimental consequences point out that if the total routing length is short, maximum wire congestion of segment is small and vice versa. Therefore control parameter, that is, congestion parameter, which mintnizes total length and concurrently reduces maximal wire congestion of segment, is obtained by experiment.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.1
• /
• pp.137-142
• /
• 2015

In the object inheritance of SR DEVS, partial or overall asset inheritance can be possible. To a asset inherited from parent object, by respective dedicated function a child object can implement partial or whole asset, or not. Even though a child has a inherited asset, if the asset is the hidden property its implementation will not be provided. A inherited asset cannot be showed in whole asset implementation, or it can be implemented by special system state. Here, the whole asset implementation means may include time parameter. In this paper, we describe a determination probability scheme for partial or whole asset inherited from the parent object to determine the hidden inheritance. By the determination probability function it is decided that the inherited asset will be hidden or normal asset.

• Journal of Educational Research in Mathematics
• /
• v.23 no.2
• /
• pp.213-235
• /
• 2013

The purpose of this study is to analyze how the teaching activities which used EXCEL influence the specialized high school underachieved students. They have difficulties in making use of various representations for better understanding of function. EXCEL is helpful for learning function because it enables the students to use real life materials in math learning as well as formulates Tabular, Algebraic and Graphical which represent function. Furthermore, the students in specialized high school also have the experience of using EXCEL while studying other subjects. For that reason they have no burdens and fears on using EXCEL in learning activities. Utilizing EXCEL in the classroom gives an expectation that it helps to have interests on studying function and prepare for the next learning in the end. Research classes were conducted in a group of five students who have different hopes of career and a variety of mathematical interests. Though the students couldn't transfer Algebraic to Graphical in the diagnostic evaluation, they could resolve the problem of connections between Graphical, Tabular and Algebraic in the process perspectives, and could also express graphical representation by linking object perspectives with process perspectives. Therefore, they solved the connection problem of Tabular, Algebraic and Graphical in the object perspectives. As a result, the students could make transitions between Algebraic and Graphical in object perspectives through the classes applying EXCEL. Consequently, teaching the students with underachievement utilizing EXCEL enables them to recover their interests on math and it helps them to complete their following curriculum.

• Journal of Broadcast Engineering
• /
• v.17 no.2
• /
• pp.400-410
• /
• 2012

In recent years, 3D displays are used in many media including 3D movies, TV, mobile phones, and PC games. Although 3D displays provide realistic viewing experience as compared with 2D displays, they also carry issues such as visual fatigue or size distortion. Focusing on the latter, we developed prediction function of object size perception as a function of object depth in 3D display. In Experiment 1, subjects observed 3D square of a fixed size of varying depth, and manipulated 2D square to make it as large as the 3D square. Conversely, in Experiment 2, subjects observed 2D square of a fixed size, and manipulated 3D square of varying depth to make it as large as the 2D square. In both Experiments 1 and 2, we found that size perception of 3D square linearly changed depending on depth of the square, and the linear relationship between depth and size was identical in both experiments. The predictive regression function, which predicts object size perception based on object depth, obtained in this research will be very useful in the creation of 3D media contents.

• Transactions of The Korea Fluid Power Systems Society
• /
• v.3 no.3
• /
• pp.20-24
• /
• 2006

Air balancer is a conveyance cargo-handling machine, used in assembly and process lines of car and machining industries. This can lift up an object, the weight of which is from 5 to 200 kg, and moves it to a position. As industrial technologies evolve, it is required to move an object and fit it into a specified position with greater accuracy, rather than performing simple tasks such as lifting objects up and down as conventional ones do. There is also a demand to handle an object with one hand, rather than with two hands,. Through designs of manifold unit for an air balancer function, pilot regulator unit to keep pressure constant, hand unit for an accurate load perception function, and air balancer circuit, this study enables everybody to work it with ease and convenience. Experiments and comparisons were conducted for the performance evaluation of the circuit.

• Journal of Korean Society for Geospatial Information Science
• /
• v.4 no.1 s.6
• /
• pp.23-29
• /
• 1996

The purpose of this study is to develope an Object-Oriented Graphic database management system to handle geographic data of geographic information systems. As the result of this study, unstructured vector model was developed to handle geographic data and graphic database management was implemented by object-oriented programming. This study was focused on liking function between graphic data and attribute data, and not focused on network analysis function.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.9
• /
• pp.3655-3671
• /
• 2015

In this paper, we develop a novel object tracking method based on sparse representation. First, we propose a relaxed sparse representation model, based on which the tracking problem is casted as an inverse sparse representation process. In this process, the target template is able to be sparsely approximated by all candidate samples. Second, we present an objective function that combines the sparse representation process of different fragments, the relaxed representation scheme and a weight reference prior. Based on some propositions, the proposed objective function can be solved by using an iteration algorithm. In addition, we design a tracking framework based on the proposed representation model and a simple online update manner. Finally, numerous experiments are conducted on some challenging sequences to compare our tracking method with some state-of-the-art ones. Both qualitative and quantitative results demonstrate that the proposed tracking method performs better than other competing algorithms.

• Journal of the Korean Data and Information Science Society
• /
• v.15 no.3
• /
• pp.663-675
• /
• 2004

A battlefield simulation is the evaluation and analysis of the battlefield area, based on the data for terrain, climate, unit's maneuver and tactics basically required in battlefield simulation. Because it is difficult for the military authorities to collect all of the information perfectly for the reason of communication technology, jamming, and tactics, the military authorities need the future moving status for the target units by using acquired moving information. Therefore, we propose a moving object management system that concurrently provides domain reasoning function for the battlefield simulation. In order to implement the proposed system, we show the data modeling of the moving object for the battlefield simulation, and propose an inference engine using domain rule base and spatiotemporal operation. Also, we analyze the query response rate by inference function to verify domain reasoning of the implemented system.