Jifeng Guo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Jifeng Guo has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Chun Lung Philip Chen
South China University of Technology
9 shared publications - Tong Zhang
South China University of Technology
5 shared publications - Zhulin Liu
School of Computer Science and Engineering, South China University of Technology, Guangzhou, China
3 shared publications - Lin Wang
Shandong Key Laboratory of Ubiquitous Intelligent Computing, University of Jinan, Jinan, China
2 shared publications Bin Lin
School of Business, Sun Yat-Sen University, Guangzhou, China
1 shared publication- Bingxiu Liu
School of Computer Science and Engineering, South China University of Technology, Guangzhou, China
1 shared publication
Latest Publications
- 8 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. PP  (00189456) , 1
A Deep Unsupervised Learning Approach for GNSS Multipath Detection in High-Precision Air Transportation
With the rapid development of the low-altitude economy, the mitigation capability of global navigation satellite system (GNSS) multipath effects has emerged as a critical factor constraining the safety performance of aviation navigation. However, due to the coupled influence of multiple factors and inherent nonlinear characteristics, the precise detection of multipath effects and efficient classification of line-of-sight (LOS), multipath, and non-line-of-sight (NLOS) signals pose significant challenges. In recent years, machine learning methods have demonstrated notable advantages in multipath detection and achieved preliminary progress. Nevertheless, existing machine learning-based methods require extensive labeled multipath data. In practical applications, the high cost of data labeling and the dynamic variability of operational environments result in limited labeled data availability, rendering these methods inadequate for complex and evolving scenarios. Moreover, the extracted GNSS signal features exhibit insufficient inter-feature correlations and limited feature dimensions, severely limiting the further improvement of GNSS multipath detection and classification performance. In this paper, we propose a deep unsupervised learning for multipath detection (DUL-MD) method trained on unlabeled samples. This approach combines autoencoders (AE) and long short-term memory (LSTM) networks for joint representation learning, achieving low-dimensional mapping and enhancing time-series feature extraction capabilities. A novel loss function is introduced to better accommodate the data characteristics of GNSS multipath effects, including spatiotemporal correlation and overlapping boundaries. Extensive experiments based on static and dynamic vehicle and drone flight data demonstrate that the proposed deep unsupervised model achieves higher accuracy in detecting GNSS multipath effects compared to existing machine learning methods.
- 8 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. PP  (00189456) , 1
A Deep Unsupervised Learning Approach for GNSS Multipath Detection in High-Precision Air Transportation
With the rapid development of the low-altitude economy, the mitigation capability of global navigation satellite system (GNSS) multipath effects has emerged as a critical factor constraining the safety performance of aviation navigation. However, due to the coupled influence of multiple factors and inherent nonlinear characteristics, the precise detection of multipath effects and efficient classification of line-of-sight (LOS), multipath, and non-line-of-sight (NLOS) signals pose significant challenges. In recent years, machine learning methods have demonstrated notable advantages in multipath detection and achieved preliminary progress. Nevertheless, existing machine learning-based methods require extensive labeled multipath data. In practical applications, the high cost of data labeling and the dynamic variability of operational environments result in limited labeled data availability, rendering these methods inadequate for complex and evolving scenarios. Moreover, the extracted GNSS signal features exhibit insufficient inter-feature correlations and limited feature dimensions, severely limiting the further improvement of GNSS multipath detection and classification performance. In this paper, we propose a deep unsupervised learning for multipath detection (DUL-MD) method trained on unlabeled samples. This approach combines autoencoders (AE) and long short-term memory (LSTM) networks for joint representation learning, achieving low-dimensional mapping and enhancing time-series feature extraction capabilities. A novel loss function is introduced to better accommodate the data characteristics of GNSS multipath effects, including spatiotemporal correlation and overlapping boundaries. Extensive experiments based on static and dynamic vehicle and drone flight data demonstrate that the proposed deep unsupervised model achieves higher accuracy in detecting GNSS multipath effects compared to existing machine learning methods.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13  (15) , 1
An Intelligent Optimization-Driven Clustering Routing Protocol for Industrial IoT Performance Boosting
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13  (15) , 1
An Intelligent Optimization-Driven Clustering Routing Protocol for Industrial IoT Performance Boosting
- 19 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36  (4) , 7196-7210
An Incremental-Self-Training-Guided Semi-Supervised Broad Learning System
The broad learning system (BLS) has recently been applied in numerous fields. However, it is mainly a supervised learning system and thus not suitable for specific practical applications with a mixture of labeled and unlabeled data. Despite a manifold regularization-based semi-supervised BLS, its performance still requires improvement, because its assumption is not always applicable. Therefore, this article proposes an incremental-self-training-guided semi-supervised BLS (ISTSS-BLS). Distinctive to traditional self-training, where all unlabeled data are labeled simultaneously, incremental self-training (IST) obtains unlabeled data incrementally from an established sorted list based on the distance between the data and their cluster center. During iterative learning, a small portion of labeled data is first used to train BLS. The system recursively self-updates its structure and meta-parameters using: 1) the double-restricted mechanism and 2) the dynamic neuron-incremental mechanism. The double-restricted mechanism is beneficial to preventing the introduction of incorrect pseudo-labeled samples, and the dynamic neuron-incremental mechanism guides the self-updating of the network structure effectively based on the training accuracy of the labeled data. These strategies guarantee a parsimonious model during the update. Besides, a novel metric, the accuracy-time ratio (A/T), is proposed to evaluate the model’s performance comprehensively regarding time and accuracy. In experimental verifications, ISTSS-BLS performs outstandingly on 11 datasets. Specifically, the IST is compared with the traditional one on three scales data, saving up to 52.02% learning time. In addition, ISTSS-BLS is compared with different state-of-the-art alternatives, and all results indicate that it possesses significant advantages in performance.
- 19 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36  (4) , 7196-7210
An Incremental-Self-Training-Guided Semi-Supervised Broad Learning System
The broad learning system (BLS) has recently been applied in numerous fields. However, it is mainly a supervised learning system and thus not suitable for specific practical applications with a mixture of labeled and unlabeled data. Despite a manifold regularization-based semi-supervised BLS, its performance still requires improvement, because its assumption is not always applicable. Therefore, this article proposes an incremental-self-training-guided semi-supervised BLS (ISTSS-BLS). Distinctive to traditional self-training, where all unlabeled data are labeled simultaneously, incremental self-training (IST) obtains unlabeled data incrementally from an established sorted list based on the distance between the data and their cluster center. During iterative learning, a small portion of labeled data is first used to train BLS. The system recursively self-updates its structure and meta-parameters using: 1) the double-restricted mechanism and 2) the dynamic neuron-incremental mechanism. The double-restricted mechanism is beneficial to preventing the introduction of incorrect pseudo-labeled samples, and the dynamic neuron-incremental mechanism guides the self-updating of the network structure effectively based on the training accuracy of the labeled data. These strategies guarantee a parsimonious model during the update. Besides, a novel metric, the accuracy-time ratio (A/T), is proposed to evaluate the model’s performance comprehensively regarding time and accuracy. In experimental verifications, ISTSS-BLS performs outstandingly on 11 datasets. Specifically, the IST is compared with the traditional one on three scales data, saving up to 52.02% learning time. In addition, ISTSS-BLS is compared with different state-of-the-art alternatives, and all results indicate that it possesses significant advantages in performance.
- 21 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 5  (10) , 5075-5089
ConvBLS: An Effective and Efficient Incremental Convolutional Broad Learning System Combining Deep and Broad Representations
Broad learning system (BLS) has to undergo a vectorization operation before modeling image data, which makes it challenging for BLS to learn local semantic features. Thus, various convolutional-based broad learning systems (C-BLS) have been introduced to address these challenges. Regrettably, the existing C-BLS variants either lack an efficient training algorithm and incremental learning capability or suffer from poor performance. To this end, we propose a novel convolutional broad learning system (ConvBLS) based on the spherical K-means (SKM) algorithm and two-stage multi-scale (TSMS) feature fusion, which consists of the convolutional feature layer (CFL), convolutional enhancement layer (CEL), TSMS feature fusion layer, and output layer. First, unlike the current C-BLS, the simple yet efficient SKM algorithm is utilized to learn the weights of CFLs. Compared with random filters, the SKM algorithm enables the CFL to learn more comprehensive spatial features. Second, to further mine the local semantic features, CELs are established to expand the feature space. Third, the TSMS feature fusion layer is proposed to extract more effective multi-scale features by integrating deep and broad representations. Thanks to the above elaborate design and the pseudo-inverse calculation of the output layer weights, our proposed ConvBLS method is unprecedentedly efficient and effective. Finally, the corresponding incremental learning algorithms are presented for rapid remodeling if the model deems to expand. Experiments and comparisons demonstrate the superiority of our method.
- 21 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 5  (10) , 5075-5089
ConvBLS: An Effective and Efficient Incremental Convolutional Broad Learning System Combining Deep and Broad Representations
Broad learning system (BLS) has to undergo a vectorization operation before modeling image data, which makes it challenging for BLS to learn local semantic features. Thus, various convolutional-based broad learning systems (C-BLS) have been introduced to address these challenges. Regrettably, the existing C-BLS variants either lack an efficient training algorithm and incremental learning capability or suffer from poor performance. To this end, we propose a novel convolutional broad learning system (ConvBLS) based on the spherical K-means (SKM) algorithm and two-stage multi-scale (TSMS) feature fusion, which consists of the convolutional feature layer (CFL), convolutional enhancement layer (CEL), TSMS feature fusion layer, and output layer. First, unlike the current C-BLS, the simple yet efficient SKM algorithm is utilized to learn the weights of CFLs. Compared with random filters, the SKM algorithm enables the CFL to learn more comprehensive spatial features. Second, to further mine the local semantic features, CELs are established to expand the feature space. Third, the TSMS feature fusion layer is proposed to extract more effective multi-scale features by integrating deep and broad representations. Thanks to the above elaborate design and the pseudo-inverse calculation of the output layer weights, our proposed ConvBLS method is unprecedentedly efficient and effective. Finally, the corresponding incremental learning algorithms are presented for rapid remodeling if the model deems to expand. Experiments and comparisons demonstrate the superiority of our method.
- 20 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 54  (11) , 6410-6422
A Robust Semi-Supervised Broad Learning System Guided by Ensemble-Based Self-Training
Broad learning system (BLS) with semi-supervised learning relieves label dependence and expands application. Despite some efforts and progress, the semi-supervised BLS still needs improvement, especially in handling imbalanced data or concept drift scenarios for self-training-based methods. To this extent, this article proposes a robust semi-supervised BLS guided by ensemble-based self-training (ESTSS-BLS). Distinctive to self-training that assigns the pseudo-label via a single classifier and confidence, the advocated ensemble-based self-training determines the pseudo-label according to the turnout of multiple BLSs. In addition, label purity is proposed to ensure the correctness and credibility of the auxiliary training data, which is a comprehensive evaluation of the voting. During iterative learning, a small portion of labeled data first trains multiple BLSs in parallel. Then, the system recursively updates its data, structure, and meta-parameters using label purity and a data-driven dynamic nodes mechanism that dynamically guides the network’s structural adjustments to solve the concept drift problem caused by a large amount of auxiliary training data. The experimental results demonstrate that ESTSS-BLS exhibits exceptional performance compared to existing methods, with the lowest-time consumption and the highest accuracy, precision, recall, F1 score, and AUC. Exhilaratingly, it achieves an accuracy of 87.84% with only 0.1% labeled data on MNIST, and with just 2% labeled data, it matches the performance of supervised learning using all training data on NORB. In addition, ESTSS-BLS also performs stably on medical or biological data, verifying its high adaptability.
- 20 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 54  (11) , 6410-6422
A Robust Semi-Supervised Broad Learning System Guided by Ensemble-Based Self-Training
Broad learning system (BLS) with semi-supervised learning relieves label dependence and expands application. Despite some efforts and progress, the semi-supervised BLS still needs improvement, especially in handling imbalanced data or concept drift scenarios for self-training-based methods. To this extent, this article proposes a robust semi-supervised BLS guided by ensemble-based self-training (ESTSS-BLS). Distinctive to self-training that assigns the pseudo-label via a single classifier and confidence, the advocated ensemble-based self-training determines the pseudo-label according to the turnout of multiple BLSs. In addition, label purity is proposed to ensure the correctness and credibility of the auxiliary training data, which is a comprehensive evaluation of the voting. During iterative learning, a small portion of labeled data first trains multiple BLSs in parallel. Then, the system recursively updates its data, structure, and meta-parameters using label purity and a data-driven dynamic nodes mechanism that dynamically guides the network’s structural adjustments to solve the concept drift problem caused by a large amount of auxiliary training data. The experimental results demonstrate that ESTSS-BLS exhibits exceptional performance compared to existing methods, with the lowest-time consumption and the highest accuracy, precision, recall, F1 score, and AUC. Exhilaratingly, it achieves an accuracy of 87.84% with only 0.1% labeled data on MNIST, and with just 2% labeled data, it matches the performance of supervised learning using all training data on NORB. In addition, ESTSS-BLS also performs stably on medical or biological data, verifying its high adaptability.
- 17 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36  (4) , 7580-7593
Robust Incremental Broad Learning System for Data Streams of Uncertain Scale
Due to its marvelous performance and remarkable scalability, a broad learning system (BLS) has aroused a wide range of attention. However, its incremental learning suffers from low accuracy and long training time, especially when dealing with unstable data streams, making it difficult to apply in real-world scenarios. To overcome these issues and enrich its relevant research, a robust incremental BLS (RI-BLS) is proposed. In this method, the proposed weight update strategy introduces two memory matrices to store the learned information, thus the computational procedure of ridge regression is decomposed, resulting in precomputed ridge regression. During incremental learning, RI-BLS updates two memory matrices and renews weights via precomputed ridge regression efficiently. In addition, this update strategy is theoretically analyzed in error, time complexity, and space complexity compared with existing incremental BLSs. Different from Greville’s method used in the original incremental BLS, its results are closer to the solution of one-shot calculation. Compared with the existing incremental BLSs, the proposed method exhibits more stable time complexity and superior space complexity. The experiments prove that RI-BLS outperforms other incremental BLSs when handling both stable and unstable data streams. Furthermore, experiments demonstrate that the proposed weight update strategy applies to other random neural networks as well.
- 17 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36  (4) , 7580-7593
Robust Incremental Broad Learning System for Data Streams of Uncertain Scale
Due to its marvelous performance and remarkable scalability, a broad learning system (BLS) has aroused a wide range of attention. However, its incremental learning suffers from low accuracy and long training time, especially when dealing with unstable data streams, making it difficult to apply in real-world scenarios. To overcome these issues and enrich its relevant research, a robust incremental BLS (RI-BLS) is proposed. In this method, the proposed weight update strategy introduces two memory matrices to store the learned information, thus the computational procedure of ridge regression is decomposed, resulting in precomputed ridge regression. During incremental learning, RI-BLS updates two memory matrices and renews weights via precomputed ridge regression efficiently. In addition, this update strategy is theoretically analyzed in error, time complexity, and space complexity compared with existing incremental BLSs. Different from Greville’s method used in the original incremental BLS, its results are closer to the solution of one-shot calculation. Compared with the existing incremental BLSs, the proposed method exhibits more stable time complexity and superior space complexity. The experiments prove that RI-BLS outperforms other incremental BLSs when handling both stable and unstable data streams. Furthermore, experiments demonstrate that the proposed weight update strategy applies to other random neural networks as well.
- 4 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36  (3) , 4246-4266
Dynamic Neural Network Structure: A Review for its Theories and Applications
The dynamic neural network (DNN), in contrast to the static counterpart, offers numerous advantages, such as improved accuracy, efficiency, and interpretability. These benefits stem from the network’s flexible structures and parameters, making it highly attractive and applicable across various domains. As the broad learning system (BLS) continues to evolve, DNNs have expanded beyond deep learning (DL), orienting a more comprehensive range of domains. Therefore, this comprehensive review article focuses on two prominent areas where DNN structures have rapidly developed: 1) DL and 2) broad learning. This article provides an in-depth exploration of the techniques related to dynamic construction and inference. Furthermore, it discusses the applications of DNNs in diverse domains while also addressing open issues and highlighting promising research directions. By offering a comprehensive understanding of DNNs, this article serves as a valuable resource for researchers, guiding them toward future investigations.
- 4 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36  (3) , 4246-4266
Dynamic Neural Network Structure: A Review for its Theories and Applications
The dynamic neural network (DNN), in contrast to the static counterpart, offers numerous advantages, such as improved accuracy, efficiency, and interpretability. These benefits stem from the network’s flexible structures and parameters, making it highly attractive and applicable across various domains. As the broad learning system (BLS) continues to evolve, DNNs have expanded beyond deep learning (DL), orienting a more comprehensive range of domains. Therefore, this comprehensive review article focuses on two prominent areas where DNN structures have rapidly developed: 1) DL and 2) broad learning. This article provides an in-depth exploration of the techniques related to dynamic construction and inference. Furthermore, it discusses the applications of DNNs in diverse domains while also addressing open issues and highlighting promising research directions. By offering a comprehensive understanding of DNNs, this article serves as a valuable resource for researchers, guiding them toward future investigations.
- 23 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 15  (2) , 671-684
Fine-Grained Interpretability for EEG Emotion Recognition: Concat-Aided Grad-CAM and Systematic Brain Functional Network
EEG emotion recognition plays a significant role in various mental health services. Deep learning-based methods perform excellently, but still suffer from interpretability. Although methods such as Gradient-weighted Class Activation Mapping(Grad-CAM) can cope with the above problem, their coarse granularity cannot accurately reveal the mechanism to promote emotional intelligence. In this paper, fine-grained interpretability is proposed, called Concat-aided Grad-CAM. Specifically, the multi-level feature mapping before the fully connected layer is concatenated to obtain the gradients of the target concept so that the discriminant information can be directly located in the high-precision area. Unlike coarse-grained interpretability methods applied in EEG emotion recognition, it can accurately highlight the EEG channels related to emotion rather than an obscure area. In addition, a systematic brain functional network is proposed to reveal the relationship between those channels and to further improve emotion recognition performance. The channels with greater contributions are connected, and those connections are learned by dynamic graph convolutional networks, while the others are independent to eliminate interference. Experiments on two EEG emotion recognition datasets manifest that Concat-aided Grad-CAM can be interpreted by the fine-grained. In addition, it has been shown that the learned brain functional network can improve the performance of the baselines. Significantly, the experiment results achieve state-of-the-art performance in subject-dependent experiments.
- 23 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 15  (2) , 671-684
Fine-Grained Interpretability for EEG Emotion Recognition: Concat-Aided Grad-CAM and Systematic Brain Functional Network
EEG emotion recognition plays a significant role in various mental health services. Deep learning-based methods perform excellently, but still suffer from interpretability. Although methods such as Gradient-weighted Class Activation Mapping(Grad-CAM) can cope with the above problem, their coarse granularity cannot accurately reveal the mechanism to promote emotional intelligence. In this paper, fine-grained interpretability is proposed, called Concat-aided Grad-CAM. Specifically, the multi-level feature mapping before the fully connected layer is concatenated to obtain the gradients of the target concept so that the discriminant information can be directly located in the high-precision area. Unlike coarse-grained interpretability methods applied in EEG emotion recognition, it can accurately highlight the EEG channels related to emotion rather than an obscure area. In addition, a systematic brain functional network is proposed to reveal the relationship between those channels and to further improve emotion recognition performance. The channels with greater contributions are connected, and those connections are learned by dynamic graph convolutional networks, while the others are independent to eliminate interference. Experiments on two EEG emotion recognition datasets manifest that Concat-aided Grad-CAM can be interpreted by the fine-grained. In addition, it has been shown that the learned brain functional network can improve the performance of the baselines. Significantly, the experiment results achieve state-of-the-art performance in subject-dependent experiments.
- 23 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 11  (2) , 2784-2795
LiFoL: An Efficient Framework for Financial Distress Prediction in High-Dimensional Unbalanced Scenario
Corporate financial distress will significantly damage the company’s and its stakeholders’ interests and even lead to a global financial crisis. Therefore, finding an efficient method for financial distress prediction (FDP) to avoid greater losses is essential. Although there is a lot of research and progress in this field, the existing methods rarely consider the problems of high dimensionality and class imbalance, which will largely limit the models to achieve satisfactory performance. To alleviate these problems, this article first proposes a novel Lightspace-SMOTE upsampling method, which can reduce the feature dimensionality and increase the signal-to-noise ratio (SNR) of the original data and then upsample it to increase the number of minor class samples. In addition, this article proposes an efficient ensemble framework (LiFoL) that combines Lightspace-SMOTE, focal loss (FL), and LightGBM, which can not only focus more on minor class and the hard-to-class samples but also obtain better performance. At the same time, the feature importance provided by the model can provide strong support for model interpretability. Experimental results show that the Lightspace-SMOTE upsampling method can help the model achieve higher scores in area under ROC curve (AUC) and recall, especially in the case of longer prediction periods. Compared with current methods, LiFoL can achieve more than 10% improvement in AUC and more than 20% in recall.
- 23 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 11  (2) , 2784-2795
LiFoL: An Efficient Framework for Financial Distress Prediction in High-Dimensional Unbalanced Scenario
Corporate financial distress will significantly damage the company’s and its stakeholders’ interests and even lead to a global financial crisis. Therefore, finding an efficient method for financial distress prediction (FDP) to avoid greater losses is essential. Although there is a lot of research and progress in this field, the existing methods rarely consider the problems of high dimensionality and class imbalance, which will largely limit the models to achieve satisfactory performance. To alleviate these problems, this article first proposes a novel Lightspace-SMOTE upsampling method, which can reduce the feature dimensionality and increase the signal-to-noise ratio (SNR) of the original data and then upsample it to increase the number of minor class samples. In addition, this article proposes an efficient ensemble framework (LiFoL) that combines Lightspace-SMOTE, focal loss (FL), and LightGBM, which can not only focus more on minor class and the hard-to-class samples but also obtain better performance. At the same time, the feature importance provided by the model can provide strong support for model interpretability. Experimental results show that the Lightspace-SMOTE upsampling method can help the model achieve higher scores in area under ROC curve (AUC) and recall, especially in the case of longer prediction periods. Compared with current methods, LiFoL can achieve more than 10% improvement in AUC and more than 20% in recall.
- Open Access
ConvBLS: An Effective and Efficient Incremental Convolutional Broad Learning System for Image Classification
Deep learning generally suffers from enormous computational resources and time-consuming training processes. Broad Learning System (BLS) and its convolutional variants have been proposed to mitigate these issues and have achieved superb performance in image classification. However, the existing convolutional-based broad learning system (C-BLS) either lacks an efficient training method and incremental learning capability or suffers from poor performance. To this end, we propose a convolutional broad learning system (ConvBLS) based on the spherical K-means (SKM) algorithm and two-stage multi-scale (TSMS) feature fusion, which consists of the convolutional feature (CF) layer, convolutional enhancement (CE) layer, TSMS feature fusion layer, and output layer. First, unlike the current C-BLS, the simple yet efficient SKM algorithm is utilized to learn the weights of CF layers. Compared with random filters, the SKM algorithm makes the CF layer learn more comprehensive spatial features. Second, similar to the vanilla BLS, CE layers are established to expand the feature space. Third, the TSMS feature fusion layer is proposed to extract more effective multi-scale features through the integration of CF layers and CE layers. Thanks to the above design and the pseudo-inverse calculation of the output layer weights, our proposed ConvBLS method is unprecedentedly efficient and effective. Finally, the corresponding incremental learning algorithms are presented for rapid remodeling if the model deems to expand. Experiments and comparisons demonstrate the superiority of our method.
Open AccessConvBLS: An Effective and Efficient Incremental Convolutional Broad Learning System for Image Classification
Deep learning generally suffers from enormous computational resources and time-consuming training processes. Broad Learning System (BLS) and its convolutional variants have been proposed to mitigate these issues and have achieved superb performance in image classification. However, the existing convolutional-based broad learning system (C-BLS) either lacks an efficient training method and incremental learning capability or suffers from poor performance. To this end, we propose a convolutional broad learning system (ConvBLS) based on the spherical K-means (SKM) algorithm and two-stage multi-scale (TSMS) feature fusion, which consists of the convolutional feature (CF) layer, convolutional enhancement (CE) layer, TSMS feature fusion layer, and output layer. First, unlike the current C-BLS, the simple yet efficient SKM algorithm is utilized to learn the weights of CF layers. Compared with random filters, the SKM algorithm makes the CF layer learn more comprehensive spatial features. Second, similar to the vanilla BLS, CE layers are established to expand the feature space. Third, the TSMS feature fusion layer is proposed to extract more effective multi-scale features through the integration of CF layers and CE layers. Thanks to the above design and the pseudo-inverse calculation of the output layer weights, our proposed ConvBLS method is unprecedentedly efficient and effective. Finally, the corresponding incremental learning algorithms are presented for rapid remodeling if the model deems to expand. Experiments and comparisons demonstrate the superiority of our method.