• IEMEK Journal of Embedded Systems and Applications
• /
• v.8 no.4
• /
• pp.219-225
• /
• 2013

This paper presents a method using Maximum-Likelihood Linear Regression (MLLR) adaptation to improve recognition performance of Limabeam algorithm for speech recognition using microphone array. From our investigation on Limabeam algorithm, we can see that the performance of filtering optimization depends strongly on the supporting optimal state sequence and this sequence is created by using Viterbi algorithm trained with HMM model. So we propose an approach using MLLR adaptation for the recognition of speech uttered in a new environment to obtain better optimal state sequence that support for the filtering parameters' optimal step. Experimental results show that the system embedded with MLLR adaptation presents the word correct recognition rate 2% higher than that of original calibrate Limabeam and also present 7% higher than that of Delay and Sum algorithm. The best recognition accuracy of 89.4% is obtained when we use 4 microphones with 5 utterances for adaptation.

• Industrial Engineering and Management Systems
• /
• v.14 no.3
• /
• pp.318-324
• /
• 2015

This paper proposes a dynamic short-term load forecasting method that utilizes a new sequential learning algorithm based on Relevance Vector Machine (RVM). The method performs general optimization of weights and hyperparameters using the current relevance vectors and newly arriving data. By doing so, the proposed algorithm is trained with the most recent data. Consequently, it extends the RVM algorithm to real-time and nonstationary learning processes. The results of application of the proposed algorithm to prediction of electrical loads indicate that its accuracy is comparable to that of existing nonparametric learning algorithms. Further, the proposed model reduces computational complexity.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.24 no.3
• /
• pp.302-307
• /
• 2015

The automobile is an important means of transportation. For this reason, the automotive wheel is also an important component in the automotive industry because it acts as a load support and is closely related to safety. Thus, the wheel design is a very important safety aspect. In this paper, an optimal design for minimizing automotive wheel stress and increasing wheel safety is described. To study the optimal design, a central composite design (CCD) and D-optimal design theory are applied, and the approximate function using the response surface method (RSM) is generated. The optimal solutions using the non-dominant sorting genetic algorithm (NSGA-II) are then derived. Comparing CCD and D-optimal solution accuracy and verified the CCD can deduce more accuracy optimal solutions.

• Journal of Microbiology and Biotechnology
• /
• v.15 no.1
• /
• pp.7-13
• /
• 2005

Chitosan-alginate capsules were formed by electrostatic interactions and exhibited an appropriate mechanical strength, permeability, and stability for the culture of hepatocytes. Pig hepatocytes were isolated and hepatocyte spheroids formed and immobilized in chitosan-alginate capsules. An encapsulation procedure of 3 min and spheroid formation period of 24 h were the optimum conditions for the best liver functions. Pig hepatocytes with a cell density of $6.0{\tomes}10^6$ cells/ml in the capsules were found to be most suitable for application in a bioartificial liver support system. The encapsulated pig hepatocyte spheroids exhibited stable ammonia removal and urea secretion rates in a bioreactor for 2 weeks. Accordingly, chitosan-alginate encapsulated hepatocyte spheroids in a packed-bed bioreactor would appear to have potential as a bioartificial liver.

• Proceedings of the KSME Conference
• /
• 2000.11a
• /
• pp.381-386
• /
• 2000

Simple spring-damper-mass models have been widely used to understand whole-body vertical biodynamic response characteristics of the seated vehicle driver. However, most previous models have not considered about the non-rigid masses(wobbling masses). A simple mechanical model of seated human body developed in this study included the torso represented by a rigid and a wobbling mass. Within the 0.5-20Hz frequency range and for excitation amplitudes maintained below $5ms^{-2}$, this 4-degree-of-freedom driver model is proposed to satisfy the measured vertical vibration response characteristics defined from a synthesis of published data for subjects seated erect without backrest support. The parameters are identified by using the combinatorial optimization technique, simulated annealing method. The model response was found to be provided a closer agreement with the response characteristics than previously published models.

• Proceedings of the KWS Conference
• /
• 2009.11a
• /
• pp.83-83
• /
• 2009

The automotive chassis components are structural assemblies that support the engine, suspension, and steering components of the vehicle. For the development of AHSS components, the durability analysis is important. In this paper, the low cycle fatigue property of AHSS was evaluated for the geometry complex and local plasticity in the base material. The GMAW optimization was implemented for the weld soundness using the moving least square method. And the weld S-N curves of AHSS were evaluated to access durability analysis for the weld region. For the verification, the durability analysis of the couple torsion beam axle (CTBA) was performed and compared to the rig test result. The durability analysis using the low cycle fatigue property and the evaluated weld S-N curve of AHSS met the good agreement with the test result.

• International Journal of Precision Engineering and Manufacturing
• /
• v.4 no.6
• /
• pp.38-43
• /
• 2003

In this study, the optimal dynamic absorbing system for the gas operated HIF (high implusive force) device has been investigated. For this purpose, firstly, the dynamic behavior of human body induced by impulsive disturbances has been analyzed through a series of experimental works using the devised test setup. The characteristics of linear impulse has been compared under some conditions of support system. In order to design the optimal dynamic absorbing system, the parameter optimization process has been performed based on the simplified isolation system model under constraints of moving displacement and transmitted force. Finally, the performance of the designed dynamic absorbing system has been evaluated by simulation in the actual operating condition.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2014.10a
• /
• pp.341-346
• /
• 2014

Intake E-CVVT noise, generally caused by collision sound of roller and cage clearance at idle and driving condition, is considerable source of annoyance in passenger cars using the gasoline engine. Main source of this noise is the cam torque variation of an intake E-CVVT system, and can be controlled by clearance decrease such as backlash reduction, but which may increase the manufacturing cost. Thus in this paper, most effective solution for low noise intake E-CVVT was achieved through not only reduction of backlash and cam angular acceleration but also improvement of vehicle transfer system, which is optimal configuration through acoustic sensitivity optimization of engine mount support bracket.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.620-623
• /
• 2002

To cope with the challenge of competitive market, manufacturing system needs to be agile in terms of its reconfigurability and scalability. For a system to be adapted to changed requirements, decision support tools such as configurator have to be provided. This paper introduces the basic framework of a configurator for assembly system Based on the factory data model(FDM) depicting the overall structure of a manufacturing system, functions of the configurator are described, i.e., requirements analysis, module selection and configuration optimization.

• The Journal of Society for e-Business Studies
• /
• v.7 no.2
• /
• pp.143-156
• /
• 2002

The objective of supply chain planning is to satisfy the requirements for minimizing inventory costs, transportation costs, and lead times throughout the supply, production and distribution stage dispersed geographically. Therefore, the supply chain planning system should have functionalities to resolve complex optimization problems that have characteristics of multi-stage and multi-product. Ant the system should also support collaborative decision making among distributed business partners. In this study, we proposed a distributed architecture for the supply chain planning system. To do this, we analyzed functional requirements by using IDEF-0(ICAM Definition-0) methodology, defined required components, and designed each component by using object-oriented methodology. We implemented a prototype system based on CORBA (Common Object Request Broker Architecture) to show that the proposed distributed architecture based on component technology is feasible and can solve supply chain planning problem collaboratively.