Extreme learning machine and adaptive sparse representation for image classification

Optimal extreme learning machine for diagnosing brain tumor based on modified sailfish optimizer

This study proposes a hierarchical automated methodology for detecting brain tumors in Magnetic Resonance Imaging (MRI), focusing on preprocessing images to improve quality and eliminate artifacts or noise. A modified Extreme Learning Machine is then used to diagnose brain tumors that are integrated with the Modified Sailfish optimizer to enhance its performance. The Modified Sailfish optimizer is a metaheuristic algorithm known for efficiently navigating optimization landscapes and enhancing convergence speed. Experiments were conducted using the "Whole Brain Atlas (WBA)" database, which contains annotated MRI images. The results showed superior efficiency in accurately detecting brain tumors from MRI images, demonstrating the potential of the method in enhancing accuracy and efficiency. The proposed method utilizes hierarchical methodology, preprocessing techniques, and optimization of the Extreme Learning Machine with the Modified Sailfish optimizer to improve accuracy rates and decrease the time needed for brain tumor diagnosis. The proposed method outperformed other methods in terms of accuracy, recall, specificity, precision, and F1 score in medical imaging diagnosis. It achieved the highest accuracy at 93.95 %, with End/End and CNN attaining high values of 89.24 % and 93.17 %, respectively. The method also achieved a perfect score of 100 % in recall, 91.38 % in specificity, and 75.64 % in F1 score. However, it is crucial to consider factors like computational complexity, dataset characteristics, and generalizability before evaluating the effectiveness of the method in medical imaging diagnosis. This approach has the potential to make substantial contributions to medical imaging and aid healthcare professionals in making prompt and precise treatment decisions for brain tumors.

Application of hybrid fuzzy interval-based machine learning models on financial time series - A case study of Taiwan biotech index during the epidemic period

In recent years, the use of machine learning to predict stock market indices has emerged as a vital concern in the FinTech domain. However, the inherent nature of point estimation in traditional supervised machine learning models leads to an almost negligible probability of achieving perfect predictions, significantly constraining the applicability of machine learning prediction models. This study employs 4 machine learning models, namely BPN, LSTM, RF, and ELM, to establish predictive models for the Taiwan biotech index during the COVID-19 period. Additionally, it integrates the Gaussian membership function MF from fuzzy theory to develop 4 hybrid fuzzy interval-based machine learning models, evaluating their predictive accuracy through empirical analysis and comparing them with conventional point estimation models. The empirical data is sourced from the financial time series of the "M1722 Listed Biotechnology and Medical Care Index" compiled by the Taiwan Economic Journal during the outbreak of the COVID-19 pandemic, aiming to understand the effectiveness of machine learning models in the face of significant disruptive factors like the pandemic. The findings demonstrate that despite the influence of COVID-19, machine learning remains effective. LSTM performs the best among the models, both in traditional mode and after fuzzy interval enhancement, followed by the ELM and RF models. The predictive results of these three models reach a certain level of accuracy and all outperform the BPN model. Fuzzy-LSTM effectively predicts at a 68% confidence level, while Fuzzy-ELM and Fuzzy-RF yield better results at a 95% confidence level. Fuzzy-BPN exhibits the lowest predictive accuracy. Overall, the fuzzy interval-based LSTM excels in time series prediction, suggesting its potential application in forecasting time series data in financial markets to enhance the efficacy of investment analysis for investors.

An accelerated sine mapping whale optimizer for feature selection

An improved whale optimization algorithm (SWEWOA) is presented for global optimization issues. Firstly, the sine mapping initialization strategy (SS) is used to generate the population. Secondly, the escape energy (EE) is introduced to balance the exploration and exploitation of WOA. Finally, the wormhole search (WS) strengthens the capacity for exploitation. The hybrid design effectively reinforces the optimization capability of SWEWOA. To prove the effectiveness of the design, SWEWOA is performed in two test sets, CEC 2017 and 2022, respectively. The advantage of SWEWOA is demonstrated in 26 superior comparison algorithms. Then a new feature selection method called BSWEWOA-KELM is developed based on the binary SWEWOA and kernel extreme learning machine (KELM). To verify its performance, 8 high-performance algorithms are selected and experimentally studied in 16 public datasets of different difficulty. The test results demonstrate that SWEWOA performs excellently in selecting the most valuable features for classification problems.

An Accelerated Maximally Split ADMM for a Class of Generalized Ridge Regression

Ridge regression (RR) has been commonly used in machine learning, but is facing computational challenges in big data applications. To meet the challenges, this article develops a highly parallel new algorithm, i.e., an accelerated maximally split alternating direction method of multipliers (A-MS-ADMM), for a class of generalized RR (GRR) that allows different regularization factors for different regression coefficients. Linear convergence of the new algorithm along with its convergence ratio is established. Optimal parameters of the algorithm for the GRR with a particular set of regularization factors are derived, and a selection scheme of the algorithm parameters for the GRR with general regularization factors is also discussed. The new algorithm is then applied in the training of single-layer feedforward neural networks. Experimental results on performance validation on real-world benchmark datasets for regression and classification and comparisons with existing methods demonstrate the fast convergence, low computational complexity, and high parallelism of the new algorithm.

Plant-scale biogas production prediction based on multiple hybrid machine learning technique

The parameters from full-scale biogas plants are highly nonlinear and imbalanced, resulting in low prediction accuracy when using traditional machine learning algorithms. In this study, a hybrid extreme learning machine (ELM) model was proposed to improve prediction accuracy by solving imbalanced data. The results showed that the best ELM model had a good prediction for validation data (R² = 0.972), and the model was developed into the software (prediction error of 2.15 %). Furthermore, two parameters within a certain range (feed volume (FV) = 23-45 m³ and total volatile fatty acids of anaerobic digestion (TVFA_AD) = 1750-3000 mg/L) were identified as the most important characteristics that positively affected biogas production. This study combines machine learning with data-balancing techniques and optimization algorithms to achieve accurate predictions of plant biogas production at various loads.

A Semi-Supervised Progressive Learning Algorithm for Brain-Computer Interface

Brain-computer interface (BCI) usually suffers from the problem of low recognition accuracy and large calibration time, especially when identifying motor imagery tasks for subjects with indistinct features and classifying fine grained motion control tasks by electroencephalogram (EEG)-electromyogram (EMG) fusion analysis. To fill the research gap, this paper presents an end-to-end semi-supervised learning framework for EEG classification and EEG-EMG fusion analysis. Benefiting from the proposed metric learning based label estimation strategy, sampling criterion and progressive learning scheme, the proposed framework efficiently extracts distinctive feature embedding from the unlabeled EEG samples and achieves a 5.40% improvement on BCI Competition IV Dataset IIa with 80% unlabeled samples and an average 3.35% improvement on two public BCI datasets. By employing synchronous EMG features as pseudo labels for the unlabeled EEG samples, the proposed framework further extracts deep level features of the synergistic complementarity between the EEG signals and EMG features based on the deep encoders, which improves the performance of hybrid BCI (with a 5.53% improvement for the Upper Limb Motion Dataset and an average 4.34% improvement on two hybrid datasets). Moreover, the ablation experiments show that the proposed framework can substantially improve the performance of the deep encoders (with an average 5.53% improvement). The proposed framework not only largely improves the performance of deep networks in the BCI system, but also significantly reduces the calibration time for EEG-EMG fusion analysis, which shows great potential for building an efficient and high-performance hybrid BCI for the motor rehabilitation process.

Classification of Alzheimer’s Disease Based on Core-Large Scale Brain Network Using Multilayer Extreme Learning Machine

Various studies suggest that the network deficit in default network mode (DMN) is prevalent in Alzheimer’s disease (AD) and mild cognitive impairment (MCI). Besides DMN, some studies reveal that network alteration occurs in salience network motor networks and large scale network. In this study we performed classification of AD and MCI from healthy control considering the network alterations in large scale network and DMN. Thus, we constructed the brain network from functional magnetic resonance (fMR) images. Pearson’s correlation-based functional connectivity was used to construct the brain network. Graph features of the brain network were converted to feature vectors using Node2vec graph-embedding technique. Two classifiers, single layered extreme learning and multilayered extreme learning machine, were used for the classification together with feature selection approaches. We performed the classification test on the brain network of different sizes including the large scale brain network, the whole brain network and the combined brain network. Experimental results showed that the least absolute shrinkage and selection operator (LASSO) feature selection method generates better classification accuracy on large network size, and that feature selection with adaptive structure learning (FSAL) feature selection technique generates better classification accuracy on small network size.

V. Fusion Based AER System Using Deep Learning Approach for Amplitude and Frequency Analysis

Automatic emotion recognition from Speech (AERS) systems based on acoustical analysis reveal that some emotional classes persist with ambiguity. This study employed an alternative method aimed at providing deep understanding into the amplitude–frequency, impacts of various emotions in order to aid in the advancement of near term, more effectively in classifying AER approaches. The study was undertaken by converting narrow 20 ms frames of speech into RGB or grey-scale spectrogram images. The features have been used to fine-tune a feature selection system that had previously been trained to recognise emotions. Two different Linear and Mel spectral scales are used to demonstrate a spectrogram. An inductive approach for in sighting the amplitude and frequency features of various emotional classes. We propose a two-channel profound combination of deep fusion network model for the efficient categorization of images. Linear and Mel- spectrogram is acquired from Speech-signal, which is prepared in the recurrence area to input Deep Neural Network. The proposed model Alex-Net with five convolutional layers and two fully connected layers acquire most vital features form spectrogram images plotted on the amplitude-frequency scale. The state-of-the-art is compared with benchmark dataset (EMO-DB). RGB and saliency images are fed to pre-trained Alex-Net tested both EMO-DB and Telugu dataset with an accuracy of 72.18% and fused image features less computations reaching to an accuracy 75.12%. The proposed model show that Transfer learning predict efficiently than Fine-tune network. When tested on Emo-DB dataset, the propȯsed system adequately learns discriminant features from speech spectrȯgrams and outperforms many stȧte-of-the-art techniques.

Human emotion recognition from EEG-based brain–computer interface using machine learning: a comprehensive review

Affective computing, a subcategory of artificial intelligence, detects, processes, interprets, and mimics human emotions. Thanks to the continued advancement of portable non-invasive human sensor technologies, like brain–computer interfaces (BCI), emotion recognition has piqued the interest of academics from a variety of domains. Facial expressions, speech, behavior (gesture/posture), and physiological signals can all be used to identify human emotions. However, the first three may be ineffectual because people may hide their true emotions consciously or unconsciously (so-called social masking). Physiological signals can provide more accurate and objective emotion recognition. Electroencephalogram (EEG) signals respond in real time and are more sensitive to changes in affective states than peripheral neurophysiological signals. Thus, EEG signals can reveal important features of emotional states. Recently, several EEG-based BCI emotion recognition techniques have been developed. In addition, rapid advances in machine and deep learning have enabled machines or computers to understand, recognize, and analyze emotions. This study reviews emotion recognition methods that rely on multi-channel EEG signal-based BCIs and provides an overview of what has been accomplished in this area. It also provides an overview of the datasets and methods used to elicit emotional states. According to the usual emotional recognition pathway, we review various EEG feature extraction, feature selection/reduction, machine learning methods (e.g., k-nearest neighbor), support vector machine, decision tree, artificial neural network, random forest, and naive Bayes) and deep learning methods (e.g., convolutional and recurrent neural networks with long short term memory). In addition, EEG rhythms that are strongly linked to emotions as well as the relationship between distinct brain areas and emotions are discussed. We also discuss several human emotion recognition studies, published between 2015 and 2021, that use EEG data and compare different machine and deep learning algorithms. Finally, this review suggests several challenges and future research directions in the recognition and classification of human emotional states using EEG.

A Novel Reformed Reduced Kernel Extreme Learning Machine with RELIEF-F for Classification

With the exponential growth of the Internet population, scientists and researchers face the large-scale data for processing. However, the traditional algorithms, due to their complex computation, are not suitable for the large-scale data, although they play a vital role in dealing with large-scale data for classification and regression. One of these variants, which is called Reduced Kernel Extreme Learning Machine (Reduced-KELM), is widely used in the classification task and attracts attention from researchers due to its superior performance. However, it still has limitations, such as instability of prediction because of the random selection and the redundant training samples and features because of large-scaled input data. This study proposes a novel model called Reformed Reduced Kernel Extreme Learning Machine with RELIEF-F (R-RKELM) for human activity recognition. RELIEF-F is applied to discard the attributes of samples with the negative values in the weights. A new sample selection approach, which is used to further reduce training samples and to replace the random selection part of Reduced-KELM, solves the unstable classification problem in the conventional Reduced-KELM and computation complexity problem. According to experimental results and statistical analysis, our proposed model obtains the best classification performances for human activity data sets than those of the baseline model, with an accuracy of 92.87 % for HAPT, 92.81 % for HARUS, and 86.92 % for Smartphone, respectively.

Evolving kernel extreme learning machine for medical diagnosis via a disperse foraging sine cosine algorithm

Kernel extreme learning machine (KELM) has been widely used in the fields of classification and identification since it was proposed. As the parameters in the KELM model have a crucial impact on performance, they must be optimized before the model can be applied in practical areas. In this study, to improve optimization performance, a new parameter optimization strategy is proposed, based on a disperse foraging sine cosine algorithm (DFSCA), which is utilized to force some portions of search agents to explore other potential regions. Meanwhile, DFSCA is integrated into KELM to establish a new machine learning model named DFSCA-KELM. Firstly, using the CEC2017 benchmark suite, the exploration and exploitation capabilities of DFSCA were demonstrated. Secondly, evaluation of the model DFSCA-KELM on six medical datasets extracted from the UCI machine learning repository for medical diagnosis proved the effectiveness of the proposed model. At last, the model DFSCA-KELM was applied to solve two real medical cases, and the results indicate that DFSCA-KELM can also deal with practical medical problems effectively. Taken together, these results show that the proposed technique can be regarded as a promising tool for medical diagnosis.

Skin Cancer Detection Based on Extreme Learning Machine and a Developed Version of Thermal Exchange Optimization

Melanoma is defined as a disease that has been incurable in advanced stages, which shows the vital importance of timely diagnosis and treatment. To diagnose this type of cancer early, various methods and equipment have been used, almost all of which required a visit to the doctor and were not available to the public. In this study, an automated and accurate process to differentiate between benign skin pigmented lesions and malignant melanoma is presented, so that it can be used by the general public, and it does not require special equipment and special conditions in imaging. In this study, after preprocessing of the input images, the region of interest is segmented based on the Otsu method. Then, a new feature extraction is implemented on the segmented image to mine the beneficial characteristics. The process is then finalized by using an optimized Deep Believe Network (DBN) for categorization into 2 classes of normal and melanoma cases. The optimization process in DBN has been performed by a developed version of the newly introduced Thermal Exchange Optimization (dTEO) algorithm to obtain higher efficacy in different terms. To show the method's superiority, its performance is compared with 7 different techniques from the literature.

Extreme neural machines

Recurrent neural networks can solve a variety of computational tasks and produce patterns of activity that capture key properties of brain circuits. However, learning rules designed to train these models are time-consuming and prone to inaccuracies when tuning connection weights located deep within the network. Here, we describe a rapid one-shot learning rule to train recurrent networks composed of biologically-grounded neurons. First, inputs to the model are compressed onto a smaller number of recurrent neurons. Then, a non-iterative rule adjusts the output weights of these neurons based on a target signal. The model learned to reproduce natural images, sequential patterns, as well as a high-resolution movie scene. Together, results provide a novel avenue for one-shot learning in biologically realistic recurrent networks and open a path to solving complex tasks by merging brain-inspired models with rapid optimization rules.

Cholesky Factorization Based Online Sequential Multiple Kernel Extreme Learning Machine Algorithm for a Cement Clinker Free Lime Content Prediction Model

Aiming at the difficulty in real-time measuring and the long offline measurement cycle for the content of cement clinker free lime (fCaO), it is very important to build an online prediction model for fCaO content. In this work, on the basis of Cholesky factorization, the online sequential multiple kernel extreme learning machine algorithm (COS-MKELM) is proposed. The LDLT form Cholesky factorization of the matrix is introduced to avoid the large operation amount of inverse matrix calculation. In addition, the stored initial information is utilized to realize online model identification. Then, three regression datasets are used to test the performance of the COS-MKELM algorithm. Finally, an online prediction model for fCaO content is built based on COS-MKELM. Experimental results demonstrate that the fCaO content model improves the performance in terms of learning efficiency, regression accuracy, and generalization ability. In addition, the online prediction model can be corrected in real-time when the production conditions of cement clinker change.

Aircraft Engine Gas-Path Monitoring and Diagnostics Framework Based on a Hybrid Fault Recognition Approach

Considering the importance of continually improving the algorithms in aircraft engine diagnostic systems, the present paper proposes and benchmarks a gas-path monitoring and diagnostics framework through the Propulsion Diagnostic Methodology Evaluation Strategy (ProDiMES) software developed by NASA. The algorithm uses fleet-average and individual engine baseline models to compute feature vectors that form a fault classification with healthy and faulty engine classes. Using this classification, a hybrid fault-recognition technique based on regularized extreme learning machines and sparse representation classification was trained and validated to perform both fault detection and fault identification as a common process. The performance of the system was analyzed along with the results of other diagnostic frameworks through four stages of comparison based on different conditions, such as operating regimes, testing data, and metrics (detection, classification, and detection latency). The first three stages were devoted to the independent algorithm development and self-evaluation, while the final stage was related to a blind test case evaluated by NASA. The comparative analysis at all stages shows that the proposed algorithm outperforms all other diagnostic solutions published so far. Considering the advantages and the results obtained, the framework is a promising tool for aircraft engine monitoring and diagnostic systems.

Prediction of Epilepsy Based on Tensor Decomposition and Functional Brain Network

Epilepsy is a chronic neurological disorder which can affect 65 million patients worldwide. Recently, network based analyses have been of great help in the investigation of seizures. Now graph theory is commonly applied to analyze functional brain networks, but functional brain networks are dynamic. Methods based on graph theory find it difficult to reflect the dynamic changes of functional brain network. In this paper, an approach to extracting features from brain functional networks is presented. Dynamic functional brain networks can be obtained by stacking multiple functional brain networks on the time axis. Then, a tensor decomposition method is used to extract features, and an ELM classifier is introduced to complete epilepsy prediction. In the prediction of epilepsy, the accuracy and F1 score of the feature extracted by tensor decomposition are higher than the degree and clustering coefficient. The features extracted from the dynamic functional brain network by tensor decomposition show better and more comprehensive performance than degree and clustering coefficient in epilepsy prediction.

Maximum Correntropy Criterion-Based Hierarchical One-Class Classification

Due to the effectiveness of anomaly/outlier detection, one-class algorithms have been extensively studied in the past. The representatives include the shallow-structure methods and deep networks, such as the one-class support vector machine (OC-SVM), one-class extreme learning machine (OC-ELM), deep support vector data description (Deep SVDD), and multilayer OC-ELM (ML-OCELM/MK-OCELM). However, existing algorithms are generally built on the minimum mean-square-error (mse) criterion, which is robust to the Gaussian noises but less effective in dealing with large outliers. To alleviate this deficiency, a robust maximum correntropy criterion (MCC)-based OC-ELM (MC-OCELM) is first proposed and then further extended to a hierarchical network to enhance its capability in characterizing complex and large data (named HC-OCELM). The gradient derivation combining with a fixed-point iterative updation scheme is adopted for the output weight optimization. Experiments on many benchmark data sets are conducted for effectiveness validation. Comparisons to many state-of-the-art approaches are provided for the superiority demonstration.

Diagnosis of Alzheimer's Disease Using Brain Network

Recent studies suggest the brain functional connectivity impairment is the early event occurred in case of Alzheimer’s disease (AD) as well as mild cognitive impairment (MCI). We model the brain as a graph based network to study these impairment. In this paper, we present a new diagnosis approach using graph theory based features from functional magnetic resonance (fMR) images to discriminate AD, MCI, and healthy control (HC) subjects using different classification techniques. These techniques include linear support vector machine (LSVM), and regularized extreme learning machine (RELM). We used pairwise Pearson’s correlation-based functional connectivity to construct the brain network. We compare the classification performance of brain network using Alzheimer’s disease neuroimaging initiative (ADNI) datasets. Node2vec graph embedding approach is employed to convert graph features to feature vectors. Experimental results show that the SVM with LASSO feature selection method generates better classification accuracy compared to other classification technique.

A Maximally Split and Relaxed ADMM for Regularized Extreme Learning Machines

One of the salient features of the extreme learning machine (ELM) is its fast learning speed. However, in a big data environment, the ELM still suffers from an overly heavy computational load due to the high dimensionality and the large amount of data. Using the alternating direction method of multipliers (ADMM), a convex model fitting problem can be split into a set of concurrently executable subproblems, each with just a subset of model coefficients. By maximally splitting across the coefficients and incorporating a novel relaxation technique, a maximally split and relaxed ADMM (MS-RADMM), along with a scalarwise implementation, is developed for the regularized ELM (RELM). The convergence conditions and the convergence rate of the MS-RADMM are established, which exhibits linear convergence with a smaller convergence ratio than the unrelaxed maximally split ADMM. The optimal parameter values of the MS-RADMM are obtained and a fast parameter selection scheme is provided. Experiments on ten benchmark classification data sets are conducted, the results of which demonstrate the fast convergence and parallelism of the MS-RADMM. Complexity comparisons with the matrix-inversion-based method in terms of the numbers of multiplication and addition operations, the computation time and the number of memory cells are provided for performance evaluation of the MS-RADMM.

An Advanced Pruning Method in the Architecture of Extreme Learning Machines Using L1-Regularization and Bootstrapping

Extreme learning machines (ELMs) are efficient for classification, regression, and time series prediction, as well as being a clear solution to backpropagation structures to determine values in intermediate layers of the learning model. One of the problems that an ELM may face is due to a large number of neurons in the hidden layer, making the expert model a specific data set. With a large number of neurons in the hidden layer, overfitting is more likely and thus unnecessary information can deterioriate the performance of the neural network. To solve this problem, a pruning method is proposed, called Pruning ELM Using Bootstrapped Lasso BR-ELM, which is based on regularization and resampling techniques, to select the most representative neurons for the model response. This method is based on an ensembled variant of Lasso (achieved through bootstrap replications) and aims to shrink the output weight parameters of the neurons to 0 as many and as much as possible. According to a subset of candidate regressors having significant coefficient values (greater than 0), it is possible to select the best neurons in the hidden layer of the ELM. Finally, pattern classification tests and benchmark regression tests of complex real-world problems are performed by comparing the proposed approach to other pruning models for ELMs. It can be seen that statistically BR-ELM can outperform several related state-of-the-art methods in terms of classification accuracies and model errors (while performing equally to Pruning-ELM P-ELM), and this with a significantly reduced number of finally selected neurons.

Chaotic emperor penguin optimised extreme learning machine for microarray cancer classification

Microarray technology plays a significant role in cancer classification, where a large number of genes and samples are simultaneously analysed. For the efficient analysis of the microarray data, there is a great demand for the development of intelligent techniques. In this article, the authors propose a novel hybrid technique employing Fisher criterion, ReliefF, and extreme learning machine (ELM) based on the principle of chaotic emperor penguin optimisation algorithm (CEPO). EPO is a recently developed metaheuristic method. In the proposed method, initially, Fisher score and ReliefF are independently used as filters for relevant gene selection. Further, a novel population-based metaheuristic, namely, CEPO was proposed to pre-train the ELM by selecting the optimal input weights and hidden biases. The authors have successfully conducted experiments on seven well-known data sets. To evaluate the effectiveness, the proposed method is compared with original EPO, genetic algorithm, and particle swarm optimisation-based ELM along with other state-of-the-art techniques. The experimental results show that the proposed framework achieves better accuracy as compared to the state-of-the-art schemes. The efficacy of the proposed method is demonstrated in terms of accuracy, sensitivity, specificity, and F-measure.

Double-Criteria Active Learning for Multiclass Brain-Computer Interfaces

Recent technological advances have enabled researchers to collect large amounts of electroencephalography (EEG) signals in labeled and unlabeled datasets. It is expensive and time consuming to collect labeled EEG data for use in brain-computer interface (BCI) systems, however. In this paper, a novel active learning method is proposed to minimize the amount of labeled, subject-specific EEG data required for effective classifier training, by combining measures of uncertainty and representativeness within an extreme learning machine (ELM). Following this approach, an ELM classifier was first used to select a relatively large batch of unlabeled examples, whose uncertainty was measured through the best-versus-second-best (BvSB) strategy. The diversity of each sample was then measured between the limited labeled training data and previously selected unlabeled samples, and similarity is measured among the previously selected samples. Finally, a tradeoff parameter is introduced to control the balance between informative and representative samples, and these samples are then used to construct a powerful ELM classifier. Extensive experiments were conducted using benchmark and multiclass motor imagery EEG datasets to evaluate the efficacy of the proposed method. Experimental results show that the performance of the new algorithm exceeds or matches those of several state-of-the-art active learning algorithms. It is thereby shown that the proposed method improves classifier performance and reduces the need for training samples in BCI applications.

Simultaneously learning affinity matrix and data representations for machine fault diagnosis

Recently, preserving geometry information of data while learning representations have attracted increasing attention in intelligent machine fault diagnosis. Existing geometry preserving methods require to predefine the similarities between data points in the original data space. The predefined affinity matrix, which is also known as the similarity matrix, is then used to preserve geometry information during the process of representations learning. Hence, the data representations are learned under the assumption of a fixed and known prior knowledge, i.e., similarities between data points. However, the assumed prior knowledge is difficult to precisely determine the real relationships between data points, especially in high dimensional space. Also, using two separated steps to learn affinity matrix and data representations may not be optimal and universal for data classification. In this paper, based on the extreme learning machine autoencoder (ELM-AE), we propose to learn the data representations and the affinity matrix simultaneously. The affinity matrix is treated as a variable and unified in the objective function of ELM-AE. Instead of predefining and fixing the affinity matrix, the proposed method adjusts the similarities by taking into account its capability of capturing the geometry information in both original data space and non-linearly mapped representation space. Meanwhile, the geometry information of original data can be preserved in the embedded representations with the help of the affinity matrix. Experimental results on several benchmark datasets demonstrate the effectiveness of the proposed method, and the empirical study also shows it is an efficient tool on machine fault diagnosis.

Regularized correntropy criterion based semi-supervised ELM

Along with the explosive growing of data, semi-supervised learning attracts increasing attention in the past years due to its powerful capability in labeling unlabeled data and knowledge mining. As an emerging method, the semi-supervised extreme learning machine (SSELM), that builds on ELM, has been developed for data classification and shown superiorities in learning efficiency and accuracy. However, the optimization of SSELM as well as most of the other ELMs is generally based on the mean square error (MSE) criterion, which has been shown less effective in dealing with non-Gaussian noises. In this paper, a robust regularized correntropy criterion based SSELM (RC-SSELM) is developed. The optimization of the output weight matrix of RC-SSELM is derived by the fixed-point iteration based approach. A convergent analysis of the proposed RC-SSELM is presented based on the half-quadratic optimization technique. Experimental results on 4 synthetic datasets and 13 benchmark UCI datasets are provided to show the superiorities of the proposed RC-SSELM over SSELM and other state-of-the-art methods.

Decoding EEG in Motor Imagery Tasks with Graph Semi-Supervised Broad Learning

In recent years, the accurate and real-time classification of electroencephalogram (EEG) signals has drawn increasing attention in the application of brain-computer interface technology (BCI). Supervised methods used to classify EEG signals have gotten satisfactory results. However, unlabeled samples are more frequent than labeled samples, so how to simultaneously utilize limited labeled samples and many unlabeled samples becomes a research hotspot. In this paper, we propose a new graph-based semi-supervised broad learning system (GSS-BLS), which combines the graph label propagation method to obtain pseudo-labels and then trains the GSS-BLS classifier together with other labeled samples. Three BCI competition datasets are used to assess the GSS-BLS approach and five comparison algorithms: BLS, ELM, HELM, LapSVM and SMIR. The experimental results show that GSS-BLS achieves satisfying Cohen’s kappa values in three datasets. GSS-BLS achieves the better results of each subject in the 2-class and 4-class datasets and has significant improvements compared with original BLS except subject C6. Therefore, the proposed GSS-BLS is an effective semi-supervised algorithm for classifying EEG signals.

A distributed semi-supervised learning algorithm based on manifold regularization using wavelet neural network

This paper aims to propose a distributed semi-supervised learning (D-SSL) algorithm to solve D-SSL problems, where training samples are often extremely large-scale and located on distributed nodes over communication networks. Training data of each node consists of labeled and unlabeled samples whose output values or labels are unknown. These nodes communicate in a distributed way, where each node has only access to its own data and can only exchange local information with its neighboring nodes. In some scenarios, these distributed data cannot be processed centrally. As a result, D-SSL problems cannot be centrally solved by using traditional semi-supervised learning (SSL) algorithms. The state-of-the-art D-SSL algorithm, denoted as Distributed Laplacian Regularization Least Square (D-LapRLS), is a kernel based algorithm. It is essential for the D-LapRLS algorithm to estimate the global Euclidian Distance Matrix (EDM) with respect to total samples, which is time-consuming especially when the scale of training data is large. In order to solve D-SSL problems and overcome the common drawback of kernel based D-SSL algorithms, we propose a novel Manifold Regularization (MR) based D-SSL algorithm using Wavelet Neural Network (WNN) and Zero-Gradient-Sum (ZGS) distributed optimization strategy. Accordingly, each node is assigned an individual WNN with the same basis functions. In order to initialize the proposed D-SSL algorithm, we propose a centralized MR based SSL algorithm using WNN. We denote the proposed SSL and D-SSL algorithms as Laplacian WNN (LapWNN) and distributed LapWNN (D-LapWNN), respectively. The D-LapWNN algorithm works in a fully distributed fashion by using ZGS strategy, whose convergence is guaranteed by the Lyapunov method. During the learning process, each node only exchanges local coefficients with its neighbors rather than raw data. It means that the D-LapWNN algorithm is a privacy preserving method. At last, several illustrative simulations are presented to show the efficiency and advantage of the proposed algorithm.

Distributed semi-supervised learning algorithm based on extreme learning machine over networks using event-triggered communication scheme

In this paper, we propose a distributed semi-supervised learning (DSSL) algorithm based on the extreme learning machine (ELM) algorithm over communication network using the event-triggered (ET) communication scheme. In DSSL problems, training data consisting of labeled and unlabeled samples are distributed over a communication network. Traditional semi-supervised learning (SSL) algorithms cannot be used to solve DSSL problems. The proposed algorithm, denoted as ET-DSS-ELM, is based on the semi-supervised ELM (SS-ELM) algorithm, the zero gradient sum (ZGS) distributed optimization strategy and the ET communication scheme. Correspondingly, the SS-ELM algorithm is used to calculate the local initial value, the ZGS strategy is used to calculate the globally optimal value and the ET scheme is used to reduce communication times during the learning process. According to the ET scheme, each node over the communication network broadcasts its updated information only when the event occurs. Therefore, the proposed ET-DSS-ELM algorithm not only takes the advantages of traditional DSSL algorithms, but also saves network resources by reducing communication times. The convergence of the proposed ET-DSS-ELM algorithm is guaranteed by using the Lyapunov method. Finally, some simulations are given to show the efficiency of the proposed algorithm.

Low-rank analysis-synthesis dictionary learning with adaptively ordinal locality

Analysis dictionary learning (ADL) has been successfully applied to a variety of learning systems. However, the ordinal locality of analysis dictionary has rarely been explored in constructing discriminative terms. In this paper, a discriminative low-rank analysis-synthesis dictionary learning (LR-ASDL) algorithm with the adaptively ordinal locality is proposed for object classification. Specifically, we first explicitly introduce the relations between the analysis atoms and profiles (i.e., row vectors of the coefficients matrix). That is, the similarity between two profiles depends on that between the corresponding analysis atoms. Moreover, an adaptively ordinal locality preserving(AOLP) term is constructed by simultaneously exploiting the profiles and analysis atoms, which can be learned in a supervised way. In this way, the neighborhood correlations between analysis atoms and the high-order ranking information of each analysis atom's neighbors can be simultaneously preserved in the learning process. Particularly, this helps to uncover the intrinsic underlying data factors and inherit the geometry structure information of training samples. Furthermore, the low-rank model is imposed on the synthesis atoms to further facilitate the learned dictionaries to be more discriminative. Extensive experimental results on eight databases demonstrate that the LR-ASDL algorithm clearly outperforms some analysis and synthesis dictionary learning algorithms using deep and hand-crafted features.

Predicting seismic-induced liquefaction through ensemble learning frameworks

The regional nature of liquefaction records and limited information available for a certain set of explanatories motivate the development of complex prediction techniques. Indirect methods are commonly applied to incidentally derive a hyperplane to this binary classification problem. Machine learning approaches offer evolutionary prediction models which can be used as direct prediction methods to liquefaction occurrence. Ensemble learning is a recent advancement in this field. According to a predefined ensemble architecture, a number of learners are trained and their inferences are integrated to produce stable and improved generalization ability. However, there is a need to consider several aspects of the ensemble learning frameworks when exploiting them for a particular application; a comprehensive evaluation of an ensemble learner’s generalization ability is required but usually overlooked. Also, the literature falls short on work utilizing ensemble learning in liquefaction prediction. To this extent, this work examines useful ensemble learning approaches for seismic-induced liquefaction prediction. A comprehensive analysis of fifteen ensemble models is performed. The results show improved prediction performance and diminishing uncertainty of ensembles, compared with single machine learning models.

Extreme Learning Machine With Affine Transformation Inputs in an Activation Function

The extreme learning machine (ELM) has attracted much attention over the past decade due to its fast learning speed and convincing generalization performance. However, there still remains a practical issue to be approached when applying the ELM: the randomly generated hidden node parameters without tuning can lead to the hidden node outputs being nonuniformly distributed, thus giving rise to poor generalization performance. To address this deficiency, a novel activation function with an affine transformation (AT) on its input is introduced into the ELM, which leads to an improved ELM algorithm that is referred to as an AT-ELM in this paper. The scaling and translation parameters of the AT activation function are computed based on the maximum entropy principle in such a way that the hidden layer outputs approximately obey a uniform distribution. Application of the AT-ELM algorithm in nonlinear function regression shows its robustness to the range scaling of the network inputs. Experiments on nonlinear function regression, real-world data set classification, and benchmark image recognition demonstrate better performance for the AT-ELM compared with the original ELM, the regularized ELM, and the kernel ELM. Recognition results on benchmark image data sets also reveal that the AT-ELM outperforms several other state-of-the-art algorithms in general.