Search

Broad learning system (BLS) is a novel and efficient model, which facilitates representation learning and classification by concatenating feature nodes and enhancement nodes. In spite of the efficient properties, BLS is still suboptimal when facing with imbalance problem. Besides, outliers and noises in imbalanced data remain a challenge for BLS. To address the above issues, in this paper we first propose a weighted BLS, which assigns a weight to each training sample, and adopt a general weighting scheme, which augments the weight of samples from the minority class. To further explore the prior distribution of original data, we design a density based weight generation mechanism to guide the specific weight matrix generation and propose the adaptive weighted broad learning system (AWBLS). This mechanism considers the inter-class and intra-class distance simultaneously in the density calculation. Finally, we propose the incremental weighted ensemble broad learning system (IWEB) by utilizing a progressive mechanism to further improve the stability and robustness of AWBLS. Extensive comparative experiments on 38 real-world data sets verfy that IWEB outperforms most of the imbalance ensemble classification methods. [ABSTRACT FROM AUTHOR]

Electricity theft poses a huge hazard to the economic efficiency of power companies and the safe operation of the power system. Analysis of smart grid data can help to identify abnormal electricity usage patterns of the thieves. However, existing models may suffer from underfitting issues due to the high dimensionality and imbalanced class distribution in the electricity dataset. To address these challenges and improve the performance of electricity theft detection, this study proposes a multi-view detection model based on broad learning system (BLS). First, a new multi-view framework is presented to map the raw power data into different sub-views, thereby reducing redundant electricity data features. Then, an adaptive weighting strategy based on the regional distribution of the data is developed. The optimized sub-views are obtained by considering the sample size and dispersion of the data. Finally, a power theft detection model is constructed by combining the region distribution weighted BLS and the multi-view rotation BLS. Comparative experiments on real-world electricity dataset demonstrate the superiority of our proposed approach. [ABSTRACT FROM AUTHOR]

Imbalance learning has gained more and more attention from researchers. Most of the efforts so far have focused on binary imbalance problems, while there are numerous unresolved multiclass imbalance problems in real-world scenarios. The diversity of data distribution and the poor performance of traditional multiclass classification algorithms present significant challenges for classifying multiclass imbalanced data. This paper proposes a double kernel-based class-specific broad learning system (DKCSBLS) for multi-class imbalance learning. Class-specific penalty coefficients are incorporated into the model to increase the focus on minority classes. Moreover, double kernel mapping mechanism is designed to extract more robust features. Extensive experiments on various real-world datasets demonstrate the superiority of our proposed approach. [ABSTRACT FROM AUTHOR]

Incremental learning algorithms have been developed as an efficient solution for fast remodeling in Broad Learning Systems (BLS) without a retraining process. Even though the structure and performance of broad learning are gradually showing superiority, private data leakage in broad learning systems is still a problem that needs to be solved. Recently, Multiparty Secure Broad Learning System (MSBLS) is proposed to allow two clients to participate training. However, privacy-preserving broad learning across multiple clients has received limited attention. In this paper, we propose a Self-Balancing Incremental Broad Learning System (SIBLS) with privacy protection by considering the effect of different data sample sizes from clients, which allows multiple clients to be involved in the incremental learning. Specifically, we design a client selection strategy to select two clients in each round by reducing the gap in the number of data samples in the incremental updating process. To ensure the security under the participation of multiple clients, we introduce a mediator in the data encryption and feature mapping process. Three classical datasets are used to validate the effectiveness of our proposed SIBLS, including MNIST, Fashion and NORB datasets. Experimental results show that our proposed SIBLS can have comparable performance with MSBLS while achieving better performance than federated learning in terms of accuracy and running time. [ABSTRACT FROM AUTHOR]

Mechanical activities near energy pipelines pose a significant threat to energy transportation safety and energy system supply. The distributed acoustic sensing (DAS) system, which is an emerging intelligent sensing technology, can help to identify threat activities outside the pipeline. However, existing research has not distinguished fine-grained threat conditions because of insufficient information utilization and real-time requirements in the DAS system dataset, resulting in a large number of false alarms and time-consuming training in practice. To address these issues, this study proposes a pipeline radial threat condition recognition model based on multidimensional information fusion and a broad learning system (MIFBLS). First, the signal is preprocessed to improve the signal-to-noise ratio and generate the original features. Then, the extracted multidimensional temporal features are dimensionally reduced through information entropy, and the time–frequency map is fused and extracted based on a pretrained deep module, thereby achieving information fusion. Finally, the BLS incremental learning strategy is adopted to enhance the updating ability of the model and reduce the burden of data increments on the model training. Comparative experiments on a real-world natural gas pipeline dataset demonstrate the effectiveness and efficiency of the proposed method, indicating the potential for real-time monitoring and intelligent identification in pipeline transportation scenarios. [ABSTRACT FROM AUTHOR]