Fast Learning Speed Research Articles

Enhancing robustness and time efficiency of random vector functional link with optimized affine parameters in activation functions and orthogonalization

Random Vector Functional Link (RVFL) is a widely used learning technique due to its less computational complexity, fast learning speed, and ease of implementation. However, generalization ability of RVFL is not good because its randomly generated parameters in the hidden layer makes input data distribution vulnerable to saturated regime of an activation function. For making data distribution evenly distributed within the hidden layer, this paper proposes a robust and efficient affine-transformation-based RVFL approach, termed as RT-ATRVFL, with optimized parameters. The proposed RT-ATRVFL, introduces sparse and shallow network in RVFL, that uses a subset of hidden layer structure, and obtains optimized and robust affine parameters for an activation function. This way it not only avoids saturated regime, but also learns the non-linearity more effectively and efficiently. This paper also investigates the different variants of the proposed approaches viz., RT-ATRVFL-ORTHO, RT-ATRVFL-CLOG, and RT-ATRVFL-CLOG-ORTHO using orthogonalization and cloglogm activation functions. For a thorough investigation of the proposed approaches, we conduct extensive experiments considering 28 benchmark classification datasets for a set of [60,2000] Monte Carlo runs. We show that our proposed approaches are more generalized and reliable, and outperform the affine-transformation-based extreme learning machine (ATELM) and its variants in terms of accuracy and computational time. Also, analysis of the results through well-accepted metrics such as Levene’s test, inter quartile range, mean absolute deviation and standard deviation confirms that proposed RT-ATRVFL and its other introduced variants are more robust than their respective counterparts. Results of two well-known statistical significance tests: Wilcoxon test and Friedman ranking, and the time complexity analysis also establishes the superiority of the proposed RT-ATRVFL approach and its other variants over their respective counterparts.

Neuromorphic learning and recognition in WO3−x thin film-based forming-free flexible electronic synapses

In pursuing advanced neuromorphic applications, this study introduces the successful engineering of a flexible electronic synapse based on WO3-x, structured as W/WO3-x/Pt/Muscovite-Mica. This artificial synapse is designed to emulate crucial learning behaviors fundamental to in-memory computing. We systematically explore synaptic plasticity dynamics by implementing pulse measurements capturing potentiation and depression traits akin to biological synapses under flat and different bending conditions, thereby highlighting its potential suitability for flexible electronic applications. The findings demonstrate that the memristor accurately replicates essential properties of biological synapses, including short-term plasticity (STP), long-term plasticity (LTP), and the intriguing transition from STP to LTP. Furthermore, other variables are investigated, such as paired-pulse facilitation, spike rate-dependent plasticity, spike time-dependent plasticity, pulse duration-dependent plasticity, and pulse amplitude-dependent plasticity. Utilizing data from flat and differently bent synapses, neural network simulations for pattern recognition tasks using the Modified National Institute of Standards and Technology dataset reveal a high recognition accuracy of ∼95% with a fast learning speed that requires only 15 epochs to reach saturation.

SSA-ELM: A Hybrid Learning Model for Short-Term Traffic Flow Forecasting

Nowadays, accurate and efficient short-term traffic flow forecasting plays a critical role in intelligent transportation systems (ITS). However, due to the fact that traffic flow is susceptible to factors such as weather and road conditions, traffic flow data tend to exhibit dynamic uncertainty and nonlinearity, making the construction of a robust and reliable forecasting model still a challenging task. Aiming at this nonlinear and complex traffic flow forecasting problem, this paper constructs a short-term traffic flow forecasting hybrid optimization model, SSA-ELM, based on extreme learning machine by embedding the sparrow search algorithm in order to solve the above problem. Extreme learning machine has been widely used in short-term traffic flow forecasting due to its characteristics such as low computational complexity and fast learning speed. By using the sparrow search algorithm to optimize the input weight values and hidden layer deviations in the extreme learning machine, the sparrow search algorithm is utilized to search for the global optimal solution while taking into account the original characteristics of the extreme learning machine, so that the model improves stability while increasing prediction accuracy. Experimental results on the Amsterdam A10 road traffic flow dataset show that the traffic flow forecasting model proposed in this paper has higher forecasting accuracy and stability, revealing the potential of hybrid optimization models in the field of short-term traffic flow forecasting.

RDCSAE-RKRVFLN: A unified deep learning framework for robust and accurate DOA estimation

This paper introduces an innovative unified deep learning (DL) model, “reduced deep convolutional stack autoencoder (RDCSAE)-robust kernel-based random vector functional link network (RKRVFLN)” (RDCSAE-RKRVFLN), for addressing practical challenges like phase and gain uncertainty, mutual coupling effects, and element position errors in direction of arrival (DOA) estimation. The RDCSAE utilizes deep convolutional neural network (DCNN) and stack autoencoder (SAE) for robust feature extraction. The RKRVFLN integrates a concise SAE output with kernel-based learning. Thus, the integration of RDCSAE (suitable for unsupervised feature extraction) and RKRVFLN (for supervised learning) in the developed model results in efficient use of limited training data. Performance metrics of this method include among others the accuracy (separation between sources), root mean square error (RMSE), signal-to-noise ratio (SNR), etc. The method performs better than existing data driven methods in terms of computational efficiency, faster learning speed, enhanced model generalization, higher accuracy, and shorter event regression time and empirical methods. In the presence of above mentioned four perturbations, this method successfully resolves multiple sources with a resolution of 0.3° with a RMSE of 0.00376. For real time application, the paper implements RDCSAE-RKRVFLN on a high-speed reconfigurable Xilinx Virtex-5 field-programmable gate array (FPGA) realizing a digital DOA estimator for one source. The hardware estimates the DOA with a maximum error of 0.01953125 which follows closely the simulation results indicating the efficiency and feasibility of the method.

GAITBOOST: Boosting gait recognition performance with BAT-extreme learning machines algorithm

Gait analysis is a widely used technique for passive human identification and tracking, with potential applications in security and surveillance systems. However, existing gait recognition methods face challenges in handling changing angles and uncertain features. In this paper, we propose a novel gait recognition approach that leverages real-time spatio-temporal gait features, including step length, gait cycle, height, cadence, swing ratio, and foot length. We apply the Extreme Learning Machines (ELM) algorithm for classification, which has been shown to be effective in various applications due to its fast-learning speed and good generalization performance. To further enhance the recognition rate, we introduce an evolutionary BAT-optimized ELM algorithm that addresses the instability issue in ELM. The proposed BAT-ELM algorithm can optimize the hidden nodes and weights of ELM, which leads to improved efficiency in recognizing gait from multiple view angles ranging from 0° to 180°. Our comprehensive analysis of the proposed approach indicates that it outperforms other reported algorithms in terms of recognition rate and efficiency. Our work demonstrates the effectiveness of combining real-time spatio-temporal gait features with the BAT-ELM algorithm for gait recognition. The proposed approach has potential applications in various fields, including security and surveillance systems, healthcare, and robotics. Our findings highlight the importance of leveraging evolutionary algorithms to optimize machine learning models and achieve better performance in complex recognition tasks.

FORECASTING THE NUMBER OF AIRPLANE PASSENGERS USING HOLT WINTER'S EXPONENTIAL SMOOTHING METHOD AND EXTREME LEARNING MACHINE METHOD

Airplanes provide comfort and speed for their users, especially for those who have limited time. The number of passengers has continued to increase in the last few months at Ahmad Yani International Airport, so a forecast is needed in making decisions to predict the number of passengers in order to maximize existing performance. The data used is secondary data on the number of airplane passengers at Ahmad Yani International Airport from 2012 to 2022 obtained from PT Angkasa Pura 1 (Persero). The Holt Winters Exponential Smoothing method is used because it aligns with the data pattern that includes trends and seasonality in the research, and it has a low level of accuracy. In this study also used the Extreme Learning Machine (ELM) method, apart from being a relatively new method, it has a fast learning speed and has low accuracy. This study aims to predict the number of airplane passengers at Ahmad Yani International Airport in Semarang using the Holt Winters Exponential Smoothing and ELM methods. The results of the analysis show that the MAPE value in the Holt Winters Exponential Smoothing method is 8,18% and in the ELM method using 12 input neurons and 43 neurons in the hidden layer, a MAPE of 6,04% is obtained. so that the ELM method is the right method for predicting the number of airplane passengers at Ahmad Yani International Airport in Semarang.

Improving extreme learning machine model using deep learning feature extraction and grey wolf optimizer: Application to image classification

The Extreme Learning Machine (ELM) is a highly efficient model for real-time network retraining due to its fast learning speed, unlike traditional machine learning methods. However, the performance of ELM can be negatively impacted by the random initialization of weights and biases. Moreover, poor input feature quality can further degrade performance, particularly with complex visual data. To overcome these issues, this paper proposes optimizing the input features as well as the initial weights and biases. We combine both Convolutional Neural Network (CNN) and Convolutional AutoEncoder (CAE) extracted features to optimize the quality of the input features. And we use our hybrid Grey Wolf Optimizer-Multi-Verse Optimizer (GWO-MVO) metaheuristic for initializing weights and biases by applying four fitness functions based on: the norm of the output weights, the error rate on the training set, and the error rate on the validation set. Our method is evaluated on image classification tasks using two benchmark datasets: CIFAR-10 and CIFAR-100. Since image quality may vary in real-world applications, we trained and tested our models on the dataset’s original and noisy versions. The results demonstrate that our method provides a robust and efficient alternative for image classification tasks, offering improved accuracy and reduced overfitting.

Extreme Learning Machine Classification Method based on Twin Strategy Salp Swarm Algorithm

Extreme Learning Machines (ELM) are a type of Single Hidden Layer Feedforward Neural Network (SLFN). In recent years, they have attracted attention for their powerful approximation ability and fast learning speed. Compared with traditional neural network algorithms, ELM have the advantages of simple structure, fast learning speed, and good generalization performance. However, since the input weights and biases of ELM are randomly generated, there may be some suboptimal or unnecessary input weights and biases. In addition, ELM may require more hidden nodes, which may slow down its response to unknown test data. To address these issues, a twin strategy Salp Swarm Algorithm (TSSA) is proposed to increase the population diversity to improve the convergence speed of the algorithm through chaotic initialization, while shock inertia weights and learning paradigms are introduced into the follower position updating to enhance the stochasticity of the particles. Classification tests are conducted on six datasets using the proposed TSSA, and the experimental results show that the proposed TSSA-ELM has higher accuracy and better generalization performance than some existing ELM variants.

Robust and efficient algorithms for conversational contextual bandit

Conversational contextual bandit is one of the notable variants of contextual bandit and it is shown to have superior performance in recommendation applications. The core idea of conversational contextual bandits utilizing is conversational feedback from users to improve the speed of learning user preference. We show that in real-world applications conversational feedback can be imbalanced and such feedback causes the latest conversational contextual bandit algorithm to conduct many conversations but has a slower learning speed than the baseline algorithm without conversational feedback. How to deal with imbalanced conversational feedback? How to schedule conversations across the learning horizon? In-depth analysis of the limitations of one representative conversational contextual bandit algorithm reveals insights to design ICF-UCB ((Imbalanced Conversational Feedback Upper Confidence Bound)) algorithm, which maintains a fast learning speed under imbalanced feedbacks. ICF-UCB achieves this by adaptively eliminating conversations that may slow down the learning speed. Furthermore, ICF-UCB adaptively schedules conversations to the decision rounds where suboptimal actions may trap the decision maker. It also adaptively selects appropriate conversations to avoid such traps. This algorithm is shown to have sublinear regret. Extensive experiments on synthetic datasets and public real-world datasets (from Yelp and TripAdvisor) validate the superior performance of ICF-UCB for recommendation tasks.

Short-Term Electrical Load Forecasting of 150 kV Ternate System Using Optimally Pruned Extreme Learning Machine (OPELM)

Short-term electrical loads forecasting is one of the most important factors in the design and operation of electrical systems. The purpose of electric load forecasting is to balance electricity demand and electricity supply. The load characteristics of Ternate City vary, so this study uses the Optimally Pruned Extreme Learning Machine (OPELM) method to predict electrical loads. The advantages of OPELM are the fast-learning speed and the selection of the right model, even though the data has a non-linear pattern. The accuracy of the OPELM method can be determined using a comparison method, namely the ELM method. Mean Absolute Percentage Error (MAPE) is used as the accuracy criterion. The results of the comparison of accuracy criteria show that the predictive performance of OPELM is better than that of ELM. The minimum error average of the OPELM forecast test results shows a MAPE of 5,2557%, for Saturday's forecast, while the ELM method gives a MAPE of 6.4278% on the same day.

Surface Roughness Prediction in Ultra-Precision Milling: An Extreme Learning Machine Method with Data Fusion.

This paper pioneers the use of the extreme learning machine (ELM) approach for surface roughness prediction in ultra-precision milling, leveraging the excellent fitting ability with small datasets and the fast learning speed of the extreme learning machine method. By providing abundant machining information, the machining parameters and force signal data are fused on the feature level to further improve ELM prediction accuracy. An ultra-precision milling experiment was designed and conducted to verify our proposed data-fusion-based ELM method. The results show that the ELM with data fusion outperforms other state-of-art methods in surface roughness prediction. It achieves an impressively low mean absolute percentage error of 1.6% while requiring a mere 18 s for model training.

Matrix randomized autoencoder

Randomized autoencoder (RAE) has attracted much attention due to its strong capability of representation with fast learning speed. However, the mainstream RAEs are still designed for scalar/vector data, which inevitably destroys the structure information of tensor data. To alleviate this deficiency, a novel convolutions based matrix randomized autoencoder (MRAE) is developed for two-dimensional (2D) data in this paper, including a one-side MRAE (OMRAE) exploiting the row or column information and a double-side MRAE (DMRAE) that simultaneously extracts the row and column information by 2 parallel OMRAEs. To reduce meaningless encoded features, the within-class scatter matrix (WSI) and within-class interaction distance (WID) constraints are added into OMRAE resulting WSI-OMRAE and WID-OMRAE, respectively. To demonstrate the superiority, stacked MRAEs are embedded into hierarchical regularized least squares for one-class classification and comparisons with several state-of-the-art methods are provided. The source code would be available at https://github.com/ML-HDU/MRAE.

Locating Multiple Equivalent Feature Subsets in Feature Selection for Imbalanced Classification

Feature selection can be used to solve imbalanced classification problems encountered in big data projects. There often exist multiple feature subsets achieving the same accuracy. These subsets tend to exhibit different acquisition difficulty and reliability, thus offering decision-makers with multiple choices if they can be well-identified. This work formulates feature selection as a Multimodal Multiobjective Problem (MMOP), where a point on Pareto front in objective space has multiple equivalent feature subsets in decision space. To seek more equivalent feature subsets, this work proposes a new multiobjective fireworks algorithm. It extends a latest single-objective fireworks algorithm to a multiobjective version such that it becomes suitable for solving MMOP. An adaptive strategy and special archive guidance are newly designed to improve its performance. A weighted extreme learning machine is chosen to classify datasets and return classification accuracy due to its fast learning speed. Experimental results show that the proposed algorithm outperforms its compared ones on 15 imbalanced classification datasets including 5 low-dimensional, 5 high-dimensional feature selection problems and 5 large-scale problems with larger imbalanced ratio, and its runtime is the least among them. Also, fault diagnosis in self-organizing cellular networks, as an important imbalance classification problem, is performed by the proposed algorithm and the results show that it can perform fault diagnosis well.

AUV 3D docking control using deep reinforcement learning

Autonomous docking can enable AUV to have long endurance, so it is necessary to consider the issue of robust docking control under current and wave disturbances. In this work, based on the proximal policy optimization (PPO) algorithm, we developed a model-free docking controller to complete three-dimensional docking tasks under disturbances. To improve the performance of PPO, two mechanisms are proposed, including adaptive rollback clipping and self-generated demonstration replay. A simulation environment is constructed, including fuzzy hydrodynamic parameters, ocean current and wave disturbance model. Simulation results demonstrate that our proposed method has faster learning speed, higher robustness, and can control AUV to achieve 3D docking tasks in complex environments with a high success rate.

Emergency evacuation risk assessment method for educational buildings based on improved extreme learning machine

In educational facility interiors, the risk of congestion and trampling among occupants during the evacuation process presents a significant safety concern. Therefore, assessing the risk of the evacuation process is of great practical and academic importance. To meet the requirements of rapid and timely risk assessment, this article proposes an emergency evacuation risk assessment model based on the Improved Extreme Learning Machine (ELM). The ELM with fast learning speed and good generalization performance is improved to form the Deep Extreme Learning Machine (DELM) and Kernel Based Extreme Learning Machine (KELM) models, and the Improved Seagull Optimization Algorithm (ISOA) was used to constitute the ISOA-DELM and ISOA-KELM models for training. Taking a university library as an example, the evaluation process of model data acquisition, training, and testing is analyzed and compared. The prediction accuracy of the ISOA-DELM and ISOA-KELM models proposed in this paper reached more than 92%. The results show that improved extreme learning machine models can enable an efficient and fast risk assessment.

BE-ELM: Biological ensemble Extreme Learning Machine without the need of explicit aggregation

Extreme learning machines (ELMs) are commonly adopted as base learners in ensemble methods due to unstable results and fast learning speed. However, most existing ensemble structures require explicit aggregation of ELM base learners’ results before the final decision. This study proposes a novel Biological Ensemble ELMs called BE-ELM from a biological perspective for the first time and exploit the superiority of assembling multiple ELM base learners in parallel without the need for explicit aggregation, and thus simplifying the learning procedure. BE-ELM’s structure is inspired by recent MIT neuroscience findings of brain learning mechanisms. The expression of the analytical solution of BE-ELM is similar to that of basic ELMs, which allows it to inherit their fast learning speed in the ensemble structure. Moreover, BE-ELM also has the added advantage of superior performance. Our theoretical analysis shows that BE-ELM consisting of multiple ELM base learners built on subsets of the original features is equivalent to a more complex ELM on the original feature space. We prove that BE-ELM, even without any explicit aggregation, can guarantee enhanced generalization capabilities. To confirm our findings, we conducted extensive experiments on various datasets. The results demonstrate that BE-ELM outperforms traditional ELMs and other state-of-the-art ensemble ELMs in terms of generalization performance on most datasets. These findings suggest that BE-ELM has the potential to improve prediction outcomes in practical applications.

Range-Free Localization Using Extreme Learning Machine and Ring-Shaped Salp Swarm Algorithm in Anisotropic Networks

Node localization is one of the basic requirements in various Internet of Things applications. Among a wide range of localization schemes, the range-free localization algorithm is promising as a cost-effective technique. However, the localization accuracy of this technique is susceptible to various anisotropy factors such as the existence of holes, non-uniform node distribution, and dynamic radio propagation pattern. To this end, an accurate range-free localization model using extreme learning machine and ring-shaped salp swarm algorithm is proposed for anisotropic wireless sensor networks. First, the integer hop count between two adjacent nodes is quantized as a real number according to the Jaccard coefficient of their shared neighbor nodes. Second, exploiting the strong generalization and fast learning speed of extreme learning machine, a distance mapping model based on the modified real hop count is developed for solving anisotropic signal attenuation. Third, the coordinate calculation of normal nodes is formulated as a minimum problem by taking into account the weighted squared error of estimated distance, and the bounding box method is utilized to initialize the possible location boundary area of normal nodes. Finally, the salp swarm algorithm based on the ring-shaped topology is designed to compute the coordinates of normal nodes. Extensive simulations on several network topologies are conducted with the effect of multiple anisotropic factors. Experimental results show that the proposed algorithm is superior to other developed ones not only in localization accuracy but also in robustness against network anisotropy.

Joint Transfer Extreme Learning Machine with Cross-Domain Mean Approximation and Output Weight Alignment

With fast learning speed and high accuracy, extreme learning machine (ELM) has achieved great success in pattern recognition and machine learning. Unfortunately, it will fail in the circumstance where plenty of labeled samples for training model are insufficient. The labeled samples are difficult to obtain due to their high cost. In this paper, we solve this problem with transfer learning and propose joint transfer extreme learning machine (JTELM). First, it applies cross-domain mean approximation (CDMA) to minimize the discrepancy between domains, thus obtaining one ELM model. Second, subspace alignment (sa) and weight approximation are together introduced into the output layer to enhance the capability of knowledge transfer and learn another ELM model. Third, the prediction of test samples is dominated by the two learned ELM models. Finally, a series of experiments are carried out to investigate the performance of JTELM, and the results show that it achieves efficiently the task of transfer learning and performs better than the traditional ELM and other transfer or nontransfer learning methods.

Prediction of line heating deformation for sheet based on SSA-ELM algorithm

Line heating is highly susceptible to plastic deformation leading to structural changes, which seriously affects shipbuilding efficiency. It is extremely important to obtain the precise line heating deformation law. There is much research on plate deformation prediction, but there is still no mature, accurate and fast prediction method. Based on this, it is necessary to research the line heating deformation prediction method. ELM has the advantages of fast learning speed, good generalization performance and strong function approximation ability. To address the poor stability of the regression model due to the randomly generated weights and thresholds of ELM, a combined prediction model (SSA-ELM) based on a squirrel search algorithm (SSA) optimized limit learning machine is proposed. The results show that the relative errors of transverse shrinkage and angular deformation of SSA-ELM are improved by 4.7% and 3.9%. The SSA-ELM prediction model has good regression accuracy and generalization ability. It gives more accurate prediction results in terms of line heating deformation prediction.

An improved ELM-WOA–based fault diagnosis for electric power

Due to its fast learning speed, the extreme learning machine (ELM) plays a very important role in the real-time monitoring of electric power. However, the initial weights and thresholds of the ELM are randomly selected, therefore it is difficult to achieve an optimal network performance; in addition, there is a lack of distance selection when detecting faults using artificial intelligence algorithms. To solve the abovementioned problem, we present a fault diagnosis method for microgrids on the basis of the whale algorithm optimization–extreme learning machine (WOA-ELM). First, the wavelet packet decomposition is used to analyze the three-phase fault voltage, and the energy entropy of the wavelet packet is calculated to form the eigenvector as the data sample; then, we use the original ELM model coupled with the theory of distance selection to locate faults and compared it with the SVM method; finally, the whale algorithm is used to optimize the input weight and hidden layer neuron threshold of the ELM, i.e., the WOA-ELM model, which solves the problem of the random initialization of the input weight and hidden layer neuron threshold that easily affects the network performance, further improves the learning speed and generalization ability of the network, and is conducive to the overall optimization. The results show that 1) the accuracy of selecting the data according to the fault distance is twice that of not selecting data according to it; 2) compared with the BP neural network, RBF neural network, and ELM, the fault diagnosis model based on the WOA-ELM has a faster learning speed, stronger generalization ability, and higher recognition accuracy; and 3) after optimization of the WOA, the WOA-ELM can improve 22.5% accuracy in fault detection when compared to the traditional ELM method. Our results are of great significance in improving the security of smart grid.