Jiuwen Cao

Extreme learning machine and adaptive sparse representation for image classification

Recent research has shown the speed advantage of extreme learning machine (ELM) and the accuracy advantage of sparse representation classification (SRC) in the area of image classification. Those two methods, however, have their respective drawbacks, e.g., in general, ELM is known to be less robust to noise while SRC is known to be time-consuming. Consequently, ELM and SRC complement each other in computational complexity and classification accuracy. In order to unify such mutual complementarity and thus further enhance the classification performance, we propose an efficient hybrid classifier to exploit the advantages of ELM and SRC in this paper. More precisely, the proposed classifier consists of two stages: first, an ELM network is trained by supervised learning. Second, a discriminative criterion about the reliability of the obtained ELM output is adopted to decide whether the query image can be correctly classified or not. If the output is reliable, the classification will be performed by ELM; otherwise the query image will be fed to SRC. Meanwhile, in the stage of SRC, a sub-dictionary that is adaptive to the query image instead of the entire dictionary is extracted via the ELM output. The computational burden of SRC thus can be reduced. Extensive experiments on handwritten digit classification, landmark recognition and face recognition demonstrate that the proposed hybrid classifier outperforms ELM and SRC in classification accuracy with outstanding computational efficiency.

Landmark recognition with compact BoW histogram and ensemble ELM

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.

Landmark recognition with sparse representation classification and extreme learning machine

Abstract Along with the rapid development of intelligent mobile terminals, applications on landmark recognition attract increasingly attentions by world wide researchers in the past several years. Although promising achievements have been presented, designing a robust recognition system with an accurate recognition rate and fast response speed is still challenging. To address these issues, we propose a novel landmark recognition algorithm in this paper using the spatial pyramid kernel based bag-of-words (SPK-BoW) histogram approach with the feedforward artificial neural networks (FNN) and the sparse representation classifier (SRC). In the proposed algorithm, the SPK-BoW approach is first employed to extract features and construct an overcomplete dictionary for landmark image representation. Then, the FNN trained with the extreme learning machine (ELM) algorithm combined with the SRC is implemented for landmark image recognition. We conduct experiments using the Nanyang Technological University (NTU) campus landmark database to show that the proposed method achieves a high recognition rate than ELM and a lower response time than the sparse representation technique.

Fast online learning algorithm for landmark recognition based on BoW framework

In this paper, we propose a fast online learning framework for landmark recognition based on single hidden layer feedforward neural networks (SLFNs). Conventional landmark recognition frameworks generally assume that all images are available at hand to train the classifier. However, in real world applications, people may encounter the issue that the classifier built on the existing landmark dataset needs to be tuned when new landmark images are collected. To address this issue, a fast online sequential learning framework based on the recent extreme learning machine (ELM) which can update the classifier by learning the new images one-by-one or chunk-by-chunk is developed for the landmark recognition. The recent spatial pyramid kernel bag-of-words (BoW) method is employed for the feature extraction of landmark images. To show the effectiveness of the proposed online learning framework, the batch mode learning method based on ELM is also employed for comparison. Experimental results based on the landmark database collected from the campus in Nanyang Technological University (NTU) are also given to verify our proposed online learning framework.

Excavation Equipment Recognition Based on Novel Acoustic Statistical Features

Excavation equipment recognition attracts increasing attentions in recent years due to its significance in underground pipeline network protection and civil construction management. In this paper, a novel classification algorithm based on acoustics processing is proposed for four representative excavation equipments. New acoustic statistical features, namely, the short frame energy ratio, concentration of spectrum amplitude ratio, truncated energy range, and interval of pulse are first developed to characterize acoustic signals. Then, probability density distributions of these acoustic features are analyzed and a novel classifier is presented. Experiments on real recorded acoustics of the four excavation devices are conducted to demonstrate the effectiveness of the proposed algorithm. Comparisons with two popular machine learning methods, support vector machine and extreme learning machine, combined with the popular linear prediction cepstral coefficients are provided to show the generalization capability of our method. A real surveillance system using our algorithm is developed and installed in a metro construction site for real-time recognition performance validation.

Ensemble extreme learning machine and sparse representation classification

Abstract Extreme learning machine (ELM) combining with sparse representation classification (ELM-SRC) has been developed for image classification recently. However, employing a single ELM network with random hidden parameters may lead to unstable generalization and data partition performance in ELM-SRC. To alleviate this deficiency, we propose an enhanced ensemble based ELM and SRC algorithm (En-SRC) in this paper. Rather than using the output of a single ELM to decide the threshold for data partition, En-SRC incorporates multiple ensembles to enhance the reliability of the classifier. Different from ELM-SRC, a theoretical analysis on the data partition threshold selection of En-SRC is given. Extension to the ensemble based regularized ELM with SRC (EnR-SRC) is also presented in the paper. Experiments on a number of benchmark classification databases show that the proposed methods win a better classification performance with a lower computational complexity than the ELM-SRC approach.

An enhance excavation equipments classification algorithm based on acoustic spectrum dynamic feature

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.

Acoustic vector sensor: reviews and future perspectives

Acoustic vector sensor (AVS) has been recently researched and developed for acoustic wave capturing and signal processing. Conventional array generally employs spatially displayed sensors for signal enhancement, source localisation, target tracking, etc. However, the large size usually limits its implementations on some portable devices. AVS which generally includes one omni-directional sensor and three orthogonally co-located directional sensors has been recently introduced. An AVS is able to provide the four-dimensional information of sound field in space: the acoustic pressure and its three-dimensional particle velocities. A compact assembled AVS could be as small as a match head and the weight can be <;50 g. Benefits from these properties, AVS tends to be more attractive for exploitation and commercialisation than conventional sensor array. To have a well understanding of the research progress on AVS, an overview on its recent developments is first given in this study. Then, discussions of challenges on AVS and extensions on its possible future prospects are presented.

Kernel-Based Multilayer Extreme Learning Machines for Representation Learning

Recently, multilayer extreme learning machine (ML-ELM) was applied to stacked autoencoder (SAE) for representation learning. In contrast to traditional SAE, the training time of ML-ELM is significantly reduced from hours to seconds with high accuracy. However, ML-ELM suffers from several drawbacks: 1) manual tuning on the number of hidden nodes in every layer is an uncertain factor to training time and generalization; 2) random projection of input weights and bias in every layer of ML-ELM leads to suboptimal model generalization; 3) the pseudoinverse solution for output weights in every layer incurs relatively large reconstruction error; and 4) the storage and execution time for transformation matrices in representation learning are proportional to the number of hidden layers. Inspired by kernel learning, a kernel version of ML-ELM is developed, namely, multilayer kernel ELM (ML-KELM), whose contributions are: 1) elimination of manual tuning on the number of hidden nodes in every layer; 2) no random projection mechanism so as to obtain optimal model generalization; 3) exact inverse solution for output weights is guaranteed under invertible kernel matrix, resulting to smaller reconstruction error; and 4) all transformation matrices are unified into two matrices only, so that storage can be reduced and may shorten model execution time. Benchmark data sets of different sizes have been employed for the evaluation of ML-KELM. Experimental results have verified the contributions of the proposed ML-KELM. The improvement in accuracy over benchmark data sets is up to 7%.

Voting based weighted online sequential extreme learning machine for imbalance multi-class classification

In this paper, a voting based weighted online sequential extreme learning machine (VWOS-ELM) is proposed for class imbalance learning (CIL). VWOS-ELM is the first sequential classifier that can tackle the class imbalance problem in multi-class data streams. Utilizing WOS-ELM and the recently proposed voting based online sequential extreme learning machine (VOS-ELM) method, VWOS-ELM adapts better to newly received data than the original WOS-ELM method. Experimental results show that VWOS-ELM outperforms both the WOS-ELM and the recent meta-cognitive extreme learning machine methods. It also achieves similar performance to that of ensemble of subset OS-ELM (ESOS-ELM) but using fewer independent classifiers.