Granular computing with multiple granular layers for brain big data processing

Wang, Guoyin; Ji, Xu

doi:10.1007/s40708-014-0001-z

Cited by 22 publications

(3 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multi-granularity data analysis is an important research content in the field of data mining. It conducts multi-angle and in-depth analysis and processing of data sets based on the idea of multi-granularity, and mines the potential information or knowledge representations in the data sets [57]. Our proposed algorithm uses a multi-granularity learning framework, which can effectively mine the potential overlapping instances of the data set and improve the classification performance of the model.…”

Section: The Proposed Algorithmmentioning

confidence: 99%

Multi-granularity Relabeled Under-sampling Algorithm for Imbalanced Data

Dai¹,

Liu²,

Liu³

2022

Preprint

View full text Add to dashboard Cite

The imbalanced classification problem turns out to be one of the important and challenging problems in data mining and machine learning. The performances of traditional classifiers will be severely affected by many data problems, such as class imbalanced problem, class overlap and noise. When the number of one class in the data set is larger than other classes, class imbalanced problem will inevitably occur. Therefore, many researchers are committed to solving the problem of category imbalance and improving the overall classification performances of the classifier. The Tomek-Link algorithm was only used to clean data when it was proposed. In recent years, there have been reports of combining Tomek-Link algorithm with sampling technique. The Tomek-Link sampling algorithm can effectively reduce the class overlap on data, remove the majority instances that are difficult to distinguish, and improve the algorithm classification accuracy. However, the Tomek-Links under-sampling algorithm only considers the boundary instances that are the nearest neighbors to each other globally and ignores the potential local overlapping instances. When the number of minority instances is small, the undersampling effect is not satisfactory, and the performance improvement of the classification model is not obvious. Therefore, on the basis of Tomek-Link, a multi-granularity relabeled under-sampling algorithm (MGRU) is proposed. This algorithm fully considers the local information of the data set in the local granularity subspace, and detects the local potential overlapping instances in the data set. Then, the overlapped majority instances are eliminated according to the global relabeled index value, which effectively expands the detection range of Tomek-Links. The simulation results show that when we select the optimal global relabeled index value for under-sampling, the classification accuracy and generalization performance of the proposed under-sampling algorithm are significantly better than other baseline algorithms.

show abstract

Section: The Proposed Algorithmmentioning

confidence: 99%

Multi-granularity Relabeled Under-sampling Algorithm for Imbalanced Data

Dai¹,

Liu²,

Liu³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Gacek and Pedrycz [21] developed a general framework for a granular representation of electrocardiogram signals, which shares many common features with the EEG. Wang et al [22] further discussed the potential of this multi-granular information (MGI)-based computing paradigm for brain data. These studies are of great interest and encourage the design of new algorithms to extract more discriminative representations through multigranular data information.…”

Section: Introductionmentioning

confidence: 99%

Decoupling representation learning for imbalanced electroencephalography classification in rapid serial visual presentation task

Fu¹,

Li²,

Li³

et al. 2022

J. Neural Eng.

View full text Add to dashboard Cite

Objective. The class imbalance problem considerably restricts the performance of electroencephalography (EEG) classification in the rapid serial visual presentation (RSVP) task. Existing solutions typically employ re-balancing strategies (e.g. re-weighting and re-sampling) to alleviate the impact of class imbalance, which enhances the classifier learning of deep networks but unexpectedly damages the representative ability of the learned deep features as original distributions become distorted. Approach. In this study, a novel decoupling representation learning (DRL) model, has been proposed that separates the representation learning and classification processes to capture the discriminative feature of imbalanced RSVP EEG data while classifying it accurately. The representation learning process is responsible for learning universal patterns for the classification of all samples, while the classifier determines a better bounding for the target and non-target classes. Specifically, the representation learning process adopts a dual-branch architecture, which minimizes the contrastive loss to regularize the representation space. In addition, to learn more discriminative information from RSVP EEG data, a novel multi-granular information (MGI) based extractor is designed to extract spatial-temporal information. Considering the class re-balancing strategies can significantly promote classifier learning, the classifier was trained with rebalanced EEG data while freezing the parameters of the representation learning process. Main results. To evaluate the proposed method, experiments were conducted on two public datasets and one self-conducted dataset. The results demonstrate that the proposed DRL can achieve state-of-the-art performance for EEG classification in the RSVP task. Significance. This is the first study to focus on the class imbalance problem and propose a generic solution in the RSVP task. Furthermore, multi-granular data was explored to extract more complementary spatial-temporal information. The code is open-source and available at https://github.com/Tammie-Li/DRL.

show abstract

“…Granular computing is a general computation theory for effectively using granules such as classes, clusters, subsets, groups and intervals to build an efficient computational model for complex applications with huge amounts of data, information and knowledge (Zhang et al 2000;Zadeh and Kacprzyk 1999;Pal and Meher 2013;Pedrycz et al 2004;Pedrycz 2002;Bianchi et al 2014;Pedrycz 2013;Wang and Xu 2014). Granulation of information can be an effective way of abstraction to solve problems in a hierarchical fashion (Pedrycz and Song 2011).…”

Section: Introductionmentioning

confidence: 99%

A study of granular computing in the agenda of growth of artificial neural networks

Song

Wang

2016

Granul. Comput.

View full text Add to dashboard Cite

Granular neural networks (GNN) are designed to process complex non-numerical data or the combination of numerical and non-numerical data. The concept of ''granules'' here refers to various data groups which are drawn together by the criteria of similarity or functionality. Granular neural networks are being used in areas of knowledge discovery, pattern recognition, etc. This paper carries out a comprehensive review of articles that involve a comparative study of different types of granular neural networks and their application. This study aims to give useful insight into the capability of granular neural networks.

show abstract

Granular computing with multiple granular layers for brain big data processing

Cited by 22 publications

References 52 publications

Multi-granularity Relabeled Under-sampling Algorithm for Imbalanced Data

Multi-granularity Relabeled Under-sampling Algorithm for Imbalanced Data

Decoupling representation learning for imbalanced electroencephalography classification in rapid serial visual presentation task

A study of granular computing in the agenda of growth of artificial neural networks

Contact Info

Product

Resources

About