Adaptive Online Sequential Extreme Learning Research Articles

Adaptive Online Sequential Extreme Learning Machine with Kernels for Online Ship Power Prediction

With the in-depth penetration of renewable energy in the shipboard power system, the uncertainty of its output power and the variability of sea conditions have brought severe challenges to the control of shipboard integrated power system. In order to provide additional accurate signals to the power control system to eliminate the influence of uncertain factors, this study proposed an adaptive kernel based online sequential extreme learning machine to accurately predict shipboard electric power fluctuation online. Three adaptive factors are introduced, which control the kernel function scale adaptively to ensure the accuracy and speed of the algorithm. The electric power fluctuation data of real-ship under two different sea conditions are used to verify the effectiveness of the algorithm. The simulation results clearly demonstrate that in the case of ship power fluctuation prediction, the proposed method can not only meet the rapidity demand of real-time control system, but also provide accurate prediction results.

Adaptive online sequential extreme learning machine for dynamic modeling

Extreme learning machine (ELM) is an emerging machine learning algorithm for training single-hidden-layer feedforward networks (SLFNs). The salient features of ELM are that its hidden layer parameters can be generated randomly, and only the corresponding output weights are determined analytically through the least-square manner, so it is easier to be implemented with faster learning speed and better generalization performance. As the online version of ELM, online sequential ELM (OS-ELM) can deal with the sequentially coming data one by one or chunk by chunk with fixed or varying chunk size. However, OS-ELM cannot function well in dealing with dynamic modeling problems due to the data saturation problem. In order to tackle this issue, in this paper, we propose a novel OS-ELM, named adaptive OS-ELM (AOS-ELM), for enhancing the generalization performance and dynamic tracking capability of OS-ELM for modeling problems in nonstationary environments. The proposed AOS-ELM can efficiently reduce the negative effects of the data saturation problem, in which approximate linear dependence (ALD) and a modified hybrid forgetting mechanism (HFM) are adopted to filter the useless new data and alleviate the impacts of the outdated data, respectively. The performance of AOS-ELM is verified using selected benchmark datasets and a real-world application, i.e., device-free localization (DFL), by comparing it with classic ELM, OS-ELM, FOS-ELM, and DU-OS-ELM. Experimental results demonstrate that AOS-ELM can achieve better performance.

MFA-OSELM Algorithm for WiFi-Based Indoor Positioning System

Indoor localization is a dynamic and exciting research area. WiFi has exhibited a tremendous capability for internal localization since it is extensively used and easily accessible. Facilitating the use of WiFi for this purpose requires fingerprint formation and the implementation of a learning algorithm with the aim of using the fingerprint to determine locations. The most difficult aspect of techniques based on fingerprints is the effect of dynamic environmental changes on fingerprint authentication. With the aim of dealing with this problem, many experts have adopted transfer-learning methods, even though in WiFi indoor localization the dynamic quality of the change in the fingerprint has some cyclic factors that necessitate the use of previous knowledge in various situations. Thus, this paper presents the maximum feature adaptive online sequential extreme learning machine (MFA-OSELM) technique, which uses previous knowledge to handle the cyclic dynamic factors that are brought about by the issue of mobility, which is present in internal environments. This research extends the earlier study of the feature adaptive online sequential extreme learning machine (FA-OSELM). The results of this research demonstrate that MFA-OSELM is superior to FA-OSELM given its capacity to preserve previous data when a person goes back to locations that he/she had visited earlier. Also, there is always a positive accuracy change when using MFA-OSELM, with the best change achieved being 27% (ranging from eight to 27% and six to 18% for the TampereU and UJIIndoorLoc datasets, respectively), which proves the efficiency of MFA-OSELM in restoring previous knowledge.

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

Data streams online modeling and prediction is an important research direction in the field of data mining. In practical applications, data streams are often of nonstationary nature and containing outliers, hence an online learning algorithm with dynamic tracking capability as well as anti-outlier capability is urgently needed. With this in mind, this paper proposes a novel robust adaptive online sequential extreme learning machine (RA-OSELM) algorithm for the online modeling and prediction of nonstationary data streams with outliers. The RA-OSELM is developed from the famous online sequential extreme learning machine algorithm, but it uses a more robust M-estimation loss function to replace the conventional least square loss function so as to suppress the incorrect online update of the learning algorithm with respect to outliers, and hence enhances its robustness in the presence of outliers. Moreover, the RA-OSELM adopts a variable forgetting factor method to automatically track the dynamic changes of the nonstationary data streams and timely eliminate the negative impacts of the outdated data, so it tends to produce satisfying tracking results in nonstationary environments. The performances of RA-OSELM are evaluated and compared with other representative algorithms with synthetic and real data sets, and the experimental results indicate that the proposed algorithm has better adaptive tracking capability with stronger robustness than its counterparts for predicting nonstationary data streams with outliers.

Adaptive online sequential extreme learning machine for frequency-dependent noise data on offshore oil rig

An adaptive online sequential extreme learning machine (AOS-ELM) is proposed to predict the frequency-dependent sound pressure level (SPL) data of various compartments onboard of the offshore platform. With limited samples and sequential data for training during the initial design stage, conventional neural network training gives significant errors and long computing time when it maps the available inputs to sound pressure level for the entire offshore platform. By using AOS-ELM, it allows a gradual increase in the dataset that is hard to obtain during the initial design stage of the offshore platform. The SPL prediction using AOS-ELM has improved with smaller root mean squared error in testing and shorter training time as compared with other types of ELM based learnings and other gradient based methods in neural network training.

State-of-Charge Estimation of Battery Pack under Varying Ambient Temperature Using an Adaptive Sequential Extreme Learning Machine

An adaptive online sequential extreme learning machine (AOS-ELM) is proposed to predict the state-of-charge of the battery cells at different ambient temperatures. With limited samples and sequential data for training during the initial design stage, conventional neural network training gives higher errors and longer computing times when it maps the available inputs to SOC. The use of AOS-ELM allows a gradual increase in the dataset that can be time-consuming to obtain during the initial stage of the neural network training. The SOC prediction using AOS-ELM gives a smaller root mean squared error in testing (and small standard deviation in the trained results) and reasonable training time as compared to other types of ELM-based learnings and gradient-based machine learning. In addition, the subsequent identification of the cells’ static capacity and battery parameters from actual experiments is not required to estimate the SOC of each cell and the battery stack.

Guest editorial: Special issue on Extreme learning machine and applications (II)

It is our great pleasure to present this special issue on Extreme learning machine (ELM) and applications (II) to all NCA readers and neural computing society. Our initial schedule was to publish the special issue on ELM and applications with about 15 articles and to report the recent development of ELM theory and applications as well as the challenges in designing, analysing and implementing the algorithms and systems. However, after rigorously reviewing all of received papers on the basis of innovativeness and relevance for all NCA readers, we realized that many of them were high quality and finally selected 30 top papers. After getting the permission from Editor-inChief, Professor John MacIntyre, we are very happy to present these selected top papers in two special issues. The following is the brief introduction of 15 articles in the special issue: Extreme Learning Machine and Applications (II). In ‘‘Fault detection and diagnosis method for batch process based on ELM-based fault feature phase identification’’, the authors propose a fault detection and diagnosis algorithm for batch processes with ELM methodology. In this work, ELM is first utilized to identify the feature phases for each fault, and the whole batch is divided into a few ‘‘short stages’’. The multiway Fisher discriminant analysis (MFDA) models are then built for these divided ‘‘short stages’’ to perform fault detection and diagnosis for a batch process. The simulation results have shown the excellent performance of the algorithm for the fault detection in a hydrostatic testing process. In ‘‘Multiplekernel-learning-based extreme learning machine for classification design’’, the authors develop two multiple kernel classifiers. The first one is based on a convex combination of the given base kernels, while the second one uses a convex combination of the so-called equivalent kernels. Experimental results have shown that, for a large number of data sets, the proposed classifiers are fast, accurate and easily trained. In ‘‘Variational Bayesian extreme learning machine’’, the authors present a Bayesian probabilistic model based on ELM to avoid the ill-posed problem in input–hidden node matrix. Both the regression experiments and classification experiments have clearly shown the excellent performance compared with a few existing ELMbased schemes. In ‘‘A recurrent neural network for modelling crack growth of aluminium alloy’’, the authors develop a new recurrent neural model for crack growth process of aluminium alloy. It has been shown that a recurrent neural network with the feedback loops at the output layer is constructed to model the dynamic relationship between the crack growth and cyclic stress excitations of aluminium alloy. The extreme learning machine is then used to uniformly randomly assign the input weights in a proper range and globally optimize both the output weights and feedback parameters, to ensure that the dynamics of crack growth under variable amplitude loading can be accurately modelled. The simulations with experimental data have shown excellent results. In ‘‘Extend semi-supervised ELM and a frame work’’, the authors analyse the semi-supervised ELM (SELM) indepth and propose an extended SELM algorithm that can efficiently solve the classification problems with a small number of labelled samples. The simulation results have shown excellent classification performance compared with both ELM and SELM algorithms. In ‘‘Feature adaptive online sequential extreme learning machine for lifelong & Zhihong Man zman@swin.edu.au

Feature Adaptive Online Sequential Extreme Learning Machine for lifelong indoor localization

Wi-Fi-based indoor localization with high capability and feasibility needs to implement lifelong online learning mechanism. However, the characteristic of Wi-Fi is wide variability, which lies in not only the fluctuation of signal strength value, but also the increase or decrease in the number of access points (APs). The traditional algorithms are effective for signal fluctuation, but cannot handle the dimension-changing problem of features caused by increase and decrease in APs' number. To solve this problem, we propose a Feature Adaptive Online Sequential Extreme Learning Machine (FA-OSELM) algorithm. It can transfer the original model to a new one with a small number of data with new features, so as to make the new model suitable for the new feature dimension. The experiments show that the FA-OSELM can get higher accuracy with a small amount of new data, and it is an effective method to make lifelong indoor localization practical.