• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제16권2호
• /
• pp.125-130
• /
• 2016

The proposal of this study is a fast version of the conventional extreme learning machine (ELM), called pseudoinverse matrix decomposition based incremental ELM (PDI-ELM). One of the main problems in ELM is to determine the number of hidden nodes. In this study, the number of hidden nodes is automatically determined. The proposed model is an incremental version of ELM which adds neurons with the goal of minimization the error of the ELM network. To speed up the model the information of pseudoinverse from previous step is taken into account in the current iteration. To show the ability of the PDI-ELM, it is applied to few benchmark classification datasets in the University of California Irvine (UCI) repository. Compared to ELM learner and two other versions of incremental ELM, the proposed PDI-ELM is faster.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권12호
• /
• pp.5765-5781
• /
• 2018

Extreme learning machine (ELM) is emerging as a powerful machine learning method in a variety of application scenarios due to its promising advantages of high accuracy, fast learning speed and easy of implementation. However, how to select the optimal hidden layer of ELM is still an open question in the ELM community. Basically, the number of hidden layer nodes is a sensitive hyperparameter that significantly affects the performance of ELM. To address this challenging problem, we propose to adopt multiple kernel learning (MKL) to design a multi-hidden-layer-kernel ELM (MHLK-ELM). Specifically, we first integrate kernel functions with random feature mapping of ELM to design a hidden-layer-kernel ELM (HLK-ELM), which serves as the base of MHLK-ELM. Then, we utilize the MKL method to propose two versions of MHLK-ELMs, called sparse and non-sparse MHLK-ELMs. Both two types of MHLK-ELMs can effectively find out the optimal linear combination of multiple HLK-ELMs for different classification and regression problems. Experimental results on seven data sets, among which three data sets are relevant to classification and four ones are relevant to regression, demonstrate that the proposed MHLK-ELM achieves superior performance compared with conventional ELM and basic HLK-ELM.

• 전자공학회논문지C
• /
• 제35C권6호
• /
• pp.1-8
• /
• 1998

본 논문에서는 동일 칩 내부에 static CMOS와 하이브리드 로직 스타일(hybrid logic style)을 이용하여 저전력 8비트 ELM 덧셈기를 설계하였다. 두 개의 로직 스타일로 설계된 8비트 ELM 덧셈기는 0.8㎛ 단일 폴리 이중 금속, LG CMOS 공정으로 설계되어 측정되었다. 하이브리드 로직 스타일은 CCPL(Combinative Complementary Pass-transistor Logic), Wang's XOR 게이트와 ELM 덧셈기의 속도를 결정하는 임계경로(critical path)를 위한 static CMOS 등으로 구성된다. 칩 측정 결과, 전원 전압 5.0V에서 하이브리드로직으로 구현한 ELM 덧셈기가 static CMOS로 구현한 덧셈기에 비해 각각 전력소모 면에서 9.29%, 지연시간 면에서 14.9%, PDP(Power Delay Product)면에서 22.8%의 향상을 얻었다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2018년도 학술발표회
• /
• pp.157-157
• /
• 2018

A reliable and accurate downscaling model which can provide climate change information, obtained from global climate models (GCMs), at finer resolution has been always of great interest to researchers. In order to achieve this model, linear methods widely have been studied in the past decades. However, nonlinear methods also can be potentially beneficial to solve downscaling problem. Therefore, this study explored the applicability of some nonlinear machine learning techniques such as neural network (NN), extreme learning machine (ELM), and ELM autoencoder (ELM-AE) as well as a linear method, least absolute shrinkage and selection operator (LASSO), to build a reliable temperature downscaling model. ELM is an efficient learning algorithm for generalized single layer feed-forward neural networks (SLFNs). Its excellent training speed and good generalization capability make ELM an efficient solution for SLFNs compared to traditional time-consuming learning methods like back propagation (BP). However, due to its shallow architecture, ELM may not capture all of nonlinear relationships between input features. To address this issue, ELM-AE was tested in the current study for temperature downscaling.

• 한국시뮬레이션학회논문지
• /
• 제17권4호
• /
• pp.81-88
• /
• 2008

센서 네트워크에서 에너지 효율적인 MAC 프로토콜에 대한 연구가 중요하다. 본 논문에서는 센서 네트워크의 에너지 효율을 향상시키기 위한 ELM-MAC(Energy efficient Link Management MAC) 프로토콜을 제안한다. 제안하는 ELM-MAC 프로토콜은 주변 노드와의 최적화된 전송 전력 수준을 연산하고 전송 시 해당 노드와의 최적화된 전송 전력 수준으로 전송하는 방법을 통하여 센서 네트워크의 에너지 효율을 향상시킨다. ELM-MAC 프로토콜은 환경의 변화에 적응하는 방법을 이용하여 링크품질을 보장하는 메커니즘을 포함한다. 본 논문에서는 제안한ELM-MAC 프로토콜을 구현하고 성능을 평가한다.

• 조명전기설비학회논문지
• /
• 제23권9호
• /
• pp.108-116
• /
• 2009

본 논문에서는 단기 물 수요 예측에 대한 모델구현을 위해 MLP의 과도학습 문제를 해결할 수 있고 빠른 학습이 가능한 ELM 기반 단기 물 수요 예측 알고리즘을 제안한다. 제시된 알고리즘의 검증을 위해 2007년도와 2008년도 충남지역 광역상수도인 A정수장에서 취득된 데이터를 분석하여 알고리즘 구현의 정확도 분석에 사용하였다. 실험 결과 MLP모델은 MAPE가 5.82[%]인 반면, 제안된 방법인 ELM기반 모델은 5.61[%]로 성능이 향상된 것으로 나타났다. 또한, MLP모델은 학습에 소요된 시간이 7.57초인 반면, ELM 기반 모델은 0.09초로 빠른 학습이 가능함을 알 수 있었다. 따라서 제안된 ELM 기반 알고리즘은 정수장의 효율적 운영을 위한 단기 물 수요 예측에 활용할 수 있음을 보였다.

• 전자공학회논문지C
• /
• 제35C권8호
• /
• pp.33-41
• /
• 1998

We have designed a high speed and low power 16bit-ELM adder with variable-sized cells uitlizing the fact that the logic depth of lower bit position is less than that of the higher bit position int he conventional ELM architecture. As a result of HSPICE simulation with 0.8.mu.m single-poly double-metal LG CMOS process parameter, out 16bit-ELM adder with variable-sized cells shows the reduction of power-delay-product, which is less than that of the conventional 16bit-ELM adder with reference-sized cells by 19.3%. We optimized the desin with various logic styles including static CMOs, pass-transistor logic and Wang's XOR/XNOR gate. Maximum delay path of an ELM adder depends on the implementation method of S cells and their logic style.

• Journal of Electrical Engineering and Technology
• /
• 제11권4호
• /
• pp.993-1002
• /
• 2016

Hepatitis is a major public health problem all around the world. This paper proposes an automatic disease diagnosis system for hepatitis based on Genetic Algorithm (GA) Wavelet Kernel (WK) Extreme Learning Machines (ELM). The classifier used in this paper is single layer neural network (SLNN) and it is trained by ELM learning method. The hepatitis disease datasets are obtained from UCI machine learning database. In Wavelet Kernel Extreme Learning Machine (WK-ELM) structure, there are three adjustable parameters of wavelet kernel. These parameters and the numbers of hidden neurons play a major role in the performance of ELM. Therefore, values of these parameters and numbers of hidden neurons should be tuned carefully based on the solved problem. In this study, the optimum values of these parameters and the numbers of hidden neurons of ELM were obtained by using Genetic Algorithm (GA). The performance of proposed GA-WK-ELM method is evaluated using statical methods such as classification accuracy, sensitivity and specivity analysis and ROC curves. The results of the proposed GA-WK-ELM method are compared with the results of the previous hepatitis disease studies using same database as well as different database. When previous studies are investigated, it is clearly seen that the high classification accuracies have been obtained in case of reducing the feature vector to low dimension. However, proposed GA-WK-ELM method gives satisfactory results without reducing the feature vector. The calculated highest classification accuracy of proposed GA-WK-ELM method is found as 96.642 %.

• 전기학회논문지P
• /
• 제64권3호
• /
• pp.164-168
• /
• 2015

Due to the uncertainty of weather, it is difficult to construct an accurate forecasting model for daily PV power generation. It is very important work to know PV power in next day to manage power system. In this paper, correlation analysis between weather and power generation was carried out and daily PV power forecasting models based on Extreme Learning Machine(ELM) was presented. Performance of district ELM model was compared with single ELM model. The proposed method has been tested using actual data set measured in 2014.

• Asian-Australasian Journal of Animal Sciences
• /
• 제28권7호
• /
• pp.951-957
• /
• 2015

Four rumen fistulated swamp buffaloes were randomly assigned according to a $4{\times}4$ Latin square design to investigate the effects of Eucalyptus (E. Camaldulensis) leaf meal (ELM) supplementation as a rumen enhancer on feed intake and rumen fermentation characteristics. The dietary treatments were as follows: T1 = 0 g ELM/hd/d; T2 = 40 g ELM/hd/d; T3 = 80 g ELM/hd/d; T4 = 120 g ELM/hd/d, respectively. Experimental animals were kept in individual pens and concentrate was offered at 0.3% BW while rice straw was fed ad libitum. The results revealed that voluntary feed intake and digestion coefficients of nutrients were similar among treatments. Ruminal pH, temperature and blood urea nitrogen concentrations were not affected by ELM supplementation; however, ELM supplementation resulted in lower concentration of ruminal ammonia nitrogen. Total volatile fatty acids, propionate concentration increased with the increasing level of EML (p<0.05) while the proportion of acetate was decreased (p<0.05). Methane production was linearly decreased (p<0.05) with the increasing level of ELM supplementation. Protozoa count and proteolytic bacteria population were reduced (p<0.05) while fungal zoospores and total viable bacteria, amylolytic, cellulolytic bacteria were unchanged. In addition, nitrogen utilization and microbial protein synthesis tended to increase by the dietary treatments. Based on the present findings, it is suggested that ELM could modify the rumen fermentation and is potentially used as a rumen enhancer in methane mitigation and rumen fermentation efficiency.