KMITL

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

Browse

Settings

Subject: search.filters.subject.Time series prediction

Search Results

Now showing 1 - 3 of 3
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Self-attention hierarchical kernel reservoir state network for inland water level prediction
    (2026-01-15)
    Liu, Zongying
    ;
    Xu, Xiaohan
    ;
    Pasupa, Kitsuchart
    ;
    Loo, Chu Kiong
    ;
    Wei, Yang
    Waterway transportation sustainably facilitates global trade through eco-efficient cargo movement, where accurate water level forecasting is critical for ensuring navigational safety and operational continuity. To develop a highly accurate prediction model, it is essential to consider the periodic characteristics of water level data, which often emerge in real-world datasets. This study introduces a novel reservoir state structure based on reservoir computing theory, the Self-attention Hierarchical Kernel Reservoir State Network (SHK-RSN). It employs three primary mechanisms. First, a hierarchical feature extraction method groups training data and extracts high-dimensional features from these groups using the kernel trick in a hierarchical manner. Second, a self-attention weight selection approach is introduced to replace the random weights in the Hierarchical Kernel Reservoir State Network (HK-RSN), improving the rationale for hidden neuron connections and enhancing the interpretability of weight selection. Third, a novel reservoir state structure is proposed to capture periodic information and extract temporal features across periods, enabling the model to capture richer temporal information and identify relationships among periods. Experiments are conducted on one artificial and five real-world time series datasets, with forecast performance evaluated over 1–7 steps. Our proposed model, SHK-RSN, is compared with models based on randomization, the kernel trick, and deep learning. The experimental results demonstrate that SHK-RSN exhibits superior forecasting ability relative to the baselines. It achieves the best Symmetric Mean Absolute Percentage Error (SMAPE) across all datasets in the 1–7 period average among baseline methods, demonstrating a relative improvement of 25.7% to 46.9% over the conventional Echo State Network.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Meta-cognitive recurrent kernel online sequential extreme learning machine with kernel adaptive filter for concept drift handling
    (2020-02-01)
    Liu, Zongying
    ;
    Loo, Chu Kiong
    ;
    Pasupa, Kitsuchart
    ;
    Seera, Manjeevan
    This paper proposes a multi-step prediction model for time series prediction, i.e. Meta-cognitive Recurrent Kernel Online Sequential Extreme Learning Machine with Drift Detector Mechanism (Meta-RKOS-ELM<inf>ALD</inf>). Recurrent multi-step algorithm is applied to release the limitation in the number of prediction steps, and Drift Detector Mechanism (DDM) is used to overcome the problem of concept drift in the prediction model. The new meta-cognitive strategy decides the way of the incoming data during training, which decreases the training computation of prediction model and solves the parameter dependency. In our evaluation, we use a total of six artificial data sets and three real-world data sets (Standard & Poor's 500 Index, Shanghai Stock Exchange Composite Index, and Ozone Concentration in Toronto) to prove the ability of kernel filters, the detecting ability of concept drift detector, and situation of applying meta-cognitive strategy in our proposed model. Experiments results indicate that the Meta-KOS-ELM<inf>ALD</inf> with DDM has better forecasting ability in various predicting periods with the shortest learning time, as compared with other algorithms.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    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.