Publications

In this paper, we propose a new approach to solve linguistic group decision making (GDM) problems through defining different linguistic terms for each expert and optimizing those terms. Information granules are often designed as the framework of linguistic terms and to vividly describe the approach, intervals are selected to express linguistic terms as large, medium, and small in the paper. Analytic Hierarchy Process (AHP) is set as the basic model and abstracted as linguistic reciprocal matrices. The abstraction process is carefully designed considering two strategies: each expert owns same linguistic terms (same distribution of cutting-points in an interval) and each expert owns different linguistic terms. As comparison, three methods of cutting-points allocation for the two strategies are realized with a synthetic example: optimizing allocation, uniform allocation and random allocation. The results coincide with theoretical analysis: each expert owns different linguistic terms reach the highest consensus.

Existing FNNs are mostly developed under a shallow network configuration having lower generalization power than those of deep structures. This paper proposes a novel self-organizing deep FNN, namely DEVFNN. Fuzzy rules can be automatically extracted from data streams or removed if they play limited role during their lifespan. The structure of the network can be deepened on demand by stacking additional layers using a drift detection method which not only detects the covariate drift, variations of input space, but also accurately identifies the real drift, dynamic changes of both feature space and target space. DEVFNN is developed under the stacked generalization principle via the feature augmentation concept where a recently developed algorithm, namely gClass, drives the hidden layer. It is equipped by an automatic feature selection method which controls activation and deactivation of input attributes to induce varying subsets of input features. A deep network simplification procedure is put forward using the concept of hidden layer merging to prevent uncontrollable growth of dimensionality of input space due to the nature of feature augmentation approach in building a deep network structure. DEVFNN works in the sample-wise fashion and is compatible for data stream applications. The efficacy of DEVFNN has been thoroughly evaluated using seven datasets with non-stationary properties under the prequential test-then-train protocol. It has been compared with four popular continual learning algorithms and its shallow counterpart where DEVFNN demonstrates improvement of classification accuracy. Moreover, it is also shown that the concept drift detection method is an effective tool to control the depth of network structure while the hidden layer merging scenario is capable of simplifying the network complexity of a deep network with negligible compromise of generalization performance.

Instead of directly utilizing an observed image including some outliers,\nnoise or intensity inhomogeneity, the use of its ideal value (e.g. noise-free\nimage) has a favorable impact on clustering. Hence, the accurate estimation of\nthe residual (e.g. unknown noise) between the observed image and its ideal\nvalue is an important task. To do so, we propose an $\\ell_0$\nregularization-based Fuzzy $C$-Means (FCM) algorithm incorporating a\nmorphological reconstruction operation and a tight wavelet frame transform. To\nachieve a sound trade-off between detail preservation and noise suppression,\nmorphological reconstruction is used to filter an observed image. By combining\nthe observed and filtered images, a weighted sum image is generated. Since a\ntight wavelet frame system has sparse representations of an image, it is\nemployed to decompose the weighted sum image, thus forming its corresponding\nfeature set. Taking it as data for clustering, we present an improved FCM\nalgorithm by imposing an $\\ell_0$ regularization term on the residual between\nthe feature set and its ideal value, which implies that the favorable\nestimation of the residual is obtained and the ideal value participates in\nclustering. Spatial information is also introduced into clustering since it is\nnaturally encountered in image segmentation. Furthermore, it makes the\nestimation of the residual more reliable. To further enhance the segmentation\neffects of the improved FCM algorithm, we also employ the morphological\nreconstruction to smoothen the labels generated by clustering. Finally, based\non the prototypes and smoothed labels, the segmented image is reconstructed by\nusing a tight wavelet frame reconstruction operation. Experimental results\nreported for synthetic, medical, and color images show that the proposed\nalgorithm is effective and efficient, and outperforms other algorithms.\n

This article presents a multipath imaging system for thunderstorm developments, wherein data are three-dimensional atmospheric electric-field signals (3DAEFSs) collected with a self-made 3DAEF apparatus (3DAEFA). In this way, thunderstorms are presented in a staged and visual form. To start with, entropy-based intervals are constructed from historical AEF data, to classify denoised AEFS components, according to the entropy value of each component. Furthermore, AEFS time sequences are reconstructed with a reference to whether components within the same entropy-based interval are sequential or not, providing time information for the subsequent clustering-based spatial denoising to thunderstorm point charge coordinates. Finally, predicted value (PV) intervals, which are used to divide and then reconstruct AEFS time periods, are acquired to realize the point charge multipath imaging corresponding to periods, based on the established stacked autoencoder and the extreme gradient boosting (SAE-XGBoost) model. Empirical results demonstrate that the multipath better visualizes the whole process of thunderstorm activities. Comparisons with radar charts further confirm that the proposed system effectively images charge multipaths and provides a valid reference for visual thunderstorm monitoring.