• Structural Engineering and Mechanics
• /
• 제70권5호
• /
• pp.513-524
• /
• 2019

This study proposed an improved particle swarm optimization (IPSO) method ensemble with kriging model for model updating. By introducing genetic algorithm (GA) and grouping strategy together with elite selection into standard particle optimization (PSO), the IPSO is obtained. Kriging metamodel serves for predicting the structural responses to avoid complex computation via finite element model. The combination of IPSO and kriging model shall provide more accurate searching results and obtain global optimal solution for model updating compared with the PSO, Simulate Annealing PSO (SimuAPSO), BreedPSO and PSOGA. A plane truss structure and ASCE Benchmark frame structure are adopted to verify the proposed approach. The results indicated that the hybrid of kriging model and IPSO could serve for model updating effectively and efficiently. The updating results further illustrated that IPSO can provide superior convergent solutions compared with PSO, SimuAPSO, BreedPSO and PSOGA.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2007년도 추계학술대회논문집
• /
• pp.23-27
• /
• 2007

Many trials have been used to model room impulse responses, all attempting to provide efficient representations of room acoustics. The traditional model designs for room impulse response seem to fail in accuracy, controllability, or computational efficiency. In time domain, a room impulse response is generally considered as the combination of three parts having different acoustic characteristics, initial time delay, early reflection, and late reverberation. This paper introduces new learning hybrid model for the room impulse response. In this proposed model, those three parts are modeled using different models with learning algorithms that determine the length or boundary of each model in the hybrid model. By the simulation with measured room impulse responses, it was examined that the performance of proposed model shows the best efficiency in views of both the parameter numbers and modeling error.

• 대한의용생체공학회:의공학회지
• /
• 제6권1호
• /
• pp.55-64
• /
• 1985

The cardiac activation process using three dimensional ventricular model is simulated.To study this theme, we constructed a cardiac ventricular model and simulated the cardiac activation process using the action potential duration and the activation time. The cardiac ventricular model is generated by the logical combination of the elliptic equations. The action potential duration could be obtained from the fact that it is linearly distributed between model cells. The cardiac activation process was simulated by the law of "all-or-none" Based on the activation time and the action potential do-ration the cardiac potential at the arbitrary time after the activation of the model cell was computed. To test the validity of model, the comparison of the results of model simulation with the physiological data was performed. In conclusion, this model shows the simular results which is comparable to the real conduction of the cardiac excitation.xcitation.

• 음성과학
• /
• 제10권4호
• /
• pp.149-157
• /
• 2003

In this paper, we proposed the principal component analysis (PCA) fuzzy mixture model for speaker identification. A PCA fuzzy mixture model is derived from the combination of the PCA and the fuzzy version of mixture model with diagonal covariance matrices. In this method, the feature vectors are first transformed by each speaker's PCA transformation matrix to reduce the correlation among the elements. Then, the fuzzy mixture model for speaker is obtained from these transformed feature vectors with reduced dimensions. The orthogonal Gaussian Mixture Model (GMM) can be derived as a special case of PCA fuzzy mixture model. In our experiments, with having the number of mixtures equal, the proposed method requires less training time and less storage as well as shows better speaker identification rate compared to the conventional GMM. Also, the proposed one shows equal or better identification performance than the orthogonal GMM does.

• Journal of Mechanical Science and Technology
• /
• 제15권11호
• /
• pp.1482-1489
• /
• 2001

Thermally-induced errors originating from machine tool errors have received significant attention recently because high speed and precise machining is now the principal trend in manufacturing proce sses using CNC machine tools. Since the thermal error model is generally a function of temperature, the thermal error compensation system contains temperature sensors with the same number of temperature variables. The minimization of the number of variables in the thermal error model can affect the economical efficiency and the possibility of unexpected sensor fault in a error compensation system. This paper presents a thermal error model with minimum number of variables using a fuzzy logic strategy. The proposed method using a fuzzy logic strategy does not require any information about the characteristics of the plant contrary to numerical analysis techniques, but the developed thermal error model guarantees good prediction performance. The proposed modeling method can also be applied to any type of CNC machine tool if a combination of the possible input variables is determined because the error model parameters are only calculated mathematically-based on the number of temperature variables.

• 한국정밀공학회지
• /
• 제16권3호통권96호
• /
• pp.215-221
• /
• 1999

The object of the thermal error compensation system in machine tools is improving the accuracy of a machine tool through real time error compensation. The accuracy of the machine tool totally depends on the accuracy of thermal error model. A thermal error model can be obtained by appropriate combination of temperature variables. The proposed method for optimal variable selection in the thermal error model is based on correlation grouping and successive regression analysis. Collinearity matter is improved with the correlation grouping and the judgment function which minimizes residual mean square is used. The linear model is more robust against measurement noises than an engineering judgement model that includes the higher order terms of variables. The proposed method is more effective for the applications in real time error compensation because of the reduction in computational time, sufficient model accuracy, and the robustness.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제12권3호
• /
• pp.133-140
• /
• 2023

리튬 이온 배터리는 사용 환경과 양극재 조합 비율에 따라 배터리의 성능이 좌우된다. 고성능 리튬 이온 배터리를 개발하기 위해서는 양극재 비율을 다양하게 변화시켜가면서 배터리를 제작하고 성능을 측정해야 한다. 하지만 모든 변수 조합에 대해 배터리를 제작하고 성능을 측정하기에는 많은 시간과 비용이 소모된다. 그렇기 때문에 최근에는 데이터 기반으로 인공지능 모델을 활용하여 배터리의 성능을 예측하고자 하는 연구가 활발히 진행되고 있다. 그러나 기존 공개 배터리 데이터는 동일한 배터리로 측정 실험을 하였기 때문에 양극재 조합 비율은 고정되어 있어서 데이터 속성으로 포함되지 않았다. 본 논문에서는 양극재 소재 조합 비율에 따른 배터리의 성능을 예측할 수 있는 인공지능 모델 개발에 필요한 학습 데이터 모델을 정의한다. 우리는 리튬 이온 배터리의 성능에 영향을 미칠 수 있는 요인을 분석하여 양극재 소재별 질량과 배터리 사용 환경을 입력데이터로, 배터리의 출력과 용량을 목적 데이터로 정의하였다. 공개 배터리 데이터 중에는 양극재 비율이 포함된 데이터가 없어 양극재 비율을 모두 동일한 값으로 설정한 제한된 데이터로 다중 선형회귀 분석, 서포트 벡터 회귀분석, 다중 로지스틱 회귀 분석, LSTM 분석을 수행하였다. 실험 환경이 다른 배터리 데이터에서 각각의 배터리 데이터는 고유한 패턴을 유지하였으며, 배터리 분류 모델은 각각의 배터리를 약 2%의 오차로 분류하는 것으로 나타났다.

• 한국컴퓨터정보학회논문지
• /
• 제21권5호
• /
• pp.79-89
• /
• 2016

In this paper, we proposed the object classification method using genetic and dynamic random forest consisting of optimal combination of unit tree. The random forest can ensure good generalization performance in combination of large amount of trees by assigning the randomization to the training samples and feature selection, etc. allocated to the decision tree as an ensemble classification model which combines with the unit decision tree based on the bagging. However, the random forest is composed of unit trees randomly, so it can show the excellent classification performance only when the sufficient amounts of trees are combined. There is no quantitative measurement method for the number of trees, and there is no choice but to repeat random tree structure continuously. The proposed algorithm is composed of random forest with a combination of optimal tree while maintaining the generalization performance of random forest. To achieve this, the problem of improving the classification performance was assigned to the optimization problem which found the optimal tree combination. For this end, the genetic algorithm methodology was applied. As a result of experiment, we had found out that the proposed algorithm could improve about 3~5% of classification performance in specific cases like common database and self infrared database compare with the existing random forest. In addition, we had shown that the optimal tree combination was decided at 55~60% level from the maximum trees.

• 디자인학연구
• /
• 제16권3호
• /
• pp.329-340
• /
• 2003

본 연구의 목적은 도시경관의 이미지를 개선하기 위한 환경색채의 배색조화 방법을 제공하는 것이다. 연구 대상지역은 익산시 22개 아파트단지이며 이를 분석하였다. 본 연구는 자연색체계에 기초한 하드와 시빅의 배색모델을 준거의 틀로 사용하였다. 그리고 환경색채 지각과 색채미학에서 새롭게 제시된 다양한 이론들을 검토하였으며 환경 색채디자인에 적용될 수 있는 미학적 특성들을 제안하였다. 첫째, 색채조화 원리는 뉘앙스와 톤에 기초한다. 그러므로 뉘앙스와 관계된 명도와 채도의 조절이 배색에 중요하게 작용된다. 둘째, 색채지각에 있어 미적경험은 색채 속성들의 유사성과 차이성의 상호결합에 의한 효과로 정의되었다. 셋째, 색채조화이론은 더욱 통합적인 학제 간 연구를 통해 발전 될 수 있으며 이러한 경험적 자료는 환경색채디자인과 평가를 위한 기초적 정보가 될 수 있을 것으로 판단된다.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권22호
• /
• pp.9667-9672
• /
• 2014

Background: Pancreatic adenocarcinoma is a malignant gastrointestinal cancer with significant morbidity and mortality. Despite severe side effects of chemotherapy, the use of immunotherapy combined with chemotherapy has emerged as a common clinical treatment. In this study, we investigated the efficacy of the combined doxorubicin and interferon-${\alpha}$ (IFN-${\alpha}$) therapy on murine pancreatic cancer Panc02 cells in vitro and in vivo and underlying mechanisms. Materials and Methods: A Panc02-bearing mouse model was established to determine whether doxorubicin and interferon-${\alpha}$ (IFN-${\alpha}$) could effectively inhibit tumor growth in vivo. Cytotoxicity of natural killer (NK) cells and cytotoxic T lymphocytes (CTLs) was evaluated using a standard LDH release assay. To evaluate the relevance of NK cells and CD8 T cells to the combination therapy-mediated anti-tumor effects, they were depleted in tumor-bearing mice by injecting anti-asialo-GM-1 antibodies or anti-CD8 antibodies, respectively. Finally, the influence of doxorubicin+interferon-${\alpha}$ (IFN-${\alpha}$) on the ligands of NK and T cells was assessed by flow cytometry. Results: The combination therapy group demonstrated a significant inhibition of growth of Panc02 in vivo, resulting from activated cytotoxicity of NK cells and CTLs. Depleting CD8 T cells or NK cells reduced the anticancer effects mediated by immunochemotherapy. Furthermore, the doxorubicin+IFN-a treatment increased the expression of major histocompatibility complex class I (MHC I) and NKG2D ligands on Panc02 cells, suggesting that the combined therapy may be a potential strategy for enhancing immunogenicity of tumors. All these data indicate that the combination therapy using doxorubicin and interferon-${\alpha}$ (IFN-${\alpha}$) may be a potential strategy for treating pancreatic adenocarcinoma.