Local preserving logistic I-Relief for semi-supervised feature selection

Semi-supervised regression with adaptive graph learning for EEG-based emotion recognition

Electroencephalogram (EEG) signals are widely used in the field of emotion recognition since it is resistant to camouflage and contains abundant physiological information. However, EEG signals are non-stationary and have low signal-noise-ratio, making it more difficult to decode in comparison with data modalities such as facial expression and text. In this paper, we propose a model termed semi-supervised regression with adaptive graph learning (SRAGL) for cross-session EEG emotion recognition, which has two merits. On one hand, the emotional label information of unlabeled samples is jointly estimated with the other model variables by a semi-supervised regression in SRAGL. On the other hand, SRAGL adaptively learns a graph to depict the connections among EEG data samples which further facilitates the emotional label estimation process. From the experimental results on the SEED-IV data set, we have the following insights. 1) SRAGL achieves superior performance compared to some state-of-the-art algorithms. To be specific, the average accuracies are 78.18%, 80.55%, and 81.90% in the three cross-session emotion recognition tasks. 2) As the iteration number increases, SRAGL converges quickly and optimizes the emotion metric of EEG samples gradually, leading to a reliable similarity matrix finally. 3) Based on the learned regression projection matrix, we obtain the contribution of each EEG feature, which enables us to automatically identify critical frequency bands and brain regions in emotion recognition.

An Adapting Chemotaxis Bacterial Foraging Optimization Algorithm for Feature Selection in Classification

Efficient classification methods can improve the data quality or relevance to better optimize some Internet applications such as fast searching engine and accurate identification. However, in the big data era, difficulties and volumes of data processing increase drastically. To decrease the huge computational cost, heuristic algorithms have been used. In this paper, an Adapting Chemotaxis Bacterial Foraging Optimization (ACBFO) algorithm is proposed based on basic Bacterial Foraging Optimization (BFO) algorithm. The aim of this work is to design a modified algorithm which is more suitable for data classification. The proposed algorithm has two updating strategies and one structural changing. First, the adapting chemotaxis step updating strategy is responsible to increase the flexibility of searching. Second, the feature subsets updating strategy better combines the proposed heuristic algorithm with the KNN classifier. Third, the nesting structure of BFO has been simplified to reduce the computation complexity. The ACBFO has been compared with BFO, BFOLIW and BPSO by testing on 12 widely used benchmark datasets. The result shows that ACBFO has a good ability of solving classification problems and gets higher accuracy than the other comparation algorithm.