• Advances in Computational Design
• /
• 제2권3호
• /
• pp.225-240
• /
• 2017

This paper presents the application of multiple linear regression (MLR) and artificial neural network (ANN) techniques for developing the models to predict the unconfined compressive strength (UCS) and Brazilian tensile strength (BTS) of the fiber reinforced cement stabilized fly ash mixes. UCS and BTS is a highly nonlinear function of its constituents, thereby, making its modeling and prediction a difficult task. To establish relationship between the independent and dependent variables, a computational technique like ANN is employed which provides an efficient and easy approach to model the complex and nonlinear relationship. The data generated in the laboratory through systematic experimental programme for evaluating UCS and BTS of fiber reinforced cement fly ash mixes with respect to 7, 14 and 28 days' curing is used for development of the MLR and ANN model. The data used in the models is arranged in the format of four input parameters that cover the contents of cement and fibers along with maximum dry density (MDD) and optimum moisture contents (OMC), respectively and one dependent variable as unconfined compressive as well as Brazilian tensile strength. ANN models are trained and tested for various combinations of input and output data sets. Performance of networks is checked with the statistical error criteria of correlation coefficient (R), mean square error (MSE) and mean absolute error (MAE). It is observed that the ANN model predicts both, the unconfined compressive and Brazilian tensile, strength quite well in the form of R, RMSE and MAE. This study shows that as an alternative to classical modeling techniques, ANN approach can be used accurately for predicting the unconfined compressive strength and Brazilian tensile strength of fiber reinforced cement stabilized fly ash mixes.

• 한국항행학회논문지
• /
• 제23권6호
• /
• pp.561-569
• /
• 2019

태양광 발전은 일사량만 있으면 전기에너지를 얻을 수 있기 때문에, 새로운 에너지 공급원으로 용도가 급증하고 있다. 본 논문은 실제 태양광 발전 시스템의 컨버터 출력을 이용하여 장단기 출력 예측을 하였다. 예측 알고리즘은 다중선형회귀와 머신러닝의 지도학습 중 분류모델인 서포트 벡터 머신 그리고 DNN과 LSTM 등 딥러닝을 이용하였다. 또한 기상요소의 입출력 구조에 따라 3개의 모델을 이용하였다. 장기 예측은 월별, 계절별, 연도별 예측을 하였으며, 단기 예측은 7일간의 예측을 하였다. 결과로서 RMSE 측도에 의한 예측 오차로 비교해 본 결과 다중선형회귀와 SVM 보다는 딥러닝 네트워크가 예측 정확도 측면에서 더 우수하였다. 또한, DNN 보다 시계열 예측에 우수한 모델인 LSTM이 예측 정확도 측면에서 우수하였다. 입출력 구조에 따른 실험 결과는 모델 1보다 모델 2가 오차가 적었으며, 모델 2보다는 모델 3이 오차가 적었다.

• 한국지반신소재학회논문집
• /
• 제21권2호
• /
• pp.21-30
• /
• 2022

전단강도는 암반 비탈면 안정성 평가에서 가장 중요한 지표이다. 일반적으로 기존 문헌자료, 역해석, 실험 등의 결과를 비교하여 산정한다. 암반 비탈면에서의 전단강도는 불연속면의 상태와 관련된 변수를 추가로 고려해야 한다. 이 변수들은 시추조사를 통해 여부를 파악하는 것이 어려울뿐더러 전단강도와의 정확한 관계를 찾아내기도 어렵다. 본 연구에서는 역해석을 통해 산정된 데이터를 이용했다. 기존 고려되었던 변수들의 관계를 딥러닝에 접목시켜 전단강도 산정에 적합한지 그 가능성을 모색하였다. 비교를 위해 기존에 사용되는 간단한 선형회귀(Linear Regression) 모델과 딥러닝 알고리즘인 심층인공신경망(DNN) 모델을 사용하였다. 각 분석 모델은 비슷한 예측결과를 도출해내었지만 미세한 차이로 DNN의 설명력이 개선된 결과를 나타내었다.

• Journal of Electrical Engineering and Technology
• /
• 제10권3호
• /
• pp.1356-1362
• /
• 2015

The location of PV systems in distribution system has been increased as one of countermeasure for global environmental issues. As the operation efficiency of PV systems is getting decreased year by year due to the aging phenomenon and maintenance problems, the optimal algorithm for state diagnosis in PV systems is required in order to improve operation performance in PV systems. The existing output prediction algorithms considering various parameters and conditions of PV modules could have complicated calculation process and then their results may have a possibility of significant prediction error. To solve these problems, this paper proposes an optimal prediction algorithm of PV system by using least square methods of linear regression analysis. And also, this paper presents a performance evaluation algorithm in PV modules based on the proposed optimal prediction algorithm of PV system. The simulation results show that the proposed algorithm is a practical tool of the state diagnosis for performance improvement in PV systems.

• Computers and Concrete
• /
• 제22권4호
• /
• pp.355-363
• /
• 2018

In the following paper, a socio-political heuristic search approach, named the imperialist competitive algorithm (ICA) has been used to improve the efficiency of the multi-layer perceptron artificial neural network (ANN) for predicting the compressive strength of concrete. 173 concrete samples have been investigated. For this purpose the values of slump flow, the weight of aggregate and cement, the maximum size of aggregate and the water-cement ratio have been used as the inputs. The compressive strength of concrete has been used as the output in the hybrid ICA-ANN model. Results have been compared with the multiple-linear regression model (MLR), the genetic algorithm (GA) and particle swarm optimization (PSO). The results indicate the superiority and high accuracy of the hybrid ICA-ANN model in predicting the compressive strength of concrete when compared to the other methods.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 제13회 신호처리 합동 학술대회 논문집
• /
• pp.157-160
• /
• 2000

In the generally a voice conversion has used VQ(Vector Quantization) for partitioning the spectral feature and has performed by adding an appropriate offset vector to the source speaker's spectral vector. But there is not represented the target speaker's various characteristics because of discrete characteristics of transformed parameter. In this paper, these problems are solved by using the LMR(Linear Multivariate Regression) instead of the mapping codebook which is determined to the relationship of source and target speaker vocal tract characteristics. Also we propose the method for solved the discontinuity which is caused by applying to time aligned parameters using Dynamic Time Warping the time or pitch-scale modified speech. In our proposed algorithm for overcoming the transitional discontinuities, first of all, we don't change time or pitch scale and by using the LMR change a speaker's vocal tract characteristics in speech with non-modified time or pitch. Compared to existed methods based on VQ and LMR, we have much better voice quality in the result of the proposed algorithm.

• 대한의용생체공학회:의공학회지
• /
• 제6권2호
• /
• pp.53-62
• /
• 1985

The position and time interval of wave components of the electrocardiogram are used as important data for physician's diagnosis. In case of using the existing definition of the onset of the wave component of the electrocardiogram, they have some problems of defining the precise position of the isoelectric line, of defining the limit of the gradient accepted as the onset, and of the gradient being changed by noise. Therefore, in this paper all time intervals and positions of wave components needed for data of diagnosis were obtained correctly by turning point data reduction algorithm and linear regression intersection algorithm, and the viability of the method of intersecting lines was established in comparison to the four methods of calculating the PR interval.

• 한국군사과학기술학회지
• /
• 제4권1호
• /
• pp.30-40
• /
• 2001

This paper presents a study on the design and simulation of bearing only target motion analysis to enhance the TMA capability using SONAR in underwater environment. A bearing only target motion analysis algorithm using aperiod bearing input signals has been developed and simulated in the MATLAB.

• 한국음향학회지
• /
• 제22권8호
• /
• pp.727-739
• /
• 2003

본 논문에서는 HM-Net (Hidden Markov Network)을 다양한 태스크에의 적용과 화자의 특성을 효과적으로 나타내기 위해 HM-Net 음성인식 시스템에 MLLR (Maximum Likelihood Linear Regression) 적응방법을 도입하였으며, HM-Net 학습 알고리즘을 개량하여 회귀클래스 생성방법을 제안한다. 제안방법은 PDT-SSS (Phonetic Decision Tree-based Successive State Splitting)알고리즘의 문맥방향 상태분할에 의한 상태레벨 공유를 이용한 방법이다. 즉, 문맥방향의 각 상태에 적응화자 음성데이터에 포함된 문맥정보를 분할하여 적응화될 음소환경을 결정하는 것이다. 따라서 제안방법은 새로운 화자로부터 문맥정보와 적응화 데이터의 발성 양에 의존하여 결정된 많은 적응 파라미터들을 (평균, 분산) 자유롭게 제어할 수 있게 된다. 제안방법의 유효성을 확인하기 위해 국어공학센터 (KLE) 452 데이터와 항공편 예약관련 (YNU200) 연속음성을 대상으로 인식실험을 수행한 결과, 음소인식, 단어인식, 연속음성인식에 대해서, 평균 34∼37%, 평균 9%, 평균 20%의 성능 향상을 각각 보였다. 또한 적응화 데이터의 양에 따른 인식성능 비교에서 제안방법을 적용한 인식 시스템이 적응 데이터의 양이 적은 경우에도 향상된 인식률을 보여 MLLR 적응방법의 특성을 만족하였다. 따라서 MLLR 적응방법을 도입한 HM-Net 음성인식 시스템에 제안한 회귀클래스 생성방법이 유효함을 확인할 수 있었다.

• 품질경영학회지
• /
• 제49권4호
• /
• pp.527-537
• /
• 2021

Purpose: The purpose of this study was to suggest an improved version of Proof-of-Nonce (PoN) algorithm, which is a distributed consensus algorithm used for block chain system. Methods: First, we used response surface method for design of experiment that is to generate experimental points considering non-linear relationship among variables. Then, we employed overlapped contour plots for visualizing the impact of control variables to performance target. Results: First, we modified the consensus procedure of the existing PoN algorithm by diminishing the content of the exchanged message. Then, we verified the performance improvement of the new PoN algorithm by performing a numerical experiment and paired t-test. Finally, we established new regression models for consensus time and Transactions per second (TPS) and proposed a method for optimizing control variables for obtaining performance target. Conclusion: We could improve the performance of the previous version of PoN algorithm by modifying the content of the exchanged message during 4-steps of consensus procedure, which might be a stepping stone for designing an efficient and effective consensus algorithm for blockchain system with dynamic operation environment.