• Journal of Power Electronics
• /
• v.13 no.4
• /
• pp.516-527
• /
• 2013

This paper presents a new overall system for state-of-available-power (SoAP) prediction for a lithium-ion battery pack. The essential part of this method is based on an adaptive network architecture which utilizes both fuzzy model (FIS) and artificial neural network (ANN) into the framework of adaptive neuro-fuzzy inference system (ANFIS). While battery aging proceeds, the system is capable of delivering accurate power prediction not only for room temperature, but also at lower temperatures at which power prediction is most challenging. Due to design property of ANN, the network parameters are adapted on-line to the current battery states (state-of-charge (SoC), state-of-health (SoH), temperature). SoC is required as an input parameter to SoAP module and high accuracy is crucial for a reliable on-line adaptation. Therefore, a reasonable way to determine the battery state variables is proposed applying a combination of several partly different algorithms. Among other SoC boundary estimation methods, robust extended Kalman filter (REKF) for recalibration of amp hour counters was implemented. ANFIS then achieves the SoAP estimation by means of time forward voltage prognosis (TFVP) before a power pulse occurs. The trade-off between computational cost of batch-learning and accuracy during on-line adaptation was optimized resulting in a real-time system with TFVP absolute error less than 1%. The verification was performed on a software-in-the-loop test bench setup using a 53 Ah lithium-ion cell.

• Biotechnology and Bioprocess Engineering:BBE
• /
• v.10 no.6
• /
• pp.564-570
• /
• 2005

In the present study, the protective effects of Bcl-2 over-expression in a suspension culture (without any adaptation) and spent medium (low nutrient and high toxic metabolite conditions) were investigated. In the suspension culture without prior adaptation, the viability of the control cell line fall to 0% by day 7, whereas the Bcl-2 cell line had a viability of 65%. The difference in the viability and viable cell density between the Bcl-2 and control cell lines was more apparent in the suspension culture than the static culture, and became even more apparent on day 6. Fluorescence microscopic counting revealed that the major mechanism of cell death in the control cell line in both the static and suspension cultures was apoptosis. For the Bcl-2 cell lines, necrosis was the major mode of cell death in the static culture, but apoptosis became equally important in the suspension culture. When the NS0 6A1 cell line was cultured in spent medium taken from a 14 day batch culture, the control cell line almost completely lost its viability by day 5, whereas, the Bcl-2 still had a viability of 73%. The viable cell density and viability of the Bcl-2 cell line cultivated in fresh medium were 2.2 and 2.7 fold higher, respectively, than those of the control cultures. However, the viable cell density and viability of the Bcl-2 cultivated in the spent medium were 8.7 and 7.8 fold higher, respectively, than those of the control cultures. Most of the dead cells in the control cell line were apoptotic; whereas, the major cell death mechanisms in the Bcl-2 cell line were necrotic.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.7
• /
• pp.603-611
• /
• 2003

This paper proposes an effective feature compensation scheme based on speech model for achieving robust speech recognition. Conventional model-based method requires off-line training with noisy speech database and is not suitable for online adaptation. In the proposed scheme, we can relax the off-line training with noisy speech database by employing the parallel model combination technique for estimation of correction factors. Applying the model combination process over to the mixture model alone as opposed to entire HMM makes the online model combination possible. Exploiting the availability of noise model from off-line sources, we accomplish the online adaptation via MAP (Maximum A Posteriori) estimation. In addition, the online channel estimation procedure is induced within the proposed framework. For more efficient implementation, we propose a selective model combination which leads to reduction or the computational complexities. The representative experimental results indicate that the suggested algorithm is effective in realizing robust speech recognition under the combined adverse conditions of additive background noise and channel distortion.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1993.04b
• /
• pp.370-374
• /
• 1993

This paper describes a study on the expert system based process planning of the block division process in shipbuilding. The prototype system developed deterines the block division line of the midship of crude-oil tanker. Case-based reasoning (CBR) approach relying on previous similar cases to solve the problem is applied instead of rule-based reasoning (RBR). Similar cases are retrieved from case base according to the similarity metrics between input problem and cases. The retrieved case with the highest priority is then adapted to fit to the input problem buy adaptation rules. The adapted solution is proposed as the division line for the input problem.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.3 s.303
• /
• pp.17-28
• /
• 2005

Recently intelligent characters in computer games have been an important element more and more because they continually stimulate gamers' interests. As a typical method for implementing such intelligent characters, neural networks have been used for training action patterns of opponent's characters and game rules. However, some of the game rules can be abruptly changed and action properties of garners in on-line game environments are quite different according to gamers. In this paper, we address how a neural network adapts to those environmental changes. Our adaptation solution includes two components: an individual adaptation mechanism and a group adaptation mechanism. With the individual adaptation algorithm, an intelligent character steadily checks its game score, assesses the environmental change with taking into consideration of the lastly earned scores, and initiates a new learning process when a change is detected. In multi-user games, including massively multiple on-line games, intelligent characters confront diverse opponents that have various action patterns and strategies depending on the gamers controlling the opponents. The group adaptation algorithm controls the birth of intelligent characters to conserve an equilibrium state of a game world by using a genetic algorithm. To show the performance of the proposed schemes, we implement a simple fighting action game and experiment on it with changing game rules and opponent characters' action patterns. The experimental results show that the proposed algorithms are able to make intelligent characters adapt themselves to the change.

• The Research Journal of the Costume Culture
• /
• v.23 no.6
• /
• pp.972-986
• /
• 2015

This study seeks to explore the relationship between clothing adaptation and acculturation for married Chinese immigrant women. In addition, it aims to analyze the differences in their clothing consumption behaviors according to acculturation level. To achieve these purposes, a quantitative research study was conducted on 291 wives of Korean-Chinese multicultural families in Seoul and Gyeonggi. The data was analyzed using factor analysis, cluster analysis, ANOVA, and the Duncun test. The findings were as follows. First, the women were divided into three groups based on their level of acculturation, which was defined as 'assimilated', 'marginalized' and 'segregated'. Second, the relationship between their acculturation level and their clothing adaptation was identified. The marginalized group had the lowest level of clothing adaptation. Third, the groups' differences in clothing selection criteria were analyzed. The segregated group considered the practical aspects (price, color, quality) of clothing to be more important than the other groups. The marginalized group scored the lowest in valuing the aesthetic factors (design, style, trendiness) of clothing. Finally, conformity of clothing consumption varied significantly based on acculturation level. The assimilated and marginalized groups showed higher levels conformity than did the segregated group. Clothing purchase location also varied significantly between the three groups. The assimilated and marginalized groups preferred online shopping, but members of the segregated group preferred to carry out their shopping off-line. This study showed that clothing adaptation and clothing consumption behaviors play key roles in understanding the acculturation of multicultural families.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2003.06a
• /
• pp.6-9
• /
• 2003

In this paper, we studied on the difference of speaker adaptation according to the phoneme classification for Korean Speech recognition. In order to study of speech adaptation according to the weight of difference of phoneme as recognition unit, we used SCHMM as recognition system. And Speaker adaptation method used in this paper was MAPE(Maximum A Posteriori Probability Estimation), Linear Spectral Estimation. In order to evaluate the performance of these methods, we used 10 Korean isolated numbers as the experimental data. It is possible for the first and the second methods to be carried out unsupervised learning and used in on-line system. And the first method was shown performance improvement over the second method, and hybrid adaptation showed the better recognition results than those which performed each method. And the result of Speaker adaptation using the variable weight according to the phoneme had better than the result using fixed weight.

• KSBB Journal
• /
• v.32 no.2
• /
• pp.90-95
• /
• 2017

Mammalian cell cultures have been used extensively to produce proteins for therapeutic agent because of their ability to perform post-translational modification including glycosylation. To produce recombinant protein, many factors and parameter are considered such as media composition, host cell type, and culture process. In this study, recombinant human erythropoietin (rhEPO) producing cell line was established by using glutamine synthetase system. To reduce serum concentration in media, we compared direct adaptation with step adaptation. Cell growth was faster in step adaptation. In low-level serum media, there were insufficient glucose for cell growth. Thus, we added glucose in low-level serum media from 2 g/L to 4.5 g/L. Titer of rhEPO was higher than other conditions at 4.5 g/L of glucose. Additionally, N-methyl-D-aspartate (NMDA), 13-cis-retinal, and pluronic F-68 (PF-68) were added to enhance productivity in CHO cell cultures. In conclusion, we applied CHO cell producing rhEPO to low-level of serum in media using step-adaptation. Also, we confirmed positive effect of NMDA, 13-cis-retinal, and PF-68.

• The Journal of the Convergence on Culture Technology
• /
• v.5 no.3
• /
• pp.191-195
• /
• 2019

South Korea is in a dangerous situation where a war between the two Koreas could be triggered at any time based on the MDL (Military Demarcation Line) between the two Koreas due to the inter-Korean standoff over the armistice. Also, unlike the borders of other countries, the border between the two Koreas is the front-line area where people can feel the threat of life that could be triggered by war. Soldiers who work in special areas such as the contact area are not easily accessible due to local conditions, and are less likely to go out, stay out, stay out, or visit, and the working environment is overloaded with vast forests and silence at night, and feel anxious, lonely and insecure because they don't know when any situation will occur near the enemy. Therefore, a great deal of help will be needed to pay attention to soldiers who give up their lives here and perform their national defense duties, and to finish their barracks life safely and faithfully, and support for psychological adaptation of service members in the border areas.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.300-303
• /
• 2003

An Algorithm based on direct implementation of variable structure systems theory approach is proposed for on-line training of multilayer perceptrons. Network structures which have multiple inputs, single output and one hidden layer are considered and the weights are assumed to have capabilities for continuous time adaptation. The zero level set of the network learning error is regarded as a sliding surface in the learning parameters space. A sliding mode trajectory can be brought on and reached in finite time on such a sliding manifold. Results from simulated on-line identification task for a two-link planar manipulator dynamics are also presented.