Search

In this paper, we improve the broad learning system (BLS) by speeding up the incremental learning for added inputs. We propose an efficient implementation for a step that is in the pseudoinverse computation of a partitioned matrix, to reduce the computational complexity. The proposed efficient implementation has two different forms for the cases of q > k and q ≤ k , respectively, where q and k denote the number of additional training samples and the total number of nodes, respectively. The proposed implementation for q > k utilizes the inverse of a sum of matrices to compute only a k × k matrix inverse, instead of a q × q matrix inverse in the original implementation, and the corresponding speedup for the matrix inversion operation in the number of floating-point operations is 1 2 (q / k) 3 . Moreover, it also speeds up two relevant matrix multiplication operations in the original implementation. On the other hand, the proposed implementation for q ≤ k speeds up one matrix multiplication operation in the original implementation. The numerical simulations show that both the proposed and original implementations always achieve the same testing accuracy. On the Modified National Institute of Standards and Technology dataset, the speedups of the proposed efficient BLS implementation over the original BLS implementation in total training time are 1.35–1.57 when q > k and 1.09–1.13 when q < k , while on the NYU object recognition benchmark dataset, the speedups are 1.10–1.35 when q > k and 1.07–1.09 when q < k. [ABSTRACT FROM AUTHOR]

Although multimodal physiological data from the central and peripheral nervous systems can objectively respond to human emotional states, the individual differences caused by non-stationary and low signal-to-noise properties bring several challenges to cross-subject emotion recognition tasks. Many previous studies usually focused on learning high correlation information between different modalities, which easily leads to incomplete descriptions of different physiological signals and difficulties in aligning critical emotional information. To tackle these challenges, this paper proposes a novel multimodal emotion recognition model for improving the generalization performance to unseen target domain subjects, termed Completeness-induced Adaptative Broad Learning (CiABL). The proposed CiABL can gradely explore the completeness modality representation that encompasses both modality-relevant and modality-independent information, avoiding the loss of performance due to spurious correlations from different modalities. Subsequently, a well-designed weighted representation distribution alignment mechanism of CiABL can appropriately align the marginal and conditional distributions to reduce the influences of individual differences greatly. Extensive experiments on the SEED and SEED-FRA datasets demonstrate the effectiveness and generalization of the proposed CiABL, which outperforms current state-of-the-art methods. In addition, CiABL can precisely quantify the importance of global features to properly explain the modality contribution and averaged activation patterns of the brain under cross-subject emotion recognition tasks. [ABSTRACT FROM AUTHOR]

Abstract To deal with the highly nonlinear and time-varying characteristics of Batch Process, a model named adaptive stacking approximate kernel based broad learning system is proposed in this paper. This model innovatively introduces the approximate kernel based broad learning system (AKBLS) algorithm and the Adaptive Stacking framework, giving it strong nonlinear fitting ability, excellent generalization ability, and adaptive ability. The Broad Learning System (BLS) is known for its shorter training time for effective nonlinear processing, but the uncertainty brought by its double random mapping results in poor resistance to noisy data and unpredictable impact on performance. To address this issue, this paper proposes an AKBLS algorithm that reduces uncertainty, eliminates redundant features, and improves prediction accuracy by projecting feature nodes into the kernel space. It also significantly reduces the computation time of the kernel matrix by searching for approximate kernels to enhance its ability in industrial online applications. Extensive comparative experiments on various public datasets of different sizes validate this. The Adaptive Stacking framework utilizes the Stacking ensemble learning method, which integrates predictions from multiple AKBLS models using a meta-learner to improve generalization. Additionally, by employing the moving window method—where a fixed-length window slides through the database over time—the model gains adaptive ability, allowing it to better respond to gradual changes in industrial Batch Process. Experiments on a substantial dataset of penicillin simulations demonstrate that the proposed model significantly improves predictive accuracy compared to other common algorithms.

To deal with the highly nonlinear and time-varying characteristics of Batch Process, a model named adaptive stacking approximate kernel based broad learning system is proposed in this paper. This model innovatively introduces the approximate kernel based broad learning system (AKBLS) algorithm and the Adaptive Stacking framework, giving it strong nonlinear fitting ability, excellent generalization ability, and adaptive ability. The Broad Learning System (BLS) is known for its shorter training time for effective nonlinear processing, but the uncertainty brought by its double random mapping results in poor resistance to noisy data and unpredictable impact on performance. To address this issue, this paper proposes an AKBLS algorithm that reduces uncertainty, eliminates redundant features, and improves prediction accuracy by projecting feature nodes into the kernel space. It also significantly reduces the computation time of the kernel matrix by searching for approximate kernels to enhance its ability in industrial online applications. Extensive comparative experiments on various public datasets of different sizes validate this. The Adaptive Stacking framework utilizes the Stacking ensemble learning method, which integrates predictions from multiple AKBLS models using a meta-learner to improve generalization. Additionally, by employing the moving window method—where a fixed-length window slides through the database over time—the model gains adaptive ability, allowing it to better respond to gradual changes in industrial Batch Process. Experiments on a substantial dataset of penicillin simulations demonstrate that the proposed model significantly improves predictive accuracy compared to other common algorithms. [ABSTRACT FROM AUTHOR]

The insufficient generalisation capability of the conventional learning from demonstration (LfD) model necessitates redemonstrations. In addition, retraining the model can overwrite existing knowledge, making it impossible to perform previously acquired skills in new application scenarios. These are not economical and efficient. To address the issues, in this study, a broad learning system (BLS) and probabilistic roadmap (PRM) are integrated with dynamic movement primitive (DMP)-based LfD. Three key innovations are proposed in this paper: (1) segmentation and extended demonstration: a 1D-based topology trajectory segmentation algorithm (1D-SEG) is designed to divide the original demonstration into several segments. Following the segmentation, a Gaussian probabilistic roadmap (G-PRM) is proposed to generate an extended demonstration that retains the geometric features of the original demonstration. (2) DMP modelling and incremental learning updating: BLS-based incremental learning for DMP (Bi-DMP) is performed based on the constructed DMP and extended demonstration. With this incremental learning approach, the DMP is capable of self-updating in response to task demands, preserving previously acquired skills and updating them without training from scratch. (3) Electric vehicle (EV) battery disassembly case study: this study developed a solution suitable for EV battery disassembly and established a decommissioned battery disassembly experimental platform. Unscrewing nuts and battery cell removal are selected to verify the effectiveness of the proposed algorithms based on the battery disassembly experimental platform. In this study, the effectiveness of the algorithms designed in this paper is measured by the success rate and error of the task execution. In the task of unscrewing nuts, the success rate of the classical DMP is 57.14% and the maximum error is 2.760 mm. After the optimisation of 1D-SEG, G-PRM, and Bi-DMP, the success rate of the task is increased to 100% and the maximum error is reduced to 1.477 mm. [ABSTRACT FROM AUTHOR]

Physiological signals, such as EEG and eye movements, have emerged as promising research topics in emotion recognition due to their inherent advantages of objectivity, high recognition accuracy, and cost-effectiveness. However, most existing methods for fusing EEG and eye movement signals use concatenation or weighted summation, which may lead to information loss and limited ability to resist noise. To tackle this issue, in this paper, we propose a Coordinated-representation Decision Fusion Network (CoDF-Net) to efficiently fuse the representation of EEG and eye movement signals. Specifically, CoDF-Net first learns personalized information by maximizing the correlation between modalities. Next, the Decision-level Fusion Broad Learning System (DF-BLS) is developed to construct multiple sub-systems to obtain the final emotional states via the effective decision-making mechanism. To evaluate the performance of the proposed method, subject-dependent and subject-independent experiments are designed on two public datasets. Extensive experiments demonstrate that the proposed method has superior emotion recognition performance over traditional approaches and current state-of-the-art methods. The CoDF-Net achieves 94.09 and 91.62% in the subject-dependent setting and 87.04 and 83.87% in the subject-independent setting on the SEED-CHN and SEED-GER datasets, respectively. Moreover, it is found that the proposed method exhibits a more significant ability to resist noise by adding Gaussian noise with different standard deviations. [ABSTRACT FROM AUTHOR]

Fuzzy broad learning system (FBLS) is a newly proposed fuzzy system, which introduces Takagi–Sugeno fuzzy model into broad learning system. It has shown that FBLS has better nonlinear fitting ability and faster calculation speed than the most of fuzzy neural networks proposed earlier. At the same time, compared to other fuzzy neural networks, FBLS has fewer rules and lower cost of training time. However, label errors or missing are prone to appear in large-scale dataset, which will greatly reduce the performance of FBLS. Therefore, how to use limited label information to train a powerful classifier is an important challenge. In order to address this problem, we introduce Mean-Teacher model for the fuzzy broad learning system. We use the Mean-Teacher model to rebuild the weights of the output layer of FBLS, and use the Teacher–Student model to train FBLS. The proposed model is an implementation of semi-supervised learning which integrates fuzzy logic and broad learning system in the Mean-Teacher-based knowledge distillation framework. Finally, we have proved the great performance of Mean-Teacher-based fuzzy broad learning system (MT-FBLS) through a large number of experiments. [ABSTRACT FROM AUTHOR]

Seizure prediction are necessary for epileptic patients. The global spatial interactions among channels, and long-range temporal dependencies play a crucial role in seizure onset prediction. In addition, it is necessary to search for seizure prediction features in a vast space to learn new generalized feature representations. Many previous deep learning algorithms have achieved some results in automatic seizure prediction. However, most of them do not consider global spatial interactions among channels and long-range temporal dependencies together, and only learn the feature representation in the deep space. To tackle these issues, in this study, an novel bi-level programming seizure prediction model, B2-ViT Net, is proposed for learning the new generalized spatio-temporal long-range correlation features, which can characterize the global interactions among channels in spatial, and long-range dependencies in temporal required for seizure prediction. In addition, the proposed model can comprehensively learn generalized seizure prediction features in a vast space due to its strong deep and broad feature search capabilities. Sufficient experiments are conducted on two public datasets, CHB-MIT and Kaggle datasets. Compared with other existing methods, our proposed model has shown promising results in automatic seizure prediction tasks, and provides a certain degree of interpretability.

Seizure prediction are necessary for epileptic patients. The global spatial interactions among channels, and long-range temporal dependencies play a crucial role in seizure onset prediction. In addition, it is necessary to search for seizure prediction features in a vast space to learn new generalized feature representations. Many previous deep learning algorithms have achieved some results in automatic seizure prediction. However, most of them do not consider global spatial interactions among channels and long-range temporal dependencies together, and only learn the feature representation in the deep space. To tackle these issues, in this study, an novel bi-level programming seizure prediction model, B2-ViT Net, is proposed for learning the new generalized spatio-temporal long-range correlation features, which can characterize the global interactions among channels in spatial, and long-range dependencies in temporal required for seizure prediction. In addition, the proposed model can comprehensively learn generalized seizure prediction features in a vast space due to its strong deep and broad feature search capabilities. Sufficient experiments are conducted on two public datasets, CHB-MIT and Kaggle datasets. Compared with other existing methods, our proposed model has shown promising results in automatic seizure prediction tasks, and provides a certain degree of interpretability. [ABSTRACT FROM AUTHOR]

During subway tunnel construction, the consumed time for each ring (unit of construction progress) is highly dependent on objective factors such as geological conditions and shield performances, as well as subjective reasons including workers' proficiency and contractors' management skills. It is nontrivial to score each ring's efficiency from an objective angle, so that workers and contractors can receive fair evaluations. In this paper, a scoring method driven by construction big data is proposed. First, to resolve the high-dimensionality problem, a Gaussian mixture model (GMM) was employed to cluster rings of similar conditions in a probabilistic style so that detailed information can be retained. Second, the standard time to finish one ring was analyzed, so that each ring can be labeled as fail or pass, and our task can be considered as a classification problem. Third, for each cluster, a broad learning system (BLS) was developed as a classifier due to its advantages of fast computation and incremental learning. Finally, the BLS was trained with real tunneling data of 23,822 rings, and then scorecards were developed, where results of validation and statistical tests suggested that our method outperforms conventional ones. Feedback from the subway company and two compared contractors suggested that the proposed method is fair and practical, and it could reveal management problems that were easily overlooked. For subway shield tunnels, this study proposes a construction progress scoring method driven by big data for subway companies to evaluate the performance of each construction unit, e.g., each ring of the shield tunnel is treated as a sample analysis. First, in view of the difficulty of many geological types and risk variables, the Gaussian mixture method is used to classify the samples and obtain probability that each ring belongs to a certain geological type. Statistical analysis is used to calculate the shield standard time of each geological type, so that the time interval of pass can be determined. Second, a broad learning model with low calculation and updating cost is constructed to fit the mapping relationship between geological factors and construction progress. With this model, each ring can be scored. Finally, through the model training and verification of 23,822 ring data in seven subway intervals, results suggest that the method is practical. Our method can objectively reflect the work efficiency and management ability of different contractors and workers. In addition, suggestions can be elicited to improve the management level of construction units. [ABSTRACT FROM AUTHOR]

The heterogeneous unmanned system, which is composed of unmanned aerial vehicles (UAV) and unmanned ground vehicles (UGV), has been broadly applied in many domains. Collaborative fault diagnosis (CFD) among UAVs and UGVs has become a key technology in these unmanned systems. However, collaborative fault diagnosis in unmanned systems faces the challenges of the dynamic environment and limited communication bandwidth. This paper proposes an event-triggered collaborative fault diagnosis framework for the UAV–UGV system. The framework aims to achieve autonomous fault monitoring and cooperative diagnosis among unmanned systems, thus enhancing system security and reliability. Firstly, we propose a fault trigger mechanism based on broad learning systems (BLS), which utilizes sensor data to accurately detect and identify faults. Then, under the dynamic event triggering mechanism, the network communication topology between the UAV–UGV system and BLS is used to achieve cooperative fault diagnosis. To validate the effectiveness of our proposed scheme, we conduct experiments on a software-in-the-loop (SIL) simulation platform. The experimental results demonstrate that our method achieves high diagnosis accuracy for the UAV–UGV system.

The insufficient generalisation capability of the conventional learning from demonstration (LfD) model necessitates redemonstrations. In addition, retraining the model can overwrite existing knowledge, making it impossible to perform previously acquired skills in new application scenarios. These are not economical and efficient. To address the issues, in this study, a broad learning system (BLS) and probabilistic roadmap (PRM) are integrated with dynamic movement primitive (DMP)-based LfD. Three key innovations are proposed in this paper: (1) segmentation and extended demonstration: a 1D-based topology trajectory segmentation algorithm (1D-SEG) is designed to divide the original demonstration into several segments. Following the segmentation, a Gaussian probabilistic roadmap (G-PRM) is proposed to generate an extended demonstration that retains the geometric features of the original demonstration. (2) DMP modelling and incremental learning updating: BLS-based incremental learning for DMP (Bi-DMP) is performed based on the constructed DMP and extended demonstration. With this incremental learning approach, the DMP is capable of self-updating in response to task demands, preserving previously acquired skills and updating them without training from scratch. (3) Electric vehicle (EV) battery disassembly case study: this study developed a solution suitable for EV battery disassembly and established a decommissioned battery disassembly experimental platform. Unscrewing nuts and battery cell removal are selected to verify the effectiveness of the proposed algorithms based on the battery disassembly experimental platform. In this study, the effectiveness of the algorithms designed in this paper is measured by the success rate and error of the task execution. In the task of unscrewing nuts, the success rate of the classical DMP is 57.14% and the maximum error is 2.760 mm. After the optimisation of 1D-SEG, G-PRM, and Bi-DMP, the success rate of the task is increased to 100% and the maximum error is reduced to 1.477 mm.

Landslides are common and highly destructive geological hazards that pose significant threats to both human lives and property on a global scale every year. In this study, a novel ensemble broad learning system (BLS) was proposed for evaluating landslide susceptibility in Taiyuan City, Northern China. Meanwhile, ensemble learning models based on the classification and regression tree (CART) and support vector machine (SVM) algorithms were applied for a comparison with the BLS-AdaBoost model. Firstly, in this study, a grand total of 114 landslide locations were identified, which were randomly divided into two parts, namely 70% for model training and the remaining 30% for model validation. Twelve landslide conditioning factors were selected for mapping landslide susceptibility. Subsequently, three models, namely CART-AdaBoost, SVM-AdaBoost and BLS-AdaBoost, were constructed and used to map landslide susceptibility. The frequency ratio (FR) was used to assess the relationship between landslides and different influencing factors. Finally, the three models were validated and compared on the basis of both statistical-based evaluations and ROC curve-based evaluations. The results showed that the integrated model with BLS as the base learner achieved the highest AUC value of 0.889, followed by the integrated models that used CART (AUC = 0.873) and SVM (AUC = 0.846) as the base learners. In general, the BLS-based integrated learning methods are effective for evaluating landslide susceptibility. Currently, the application of BLS and the integrated BLS model for evaluating landslide susceptibility is limited. This study is one of the first efforts to use BLS and the integrated BLS model for evaluating landslide susceptibility. BLS and its improvements have the potential to provide a more powerful approach to assess landslide susceptibility. [ABSTRACT FROM AUTHOR]

Intelligent fault diagnosis (IFD) plays an indispensable role in protecting machinery from catastrophic accidents. Existing IFD methods are mainly developed in the framework of one-time learning. Therefore, they work under the hypothesis of complete dataset. Nevertheless, it is unrealistic to gain the complete dataset of machinery faults at once. More practically, new data will be progressively acquired over time. Therefore, it is urgently required to develop the incremental learning (IL) capabilities for IFD models to learn new knowledge continually from new data. For this purpose, this study proposes an improved broad learning system (IBLS) for lifelong learning IFD. Firstly, the initial IBLS is constructed based on the original broad learning system (BLS). Then, the IL capabilities of the IBLS are developed for three scenarios: increasing fault samples, increasing fault modes, and increasing running conditions. Based on these IL capabilities, the IBLS can be progressively updated to learn more and more diagnosis functions. Finally, the effectiveness of the proposed IBLS is verified using three experiments of high-speed train bearing, disc component, and Case Western Reserve University bearing. The results show that the IBLS is capable of learning continually new knowledge from new data. Besides, the diagnosis accuracy of the IBLS is 12.45%, 7.84%, and 5.10% higher than that of the original BLS in the three case studies. The satisfying results prove that the proposed IBLS is a useful method to solve the lifelong learning IFD problem. • An improved broad learning system (IBLS) is developed. • An IBLS based lifelong learning intelligent diagnosis framework is proposed. • Three case studies are carried out for validations. [ABSTRACT FROM AUTHOR]

As one of the fastest-growing new energy sources, wind power technology has attracted widespread attention from all over the world. In order to improve the quality of wind power generation, wind speed prediction is an indispensable task. In this paper, an error correction-based Variational Mode Decomposition and Broad Learning System (VMD-BLS) hybrid model is proposed for wind speed prediction. First, the wind speed is decomposed into multiple components by the VMD algorithm, and then an ARMA model is established for each component to find the optimal number of sequence divisions. Second, the BLS model is used to predict each component, and the prediction results are summed to obtain the wind speed forecast value. However, in some traditional methods, there is always time lag, which will reduce the forecast accuracy. To deal with this, a novel error correction technique is developed by utilizing BLS. Through verification experiment with actual data, it proves that the proposed method can reduce the phenomenon of prediction lag, and can achieve higher prediction accuracy than traditional approaches, which shows our method's effectiveness in practice. [ABSTRACT FROM AUTHOR]

In actual industrial application scenarios, noise pollution makes it difficult to extract fault features accurately via conventional methods. A novel method for rolling bearing fault diagnosis combining a convolutional neural network (CNN), an attention mechanism for a squeeze-and-excitation network (SENet) module and a broad learning system (BLS) is proposed (SECNN–BLS). The one-dimensional bearing vibration signal is processed by using multiple short-time Fourier transforms (STFT); the two-dimensional image in the time-frequency domain is used as the model input. In the CNN fault feature extraction process, SENet is introduced to replace the CNN convolution layer, and global information is obtained through the squeeze operation. Excitation operation captures the importance of image channels, assigns weights adaptively to improve the attention on important information and eliminates the interference of irrelevant features without increasing the spatial and temporal complexity. The weighted feature representation is then transferred to the BLS input. The BLS has the characteristics of a flat structure and ridge regression to quickly solve the weights; as a fault classifier, it can save more computing resources and improve the accuracy of the fault classification. The SECNN–BLS fault diagnosis has achieved more than 98% accuracy on the Society for Machinery Failure Prevention Technology (MFPT) dataset. We also demonstrate the excellent performance of SECNN–BLS in a noisy environment. [ABSTRACT FROM AUTHOR]

With the vigorous development of Industry 4.0, industrial Big Data has turned into the core element of the Industrial Internet of Things. As one of the most fundamental and indispensable components in industrial cyber-physical systems (CPS), intelligent anomaly detection is still an essential and challenging issue. However, with the development of the network, there may exist unknown types of attacks, which are difficult to collect. Facing one-class industrial intrusion detection scenario that the collected training data only includes normal state, the one-class broad learning system (OCBLS) and the stacked OCBLS (ST-OCBLS) algorithms are developed. Benefiting from the characteristics of BLS, our proposed approaches retain the advantage of efficient training process. Moreover, the high-level hidden features of the network traffic data can be learned through the progressive encoding and decoding mechanism in ST-OCBLS. Extensive comparative experiments on several real-world intrusion detection tasks are carried out to demonstrate that our proposed methods have competitive performance and high efficiency in the face of complex network data and diversified types of intrusions. Overall, this article provides a new alternative solution for network intrusion detection in Industry 4.0. [ABSTRACT FROM AUTHOR]

As the controller parameter adjustment process is simplified significantly by using learning algorithms, the studies about learning-based control attract a lot of interest in recent years. This article focuses on the intelligent servo control problem using learning from desired demonstrations. Compared with the previous studies about the learning-based servo control, a control policy using the broad learning system (BLS) is developed and first applied to a microrobotic system, since the advantages of the BLS, such as simple structure and no-requirement for retraining when new demos’ data is provided. Then, the Lyapunov theory is skillfully combined with the complex learning algorithm to derive the controller parameters’ constraints. Thus, the final control policy not only can obtain the movement skills of the desired demonstrations but also have the strong ability of generalization and error convergence. Finally, simulation and experimental examples verify the effectiveness of the proposed strategy using MATLAB and a microswimmer trajectory tracking system. [ABSTRACT FROM AUTHOR]

With the development of urbanization, the hourly PM2.5 concentration in the air is constantly changing. In order to improve the accuracy of PM2.5 prediction, a prediction model based on the Classification and Regression Tree (CART) and Broad Learning System (BLS) was constructed. Firstly, the CART algorithm was used to segment the dataset in a hierarchical way to obtain a subset with similar characteristics. Secondly, the BLS model was trained by using the data of each subset, and the validation error of each model was minimized by adjusting the window number of the mapping layer in the BLS network. Finally, for each leaf in the tree, the global BLS model and the local BLS model on the path from the root node to the leaf node are compared, and the model with the smallest error is selected. The data collected in this paper come from the Chine Meteorological Historical Data website. We selected historical data from the Huaita monitoring station in Xuzhou city for experimental analysis, which included air pollutant content and meteorological data. Experimental results show that the prediction effect of the CART–BLS model is better than that of RF, V-SVR, and seasonal BLS models. [ABSTRACT FROM AUTHOR]

The broad learning system (BLS) has been identified as an important research topic in machine learning. However, the typical BLS suffers from poor robustness for uncertainties because of its characteristic of the deterministic representation. To overcome this problem, a type-2 fuzzy BLS (FBLS) is designed and analyzed in this article. First, a group of interval type-2 fuzzy neurons was used to replace the feature neurons of BLS. Then, the representation of BLS can be improved to obtain good robustness. Second, a fuzzy pseudoinverse learning algorithm was designed to adjust the parameter of type-2 FBLS. Then, the proposed type-2 FBLS was able to maintain the fast computational nature of BLS. Third, a theoretical analysis on the convergence of type-2 FBLS was given to show the computational efficiency. Finally, some benchmark and practical problems were used to test the merits of type-2 FBLS. The experimental results indicated that the proposed type-2 FBLS can achieve outstanding performance. [ABSTRACT FROM AUTHOR]

The broad learning system (BLS) is an algorithm that facilitates feature representation learning and data classification. Although weights of BLS are obtained by analytical computation, which brings better generalization and higher efficiency, BLS suffers from two drawbacks: 1) the performance depends on the number of hidden nodes, which requires manual tuning, and 2) double random mappings bring about the uncertainty, which leads to poor resistance to noise data, as well as unpredictable effects on performance. To address these issues, a kernel-based BLS (KBLS) method is proposed by projecting feature nodes obtained from the first random mapping into kernel space. This manipulation reduces the uncertainty, which contributes to performance improvements with the fixed number of hidden nodes, and indicates that manually tuning is no longer needed. Moreover, to further improve the stability and noise resistance of KBLS, a progressive ensemble framework is proposed, in which the residual of the previous base classifiers is used to train the following base classifier. We conduct comparative experiments against the existing state-of-the-art hierarchical learning methods on multiple noisy real-world datasets. The experimental results indicate our approaches achieve the best or at least comparable performance in terms of accuracy. [ABSTRACT FROM AUTHOR]

In recent years, the appearance of the broad learning system (BLS) is poised to revolutionize conventional artificial intelligence methods. It represents a step toward building more efficient and effective machine-learning methods that can be extended to a broader range of necessary research fields. In this survey, we provide a comprehensive overview of the BLS in data mining and neural networks for the first time, focusing on summarizing various BLS methods from the aspects of its algorithms, theories, applications, and future open research questions. First, we introduce the basic pattern of BLS manifestation, the universal approximation capability, and essence from the theoretical perspective. Furthermore, we focus on BLS’s various improvements based on the current state of the theoretical research, which further improves its flexibility, stability, and accuracy under general or specific conditions, including classification, regression, semisupervised, and unsupervised tasks. Due to its remarkable efficiency, impressive generalization performance, and easy extendibility, BLS has been applied in different domains. Next, we illustrate BLS’s practical advances, such as computer vision, biomedical engineering, control, and natural language processing. Finally, the future open research problems and promising directions for BLSs are pointed out. [ABSTRACT FROM AUTHOR]

This article investigates optimal control problem for a class of discrete-time (DT) nonlinear systems with unknown dynamics. With the help of a broad learning system (BLS), a novel online adaptive dynamic programming (ADP) controller is presented. First, to approximate the unknown system dynamics, an approximator based on BLS is presented. The connection weights are calculated by the data of the system by using the ridge regression algorithm. Then, two BLSs are adopted to approximate the optimal cost function and optimal control law, respectively. The connection weights of these two BLSs are updated using the given weights tuning law at each sampling instant. The proposed optimal controller is proved to ensure that all the system states and estimation errors are uniform ultimate bounded. Finally, simulation examples are carried out to further demonstrate the effectiveness of the proposed BLS-based approximator and optimal controller. [ABSTRACT FROM AUTHOR]

This article investigates the feasibility of applying the broad learning system (BLS) to realize a novel Takagi–Sugeno–Kang (TSK) neuro-fuzzy model, namely a broad learning based dynamic fuzzy inference system (BL-DFIS). It not only improves the accuracy and interpretability of neuro-fuzzy models but also solves the challenging problem that models are incapable of determining the optimal architecture autonomously. BL-DFIS first accomplishes a TSK fuzzy system under the framework of BLS, in which an extreme learning machine auto-encoder is employed to obtain feature representation in a fast and analytical way, and an interpretable linguistic fuzzy rule is integrated into the enhancement node to ensure the high interpretability of the system. Meanwhile, the extended-enhancement unit is designed to achieve the first-order TSK fuzzy system. In addition, a dynamic incremental learning algorithm with internal pruning and updating mechanism is developed for the learning of BL-DFIS, which enables the system to automatically assemble the optimal structure to obtain a compact rule base and an excellent classification performance. Experiments on benchmark datasets demonstrate that the proposed BL-DFIS can achieve a better classification performance than some state-of-the-art nonfuzzy and neuro-fuzzy methods, simultaneously using the most parsimonious model structure. [ABSTRACT FROM AUTHOR]

Landslides are common and highly destructive geological hazards that pose significant threats to both human lives and property on a global scale every year. In this study, a novel ensemble broad learning system (BLS) was proposed for evaluating landslide susceptibility in Taiyuan City, Northern China. Meanwhile, ensemble learning models based on the classification and regression tree (CART) and support vector machine (SVM) algorithms were applied for a comparison with the BLS-AdaBoost model. Firstly, in this study, a grand total of 114 landslide locations were identified, which were randomly divided into two parts, namely 70% for model training and the remaining 30% for model validation. Twelve landslide conditioning factors were selected for mapping landslide susceptibility. Subsequently, three models, namely CART-AdaBoost, SVM-AdaBoost and BLS-AdaBoost, were constructed and used to map landslide susceptibility. The frequency ratio (FR) was used to assess the relationship between landslides and different influencing factors. Finally, the three models were validated and compared on the basis of both statistical-based evaluations and ROC curve-based evaluations. The results showed that the integrated model with BLS as the base learner achieved the highest AUC value of 0.889, followed by the integrated models that used CART (AUC = 0.873) and SVM (AUC = 0.846) as the base learners. In general, the BLS-based integrated learning methods are effective for evaluating landslide susceptibility. Currently, the application of BLS and the integrated BLS model for evaluating landslide susceptibility is limited. This study is one of the first efforts to use BLS and the integrated BLS model for evaluating landslide susceptibility. BLS and its improvements have the potential to provide a more powerful approach to assess landslide susceptibility.

As one of the fastest-growing new energy sources, wind power technology has attracted widespread attention from all over the world. In order to improve the quality of wind power generation, wind speed prediction is an indispensable task. In this paper, an error correction-based Variational Mode Decomposition and Broad Learning System (VMD-BLS) hybrid model is proposed for wind speed prediction. First, the wind speed is decomposed into multiple components by the VMD algorithm, and then an ARMA model is established for each component to find the optimal number of sequence divisions. Second, the BLS model is used to predict each component, and the prediction results are summed to obtain the wind speed forecast value. However, in some traditional methods, there is always time lag, which will reduce the forecast accuracy. To deal with this, a novel error correction technique is developed by utilizing BLS. Through verification experiment with actual data, it proves that the proposed method can reduce the phenomenon of prediction lag, and can achieve higher prediction accuracy than traditional approaches, which shows our method’s effectiveness in practice.

Sentiment analysis uses a series of automated cognitive methods to determine the author’s or speaker’s attitudes toward an expressed object or text’s overall emotional tendencies. In recent years, the growing scale of opinionated text from social networks has brought significant challenges to humans’ sentimental tendency mining. The pretrained language model designed to learn contextual representation achieves better performance than traditional learning word vectors. However, the existing two basic approaches for applying pretrained language models to downstream tasks, feature-based and fine-tuning methods, are usually considered separately. What is more, different sentiment analysis tasks cannot be handled by the single task-specific contextual representation. In light of these pros and cons, we strive to propose a broad multitask transformer network (BMT-Net) to address these problems. BMT-Net takes advantage of both feature-based and fine-tuning methods. It was designed to explore the high-level information of robust and contextual representation. Primarily, our proposed structure can make the learned representations universal across tasks via multitask transformers. In addition, BMT-Net can roundly learn the robust contextual representation utilized by the broad learning system due to its powerful capacity to search for suitable features in deep and broad ways. The experiments were conducted on two popular datasets of binary Stanford Sentiment Treebank (SST-2) and SemEval Sentiment Analysis in Twitter (Twitter). Compared with other state-of-the-art methods, the improved representation with both deep and broad ways is shown to achieve a better $F1$ -score of 0.778 in Twitter and accuracy of 94.0% in the SST-2 dataset, respectively. These experimental results demonstrate the abilities of recognition in sentiment analysis and highlight the significance of previously overlooked design decisions about searching contextual features in deep and broad spaces. [ABSTRACT FROM AUTHOR]

Prognostics and health management (PHM) are gradually being applied to production management processes as industrial production is gradually undergoing a transformation, turning into intelligent production and leading to increased demands on the reliability of industrial equipment. Remaining useful life (RUL) prediction plays a pivotal role in this process. Accurate prediction results can effectively provide information about the condition of the equipment on which intelligent maintenance can be based, with many methods applied to this task. However, the current problems of inadequate feature extraction and poor correlation between prediction results and data still affect the prediction accuracy. To overcome these obstacles, we constructed a new fusion model that extracts data features based on a broad learning system (BLS) and embeds long short-term memory (LSTM) to process time-series information, named as the B-LSTM. First, the LSTM controls the transmission of information from the data to the gate mechanism, and the retained information generates the mapped features and forms the feature nodes. Then, the random feature nodes are supplemented by an activation function that generates enhancement nodes with greater expressive power, increasing the nonlinear factor in the network, and eventually the feature nodes and enhancement nodes are jointly connected to the output layer. The B-LSTM was experimentally used with the C-MAPSS dataset and the results of comparison with several mainstream methods showed that the new model achieved significant improvements. [ABSTRACT FROM AUTHOR]

The broad learning system (BLS) is an emerging flat network, which has demonstrated its outstanding performance in classification and regression problems. The regularization plays an important role in the performance of the BLS. In real applications, since the BLS network is usually expanded dynamically, a predetermined regularization parameter may reduce the performance of the network. Using a fixed regularization in some cases, the classification accuracy of the BLS decreases dramatically when we expand the network. To alleviate this problem, we propose a method that automatically finds appropriate regularization parameters for different datasets, which is based on the weighted generalized cross-validation (WGCV). The experimental results indicate that the WGCV method improves the performance of the BLS, and alleviates the accuracy decrease of the incremental learning algorithm. [ABSTRACT FROM AUTHOR]

As a classification model, a broad learning system is widely used in wind turbine fault diagnosis. However, the setting of hyperparameters for the models directly affects the classification accuracy of the models and it generally relies on practical experience and prior knowledge. In order to effectively solve the problem, the parameters of the broad learning system such as the number of feature nodes, the number of enhancement nodes, and the number of mapped features layer were optimized by the improved pelican optimization algorithm, and a classification model was built based on the broad learning system optimized by the improved pelican optimization algorithm. The classification accuracy of the proposed model was the highest and reached 98.75%. It is further shown that compared with the support vector machine, deep belief networks, and broad learning system models optimized by particle swarm optimization algorithm, the proposed model effectively improves the accuracy of wind turbine fault diagnosing. [ABSTRACT FROM AUTHOR]

In this paper, we propose an efficient algorithm to accelerate the existing Broad Learning System (BLS) algorithm for new added nodes. The existing BLS algorithm computes the output weights from the pseudoinverse with the ridge regression approximation, and updates the pseudoinverse iteratively. As a comparison, the proposed BLS algorithm computes the output weights from the inverse Cholesky factor of the Hermitian matrix in the calculation of the pseudoinverse, and updates the inverse Cholesky factor efficiently. Since the Hermitian matrix in the definition of the pseudoinverse is smaller than the pseudoinverse, the proposed BLS algorithm can reduce the computational complexity, and usually requires less than $\frac {2}{3}$ of complexities with respect to the existing BLS algorithm. Our experiments on the Modified National Institute of Standards and Technology (MNIST) dataset show that the speedups in accumulative training time and each additional training time of the proposed BLS over the existing BLS are 24.81%~ 37.99% and 36.45%~ 58.96%, respectively, and the speedup in total training time is 37.99%. In our experiments, the proposed BLS and the existing BLS both achieve the same testing accuracy when the tiny differences (≤ 0.05%) caused by the numerical errors are neglected, and the above-mentioned tiny differences and numerical errors become zeroes and ignorable, respectively, when the ridge parameter is not too small.

Alzheimer's Disease (AD) is a neurodegenerative disease of unknown etiology that progresses progressively and is currently incurable. It is more common in the elderly that seriously affects the physical and mental health of patients, thus early detection is very important for the prevention of AD progression. By using PCANet and Broad Learning System (BLS), we propose a novel method to identify Alzheimer's patients according to the clinical symptom of hippocampal atrophy, which is the most important indicator of AD. T1-weighted magnetic resonance images (MRIs) are used in this study, containing 207 patients with AD, 209 patients with mild cognitive impairment (MCI) and 109 cognitively normal (CN) cohorts from ADNI dataset. The left and right hippocampus are segmented from MRI at the first step, then the PACNet is applied to extract features from these images, finally the BLS is used to distinguish the different types of patients. Compared with the traditional machine learning methods, PCANet is able to extract the most informative features inside pictures effectively, while BLS can reach over 95% accuracy rate with lower time consuming. Experimental results have revealed that our method improves the performance of computer-aided diagnosis of Alzheimer's disease in both accuracy and speed of classification task. [ABSTRACT FROM AUTHOR]

This article presents a novel health management method of the dry-type transformer to diagnose the early unhealthy behavior and evaluate the transformer's health condition by health score. The health condition diagnosis implemented by a proposed dynamic-weighted-feed-back broad learning system (BLS) (DW-FB-BLS) method, which helps to determine the BLS network structure effectively, and adjusts the weight of features in the online application to avoid reduction of accuracy caused by concept drift. Then, a rational score rule is set to evaluate the health condition of the dry-type transformer by health score, which allows intuitive presentation and preservation of transformer's health condition over a long period. Finally, the effectiveness and validity of the proposed method are verified based on the real field data of dry-type transformer. Satisfactory results for unhealthy behavior diagnosis and health evaluation are obtained, it shows that health management of this article can reflect the real health condition of dry-type transformer appropriately. [ABSTRACT FROM AUTHOR]

A fast architecture for real-time (i.e., minute-based) training of a traffic predictor is studied, based on the so-called broad learning system (BLS) paradigm. The study uses various traffic datasets by the California Department of Transportation, and employs a variety of standard algorithms (LASSO regression, shallow and deep neural networks, stacked autoencoders, convolutional, and recurrent neural networks) for comparison purposes: all algorithms are implemented in MATLAB on the same computing platform. The study demonstrates a BLS training process two-three orders of magnitude faster (tens of seconds against tens-hundreds of thousands of seconds), allowing unprecedented real-time capabilities. Additional comparisons with the extreme learning machine architecture, a learning algorithm sharing some features with BLS, confirm the fast training of least-square training as compared to gradient training. [ABSTRACT FROM AUTHOR]

Hyperspectral images (HSIs) classification have aroused a great deal of attention recently due to their wide range of practical prospects in numerous fields. Spatial-spectral fusion feature is widely used in HSI classification to get better performance. These methods are mostly based on a simple linear addition with the combined hyper-parameter to fuse the spatial and spectral information. It is necessary to fuse the features in a more suitable method. To solve this problem, we propose a novel HSI classification approach based on Hybrid spatial-spectral feature in broad learning system (HSFBLS). First, we employ an adaptive weighted mean filter to obtain spatial feature. Computing the weights of spatial and spectral channels in hybrid module by two BLS and uniting them with a weighted linear function. Then, we fuse the spectral-spatial feature by sparse autoencoder to get weighted fusion feature as the feature nodes to classify HSI data in BLS. By a two-stage fusion of spatial and spectral information, it can increase the classification accuracy contrast to simple combination. Very satisfactory classification results on typical HSI datasets illustrate the availability of proposed HSFBLS. Moreover, HSFBLS also reduce training time greatly contrast to time-consuming network. [ABSTRACT FROM AUTHOR]

In actual industrial application scenarios, noise pollution makes it difficult to extract fault features accurately via conventional methods. A novel method for rolling bearing fault diagnosis combining a convolutional neural network (CNN), an attention mechanism for a squeeze-and-excitation network (SENet) module and a broad learning system (BLS) is proposed (SECNN–BLS). The one-dimensional bearing vibration signal is processed by using multiple short-time Fourier transforms (STFT); the two-dimensional image in the time-frequency domain is used as the model input. In the CNN fault feature extraction process, SENet is introduced to replace the CNN convolution layer, and global information is obtained through the squeeze operation. Excitation operation captures the importance of image channels, assigns weights adaptively to improve the attention on important information and eliminates the interference of irrelevant features without increasing the spatial and temporal complexity. The weighted feature representation is then transferred to the BLS input. The BLS has the characteristics of a flat structure and ridge regression to quickly solve the weights; as a fault classifier, it can save more computing resources and improve the accuracy of the fault classification. The SECNN–BLS fault diagnosis has achieved more than 98% accuracy on the Society for Machinery Failure Prevention Technology (MFPT) dataset. We also demonstrate the excellent performance of SECNN–BLS in a noisy environment.

The broad learning system (BLS) is designed based on the technology of compressed sensing and pseudo-inverse theory, and consists of feature nodes and enhancement nodes, has been proposed recently. Compared with the popular deep learning structures, such as deep neural networks, BLS has the ability of rapid incremental learning and can remodel the system without the usual tedious retraining process. However, given that BLS is still in its infancy, it still needs analysis, improvements, and verification. In this article, we first analyze the principle of fast incremental learning ability of BLS in depth. Second, in order to provide an in-depth analysis of the BLS structure, according to the novel structure design concept of deep neural networks, we present four brand-new BLS variant networks and their incremental realizations. Third, based on our analysis of the effect of feature nodes and enhancement nodes, a new BLS structure with a semantic feature extraction layer has been proposed, which is called SFEBLS. The experimental results show that SFEBLS and its variants can increase the accuracy rate on the NORB dataset 6.18%, Fashion-MNIST dataset by 3.15%, ORL data by 5.00%, street view house number dataset by 12.88%, and CIFAR-10 dataset by 18.42%, respectively, and the four brand-new BLS variant networks also obviously outperform the original BLS. [ABSTRACT FROM AUTHOR]

Broad Learning System (BLS) has been proven to be one of the most important techniques for classification and regression in machine learning and data mining. BLS directly collects all the features from feature and enhancement nodes as input of the output layer, which neglects vast amounts of redundant information. It usually leads to be inefficient and overfitting. To resolve this issue, we propose sparse regularization-based compact broad learning system (CBLS) framework, which can simultaneously remove redundant nodes and weights. To be more specific, we use group sparse regularization based on ℓ 2 , 1 norm to promote the competition between different nodes and then remove redundant nodes, and a class of nonconvex sparsity regularization to promote the competition between different weights and then remove redundant weights. To optimize the resulting problem of the proposed CBLS, we exploit an efficient alternative optimization algorithm based on proximal gradient method together with computational complexity. Finally, extensive experiments on the classification task are conducted on public benchmark datasets to verify the effectiveness and superiority of the proposed CBLS. [ABSTRACT FROM AUTHOR]

This article presents a new user-independent emotion classification method that classifies four distinct emotions using electroencephalograph (EEG) signals and the broad learning system (BLS). The public DEAP and MAHNOB-HCI databases are used. Just one EEG electrode channel is selected for the feature extraction process. Continuous wavelet transform (CWT) is then utilized to extract the proposed gray-scale image (GSI) feature which describes the EEG brain activation in both time and frequency domains. Finally, the new BLS is constructed for the emotion classification process, which successfully upgrades the efficiency of emotion classification based on EEG brain signals. The experiment results show that the proposed work produces a robust system with high accuracy of approximately 93.1% and training process time of approximately 0.7 s for the DEAP database, as well as, the high average accuracy of approximately 94.4% and training process time of approximately 0.6 s for MAHNOB-HCI database. [ABSTRACT FROM AUTHOR]

Brain–computer interface (BCI) systems based on electroencephalography (EEG) signals have been extensively used in medical practice. To enhance the BCI performance, improving the classification accuracy of EEG signals is the key, which has always been the focus of research and development. In this article, a novel method integrating complex network and broad learning system (BLS) is proposed for visual evoked potential (VEP)-based BCI research. First, systematic VEP-based brain experiments are conducted for obtaining EEG signals, including steady-state VEP (SSVEP) and steady-state motion VEP (SSMVEP). Then, limited penetrable visibility graph (LPVG) and its degree sequence are employed to implement the preliminary feature extraction. All these features are finally fed into a BLS to study and classify the SSVEP and SSMVEP signals, respectively. The classification results show that our LPVG-based BLS can effectively classify VEP-based EEG signals, with average classification accuracy 96.22% for SSVEP and 74.54% for SSMVEP. These results are significantly better than other comparison methods as well as traditional CCA-based methods. All these open up new venues for studying EEG-based BCI systems via the fusion of network science and BLS. [ABSTRACT FROM AUTHOR]

Feature processing is an important step for modeling and can improve the accuracy of machine learning models. Feature extraction methods can effectively extract features from high-dimensional data sets and enhance the accuracy of tasks. However, the performance of feature extraction methods is not stable in low-dimensional data sets. This article extends the broad learning system (BLS) to a framework for constructing robust representations in low-dimensional and small data sets. First, the BLS changed from a supervised prediction method to an ensemble feature extraction method. Second, feature extraction methods instead of random mapping are used to generate mapped features. Third, deep representations, called enhancement features, are learned from the ensemble mapped features. Fourth, data for generating mapped features and enhancement features can be randomly selected. The ensemble of mapped features and enhancement features can provide robust representations to enhance the performance of downstream tasks. A label-based autoencoder (LA) is embedded in the BLS framework as an example to show the effectiveness of the framework. A random LA (RLA) is presented to generate more different features. The experimental results show that the BLS framework can construct robust representations and significantly promote the performance of machine learning models. [ABSTRACT FROM AUTHOR]

Recently, broad learning system (BLS) has been introduced to solve industrial fault diagnosis problems and has achieved impressive performance. As a flat network, BLS enjoys a simple linear structure, which enables BLS to train and update the model efficiently in an incremental manner, and it potentially has better generalization capacity than deep learning methods when training data are limited. The basic BLS is a supervised learning method that requires all the training data to be labeled. However, in many practical industrial scenarios, data labels are usually difficult to obtain. Existing semisupervised variant uses manifold regularization framework to capture the information of unlabeled data, however, such a method will sacrifice the incremental learning capacity of BLS. Considering that in many practical applications, training data are sequentially generated, in this article, an online semisupervised broad learning system (OSSBLS) is proposed for fault diagnosis in these cases. The proposed method not only can efficiently construct and incrementally update the model, but also can take advantage of unlabeled data to improve the model's diagnostic performance. Experimental results on the Tennessee Eastman process and a real-world air compressor working process demonstrate the superiority of OSSBLS in terms of both diagnostic performance and time consumption. [ABSTRACT FROM AUTHOR]

Driver fatigue detection is of great significance for guaranteeing traffic safety and further reducing economic as well as societal loss. In this article, a novel complex network (CN) based broad learning system (CNBLS) is proposed to realize an electroencephalogram (EEG)-based fatigue detection. First, a simulated driving experiment was conducted to obtain EEG recordings in alert and fatigue state. Then, the CN theory is applied to facilitate the broad learning system (BLS) for realizing an EEG-based fatigue detection. The results demonstrate that the proposed CNBLS can accurately differentiate the fatigue state from an alert state with high stability. In addition, the performances of the four existing methods are compared with the results of the proposed method. The results indicate that the proposed method outperforms these existing methods. In comparison to directly using EEG signals as the input of BLS, CNBLS can sharply improve the detection results. These results demonstrate that it is feasible to apply BLS in classifying EEG signals by means of CN theory. Also, the proposed method enriches the EEG analysis methods. [ABSTRACT FROM AUTHOR]

This article proposes a novel regularization deep cascade broad learning system (DCBLS) architecture, which includes one cascaded feature mapping nodes layer and one cascaded enhancement nodes layer. Then, the transformation feature representation is easily obtained by incorporating the enhancement nodes and the feature mapping nodes. Once such a representation is established, a final output layer is constructed by implementing a simple convex optimization model. Furthermore, a parallelization framework on the new method is designed to make it compatible with large-scale data. Simultaneously, an adaptive regularization parameter criterion is adopted under some conditions. Moreover, the stability and error estimate of this method are discussed and proved mathematically. The proposed method could extract sufficient available information from the raw data compared with the standard broad learning system and could achieve compellent successes in image denoising. The experiments results on benchmark datasets, including natural images as well as hyperspectral images, verify the effectiveness and superiority of the proposed method in comparison with the state-of-the-art approaches for image denoising. [ABSTRACT FROM AUTHOR]

Chaotic time series data is extensively applied in financial stocks, climate monitoring, and sea clutter, in which data fusion from various sources and multi-sensor information make accurate predictions of chaotic time series challenging under complex nonlinear conditions. Previous works focus on designing different model frameworks to capture the temporal dependence and extract richer nonlinear features to improve the accuracy of univariate chaotic time series prediction, which ignores the spatial dependence of multivariable. However, in this paper, we argue that spatial correlation among multiple variables is essential to improve the prediction accuracy of chaotic time series. To fill the gap, we innovatively propose a D ynamic A daptive G raph C onvolutional T ransformer with a B road L earning S ystem (DAGCT-BLS), a GCN and Transformer-based model utilizing multivariate spatial dependence for multi-dimensional chaotic time series forecasting. In DAGCT-BLS, the multivariate chaotic time series are reconstructed into the phase space, and the reconstructed data are rapidly feature-extracted using a cascade network BLS with frozen weights to maximize the retention of chaotic properties and nonlinear relationships. Then, the Dynamic Adaptive Graph Convolutional Network (DAGCN) is proposed to capture the spatial correlation among the multiple variables. Finally, improved multi-head attention of the Transformer Encoder is used to capture the temporal dependence of the phase point sequence. Experiments of our proposed model on three datasets (Lorenz, Rossler, and Sea clutter) show that DAGCT-BLS can achieve the best prediction performance and have strong interpretability, and multivariate-based joint modeling of chaotic time series helps to improve the prediction performance. • A novel DAGCT-BLS model is proposed to sovel multi-dimensional chaotic time series forecasting problem, unreported previously. • The multivariate chaotic time series are reconstructed into the phase space, which are rapidly feature-extracted using a cascade network BLS with frozen weights. • Improved multi-head attention is proposed to capture the temporal dependence of the phase point sequence. • DAGCN is proposed to model multivariate spatial relationships dynamically. [ABSTRACT FROM AUTHOR]

Facial beauty prediction (FBP), as a frontier topic in the domain of artificial intelligence regarding anthropology, has witnessed some good results as deep learning technology progressively develops. However, it is still limited by the complexity of the deep structure network in need of a large number of parameters and high dimensions, easily leading to a great consumption of time. To solve this problem, this paper proposes a fast training FBP method based on local feature fusion and broad learning system (BLS). Firstly, two-dimensional principal component analysis (2DPCA) is employed to reduce the dimension of the local texture image so as to lessen its redundancy. Secondly, local feature fusion method is adopted to extract more advanced features through avoiding the effects from unstable illumination, individual differences, and various postures. Finally, extensional feature eigenvectors are input to the broad learning network to train an efficient FBP model, which effectively shortens operational time and improve its preciseness. Extensive experiments with the proposed method on large scale Asian female beauty database (LSAFBD) can be conducted within 13.33s while sustaining an accuracy of 58.97%, impressively outstripping other state-of-the-art methods in training speed.