Search

Huber robust regression (HRR) has attracted much attention in machine learning due to its greater robustness to outliers compared to least-squares regression. However, existing algorithms for HRR are computationally much less efficient than those for least-squares regression. Based on a maximally split alternating direction method of multipliers (MS-ADMM) for model fitting, a highly computationally efficient algorithm referred to as the modified MS-ADMM is derived in this article for HRR. After analyzing the convergence of the modified MS-ADMM, a parameter selection scheme is presented for the algorithm. With the parameter values calculated via this scheme, the modified MS-ADMM converges very rapidly, much faster than several typical HRR algorithms. Through applications in the training of stochastic neural networks and comparisons with existing algorithms, the modified MS-ADMM is shown to be computationally much more efficient than the convex quadratic programming method, the Newton method, the iterative reweighted least-squares method, and Nesterov's accelerated gradient method. Implementation of the proposed algorithm on a GPU-based parallel computing platform demonstrates its higher GPU acceleration ratio compared to the competing methods and, thus, its greater superiority in computational efficiency over the competing methods. [ABSTRACT FROM AUTHOR]

The existing randomized autoencoders are generally designed for vectorization data resulting in destroying the original structure information inevitably when dealing with multi-dimension data such as image and video. To address this issue, a one-side matrix randomized AE (OMRAE) is developed that takes the two-dimensional (2D) data as inputs directly by the linear mapping on one-side of inputs with matrix multiplication. For multichannel 2D (M2D) data, a multichannel OMRAE (OMMRAE) is proposed by training the output weights to rebuild each channel of inputs respectively. In this way, the structural information of each channel and the interaction between channels are explored. Then, a double-side structure using 2 OMMRAEs to simultaneously extracts the row and column structure information of M2D is developed. At last, a novel hierarchical matrix randomized neural networks is constructed for one-class classification where each layer passes information by bilinear mapping derived from DMMRAE. Experiments are conducted on 2 benchmark datasets for the effectiveness demonstration. Comparisons to several state-of-the-art AEs reveal that the proposed OMMRAE/DMMRAE can obtain better performance with a compact network size. The source code would be available at https://github.com/ML-HDU/MMRAE. [ABSTRACT FROM AUTHOR]

Recognition of epileptic electroencephalogram (EEG) signals is vital to epileptic seizure detection. Current research on seizure detection mostly focused on generalized seizure analysis. Compared with generalized seizures, childhood focal epilepsy generally originates in one hemisphere of the brain, and the seizure onset patterns vary from patient to patient, making it difficult for analysis. Meanwhile, the frequency, amplitude and rhythm of EEG activities in children of different ages are different, making childhood focal epilepsy detection challenging. In this paper, the channel correlation features (CCF) containing the regional scalp EEG cross correlations and auto-correlations are proposed for children focal epilepsy EEG representation. The spectrum features are also extracted to characterize EEGs in different frequency bands. Further, a convolutional autoencoder (CAE)-based deep feature learning and dimensionality reduction model is proposed for discriminative EEG frequency domain feature extraction. An early seizure detection framework for the childhood focal epilepsy based on the fused CAE and CCF EEG features is finally developed, and an ensemble classification model (ECM) is applied to solve the imbalance issue between ictal, interictal, and preictal. The performance is evaluated on the EEG dataset collected by the Children's Hospital, Zhejiang University School of Medicine (CHZU). Experiments show that the proposed algorithm can reach to the highest accuracy of 93.57% for the early seizure detection in childhood focal epilepsy. [ABSTRACT FROM AUTHOR]

Copyright of Frontiers of Information Technology & Electronic Engineering is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Vehicle re-identification (Re-ID) technology plays an important role in the intelligent transportation system for smart city. Due to various uncertain factors in the real-world scenarios, (e.g., resolution variation, viewpoint variation, illumination changes, occlusion, etc., vehicle Re-ID is a very challenging task. To resist the adverse effect of resolution variation, a joint pyramid feature representation network (JPFRN) for vehicle Re-ID is proposed in this paper. Based on the consideration that various convolution blocks with different depths hold different resolutions and semantic information of the vehicle image, the proposed JPFRN method employs a base network to obtain multi-resolution vehicle features in the first stage. Then, a pyramid feature representation scheme is developed to reconstruct and integrate the obtained multi-resolution vehicle features together. Finally, these pyramid features are jointly represented for learning a more discriminative feature under the supervision of joint Triplet loss and softmax loss. Extensive experimental results on two commonly-used vehicle databases (i.e., VehicleID and VeRi) show that the proposed JPFRN is superior to multiple recently-developed vehicle Re-ID methods. [ABSTRACT FROM AUTHOR]

Urban noise recognition play a vital role in city management and safety operation, especially in the recent smart city engineering. Exiting studies on urban noise recognition are mostly based on conventional acoustic features, such as Mel-Frequency Cepstral Coefficients (MFCC) and Linear Prediction Cepstral Coefficients (LPCC), and the shallow structure based classifiers, such as support vector machine (SVM). However, the urban acoustic environment is complicated and changeable. Conventional acoustic representation and recognition methods may be insufficient in characterizing urban noises, and generally suffer from a degraded performance. In this paper, we study the recent deep neural network based urban noise recognition. The log-Mel-spectrogram, namely, the FBank feature is first derived for acoustic representation. Then, the FBank spectrum constructed with a set of FBank feature vectors from multiple acoustic signal frames is fed to a convolutional neural network (CNN) for urban noise recognition. Comprehensive studies on the dimension of FBank spectrums and the parameters in CNN, including the size of learnable kernels, the dropout rate, and the activation function, etc., are presented in the paper. An acoustic database collected in real environment covering 11 most common urban noises with more than 56,000 samples is constructed for model verification and performance evaluation. In addition, the traditional LPCC and MFCC acoustic feature combining with two popular machine learning algorithms, extreme learning machine (ELM) and support vector machine (SVM), and the FBank image feature combining with extreme learning machine (ELM), hierarchical extreme learning machine (H-ELM) and multilayer extreme learning machine (ML-ELM), have also been presented for discussions. Experimental results show that the proposed method generally outperforms conventional shallow structure based classifiers. [ABSTRACT FROM AUTHOR]

Radar Emitter Identification (REI) has been broadly used in military and civil fields. In this paper, a novel method is proposed for radar emitter signal identification, where the bispectrum estimation of radar signal is extracted and the recent hierarchical extreme learning machine (BS + H-ELM) is adopted for further feature learning and recognition. Conventional REI methods generally rely on the time-difference-of-arrival, carrier frequency, pulse width, pulse amplitude, direction-of-arrival, etc., for signal representation and recognition. However, the increasingly violent electronic confrontation and the emergence of new types of radar signals generally degrade the recognition performance. With this objective, we explore radar emitter signal representation and classification method with the high order spectrum and deep network based H-ELM. After extracting the bispectrum of radar signals, the sparse autoencoder (AE) in H-ELM is employed for feature learning. Simulations on four representative radar signals, namely, the continuous wave (CW), linear frequency modulation wave(LFM), nonlinear frequency modulation wave(NLFM) and binary phase shift keying wave (BPSK), are conducted for performance validation. In comparison to the existing multilayer ELM algorithm and the popular histogram of gradient (HOG) based feature extraction method are proved that the proposal is feasible and potentially applicable in real applications. [ABSTRACT FROM AUTHOR]

Although clustering with pairwise constraints through penalty regularization has been widely adopted in existing semi-supervised clustering approaches, little work has been done on theoretical comparison of these pairwise constrained approaches with respect to difference in penalties. In this paper, we first propose two types of penalties in the context of pairwise constrained fuzzy clustering. The first one accounts for the overall consistency of assignments in terms of fuzzy memberships regarding constrained pairs. The second one is the total Euclidean distance between membership vectors of constrained pairs. After analytical discussion, we establish the connection between different penalties to provide a unified view as well as a better understanding of each of them. Following the idea of penalty regularization, variants of pairwise constrained fuzzy c-means are formulated by incorporating the consistency-type and distance-type penalties, respectively, into the objective function of fuzzy c-means. We also extend this idea to co-clustering by considering pairwise constraints of two types of objects to produce fuzzy co-clusters. Efficient and scalable algorithms have been proposed for parallel implementation. The experimental results with real-world datasets show good performance of the proposed approaches with respect to effectiveness, efficiency and scalability. [ABSTRACT FROM AUTHOR]

The imbalanced data classification attracts increasing attention in the past years due to the continuous expansion of data available in many areas, such as biomedical engineering, surveillance, and computer vision. Learning from imbalanced data is challenging as most standard algorithms fail to properly represent the inherent complex characteristics of the data distribution. As an emerging technology, the extreme learning machine (ELM) and its variants, including the weighted ELM (WELM) and the boosting weighted ELM (BWELM), have been recently developed for the classification of imbalanced data. However, the WELM suffers the following deficiencies: (i) the sample weight matrix is manually chosen and fixed during the learning phase; (ii) the representation capability, namely the capability to extract features or useful information from the original data, is insufficiently explored due to its shallow structure. The BWELM employs the AdaBoost algorithm to optimize the sample weights. But the representation capability is still restricted by the shallow structure. To alleviate these deficiencies, we propose a novel deep weighted ELM (DWELM) algorithm for imbalanced data classification in this paper. An enhanced stacked multilayer deep representation network trained with the ELM (EH-DrELM) is first proposed to improve the representation capability, and a fast AdaBoost algorithm for imbalanced multiclass data (AdaBoost-ID) is developed to optimize the sample weights. Then, the novel DWELM for the imbalance learning is obtained by combining the above two algorithms. Experimental results on nine imbalanced binary-class datasets, nine imbalanced multiclass datasets, and five large benchmark datasets (three for multiclass and two for binary-class) show that the proposed DWELM achieves a better performance than the WELM and BWELM, as well as several state-of-the-art multilayer network-based learning algorithms. [ABSTRACT FROM AUTHOR]

Challenges for optimal design of infinite impulse response digital filters include the high nonconvexity of design problem and inevitable stability constraints on the filters. To reduce the nonconvexity and tackle the stability constraints, a sequential partial optimization (SPO) algorithm was recently developed to divide the design problem into a sequence of subproblems, each updating only two second-order denominator factors. But the convergence of that algorithm is not guaranteed. By applying an incremental update with an optimized step length in each subproblem, this paper presents an improved SPO algorithm which is guaranteed to converge to a Karush-Kuhn-Tucker (not necessarily global) solution of the design problem. This paper also extends the SPO algorithm to a more general case where the number of denominator factors optimized in the subproblems can be any positive number smaller than half of the denominator order. Convergence performance of the algorithm is shown by the design of two example filters with typical specifications widely adopted in the literature. Comparisons with state-of-the-art methods demonstrate that the improved SPO algorithm obtains better filters than the competing methods in terms of the maximum magnitude of frequency-response error. [ABSTRACT FROM AUTHOR]

Accurate prediction of adverse cardiac events for the emergency department (ED) chest pain patients is essential in risk stratification due to the current ambiguity in diagnosing acute coronary syndrome. While most current practices rely on human decision by measuring clinical vital signs, computerized solutions are gaining popularity. We have previously proposed an ensemble-based scoring system (ESS). In this paper, we aim to extend the ESS system using extreme learning machine (ELM), a fast learning algorithm for neural networks. We recruited patients from the ED of Singapore General Hospital, and extracted features such as heart rate variability, 12-lead ECG parameters, and vital signs. We also proposed a novel algorithm called ESS-ELM to predict adverse cardiac events. Different from the original ESS algorithm, ESS-ELM uses the under-sampling technique only in model training. Our proposed method was compared to the original ESS algorithm and several clinical scores in predicting patient outcome. With a cohort of 797 recruited patients, we demonstrated that ESS-ELM outperformed the original ESS algorithm and three established clinical scores, namely HEART, TIMI, and GRACE, in terms of receiver operating characteristic analysis. Furthermore, we have investigated the impact of hidden node number and ensemble size on the predictive performance. ELM has demonstrated the flexibility in its integration with the ESS algorithm. Experiments showed the value of ESS-ELM in prediction of adverse cardiac events. Future works may include the use of new ELM-based learning methods and further validation with a new cohort of patients. [ABSTRACT FROM AUTHOR]

Underground pipelines suffered severe external breakage caused by excavation devices due to arbitral road excavation. Acoustic signal-based recognition has recently shown effectiveness in underground pipeline network surveillance. However, merely relying on recognition may lead to a high false alarm rate. The reason is that underground pipelines are generally paved along a fixed direction and excavations out of the region also trigger the surveillance system. To enhance the reliability of the surveillance system, the direction-of-arrival (DOA) estimation of target sources is combined into the recognition algorithm to reduce false detections in this paper. Two hybrid recognition algorithms are developed. The first one employs extreme learning machine (ELM) for acoustic recognition followed by a focusing matrix-based multiple signal classification algorithm (ELM-MUSIC) for DOA estimation. The second introduces a decision matrix (DM) to characterize the statistic distribution of results obtained by ELM-MUSIC. Real acoustic signals collected by a cross-layer sensor array are conducted for performance comparison. Four representative excavation devices working in a metro construction site are used to generate the signal. Multiple scenarios of the experiments are designed. Comparisons show that the proposed ELM-MUSIC and DM algorithms outperform the conventional focusing matrix based MUSIC (F-MUSIC). In addition, the improved DM method is capable of localizing multiple devices working in order. Two hybrid acoustic signal recognition and source direction estimation algorithms are developed for excavation device classification in this paper. The novel recognition combining DOA estimation scheme can work efficiently for underground pipeline network protection in the real-world complex environment. [ABSTRACT FROM AUTHOR]

Underground pipeline network surveillance system attracts increasingly attentions recently due to severe breakages caused by external excavation equipments in the mainland of China. In this paper, we study excavation equipments classification algorithm based on acoustic signal processing and machine learning algorithms. A cross-layer microphone array with four elements is designed to collect the acoustic database of representative excavation equipments on real construction sites. The generalized sidelobe canceller algorithm is employed for background noise reduction. The improved spectrum dynamic feature extraction algorithm is then implemented for the benchmark acoustic feature database construction of excavation equipments. To perform classification and background noise identification, the single hidden layer feedforward neural network is employed as the classifier. An improved algorithm based on the popular extreme learning machine (ELM) is proposed for classifier learning. The leave-one-out cross validation strategy is adopted for the regularization parameter optimization in ELM. Comprehensive experiments are conducted to test the effectiveness of the proposed algorithm. Comparisons with state-of-art classifiers and the Mel-frequency cepstrual coefficients acoustic features are also provided to demonstrate the superiority of our approach. [ABSTRACT FROM AUTHOR]

Extreme learning machine (ELM) is one of the most important and efficient machine learning algorithms for pattern classification due to its fast learning speed. In this paper, we propose a new ensemble based ELM approach for cross-modality face matching. Different to traditional face recognition methods, the proposed approach integrates the voting-base extreme learning machine (V-ELM) with a novel feature learning based face descriptor. Firstly, the discriminant feature learning is proposed to learn the cross-modality feature representation. Then, we used common subspace learning based method to reduce the obtained cross-modality features. Finally, Voting ELM is utilized as the classifier to improve the recognition accuracy and to speed up the feature learning process. Experiments conducted on two different heterogeneous face recognition scenarios demonstrate the effectiveness of our proposed approach. [ABSTRACT FROM AUTHOR]

Along with the rapid development of mobile terminal devices, landmark recognition applications based on mobile devices have been widely researched in recent years. Due to the fast response time requirement of mobile users, an accurate and efficient landmark recognition system is thus urgent for mobile applications. In this paper, we propose a landmark recognition framework by employing a novel discriminative feature selection method and the improved extreme learning machine (ELM) algorithm. The scalable vocabulary tree (SVT) is first used to generate a set of preliminary codewords for landmark images. An efficient codebook learning algorithm derived from the word mutual information and Visual Rank technique is proposed to filter out those unimportant codewords. Then, the selected visual words, as the codebook for image encoding, are used to produce a compact Bag-of-Words (BoW) histogram. The fast ELM algorithm and the ensemble approach using the ELM classifier are utilized for landmark recognition. Experiments on the Nanyang Technological University campus's landmark database and the Fifteen Scene database are conducted to illustrate the advantages of the proposed framework. [ABSTRACT FROM AUTHOR]

In this paper, we propose an improved learning algorithm named self-adaptive evolutionary extreme learning machine (SaE-ELM) for single hidden layer feedforward networks (SLFNs). In SaE-ELM, the network hidden node parameters are optimized by the self-adaptive differential evolution algorithm, whose trial vector generation strategies and their associated control parameters are self-adapted in a strategy pool by learning from their previous experiences in generating promising solutions, and the network output weights are calculated using the Moore-Penrose generalized inverse. SaE-ELM outperforms the evolutionary extreme learning machine (E-ELM) and the different evolutionary Levenberg-Marquardt method in general as it could self-adaptively determine the suitable control parameters and generation strategies involved in DE. Simulations have shown that SaE-ELM not only performs better than E-ELM with several manually choosing generation strategies and control parameters but also obtains better generalization performances than several related methods. [ABSTRACT FROM AUTHOR]

The robust stability of uncertain linear degenerate systems with discrete and distributed delays is studied in this paper. The uncertainties under consideration are norm bounded, and possibly time varying. A novel robust stability criterion of the system is derived by constructing Lyapunov functions. The degenerate systems are transformed to a descriptor system and the stability criteria are formulated in the form of a linear matrix inequality (LMI). Therefore, it is easy to check the robust stability of the degenerate systems by using this method. Numerical examples are also worked out to illustrate the obtained results. [ABSTRACT FROM AUTHOR]