Search

In this paper, a novel imbalance learning method for binary classes is proposed, named as Post-Boosting of classification boundary for Imbalanced data (PBI), which can significantly improve the performance of any trained neural networks (NN) classification boundary. The procedure of PBI simply consists of two steps: an (imbalanced) NN learning method is first applied to produce a classification boundary, which is then adjusted by PBI under the geometric mean (G-mean). For data imbalance, the geometric mean of the accuracies of both minority and majority classes is considered, that is statistically more suitable than the common metric accuracy. PBI also has the following advantages over traditional imbalance methods: (i) PBI can significantly improve the classification accuracy on minority class while improving or keeping that on majority class as well; (ii) PBI is suitable for large data even with high imbalance ratio (up to 0.001). For evaluation of (i), a new metric called Majority loss/Minority advance ratio (MMR) is proposed that evaluates the loss ratio of majority class to minority class. Experiments have been conducted for PBI and several imbalance learning methods over benchmark datasets of different sizes, different imbalance ratios, and different dimensionalities. By analyzing the experimental results, PBI is shown to outperform other imbalance learning methods on almost all datasets., (Copyright © 2017 Elsevier Ltd. All rights reserved.)

The automotive engine idle speed control problem is a compromise among low engine speed for fuel saving, minimum emissions and disturbance rejection ability to prevent engine stall. However, idle speed regulation is very challenging due to the presence of high nonlinearity and aging-caused uncertainties in the engine dynamics. Therefore, the engine idle speed system is a typical uncertain nonlinear system. To address the problems of inherent nonlinearity and uncertainties in idle speed regulation, an extreme learning machine (ELM)-based adaptive neural control algorithm is proposed for tracking the target idle speed adaptively. The purpose of ELM is to rapidly deal with the uncertain nonlinear engine system. Since the original ELM is not designed for adaptive control, a new adaptation law is designed to update the weights of ELM in the sense of Lyapunov stability. Experiment is conducted to validate the performance of the proposed control method. Experimental result indicates that the ELM-based adaptive neural control outperforms the classical proportional–integral–derivative (PID), fuzzy-PID and back-propagation-neural-network-based controllers in terms of tracking performance under the variation of engine load. [ABSTRACT FROM AUTHOR]

Maximum margin clustering (MMC) is a recent approach of applying margin maximization in supervised learning to unsupervised learning, aiming to partition the data into clusters with high discrimination. Recently, extreme learning machine (ELM) has been applied to MMC (called iterative ELM clustering or ELMCIter) which maximizes the data discrimination by iteratively training a weighted extreme learning machine (W-ELM). In this way, ELMCIter achieves a substantial reduction in training time and provides a unified model for both binary and multi-class clusterings. However, there exist two issues in ELMCIter: (1) random feature mappings adopted in ELMCIter are unable to well obtain high-quality discriminative features for clustering and (2) a large model is usually required in ELMCIter because its performance is affected by the number of hidden nodes, and training such model becomes relatively slow. In this paper, the hidden layer in ELMCIter is encoded by an approximate empirical kernel map (AEKM) rather than the random feature mappings, in order to solve these two issues. AEKM is generated from low-rank approximation of the kernel matrix, derived from the input data through a kernel function. Our proposed method is called iterative AEKM for clustering (AEKMCIter), whose contributions are: (1) AEKM can extract discriminative and robust features from the kernel matrix so that better performance is always achieved in AEKMCIter and (2) AEKMCIter produces an extremely small number of hidden nodes for low memory consumption and fast training. Detailed experiments verified the effectiveness and efficiency of our approach. As an illustration, on the MNIST10 dataset, our approach AEKMCIter improves the clustering accuracy over ELMCIter up to 5%, while significantly reducing the training time and the memory consumption (i.e., the number of hidden nodes) up to 1/7 and 1/20, respectively. [ABSTRACT FROM AUTHOR]

Summary: This paper proposes a new integrated vehicle dynamics management for enhancing the yaw stability and wheel slip regulation of the distributed‐drive electric vehicle with active front steering. To cope with the unknown nonlinear tire dynamics with uncertain disturbances in integrated control problem of vehicle dynamics, a neuro‐adaptive predictive control is therefore proposed for multiobjective coordination of constrained systems with unknown nonlinearity. Unknown nonlinearity with unmodeled dynamics is modeled using a random projection neural network via adaptive machine learning, where a new adaptation law is designed in premise of Lyapunov stability. Given the computational efficiency, a neurodynamic method is extended to solve the constrained programming problem with unknown nonlinearity. To test the performance of the proposed control method, simulations were conducted using a validated vehicle model. Simulation results show that the proposed neuro‐adaptive predictive controller outperforms the classical model predictive controller in tracking nominal wheel slip ratio, desired vehicle yaw rate and sideslip angle, showing its significance in vehicle yaw stability enhancement and wheels slip regulation. [ABSTRACT FROM AUTHOR]

Intelligent fault diagnosis of rotating machinery is vital for industries to improve fault prediction performance and reduce the maintenance cost. The new fault diagnostic framework is proposed which consists of three stages: (1) signal processing and feature extraction, (2) fault diagnosis by combining the classification results through a probabilistic ensemble method, and (3) parameter optimization and performance evaluation. In the first stage, ensemble empirical mode decomposition (EEMD) decomposes the acquired signal into a suite of intrinsic mode functions (IMF) which encounters redundant components and large data problems. To eliminate the redundant IMF and select fault feature from residual IMF, correlation coefficient (CC) and singular value decomposition (SVD) method are applied respectively. In the second stage, to improve the performance of fault diagnosis based on single classifier and increase the number of detectable fault, a new probabilistic committee machine (PCM) method is proposed, in which multiple pairwise-coupled sparse Bayesian extreme learning machines (PCSBELM) are individually trained using air ration, ignition pattern and engine sound signal. In addition, each classifier is assigned with an optimal weight in accordance with their reliability and accuracy so that a reliable and widely-covered fault diagnostic result can be obtained from the weighted combination of the members. To verify the effectiveness of the proposed fault diagnostic framework, it is applied to automotive engine fault detection. The evaluation results show the proposed framework is superior to the existing single classifier in terms of both single- and simultaneous-faults in automotive engine. [ABSTRACT FROM AUTHOR]

Extreme learning machine (ELM) is a kind of random projection-based neural networks, whose advantages are fast training speed and high generalization. However, three issues can be improved in ELM: (1) the calculation of output weights takes OL2N time (with N training samples and L hidden nodes), which is relatively slow to train a model for large N and L; (2) the manual tuning of L is tedious, exhaustive and time-consuming; (3) the redundant or irrelevant information in the hidden layer may cause overfitting and may hinder high generalization. Inspired from compressive sensing theory, we propose an efficient ELM via very sparse random projection (VSRP) called VSRP-ELM for training with large N and L. The proposed VSRP-ELM adds a novel compression layer between the hidden layer and output layer, which compresses the dimension of the hidden layer from N×L to N×k(wherek under projection with random sparse-Bernoulli matrix. The advantages of VSRP-ELM are (1) faster training time Ok2N,k is obtained for large L; (2) the tuning time of L can be significantly reduced by initializing a large L, and then shrunk to k using just a few trials, while maintaining a comparable result of the original model accuracy; (3) higher generalization may be benefited from the cleaning of redundant or irrelevant information through VSRP. From the experimental results, the proposed VSRP-ELM can speed ELM up to 7 times, while the accuracy can be improved up to 6%. [ABSTRACT FROM AUTHOR]

Although many combinations of biofuel blends are available in the market, it is more beneficial to vary the ratio of biofuel blends at different engine operating conditions for optimal engine performance. Dual-injection engines have the potential to implement such function. However, while optimal engine calibration is critical for achieving high performance, the use of two injection systems, together with other modern engine technologies, leads the calibration of the dual-injection engines to a very complicated task. Traditional trial-and-error-based calibration approach can no longer be adopted as it would be time-, fuel- and labor-consuming. Therefore, a new and fast calibration method based on sparse Bayesian extreme learning machine (SBELM) and metaheuristic optimization is proposed to optimize the dual-injection engines operating with biofuels. A dual-injection spark-ignition engine fueled with ethanol and gasoline is employed for demonstration purpose. The engine response for various parameters is firstly acquired, and an engine model is then constructed using SBELM. With the engine model, the optimal engine settings are determined based on recently proposed metaheuristic optimization methods. Experimental results validate the optimal settings obtained with the proposed methodology, indicating that the use of machine learning and metaheuristic optimization for dual-injection engine calibration is effective and promising. [ABSTRACT FROM AUTHOR]

The automotive engine is prone to various faults due to its complex structure and running conditions. Development of a fast response and accurate intelligent system for fault diagnosis of automotive engines is therefore greatly urged. The engine fault diagnosis faces challenges because of the existence of simultaneous-faults which are multiple single-faults appear concurrently. Another challenge is the high cost in acquiring the exponentially increased simultaneous-fault signals. Traditional signal-based engine fault diagnostic systems may not give reliable diagnostic results because they usually rely on single classifier and one kind of engine signal. To enhance the reliability of fault diagnosis and the number of detectable faults, this research proposes a new diagnostic framework namely probabilistic committee machine (PCM). The framework combines feature extraction (empirical mode decomposition and sample entropy), a parameter optimization algorithm, and multiple sparse Bayesian extreme learning machines (SBELM) to form an intelligent diagnostic framework. Multiple SBELM networks are built to form different domain committee members. The members are individually trained using air ratio, ignition pattern and engine sound signals. The diagnostic result from each fault detection member is then combined by using a new probabilistic ensemble method, which can improve the overall diagnostic accuracy and increase the number of detectable faults as compared to individual classifier. Experimental results show the proposed framework is superior to the existing single probabilistic classifier. Moreover, the proposed system can diagnose both single and simultaneous-faults for automotive engines while the system is trained by single-fault patterns only. [ABSTRACT FROM AUTHOR]

Damage location detection has direct relationship with the field of aerospace structure as the detection system can inspect any exterior damage that may affect the operations of the equipment. In the literature, several kinds of learning algorithms have been applied in this field to construct the detection system and some of them gave good results. However, most learning algorithms are time-consuming due to their computational complexity so that the real-time requirement in many practical applications cannot be fulfilled. Kernel extreme learning machine (kernel ELM) is a learning algorithm, which has good prediction performance while maintaining extremely fast learning speed. Kernel ELM is originally applied to this research to predict the location of impact event on a clamped aluminum plate that simulates the shell of aerospace structures. The results were compared with several previous work, including support vector machine (SVM), and conventional back-propagation neural networks (BPNN). The comparison result reveals the effectiveness of kernel ELM for impact detection, showing that kernel ELM has comparable accuracy to SVM but much faster speed on current application than SVM and BPNN. [ABSTRACT FROM AUTHOR]

Effective air-ratio control is desirable to maintain the best engine performance. However, traditional air-ratio control assumes the lambda sensor located at the tail pipe works properly and relies strongly on the air-ratio feedback signal measured by the lambda sensor. When the sensor is warming up during cold start or under failure, the traditional air-ratio control no longer works. To address this issue, this paper utilizes an advanced modelling technique, kernel extreme learning machine (ELM), to build a backup air-ratio model. With the prediction from the model, a limited air-ratio control performance can be maintained even when the lambda sensor does not work. Such strategy is realized as fault tolerance control. In order to verify the effectiveness of the proposed fault tolerance air-ratio control strategy, a model predictive control scheme is constructed based on the kernel ELM backup air-ratio model and implemented on a real engine. Experimental results show that the proposed controller can regulate the air-ratio to specific target values within a satisfactory tolerance under external disturbance and the absence of air-ratio feedback signal from the lambda sensor. This implies that the proposed fault tolerance air-ratio control is a promising scheme to maintain air-ratio control performance when the lambda sensor is under failure or warming up. [ABSTRACT FROM AUTHOR]

This study presents the optimization of biodiesel engine performance that can achieve the goal of fewer emissions, low fuel cost and wide engine operating range. A new biodiesel engine modeling and optimization framework based on extreme learning machine (ELM) is proposed. As an accurate model is required for effective optimization result, kernel-based ELM (K-ELM) is used instead of basic ELM because K-ELM can provide better generalization performance, and the randomness of basic ELM does not occur in K-ELM. By using K-ELM, a biodiesel engine model is first created based on experimental data. Logarithmic transformation of dependent variables is used to alleviate the problems of data scarcity and data exponentiality simultaneously. With the K-ELM engine model, cuckoo search (CS) is then employed to determine the optimal biodiesel ratio. A flexible objective function is designed so that various user-defined constraints can be applied. As an illustrative study, the fuel price in Macau is used to perform the optimization. To verify the modeling and optimization framework, the K-ELM model is compared with a least-squares support vector machine (LS-SVM) model, and the CS optimization result is compared with particle swarm optimization and experimental results. The evaluation result shows that K-ELM can achieve comparable performance to LS-SVM, resulting in a reliable prediction result for optimization. It also shows that the optimization results based on CS is effective. [ABSTRACT FROM AUTHOR]

Abstract: Real-time fault diagnostic system is very important to maintain the operation of the gas turbine generator system (GTGS) in power plants, where any abnormal situation will interrupt the electricity supply. The GTGS is complicated and has many types of component faults. To prevent from interruption of electricity supply, a reliable and quick response framework for real-time fault diagnosis of the GTGS is necessary. As the architecture and the learning algorithm of extreme learning machine (ELM) are simple and effective respectively, ELM can identify faults quickly and precisely as compared with traditional identification techniques such as support vector machines (SVM). This paper therefore proposes a new application of ELM for building a real-time fault diagnostic system in which data pre-processing techniques are integrated. In terms of data pre-processing, wavelet packet transform and time-domain statistical features are proposed for extraction of vibration signal features. Kernel principal component analysis is then applied to further reduce the redundant features in order to shorten the fault identification time and improve accuracy. To evaluate the system performance, a comparison between ELM and the prevailing SVM on the fault detection was conducted. Experimental results show that the proposed diagnostic framework can detect component faults much faster than SVM, while ELM is competitive with SVM in accuracy. This paper is also the first in the literature that explores the superiority of the fault identification time of ELM. [Copyright &y& Elsevier]

Highlights: [•] Diesel engine models are built using advanced machine learning techniques and verified based on experimental data. [•] A new hybrid inference is proposed for the selection of hyperparameters of kernel based extreme learning machine. [•] Problems of data scarcity and exponentiality are eased by using logarithmic transformation of dependent variables to pre-process the data. [•] A comparison among the models built by advanced and traditional methods is conducted. [•] The models developed by advanced methods with the hybrid inference and logarithmic transformation are more accurate than traditional ones. [ABSTRACT FROM AUTHOR]

• A novel BLS stacking framework is proposed for the accurate diagnosis of GIM. • A parallel attention module is proposed to boost the classifiers in Level-0. • A BLS-based approach is proposed in Level-1. • The proposed BLS2-MSA obtained better results on GIM diagnosis. Gastric intestinal metaplasia (GIM) is a pre-malignant lesion of gastric cancer, which is the fourth leading cause of cancer-related mortalities. The accurate diagnosis and effective treatment of GIM can decrease the incidence of gastric cancer. Traditionally, GIM diagnosis is conducted through upper endoscopy imaging, which is highly dependent on endoscopists' experience, and the diagnostic results may fluctuate with their discrepant skills or potential fatigue. Thus, computer-aided diagnosis (CAD) of GIM with high accuracy is urgently needed, while currently there is no such computer system in commercial market. In this paper, a novel broad learning system stacking framework with multi-scale attention (BLS2-MSA) is proposed, which contains Level-0 for preliminary diagnosis and Level-1 for final decision. In Level-0 of the BLS2-MSA, there are five classifiers, four of which are constructed using multi-scale features from the backbone neural network with the proposed parallel attention module, and the other classifier adopts a standard TL method only. In Level-1 of the BLS2-MSA, a broad learning system-based incremental updating approach is first proposed to boost the performance of classifiers in Level-0. Experimental results show that the True Positive Rate (TPR), the True Negative Rate (TNR), the Positive Predictive Value (PPV), the Accuracy (ACC), the F 1 and the Area Under ROC Curve (AUC) of the BLS2-MSA are 93.6 % , 91.2 % , 93.6 % , 93.2 % , 93.6 and 0.931 respectively, and the diagnostic results demonstrate that the BLS2-MSA could perform competitively compared with skilled endoscopists. All of these indicate that the proposed method enables an accurate and reliable GIM diagnosis. [ABSTRACT FROM AUTHOR]

Abstract: This study aims to determine optimal biodiesel ratio that can achieve the goals of fewer emissions, reasonable fuel economy and wide engine operating range. Different advanced machine learning techniques, namely ELM (extreme learning machine), LS-SVM (least-squares support vector machine) and RBFNN (radial-basis function neural network), are used to create engine models based on experimental data. Logarithmic transformation of dependent variables is used to alleviate the problems of data scarcity and data exponentiality simultaneously. Based on the engine models, two optimization methods, namely SA (simulated annealing) and PSO (particle swarm optimization), are employed and a flexible objective function is designed to determine the optimal biodiesel ratio subject to various user-defined constraints. A case study is presented to verify the modeling and optimization framework. Moreover, two comparisons are conducted, where one is among the modeling techniques and the other is among the optimization techniques. Experimental results show that, in terms of the model accuracy and training time, ELM with the logarithmic transformation is better than LS-SVM and RBFNN with/without the logarithmic transformation. The results also show that PSO outperforms SA in terms of fitness and standard deviation, with an acceptable computational time. [Copyright &y& Elsevier]

Recently, multilayer extreme learning machine (ML-ELM) and hierarchical extreme learning machine (H-ELM) were developed for representation learning whose training time can be reduced from hours to seconds compared to traditional stacked autoencoder (SAE). However, there are three practical issues in ML-ELM and H-ELM: (1) the random projection in every layer leads to unstable and suboptimal performance; (2) the manual tuning of the number of hidden nodes in every layer is time-consuming; and (3) under large hidden layer, the training time becomes relatively slow and a large storage is necessary. More recently, issues (1) and (2) have been resolved by kernel method, namely, multilayer kernel ELM (ML-KELM), which encodes the hidden layer in form of a kernel matrix (computed by using kernel function on the input data), but the storage and computation issues for kernel matrix pose a big challenge in large-scale application. In this paper, we empirically show that these issues can be alleviated by encoding the hidden layer in the form of an approximate empirical kernel map (EKM) computed from low-rank approximation of the kernel matrix. This proposed method is called ML-EKM-ELM, whose contributions are: (1) stable and better performance is achieved under no random projection mechanism; (2) the exhaustive manual tuning on the number of hidden nodes in every layer is eliminated; (3) EKM is scalable and produces a much smaller hidden layer for fast training and low memory storage, thereby suitable for large-scale problems. Experimental results on benchmark datasets demonstrated the effectiveness of the proposed ML-EKM-ELM. As an illustrative example, on the NORB dataset, ML-EKM-ELM can be respectively up to 16 times and 37 times faster than ML-KELM for training and testing with a little loss of accuracy of 0.35%, while the memory storage can be reduced up to 1/9. [ABSTRACT FROM AUTHOR]

While multiple model adaptive control (MMAC) scheme provides a solution to systems with unknown and rapidly time-varying parameters, many offline samples must be obtained beforehand, and the number of models is difficult to be found if no prior knowledge is given. This paper proposes a new adaptive control strategy to handle such systems. The principle is to use a change detection mechanism to check if there is an abrupt change, and immediately train a new model if a change is detected. A novel online identification algorithm, namely initial-training-free online extreme learning machine (ITF-OELM), is also proposed to allow the model to be trained anytime without concerns on prior data. With this strategy, only one model is necessary as compared to MMAC, resulting in reduction on computational complexity and memory usage. Simulation results show that the proposed strategy is effective. Besides, although the use of forgetting factor in ITF-OELM can accelerate the convergence speed for system identification, sometimes it may lead to ill-conditioned covariance matrix in the recursively updating process. This paper shows that such issue can be solved by the change detection mechanism. [ABSTRACT FROM AUTHOR]

Biofuels are important for the reduction of engine exhaust emissions and fossil fuel consumption. To use different blends of biofuels, the electronic control unit (ECU) of the engine must be modified and calibrated. However, the calibration process of ECU is very costly and time-consuming. Therefore, most of the engines can only use one specific biofuel blend; otherwise the engines cannot run properly. To alleviate this problem, a mathematical engine model can be used for predicting the engine performance at different ECU settings and biofuel blends so that the ECU can be re-calibrated in real-time via some controllers. The prediction of the engine model must be very fast and accurate for such online control purpose. It must also be very compact due to the limited memory size of the ECU. As a result, a new method called sparse Bayesian extreme learning machine (SBELM) is proposed in this paper to fulfill these requirements of the mathematical engine model for fast engine performance prediction and ECU online re-calibration. Experiments were conducted to compare SBELM with conventional ELM, Bayesian ELM (BELM) and back-propagated neural network (BPNN). Evaluation results show that SBELM can perform at least similar to, but mostly better than, ELM, BELM and BPNN, in terms of prediction accuracy. In terms of execution time, model size, and insensitivity to hidden neuron number, SBELM completely outperforms the other three methods. By these results, SBELM is verified to better fulfill the practical requirements of mathematical engine model for online engine performance prediction. [ABSTRACT FROM AUTHOR]

Abstract: Suspended particulate matters (PM10) is considered as a harmful air pollutant. Many models attempt to predict numerical levels of PM10 but a simple, clearly defined classification of PM10 levels is more readily comprehensible to the general public rather than a numerical value. However, the PM10 prediction model often suffers from data imbalance problem in the training dataset that results in failure to forecast the minority class of severe cases. In this study, a warning system using extreme learning machine (ELM), compared with support vector machine (SVM), was constructed to forecast the class of PM10 level: Good, Moderate, and Severe. An imbalance strategy called prior duplication was also applied to improve the forecast of minority class. The experimental comparisons between ELM and SVM demonstrate that ELM produces superior accuracy relative to SVM in forecasting minority class (Severe) of PM10 level with or without the imbalance strategy. Furthermore, our results show that the required training time and model size in the ELM model are much shorter and smaller than those of SVM respectively, leading to a more efficient and practical implementation of prediction model for large dataset. The performance superiority of ELM is also discussed in this paper. [Copyright &y& Elsevier]