Entropy-based matrix learning machine for imbalanced data sets

A Recognition Method of Aggressive Driving Behavior Based on Ensemble Learning

Aggressive driving behavior (ADB) is one of the main causes of traffic accidents. The accurate recognition of ADB is the premise to timely and effectively conduct warning or intervention to the driver. There are some disadvantages, such as high miss rate and low accuracy, in the previous data-driven recognition methods of ADB, which are caused by the problems such as the improper processing of the dataset with imbalanced class distribution and one single classifier utilized. Aiming to deal with these disadvantages, an ensemble learning-based recognition method of ADB is proposed in this paper. First, the majority class in the dataset is grouped employing the self-organizing map (SOM) and then are combined with the minority class to construct multiple class balance datasets. Second, three deep learning methods, including convolutional neural networks (CNN), long short-term memory (LSTM), and gated recurrent unit (GRU), are employed to build the base classifiers for the class balance datasets. Finally, the ensemble classifiers are combined by the base classifiers according to 10 different rules, and then trained and verified using a multi-source naturalistic driving dataset acquired by the integrated experiment vehicle. The results suggest that in terms of the recognition of ADB, the ensemble learning method proposed in this research achieves better performance in accuracy, recall, and F₁-score than the aforementioned typical deep learning methods. Among the ensemble classifiers, the one based on the LSTM and the Product Rule has the optimal performance, and the other one based on the LSTM and the Sum Rule has the suboptimal performance.

A Review of Fuzzy and Pattern-Based Approaches for Class Imbalance Problems

The usage of imbalanced databases is a recurrent problem in real-world data such as medical diagnostic, fraud detection, and pattern recognition. Nevertheless, in class imbalance problems, the classifiers are commonly biased by the class with more objects (majority class) and ignore the class with fewer objects (minority class). There are different ways to solve the class imbalance problem, and there has been a trend towards the usage of patterns and fuzzy approaches due to the favorable results. In this paper, we provide an in-depth review of popular methods for imbalanced databases related to patterns and fuzzy approaches. The reviewed papers include classifiers, data preprocessing, and evaluation metrics. We identify different application domains and describe how the methods are used. Finally, we suggest further research directions according to the analysis of the reviewed papers and the trend of the state of the art.

Deep stacked support matrix machine based representation learning for motor imagery EEG classification

BACKGROUND AND OBJECTIVE

Electroencephalograph (EEG) classification is an important technology that can establish a mapping relationship between EEG features and cognitive tasks. Emerging matrix classifiers have been successfully applied to motor imagery (MI) EEG classification, but they belong to shallow classifiers, making powerful stacked generalization principle not exploited for automatically learning deep EEG features. To learn the high-level representation and abstraction, we proposed a novel deep stacked support matrix machine (DSSMM) to improve the performance of existing shallow matrix classifiers in EEG classification.

METHODS

The main idea of our framework is founded on the stacked generalization principle, where support matrix machine (SMM) is introduced as the basic building block of deep stacked network. The weak predictions of all previous layers obtained via SMM are randomly projected to help move apart the manifold of the original input EEG feature, and then the newly generated features are fed into the next layer of DSSMM. The framework only involves an efficient feed-forward rather than parameter fine-tuning with backpropagation, each layer of which is a convex optimization problem, thus simplifying the objective function solving process.

RESULTS

Extensive experiments on three public EEG datasets and a self-collected EEG dataset are conducted. Experimental results demonstrate that our DSSMM outperforms the available state-of-the-art methods.

CONCLUSION

The proposed DSSMM inherits the characteristic of matrix classifiers that can learn the structural information of data as well as the powerful capability of deep representation learning, which makes it adapted to classify complex matrix-form EEG data.

Improved linear classifier model with Nyström

Most data sets consist of interlaced-distributed samples from multiple classes and since these samples always cannot be classified correctly by a linear hyperplane, so we name them nonlinearly separable data sets and corresponding classifiers are named nonlinear classifiers. Traditional nonlinear classifiers adopt kernel functions to generate kernel matrices and then get optimal classifier parameters with the solution of these matrices. But computing and storing kernel matrices brings high computational and space complexities. Since INMKMHKS adopts Nyström approximation technique and NysCK changes nonlinearly separable data to linearly ones so as to reduce the complexities, we combines ideas of them to develop an improved NysCK (INysCK). Moreover, we extend INysCK into multi-view applications and propose multi-view INysCK (MINysCK). Related experiments validate the effectiveness of them in terms of accuracy, convergence, Rademacher complexity, etc.

Medical image classification via multiscale representation learning

Multiscale structure is an essential attribute of natural images. Similarly, there exist scaling phenomena in medical images, and therefore a wide range of observation scales would be useful for medical imaging measurements. The present work proposes a multiscale representation learning method via sparse autoencoder networks to capture the intrinsic scales in medical images for the classification task. We obtain the multiscale feature detectors by the sparse autoencoders with different receptive field sizes, and then generate the feature maps by the convolution operation. This strategy can better characterize various size structures in medical imaging than single-scale version. Subsequently, Fisher vector technique is used to encode the extracted features to implement a fixed-length image representation, which provides more abundant information of high-order statistics and enhances the descriptiveness and discriminative ability of feature representation. We carry out experiments on the IRMA-2009 medical collection and the mammographic patch dataset. The extensive experimental results demonstrate that the proposed method have superior performance.