• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.5
• /
• pp.833-842
• /
• 2017

In this study, the design methodology of radial basis function neural networks based on incremental K-means clustering is introduced for learning and processing the big data. If there is a lot of dataset to be trained, general clustering may not learn dataset due to the lack of memory capacity. However, the on-line processing of big data could be effectively realized through the parameters operation of recursive least square estimation as well as the sequential operation of incremental clustering algorithm. Radial basis function neural networks consist of condition part, conclusion part and aggregation part. In the condition part, incremental K-means clustering algorithms is used tweights of the conclusion part are given as linear function and parameters are calculated using recursive least squareo get the center points of data and find the fitness using gaussian function as the activation function. Connection s estimation. In the aggregation part, a final output is obtained by center of gravity method. Using machine learning data, performance index are shown and compared with other models. Also, the performance of the incremental K-means clustering based-RBFNNs is carried out by using PSO. This study demonstrates that the proposed model shows the superiority of algorithmic design from the viewpoint of on-line processing for big data.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.3
• /
• pp.687-693
• /
• 2015

Using 378,086 lactation records on dairy cattle, environmental factors influencing acetone and ${\beta}$-hydroxybutyrate acid contents in raw milk which are used as ketosis diagnosis indicator traits were analyzed in this experiment. Significance testing was conducted on farm, lactation stage, parity, milking time and month of age by traits. The results of this experiment indicated that there was a highly significant (p < 0.01) difference in all factors and lactation stage was the most significant factor. Linear regression coefficients of month of age on daily milk yields and acetone and ${\beta}$-hydroxybutyrate acid contents were all positive, while their quadratic linear regression coefficients were negative. Least square means for milk yield at second lactation stage (36~65 days) was 19.06kg which was higher than that of late lactation stage by 6.51kg. Least square means for acetone and ${\beta}$-hydroxybutyrate acid contents at the first lactation stage (5~35 days) were highest (0.1929mM/L and 0.0742mM/L, respectively), and there was a trend that they decreased as the milking progressed, but increased slightly at the late stage of milking. However, least square means for acetone and ${\beta}$-hydroxybutyrate acid contents at the first parity were 0.1414mM/L and 0.0522mM/L, respectively, which were higher than the average milk yield after the second parity. Least square means for acetone and ${\beta}$-hydroxybutyrate acid contents of PM milk yield (0.1372mM/L and 0.0534mM/L, respectively) were higher than those of AM milk yield collectively.

• Current Research on Agriculture and Life Sciences
• /
• v.9
• /
• pp.37-49
• /
• 1991

This study was conducted to estimate the effects of year, age of dam at calving, farm and lactation period on milk yield with the data of 4,008 cows' records which were collected at 32 farms by Korea Animal Improvement Association from 1985 to 1989. The results obtained in this study are summarized as follows: 1. The average performance of the dairy cattle in the study were $5,959.23{\pm}2,113.03kg$ in actual milk yield, $49.19{\pm}22.77$ months in age of dam at calving, $27.11{\pm}5.13$ months in age at first calving and $255.11{\pm}79.68$ days in lactation period. 2. The percentages of variance component for different sources were 29.39% for the residuals, 1.91% for years, 4.86% for age at calving, 8.89% for farms and 54.94% for lactation period. 3. The overall mean of least-square estimate on the milk yield was 6,229.31kg. In the effects of year, the least-square means of milk yield were estimated 6,000.76kg in 1985-1987, 6,028.11kg in 1988 and 6,659.07kg in 1989. 4. The least-square means of calving age on the milk yield were estimated 5,456.01kg in less than 24 months, 6,565.48kg in 61-66 months which were the highest least-square means. This effects were gradually increased until the 61-66months and gradually decreased after the 61-66months, with highly significant differences among different months of age at calving(p<0.01). 5. In the effects of farm, the least-square means of milk yield were estimated 4,959.50 kg in the lowest farm and 7,497.07kg in the highest farm. Among the milk yield of each farm the effects showed highly significant difference(p<0.01). 6. The least-square means of milk yield in the effects of lactation period were gradually increased with the lapse of the lactation period. Among the lactation period the effects showed highly significant difference(p<0.01).

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.5
• /
• pp.805-810
• /
• 2019

Recently, a majority of 4G mobile telecommunication manufacturers prefer repeaters with good adaptability. In this paper, we propose a new LMF(: Least Means Fourth) algorithm for LTE(: Long Term Evolution) RF(: Radio Frequency) Repeater. The proposed algorithm is a modification of the LMF, which appropriately adjusts the step size and improves performance according to the Sign function. The steady state MSE(: Mean Square Error) performance of the proposed LMF algorithm with step size of 0.009 is low level at about -25dB, and the proposed LMF algorithm requires 500 less iterations than the conventional algorithms at MSE of -25dB.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.1
• /
• pp.99-106
• /
• 2015

In this study, we propose Radial basis function Neural Network(RBFNN) using Recursive Weighted Least Square Estimation(RWLSE) to effectively deal with big data class meteorological radar data. In the condition part of the RBFNN, Fuzzy C-Means(FCM) clustering is used to obtain fitness values taking into account characteristics of input data, and connection weights are defined as linear polynomial function in the conclusion part. The coefficients of the polynomial function are estimated by using RWLSE in order to cope with big data. As recursive learning technique, RWLSE which is based on WLSE is carried out to efficiently process big data. This study is experimented with both widely used some Machine Learning (ML) dataset and big data obtained from meteorological radar to evaluate the performance of the proposed classifier. The meteorological radar data as big data consists of precipitation echo and non-precipitation echo, and the proposed classifier is used to efficiently classify these echoes.

• 제어로봇시스템학회:학술대회논문집
• /
• 1986.10a
• /
• pp.134-136
• /
• 1986

In this paper, a new power spectral estimation technique is presented. At first, by transforming the original data with the Karhunen-Loeve Transform(KLT), we can reduce the amount of the redundant information. Next, by modeling the transformed data by means of the autoregressive(AR) model and then applying the least-squares parameter estimation algorithm to this model, even more accurate spectrum estimates can be obtained. The KLT is the optimum transform for signal representation with respect to the mean-square error criterion. And the least-squares method is used to overcome the inherent shortcomings of popular burg algorithm.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.6
• /
• pp.586-591
• /
• 2014

In this study, we introduce Radial Basis Function Neural Networks(RBFNNs) classifier using Artificial Bee Colony(ABC) algorithm in order to classify between precipitation event and non-precipitation event from given radar data. Input information data is rebuilt up through feature analysis of meteorological radar data used in Korea Meteorological Administration. In the condition phase of the proposed classifier, the values of fitness are obtained by using Fuzzy C-Mean clustering method, and the coefficients of polynomial function used in the conclusion phase are estimated by least square method. In the aggregation phase, the final output is obtained by using fuzzy inference method. The performance results of the proposed classifier are compared and analyzed by considering both QC(Quality control) data and CZ(corrected reflectivity) data being used in Korea Meteorological Administration.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.6
• /
• pp.1070-1079
• /
• 2016

In this paper, the design of recursive radial basis function neural networks based on incremental fuzzy c-means is introduced for processing the big data. Radial basis function neural networks consist of condition, conclusion and inference phase. Gaussian function is generally used as the activation function of the condition phase, but in this study, incremental fuzzy clustering is considered for the activation function of radial basis function neural networks, which could effectively do big data processing. In the conclusion phase, the connection weights of networks are given as the linear function. And then the connection weights are calculated by recursive least square estimation. In the inference phase, a final output is obtained by fuzzy inference method. Machine Learning datasets are employed to demonstrate the superiority of the proposed classifier, and their results are described from the viewpoint of the algorithm complexity and performance index.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.8
• /
• pp.754-759
• /
• 2001

In this paper, we propose a TSK(Takagi-Sugeno-Kang)-type fuzzy classifier using PCA(Principal Component Analysis), FCM(Fuzzy c-Means) clustering, ANFIS(Adaptive Neuro-Fuzzy Inference System) and hybrid GA(Genetic Algorithm). First, input data is transformed to reduce correlation among the data components by PCA. FCM clustering is applied to obtain a initial TSK-type fuzzy classifier. Parameter identification is performed by AGA(Adaptive GA) and RLSE(Recursive Least Square Estimate). Finally, we applied the proposed method to Iris data classificationl problems and obtained a better performance than previous works.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.2
• /
• pp.83-91
• /
• 2004

This paper illustrates the feasibility and the effectiveness of the disturbance feedforward compensation control proposed in the previous paper. The compensator is designed experimentally by means of the Multiple Filtered-x Least Mean Square algorithm. A 2-DOF active magnetic bearing system subject to base motion is built and the compensation control is applied. The experimental results demonstrate that the compensation control reduces the air-gap responses within 10$%$ of those by the feedback control alone without increasing the control inputs.