• IEMEK Journal of Embedded Systems and Applications
• /
• v.9 no.1
• /
• pp.53-59
• /
• 2014

In multiple object tracking, accurate detection for each of objects that appear sequentially and effective tracking in complicated cases that they are overlapped with each other are very important. In this paper, we propose a multiple object tracking system that has a concrete detection and tracking characteristics by using multi-lateral histogram and SIFT feature extraction algorithm. Especially, by limiting the matching area to object's inside and by utilizing the location informations in the keypoint matching process of SIFT algorithm, we advanced the tracking performance for multiple objects. Based on the experimental results, we found that the proposed tracking system has a robust tracking operation in the complicated environments that multiple objects are frequently overlapped in various of directions.

• Tribology and Lubricants
• /
• v.25 no.3
• /
• pp.182-186
• /
• 2009

Extruders can be basically divided into bisk and screw type of extruders. Though plastic extruders are often used for its simplicity for water and oil transportation pumps, these days screw extruders are mostly used. Screws are used in many extrusion processes to manufacture complex and complicated shaped parts made of plastics, medicine materials, food, polymer composites, iron and ceramic powders, etc. Also, material correction of deformities is caused by flow and physicochemical reaction phenomenonand material extrusion is processed according to heat transfer. various material comes to hopper because extruder has function by blender and mixing of materials can go well before come out through dice. These change process is so complicated that process condition is decided by trial and error that process condition is underground mainly at extrusion molding process.

• Journal of the Korea Safety Management & Science
• /
• v.15 no.2
• /
• pp.55-61
• /
• 2013

For years, many studies have mainly been investigated in a complicated human motion analysis. Recently, many motion analysis equipments have been studied and developed. Therefore, the more complex human movement analyses are possible, we have enabled us to perform more and more complicated human movement analyses. A Three-dimensional(3D) motion analysis on of the several methods is a useful tool for analyzing the human motion analysis. The purpose of this study was to develop the 3D human motion analysis using a kalman filter algorithm and a gyro sensor. The algorithm and sensor were used to human motion analysis with high-speed motion capture. In this study, the developed system will be adapted to facilitate golf swing analysis. Using the developed system, golfers and coaches who do not have advanced biomechanical knowledge can easily be used to their golf swing analysis. Future study is necessary for more practical and efficient area such as other sports industries, 3D game industries, rehabilitation training, etc..

• Proceedings of the KSME Conference
• /
• 2008.11b
• /
• pp.2088-2093
• /
• 2008

In this study, flow field measurement of the Pebble Bed Reactor(PBR) for the High Temperature Gas-cooled Reactor(HTGR) was performed. Large number of pebbles in the core of PBR provides complicated flow channel. Due to the complicated geometries, numerical analysis has been intensively made rather than experimental observation. However, the justification of computational simulation by the experimental study is crucial to develop solid analysis of design method. In the present study, a wind tunnel installed with pebbles stacked was constructed and equipped with the Particle Image Velocimetry(PIV). We designed the system scaled up to realize the room temperature condition according to the similarity. The PIV observation gave us stagnation points, low speed region so that the suspected high temperature region can be identified. With the further supplementary experimental works, the present system may produce valuable data to justify the Computational Fluid Dynamics(CFD) simulation method.

• Proceedings of the KIEE Conference
• /
• 2000.11b
• /
• pp.300-302
• /
• 2000

There are two kinds of the synchronous motor, one is an induction type motor started without a driving system, the other is the one started with an external driving system. but, both are complicated. Nowadays, in order to devoid for the synchronous motor being complicated in design, line start permanent magnet(LSPM) motors are being developed. The LSPM motor is composed of the rotor that has interior permanent magnet and aluminum bar instead of general rotor. In this paper, we analyzed the characteristics of the LSPM motor which has both characteristics of an induction motor and a synchronous motor, and we compared the the LSPM motor characteristics with the induction motor.

• Proceedings of the Korean Reliability Society Conference
• /
• 2004.07a
• /
• pp.37-72
• /
• 2004

Future Circuit Design means "Unimaginable Intricate Engineering Problems" Thus, Future Circuit Designers may be "Victims" of "Inexorably Complicated Signal Integrity Problems".(omitted)grity Problems".(omitted)tted)

• Proceedings of the KIEE Conference
• /
• 1997.07c
• /
• pp.761-763
• /
• 1997

As the power system network is enlarged and complicated gradually, the automation of power system network is essential to enhance the reliability and performance of the operation of power system. Distribution restoration is a major part of the automation. This paper proposes a new distribution restoration system to restore healthy blackout regions by the hierarchical cooperation with the substation automation systems. In proposed system, the range of restoration is extended to substations and the performance as well as the switching efficiency of restoration system is enhanced.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.8
• /
• pp.2993-3010
• /
• 2021

The job shop scheduling problem (JSSP) plays a critical role in smart manufacturing, an effective JSSP scheduler could save time cost and increase productivity. Conventional methods are very time-consumption and cannot deal with complicated JSSP instances as it uses one optimal algorithm to solve JSSP. This paper proposes an effective scheduler based on deep learning technology named self-supervised long-short term memory (SS-LSTM) to handle complex JSSP accurately. First, using the optimal method to generate sufficient training samples in small-scale JSSP. SS-LSTM is then applied to extract rich feature representations from generated training samples and decide the next action. In the proposed SS-LSTM, two channels are employed to reflect the full production statues. Specifically, the detailed-level channel records 18 detailed product information while the system-level channel reflects the type of whole system states identified by the k-means algorithm. Moreover, adopting a self-supervised mechanism with LSTM autoencoder to keep high feature extraction capacity simultaneously ensuring the reliable feature representative ability. The authors implemented, trained, and compared the proposed method with the other leading learning-based methods on some complicated JSSP instances. The experimental results have confirmed the effectiveness and priority of the proposed method for solving complex JSSP instances in terms of make-span.

• Proceedings of the KSR Conference
• /
• 2011.10a
• /
• pp.2517-2526
• /
• 2011

As technologies are developed and systems are complicated, hazards embedded in the system are also increasing. proving safety and managing the safety is more scientific and organizational domain so that safety management system is pursuing to be active formation detecting the factors of hazard and managing them beyond passive-way. In the future, in order to establish and manage national safety management system, it is important to have effective system and manage it and also more important that all the people related to target system has to change their recognition and to play roles in it.

• 제어로봇시스템학회:학술대회논문집
• /
• 1986.10a
• /
• pp.586-591
• /
• 1986

In this paper, we designed simultaneous 2-axis control system using commercialized custom ICs for positioning and interpolation that is very compact and high reliable. This system is primarily designed for NC system, we verified it is more complete than the other hardware & software based system in its function, control accuracy and cost. Also, this system can be expanded for multi-axis control, it can be applied to the control of more complicated mechanism such as articulated robot.