Robust adaptive online sequential extreme learning machine for predicting nonstationary data streams with outliers

Wei, Guo

doi:10.1177/1748302619895421

Cited by 5 publications

(7 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We propose a novel online learning algorithm, called SRA, to consider the tradeoff between the robustness and adaptivity. Previous studies (Chu et al, 2004;Huang et al, 2016;Cejnek and Bukovsky, 2018;Yamanishi et al, 2004;Odakura, 2018;Fearnhead and Rigaill, 2019;Guo, 2019) considered only one of them, and even if some considered both, the relation between them was not made clear. This study considers both and gives a theoretical analysis for the non-asymptotic convergence of SRA.…”

Section: Novel Online Learning Algorithm For Tradeoff Between Robustn...mentioning

confidence: 99%

“…The key idea of the algorithm is to adapt existing penalized cost approaches for detecting changes such that they use loss functions that are less sensitive to outliers. Guo proposed an algorithm based on an online sequential extreme learning machine for robust and adaptive learning (Guo, 2019).…”

Section: Robustness and Adaptivity Of Online Learning Algorithmsmentioning

confidence: 99%

“…Conversely, the adaptivity decreases if we try to learn robustly. Although many online learning algorithms have been introduced and some studies have addressed this issue (Tsay, 1988;Gama et al, 2014;Chu et al, 2004;Huang et al, 2016;Odakura, 2018;Cejnek and Bukovsky, 2018;Fearnhead and Rigaill, 2019;Guo, 2019), to the best of our knowledge, no algorithm has quantitatively considered the tradeoff between the robustness and adaptivity.…”

Section: Purpose Of This Papermentioning

confidence: 99%

See 2 more Smart Citations

Online Robust and Adaptive Learning from Data Streams

Fukushima,

Nitanda,

Yamanishi

2020

Preprint

View full text Add to dashboard Cite

In online learning from non-stationary data streams, it is both necessary to learn robustly to outliers and to adapt to changes of underlying data generating mechanism quickly. In this paper, we refer to the former nature of online learning algorithms as robustness and the latter as adaptivity. There is an obvious tradeoff between them. It is a fundamental issue to quantify and evaluate the tradeoff because it provides important information on the data generating mechanism. However, no previous work has considered the tradeoff quantitatively. We propose a novel algorithm called the Stochastic approximation-based Robustness-Adaptivity algorithm (SRA) to evaluate the tradeoff. The key idea of SRA is to update parameters of distribution or sufficient statistics with the biased stochastic approximation scheme, while dropping data points with large values of the stochastic update. We address the relation between two parameters, one of which is the step size of the stochastic approximation, and the other is the threshold parameter of the norm of the stochastic update. The former controls the adaptivity and the latter does the robustness. We give a theoretical analysis for the non-asymptotic convergence of SRA in the presence of outliers, which depends on both the step size and the threshold parameter. Since SRA is formulated on the majorization-minimization principle, it is a general algorithm including many algorithms, such as the online EM algorithm and stochastic gradient descent. Empirical experiments for both synthetic and real datasets demonstrated that SRA was superior to previous methods.

show abstract

Section: Novel Online Learning Algorithm For Tradeoff Between Robustn...mentioning

confidence: 99%

Section: Robustness and Adaptivity Of Online Learning Algorithmsmentioning

confidence: 99%

Section: Purpose Of This Papermentioning

confidence: 99%

See 1 more Smart Citation

Online Robust and Adaptive Learning from Data Streams

Fukushima,

Nitanda,

Yamanishi

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…It can relatively accurately segment the time series of air combat situation characteristic parameters and can obtain trajectory fragments reflecting different air combat situations, providing a reliable data basis for the optimization of evaluation weights. To verify the effectiveness and advancement of the algorithm proposed in this paper, OSELM [26], OSKELM [27], online regularized time series prediction algorithms (i.e., OSRELM [28], OSRKELM [29], RR-OSELM [30]), and online regularized time series forecasting algorithms with forgetting factor (i.e., FP-OSELM [31], DFF-OSELM [32], FFOS-RKELM [33], FGR-OSELM [34]) were utilized for contrast. The parameter settings of all algorithms are shown in Table 7 and the number of neurons in the hidden layer of all ELMs was set to 20.…”

Section: Performance Verification Of Multivariate Time Series Segment...mentioning

confidence: 99%

A Dynamic Air Combat Situation Assessment Model Based on Situation Knowledge Extraction and Weight Optimization

Xi,

Kou,

et al. 2023

Aerospace

View full text Add to dashboard Cite

Air combat situation assessment is the basis of target assignment and maneuver decisions. The current air combat situation assessment models, whether nonparametric or parametric, ignore the continuity and timing of situation changes, making the situation assessment results lose tactical significance. Aimed at the shortcomings of current air combat situation assessment, a dynamic air combat situation assessment model based on situation knowledge extraction and weight optimization was proposed by combining a multiple regression model of hidden logic process, a weight optimization model based on grey prospect theory, a weight mapping model based on autoencoder and extreme learning machine (AE-ELM) and an air combat situation characteristic parameter prediction model based on dynamic weight online extreme learning machine (DWOSELM). Firstly, considering the timing and continuity of air combat situation change, a hidden logic process multiple regression model was introduced to realize the segmentation of air combat situation time series data and the extraction of air combat situation primitives. Secondly, the weight optimization method based on grey prospect theory was used to obtain the weight of the evaluation index under different air combat situations. On this basis, the dynamic mapping model between air combat situation characteristic parameters and the weight of index was constructed by using AE-ELM. Then, the dynamic weighted extreme learning machine was used to build the target maneuver trajectory prediction model, and the future position information of the target was predicted. On this basis, the future situation information between the enemy and us was obtained. Finally, the time weight calculation model based on normal cumulative distribution was used to determine the importance of the situation at each time. The situation information at multiple times in the air combat process was fused to obtain the comprehensive air combat situation assessment results at the current time. The simulation results show that the model can fully exploit the influence of historical information, effectively integrate the air combat situation information at multiple moments, and generate the air combat situation assessment results with practical tactical significance according to the individual differences of different pilots.

show abstract

“…Wang et al introduced a non-convex loss function, developed a robust regularized ELM, and emphasized on solving the key problem of low efficiency [ 38 ]. Guo et al presented a robust adaptive online sequential ELM-based algorithm for online modeling and prediction of non-stationary data streams with outliers [ 39 ].…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Method Based on Extreme Learning Machine and Wavelet Transform Denoising for Stock Prediction

Wang

2021

Entropy

View full text Add to dashboard Cite

The trend prediction of the stock is a main challenge. Accidental factors often lead to short-term sharp fluctuations in stock markets, deviating from the original normal trend. The short-term fluctuation of stock price has high noise, which is not conducive to the prediction of stock trends. Therefore, we used discrete wavelet transform (DWT)-based denoising to denoise stock data. Denoising the stock data assisted us to eliminate the influences of short-term random events on the continuous trend of the stock. The denoised data showed more stable trend characteristics and smoothness. Extreme learning machine (ELM) is one of the effective training algorithms for fully connected single-hidden-layer feedforward neural networks (SLFNs), which possesses the advantages of fast convergence, unique results, and it does not converge to a local minimum. Therefore, this paper proposed a combination of ELM- and DWT-based denoising to predict the trend of stocks. The proposed method was used to predict the trend of 400 stocks in China. The prediction results of the proposed method are a good proof of the efficacy of DWT-based denoising for stock trends, and showed an excellent performance compared to 12 machine learning algorithms (e.g., recurrent neural network (RNN) and long short-term memory (LSTM)).

show abstract

Robust adaptive online sequential extreme learning machine for predicting nonstationary data streams with outliers

Cited by 5 publications

References 35 publications

Online Robust and Adaptive Learning from Data Streams

Online Robust and Adaptive Learning from Data Streams

A Dynamic Air Combat Situation Assessment Model Based on Situation Knowledge Extraction and Weight Optimization

A Hybrid Method Based on Extreme Learning Machine and Wavelet Transform Denoising for Stock Prediction

Contact Info

Product

Resources

About