Network Intrusion Detection Based on Deep Belief Network Broad Equalization Learning System

In recent years, electroencephalogram (EEG) e-motion recognition has been becoming an emerging field in artificial intelligence area, which can reflect the relation between emotional states and brain activity. In this paper, we designed a novel architecture, i.e., broad dynamical graph learning system (BDGLS), to deal with EEG signals. By integrating the advantage of dynamical graph convolution neural networks (DGCNN) and broad learning system (BLS), BDGLS has the ability of extracting features on non-Euclidean domain and randomly generating nodes to find the desired connection weights simultaneously. We evaluated our system on SJTU emotion EEG dataset (SEED), and used differential entropy (DE) features as input data. In the experiments, BDGLS achieved the best result, compared with the state-of-the-art methods, e.g., support vector machine (SVM), deep belief networks (DBN), graph convolutional neural networks (DCNN) and DGCNN. Especially the performance on all-frequency band of DE features, BDGLS reached the highest average recognition accuracy of 93.66% with the standard deviation of 6.11%. The result demonstrated the excellent classification ability of BDGLS in EEG emotion recognition.

In this paper, traditional DeepWalk method and broad learning system (BLS) are used to classify network nodes in graph embedding, and results of classification are compared. When categorizing, DeepWalk adopts one vs rest (OvR) logistic regression method, and BLS is applied after the production of vector representations. In order to obviously compare results of the two classification methods, Support Vector Machine (SVM) and Convolutional Neural Network (CNN) are employed to carry out the experiment on multi-label classification of BlogCatalog. The experimental result shows that F1 score of BLS is obviously higher than DeepWalk and other methods, and training time of BLS is much less than other methods. These performances make our method suitable to graph embedding.

Detection of evolving cyber attacks is a challenging task for conventional network intrusion detection techniques. Various supervised machine learning algorithms have been implemented in network intrusion detection systems. However, traditional algorithms require long training time and have high computational complexity. Therefore, we propose detection of denial of service cyber attacks in communication networks by employing the broad learning system (BLS) that requires shorter training time while achieving comparable performance. Because designing effective detection systems relies on training and test datasets that contain anomalous network traffic data, in this paper we evaluate the performance of various BLS models by using recently generated network intrusion datasets. The best accuracy and F-Score were often achieved using BLS with cascades while BLS with incremental learning usually required shorter training time.

Accurate short-term load forecasting (STLF) is critical to the operation and control of the power grid. In the literature, deep learning techniques have shown its superiority for accurate load forecasting over other methods due to its strong regression ability. However, the training process of the deep learning systems is time-consuming providing that they contain a large number of parameters due to the complex structure. This paper presents a novel broad learning system (BLS) approach for load forecasting. The BLS, which is established as a flat network, is an alternative to the deep learning system by expanding the structure in a wide sense. The expanded broad structure of BLS ensures its strong approximation capability of nonlinear mapping. Moreover, the BLS has a much faster training process compared to deep learning due to its simple structure. The proposed method is tested with an open dataset at low-voltage level from Australia and the testing results demonstrate the effectiveness of the proposed method.

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.

Stream label distribution learning processing via broad learning system

Accurate Electric Vehicle (EV) charging load time-series prediction is an important prerequisite for enhancing the safe and stable operation of charging stations. However, the EV charging load is strongly nonlinear, highly intermittent and random, which leads to the low accuracy of charging load time-series prediction. To this end, this paper proposes a broad learning system-based EV charging load time-series prediction method. First, the actual data of charging load of EV are analyzed and processed. Further, a charging load time-series prediction model is established using a broad learning system. Simulation experiments based on actual data indicate that the proposed charging load time-series prediction model based on the broad learning system has better prediction performance and also has less computing time compared to prediction models such as back propagation neural network and long-short term memory.

The newly proposed Broad Learning System (BLS) offers an alternative way to deep learning which saves a time-consuming training process and powerful computing resources. However, the randomly generated feature nodes and lots of enhancement nodes in BLS may reduce the performance of the final classifier. Aiming at the problems in randomly generated feature nodes which suffer from unpredictability and need guidance, this paper proposes an adaptive feature nodes evolutionary algorithm (AFNE) to extract better features; While broad learning neural network often requires a large number of enhancement nodes parameters to ensure its performance, which easily leads to the redundancy or dependency between features, as well as the performance degradation of the final model. Therefore, this article also proposes a new criterion based on node sensitivity to prune the network enhancement layer nodes to remove redundant nodes, reduce the network scale, and increase the generalization ability. The proposed algorithm ADP-BLS can improve the accuracy and generalization performance of the final classifier through the evolution of feature nodes and the pruning of enhancement nodes. Extensive comparative experiments on real world data sets verify the effectiveness of the proposed ADP-BLS. At the same time, when verifying the module validity of the innovative algorithms added in this article, experiments also show that the AFNE and pruning method integrated into BLS can improve the model to a certain extent.

Broad learning approach to Surrogate-Assisted Multi-Objective evolutionary fuzzy clustering algorithm based on reference points for color image segmentation

Generally, class imbalance is a major problem that occurs with various machine learning problems where there are a large number of instances of one class compared to another class. In this case, it has been found that a typical classification model may be biased towards a particular class and may not be able to classify instances of another class properly. This problem is critical while dealing with various real-world problems. In recent times, Broad Learning System (BLS) has gained attention from many researchers due to its fast training speed and efficiency of the flat network. However, it has been found that the conventional BLS model may not be efficient while dealing with imbalanced data sets because it uses a least squares method. Generally, a least squares method may not be efficient while dealing with imbalanced data sets. This paper proposes an adaptive margin broad learning system (AMBLS) model to improve its efficiency while handling imbalanced data sets in order to address this issue with traditional BLS models. The suggested approach may be more effective when handling imbalanced data sets than traditional BLS models, according to experimental results on a number of benchmark imbalanced data sets. Keywords- Imbalanced Learning; Broad Learning System; Adaptive Margin; Minority Classification; Machine Learning.

The study introduces a novel approach to short-term wind speed forecasting, which amalgamates statistical and machine learning techniques through the utilization of a hybrid model consisting of the broad learning system (BLS) and the relevance vector machine (RVM), to account for the nonstationary characteristics of wind speed data. Firstly, the initial wind speed time series is preprocessed using singular spectrum analysis to achieve noise reduction. Subsequently, the denoised wind speed time series is predicted using generalized learning system (BLS), and the prediction error is obtained. Finally, the prediction error of BLS is further predicted using RVM, and the final prediction result is obtained by combining it with the prediction results of BLS. By integrating multiple algorithms, this novel wind speed forecasting hybrid model improves prediction accuracy and can adapt to different wind speed characteristics and complex wind speed fluctuations. Through a case study, we find that this model outperforms other comparative models in terms of prediction, fully demonstrating its superiority.

To address the limitation of current upper limb rehabilitation exoskeletons—where pattern recognition-based assistance disrupts patients’ continuous motion—this study proposes a mechanomyography-based model for predicting shoulder and elbow joint angles. Small contact microphones were employed to collect mechanomyography signals, leveraging their ability to capture vibration signals above 8 Hz, making them ideal for mechanomyography acquisition. After extracting raw mechanomyography data, a bandpass filter (10–50 Hz) was applied to eliminate low- and high-frequency noise. To reduce computational overhead during model training, a Broad Learning System was adopted, which iteratively refines predictions by incrementally expanding nodes in the feature and enhancement layers rather than adding hidden layers. The Slime Mold Algorithm was further used to optimize hyperparameters of the Broad Learning System, enhancing prediction accuracy. Experimental results demonstrate that mechanomyography signals exhibit a typical central frequency range of 10–50 Hz, and the Slime Mold Algorithm-optimized Broad Learning System model achieved a minimum coefficient of determination (R2) of 0.978, effectively predicting arm joint angles. This approach shows promise for exoskeletons, combining high control accuracy, real-time joint angle prediction, and computational efficiency.

Recently, broad learning system (BLS) have demonstrated excellent performance in hyperspectral images (HSI) classification. However, due to the complex geometric structure and spatial layout of HSI, the linear sparse features in broad learning system are difficult to fully represent hyperspectral data. In addition, the features learned by broad learning system lack more effective discriminative ability, which leads to the limited expressive ability of features. To address the issues, we propose a graph convolutional enhanced discriminative broad learning system (GCDBLS) for HSI Classification. GCDBLS aggregates the node information in the adjacency graph through graph convolution, and then learns the context relationship, so as to obtain rich nonlinear spatial spectral features in hyperspectral images; In order to extract more discriminative hyperspectral image features, GCDBLS introduces the concept of local intra-class scatter and local inter-class scatter. By minimizing the local intra-class feature distance and maximizing the local inter-class feature distance, GCDBLS can improve the discrimination ability of BLS extracted features. On three HSI datasets, the experiments compared with the latest classification methods show that the proposed method achieves good results, and improves the classification performance of hyperspectral images.

The emergence of a massive Internet-of-Things (IoT) ecosystem is changing the human lifestyle. In several practical scenarios, IoT still faces significant challenges with reliance on human assistance and unacceptable response time for the treatment of big data. Therefore, it is very urgent to establish a new framework and algorithm to solve problems specific to this kind of fast autonomous IoT. Traditional reinforcement learning and deep reinforcement learning (DRL) approaches have abilities of autonomous decision making, but time-consuming modeling and training procedures limit their applications. To get over this dilemma, this article proposes the broad reinforcement learning (BRL) approach that fits fast autonomous IoT as it combines the broad learning system (BLS) with a reinforcement learning paradigm to improve the agent's efficiency and accuracy of modeling and decision making. Specifically, a BRL framework is first constructed. Then, the associated learning algorithm, containing training pool introduction, training sample preparation, and incremental learning for BLS, is carefully designed. Finally, as a case study of fast autonomous IoT, the proposed BRL approach is applied to traffic light control, aiming to alleviate traffic congestion in the intersections of smart cities. The experimental results show that the proposed BRL approach can learn better action policy at a shorter execution time when compared with competing approaches.

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.