KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Author: search.filters.author.Pasupa, KitsuchartSubject: search.filters.subject.Extreme learning machine

Search Results

Now showing 1 - 3 of 3
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    SELM: Siamese extreme learning machine with application to face biometrics
    (2022-07-01)
    Kudisthalert, Wasu
    ;
    Pasupa, Kitsuchart
    ;
    Morales, Aythami
    ;
    Fierrez, Julian
    Extreme learning machine (ELM) is a powerful classification method and is very competitive among existing classification methods. It is speedy at training. Nevertheless, it cannot perform face verification tasks properly because face verification tasks require the comparison of facial images of two individuals simultaneously and decide whether the two faces identify the same person. The ELM structure was not designed to feed two input data streams simultaneously. Thus, in 2-input scenarios, ELM methods are typically applied using concatenated inputs. However, this setup consumes two times more computational resources, and it is not optimized for recognition tasks where learning a separable distance metric is critical. For these reasons, we propose and develop a Siamese extreme learning machine (SELM). SELM was designed to be fed with two data streams in parallel simultaneously. It utilizes a dual-stream Siamese condition in the extra Siamese layer to transform the data before passing it to the hidden layer. Moreover, we propose a Gender-Ethnicity-dependent triplet feature exclusively trained on various specific demographic groups. This feature enables learning and extracting useful facial features of each group. Experiments were conducted to evaluate and compare the performances of SELM, ELM, and deep convolutional neural network (DCNN). The experimental results showed that the proposed feature could perform correct classification at 97.87 % accuracy and 99.45 % area under the curve (AUC). They also showed that using SELM in conjunction with the proposed feature provided 98.31 % accuracy and 99.72 % AUC. SELM outperformed the robust performances over the well-known DCNN and ELM methods.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Recurrent kernel extreme reservoir machine for time series prediction
    (2018-04-04)
    Liu, Zongying
    ;
    Loo, Chu Kiong
    ;
    Masuyama, Naoki
    ;
    Pasupa, Kitsuchart
    This paper proposes a novel recurrent multi-step-ahead prediction model called recurrent kernel extreme reservoir machine (RKERM) with quantum particle swarm optimization (QPSO). This model combines the strengths of recurrent kernel extreme learning machine (RKELM) and modified reservoir computing to overcome the limitations of prediction horizon with increased prediction accuracy based on reservoir computing theory. Furthermore, QPSO is used to optimize the parameters of kernel method and leaking rate of reservoir computing in the RKERM. In the experiment, we apply two synthetic benchmark data sets and five real-world time series data sets, including Malaysia palm oil price, ozone concentration in Toronto, sunspots, Standard Poor's 500, and water level at Phra Chulachomklao Fort in Thailand to evaluate the echo state network, recurrent support vector regression, recurrent extreme learning machine, RKELM, and RKERM. The experimental results show that the RKERM with QPSO has superior abilities in the different predicting horizons than others.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Analytical incremental learning: Fast constructive learning method for neural network
    (2016-01-01)
    Alfarozi, Syukron Abu Ishaq
    ;
    Setiawan, Noor Akhmad
    ;
    Adji, Teguh Bharata
    ;
    Woraratpanya, Kuntpong
    ;
    Pasupa, Kitsuchart
    Extreme learning machine (ELM) is a fast learning algorithm for single hidden layer feed-forward neural network (SLFN) based on random input weights which usually requires large number of hidden nodes. Recently, novel constructive and destructive parsimonious (CP and DP)-ELM which provide the effectiveness generalization and compact hidden nodes have been proposed. However, the performance might be unstable due to the randomization either in ordinary ELM or CP and DP-ELM. In this study, analytical incremental learning (AIL) algorithm is proposed in which all weights of neural network are calculated analytically without any randomization. The hidden nodes of AIL are incrementally generated based on residual error using least square (LS) method. The results show the effectiveness of AIL which has not only smallest number of hidden nodes and more stable but also good generalization than those of ELM, CP and DP-ELM based on seven benchmark data sets evaluation.