6 June 2022 in Computers & Industrial Engineering
19 November 2024 in Engineering Applications of Artificial Intelligence
5 December 2023 in IEEE Transactions on Geoscience and Remote Sensing
Hyperspectral image (HSI) characteristics of the abundant spectral information are favores by many scholars, but the challenge is how to select relevant features from such high dimensional data. Band selection (BS), one of the most fundamental dimensionality reduction (DR) techniques, removes redundant bands while providing a subset of bands that can preserve high information content and low noise for further HSI classification. Cuckoo search algorithm (CS) is well-known for its high performance of searching relevant features but struggles to get rid of local extremes in the late iteration. Therefore, in this paper, an unsupervised band selection method based on the heterogeneous cuckoo search algorithm with matched filter (HCS-MF) is proposed for hyperspectral image classification, in which an optimization model is constructed based on the sensitivity of the matching filter to noise. To reduce the similarity between selected bands, a mapping method based on neighborhood band grouping is proposed. In addition, an automatic recommendation strategy based on sliding spectrum decomposition (SSD) is proposed to determine the minimum recommended number of selected bands in different scenes. The superiority of the selected subset of bands is verified by Random Forest, Support Vector Machine (SVM) and Edge-Preserving Filtering-based SVM (EPF-SVM) classifiers. Experimental results on three well-known datasets demonstrate the robustness and superiority of the proposed HCS-MF algorithm compared with the state-of-the-art methods, such as marginalized graph self-representation (MGSR), neighborhood grouping normalized matched filter (NGNMF), and region-wise multiple graph fusion (RMGF).
26 September 2018 in Applied Network Science
An electroencephalography (EEG) coherence network is a representation of functional brain connectivity, and is constructed by calculating the coherence between pairs of electrode signals as a function of frequency. Typical visualizations of coherence networks use a matrix representation with rows and columns representing electrodes and cells representing coherences between electrode signals, or a 2D node-link diagram with vertices representing electrodes and edges representing coherences. However, such representations do not allow an easy embedding of spatial information or they suffer from visual clutter, especially for multichannel EEG coherence networks. In this paper, a new method for data-driven visualization of multichannel EEG coherence networks is proposed to avoid the drawbacks of conventional methods. This method partitions electrodes into dense groups of spatially connected regions. It not only preserves spatial relationships between regions, but also allows an analysis of the functional connectivity within and between brain regions, which could be used to explore the relationship between functional connectivity and underlying brain structures. As an example application, the method is applied to the analysis of multichannel EEG coherence networks obtained from older and younger adults who perform a cognitive task. The proposed method can serve as a preprocessing step before a more detailed analysis of EEG coherence networks.
1 June 2024 in Journal of King Saud University Computer and Information Sciences