KMITL

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

Browse

Search Results

Now showing 1 - 7 of 7

Some of the metrics are blocked by your
consent settings
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.
Some of the metrics are blocked by your
consent settings
Application of neural networks for vehicle classifiers: Extreme learning machine approach
(2019-01-18)
Jiaramaneepinit, Boonnithi
;
Nuthong, Chaiwat
Machine learning has been a popular topic in research field for many applications. One of the applications is traffic surveillance system. In many areas, traffic surveillance system is installed in order to gather and estimate important traffic information. Nowadays, there are several systems used for information's extracting, and classifying. One of the well-known approaches is decision tree. It uses a tree-like model that decides consequences outcomes from events. However, in some application, decision tree does not perform well. Another widely used approach is neural network, which has promising performance. It has been developed and become one of the most popular computing systems in research field. The traditional approach in training neural network is backpropagation. However, it has several drawbacks. One of them is the training time. In recent decades, Extreme learning machine (ELM) was proposed for training single hidden layer feed-forward neural network (SLFN) in the extremely fast way. It minimizes training error by utilizing dataset in one-shot calculation. This paper focuses on classifiers in traffic surveillance system. The classification divides into two main tasks. One is vehicle types' classification. Another is vehicle colors' classification. Neural networks trained with ELM are applied to the dataset. The performance are then compared to decision tree based approaches with ensemble methods. The experimental results show that ELM achieves better accuracy than of decision tree based approaches in both tasks.
Some of the metrics are blocked by your
consent settings
An improvement of extreme learning machine using subclass clustering
(2018-07-02)
Watchareeruetai, Ukrit
;
Jiramaneepinit, Boonnithi
Extreme learning machine (ELM) is an extremely fast learning algorithm proposed for a single-hidden-layer feed-forward neural network (SLFN). ELM projects a set of training instances into a random feature space, and then analytically calculates the weight matrix connecting between the hidden layer and the output layer, leading to a very fast learning speed. This paper proposes an improved version of ELM, named clustering-ELM, that assigns a subclass to each training instances and learns for a weight matrix that projects random features into subclass. In the prediction step, the responses from output nodes of the same class are integrated into one using maximum function. Experimental results conducted on various benchmark datasets reveal a promising performance of the proposed clustering-ELM, compared to the standard ELM.
Some of the metrics are blocked by your
consent settings
Iterative extreme learning machine
(2018-07-02)
Jiramaneepinit, Boonnithi
;
Watchareeruetai, Ukrit
This paper proposes a simple but effective method to improve the generalization performance of extreme learning machine (ELM), which is an extremely fast learning method for a single-hidden-layer feedforward neural network (SLFN). The proposed method adopts an online sequential learning technique to update the output weight matrix of a learned SLFN by using misclassified training samples. As the process of updating these weights could be iteratively performed, the proposed method is named iterative ELM (I-ELM). The proposed I-ELM was evaluated on three datasets, including MNIST, Small NORB, and CIFAR-10, and compared with the standard ELM. Experimental results indicate that by using only a few iterations, the proposed I-ELM could effectively improve the generalization performance of SLFNs.
Some of the metrics are blocked by your
consent settings
An extreme learning machine based pretraining method for multi-layer neural networks
(2018-07-02)
Noinongyao, Pavit
;
Watchareeruetai, Ukrit
One approach in training a deep neural network to perform effectively is to do unsupervised pretraining on each layer, followed by fine-tuning the whole network. A common way is to train an unsupervised model of neural network such as restricted Boltzmann machines or autoencoders and stack them on top of another. Although these unsupervised pretraining approaches yield good performance, relying on back-propagation, due to iterative learning process, they still suffer from a long pretraining time. Extreme learning machine (ELM) is an analytical training approach which is extremely fast and gives a solution with a good generalization performance. In this paper, we apply a new ELM based unsupervised learning, named backward ELM based autoencoder (BELM-AE), to pretrain each layer of a neural network before using a back-propagation based learning algorithm to fine-tune the whole network. Experimental results show that the new pretraining method requires significantly shorter training time and also yields better testing performance on various datasets.
Some of the metrics are blocked by your
consent settings
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.
Some of the metrics are blocked by your
consent settings
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.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results