Streaming data clustering is a popular research topic in data mining and machine learning. Since streaming data is usually analyzed in data chunks, it is more susceptible to encountering the dynamic cluster imbalance issue. That is, the imbalance ratio (IR) of clusters changes over time, which can easily lead to fluctuations in either the accuracy or the efficiency of streaming data clustering. Therefore, an accurate and efficient streaming data clustering approach is proposed to adapt to the drifting and imbalanced cluster distributions. We first design a self-growth map (SGM) that can automatically arrange neurons on demand according to local distribution, and thus achieve fast and incremental adaptation to the streaming distributions. Since SGM allocates an excess number of density-sensitive neurons to describe the global distribution, it can avoid missing small clusters among imbalanced distributions. We also propose a fast hierarchical merging (HM) strategy to combine the neurons that break up the relatively large clusters. It exploits the maintained SGM to quickly retrieve the intracluster distribution pairs for merging, which circumvents the most laborious global searching. It turns out that the proposed SGM can incrementally adapt to the distributions of new chunks, and the self-growth map-guided hierarchical merging for the imbalanced data clustering (SOHI) approach can quickly explore a true number of imbalanced clusters. Extensive experiments demonstrate that SOHI can efficiently and accurately explore cluster distributions for streaming data.
12 September 2022 in IEEE Transactions on Neural Networks and Learning Systems
Heterogeneous attribute data composed of attributes with different types of values are quite common in a variety of real-world applications. As data annotation is usually expensive, clustering has provided a promising way for processing unlabeled data, where the adopted similarity measure plays a key role in determining the clustering accuracy. However, it is a very challenging task to appropriately define the similarity between data objects with heterogeneous attributes because the values from heterogeneous attributes are generally with very different characteristics. Specifically, numerical attributes are with quantitative values, while categorical attributes are with qualitative values. Furthermore, categorical attributes can be categorized into nominal and ordinal ones according to the order information of their values. To circumvent the awkward gap among the heterogeneous attributes, this article will propose a new dissimilarity metric for cluster analysis of such data. We first study the connections among the heterogeneous attributes and build graph representations for them. Then, a metric is proposed, which computes the dissimilarities between attribute values under the guidance of the graph structures. Finally, we develop a new $k$ -means-type clustering algorithm associated with this proposed metric. It turns out that the proposed method is competent to perform cluster analysis of datasets composed of an arbitrary combination of numerical, nominal, and ordinal attributes. Experimental results show its efficacy in comparison with its counterparts.
Ordinal attribute has all the common characteristics of a nominal one but it differs from the nominal one by having naturally ordered possible values (also called categories interchangeably). In clustering analysis tasks, categorical data composed of both ordinal and nominal attributes (also called mixed-categorical data interchangeably) are common. Under this circumstance, existing distance and similarity measures suffer from at least one of the following two drawbacks: 1) directly treat ordinal attributes as nominal ones, and thus ignore the order information from them and 2) suppose all the attributes are independent of each other, measure the distance between two categories from a target attribute without considering the valuable information provided by the other attributes that correlate with the target one. These two drawbacks may twist the natural distances of attributes and further lead to unsatisfactory clustering results. This article, therefore, presents an entropy-based distance metric that quantifies the distance between categories by exploiting the information provided by different attributes that correlate with the target one. It also preserves the order relationship among ordinal categories during the distance measurement. Since attributes are usually correlated in different degrees, we also define the interdependence between different types of attributes to weight their contributions in forming distances. The proposed metric overcomes the two above-mentioned drawbacks for mixed-categorical data clustering. More important, it conceptually unifies the distances of ordinal and nominal attributes to avoid information loss during clustering. Moreover, it is parameter free, and will not bring extra computational cost compared to the existing state-of-the-art counterparts. Extensive experiments show the superiority of the proposed distance metric.
3 February 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
The success of categorical data clustering generally much relies on the distance metric that measures the dissimilarity degree between two objects. However, most of the existing clustering methods treat the two categorical subtypes, i.e. nominal and ordinal attributes, in the same way when calculating the dissimilarity without considering the relative order information of the ordinal values. Moreover, there would exist interdependence among the nominal and ordinal attributes, which is worth exploring for indicating the dissimilarity. This paper will therefore study the intrinsic difference and connection of nominal and ordinal attribute values from a perspective akin to the graph. Accordingly, we propose a novel distance metric to measure the intra-attribute distances of nominal and ordinal attributes in a unified way, meanwhile preserving the order relationship among ordinal values. Subsequently, we propose a new clustering algorithm to make the learning of intra-attribute distance weights and partitions of data objects into a single learning paradigm rather than two separate steps, whereby circumventing a suboptimal solution. Experiments show the efficacy of the proposed algorithm in comparison with the existing counterparts.
8 March 2024 in IEEE Journal of Biomedical and Health Informatics
The integration of structural magnetic resonance imaging (sMRI) and deep learning techniques is one of the important research directions for the automatic diagnosis of Alzheimer's disease (AD). Despite the satisfactory performance achieved by existing voxel-based models based on convolutional neural networks (CNNs), such models only handle AD-related brain atrophy at a single spatial scale and lack spatial localization of abnormal brain regions based on model interpretability. To address the above limitations, we propose a traceable interpretability model for AD recognition based on multi-patch attention (MAD-Former). MAD-Former consists of two parts: recognition and interpretability. In the recognition part, we design a 3D brain feature extraction network to extract local features, followed by constructing a dual-branch attention structure with different patch sizes to achieve global feature extraction, forming a multi-scale spatial feature extraction framework. Meanwhile, we propose an important attention similarity position loss function to assist in model decision-making. The interpretability part proposes a traceable method that can obtain a 3D ROI space through attention-based selection and receptive field tracing. This space encompasses key brain tissues that influence model decisions. Experimental results reveal the significant role of brain tissues such as the Fusiform Gyrus (FuG) in AD recognition. MAD-Former achieves outstanding performance in different tasks on ADNI and OASIS datasets, demonstrating reliable model interpretability.
8 February 2025 in Expert Systems with Applications