2,979 publications from this institution
Granular computing has been an intense research area over the past two decades, focusing on acquiring, processing, and interpreting information granules. In this study, we focus on the granulation of time series and discover the overall structure of the original time series by clustering the granular time series. During the granulation process, when time series exhibit some trend (up trend, equal trend, or down trend) or consist of a variety of tendencies, the trend is essential to be involved to construct the granular time series. Following the principle of justifiable granularity, we propose to form a series of trend-based information granules to describe the original time series and effectively reduce its dimensionality. Then, the similarity measure between trend-based information granules is provided, and considering the dynamic feature of time-series data, dynamic time warping (DTW) distance is generalized to measure the distance for granular time series. In sum, we show here a novel way of forming trend-based granular time series and the corresponding similarity measure, then based on this, the hierarchical clustering of granular time series is realized. The proposed approach can capture the main essence of time series and help to reduce the computing overhead. Experimental results show that the designed approach can reveal meaningful trend-based information granules, and provide promising clustering results on UCR and real-world datasets.
This study is concerned with a decomposition of fuzzy relations, that is their representation with the aid of a certain number of fuzzy sets. We say that some fuzzy sets decompose an original fuzzy refraction if the sum of their Cartesian products approximate the given fuzzy relation. The theoretical underpinnings of the problem are presented along with some linkages with Boolean matrices (such as a Schein rank). Subsequently, we reformulate the decomposition of fuzzy relations as a problem of numeric optimizing and propose a detailed learning scheme leading to a collection of decomposing fuzzy sets. The role of the decomposition in a general class of data compression problems (including those of image compression and rule-based system condensation) is formulated and discussed in detail.
In this paper, we formulate a qualitative classification model by means of qualitative fuzzy regression preset based fuzzy support vector machine (FQR-FSVM). This new model will make it possible to achieve discrimination of output while characterizing membership for each class in terms of multi-dimensional qualitative inputs (attributes). Moreover, the new model will largely shorten the computing time especially for large database by using linear preset of fuzzy qualitative regression classifier to limit the non-linear classification region.
<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> In a Web-oriented society, organization, retrieval, and classification of digital images have become one of the major endeavors. In this paper, we study the mechanisms of fuzzy clustering and fuzzy clustering with partial supervision in the analysis and classification of images. It is demonstrated that the main features of fuzzy clustering become essential in revealing the structure in a collection of images and supporting their classification. The discussed operational framework of fuzzy clustering is realized by means of fuzzy c-means (FCM). When dealing with the mode of partial supervision, we augment an original objective function guiding the clustering process by an additional component expressing a level of coincidence between the membership degrees produced by the FCM and class allocation supplied by the user(s). The study also contrasts the use of the technology of fuzzy sets in image clustering with other approaches studied in this area. A suite of experiments deals with two collections of images, namely, Columbia object image library (COIL-20) and a database composed of 2000 outdoor images. </para>
Crowdsourcing provides a practical approach to obtaining annotated data for data-hungry deep models. Due to its simplicity and practicality, simultaneously learning the annotation correction mechanism and the target classifier is widely studied and applied. Existing work has improved performance from the annotator and annotation process modeling perspective. However, the instance representation, which most directly affects model training, has been neglected. In this work, we investigate contrastive representation to improve learning from crowds. Specifically, we first sample confident instances and positive pairs using the pre-trained representation and human annotations. Then, we extend the supervised contrastive loss to obtain a noise-tolerant version that supports continuous consistency between labels. After that, we leverage the learned representations to train the classifier and annotator parameters. The process is generally designed as an end-to-end framework, CrowdCons, compatible with existing crowdsourcing models. Our approach is evaluated on three real-world crowdsourcing datasets; LabelMe, CIFAR10-H and Music. The experimental results show that it can significantly improve prediction accuracy, and the case study demonstrates the robustness of the model regarding noisy annotations.
Provides an abstract of the presentation and a brief professional biography of the presenter. The complete presentation was not made available for publication as part of the conference proceedings.
In order to realize stable electricity generation, nuclear power plant (NPP) generators are evaluated in their performance of generated output power in term of quality and quantity.Therefore, the evaluation is realized on the basis of several influential factors, which have to be analyzed via the exploitation of heterogeneous data sets obtained from scattered locations and different types of sources.In this paper, we stress the pivotal role of extended fuzzy switching regression analysis in handling this type of data, which come from real world of the NPPs industry.The key objective of this study is to implement the enhancement of a convex hull approach in the fuzzy switching regression analysis process which can be viewed as an intelligent data analysis (IDA) approach.This approach is concerned with the effective combination of fuzzy sets theory with the analysis of large amounts of online data.For deploying the multisource data problem, the fuzzy switching repression analysis is developed as an IDA by enhancing a fuzzy regression analysis based on convex hull, specifically Beneath-Beyond algorithm.The selected IDA becomes a potential analysis vehicle to successfully reduce the computing time as well as minimize the computational complexity.It is shown that the proposed approach becomes an efficient vehicle for the evaluation of produced output flow by NPPs.The study offers an interesting and practically appealing alterative platform to evaluate the quality and quantity of produced output flow of NPPs.
