Search Results (10)

Due to the rapid proliferation of social media and online reviews, the accurate identification and classification of controversial texts has emerged as a significant challenge in the field of natural language processing. However, traditional text-classification methodologies frequently encounter critical limitations, such as feature sensitivity and inadequate generalization capabilities. This results in a notably suboptimal performance when confronted with diverse controversial content. To address these substantial limitations, this paper proposes a novel controversial text-detection framework based on stacked ensemble learning to enhance the accuracy and robustness of text classification. Firstly, considering the multidimensional complexity of textual features, we integrate comprehensive feature engineering, i.e., encompassing word frequency, statistical metrics, sentiment analysis, and comment tree structure features, as well as advanced feature selection methodologies, particularly lassonet, i.e., a neural network with feature sparsity, to effectively address dimensionality challenges while enhancing model interpretability and computational efficiency. Secondly, we design a two-tier stacked ensemble architecture, which not only combines the strengths of multiple machine learning algorithms, e.g., gradient-boosted decision tree (GBDT), random forest (RF), and extreme gradient boosting (XGBoost), with deep learning models, e.g., gated recurrent unit (GRU) and long short-term memory (LSTM), but also implements the support vector machine (SVM) for efficient meta-learning. Furthermore, we systematically compare three hyperparameter optimization algorithms, including the sparrow search algorithm (SSA), particle swarm optimization (PSO), and Bayesian optimization (BO). The experimental results demonstrate that the SSA exhibits a superior performance in exploring high-dimensional parameter spaces. Extensive experimentation across diverse topics and domains also confirms that our proposed methodology significantly outperforms the state-of-the-art approaches. Full article

Servo systems are important actuators of aeroengines. The repetitive, reciprocating motion of the servo system leads to significant changes in its time delay and gain characteristics, and degradation increases the uncertainty of these changes. These characteristic variations may have an adverse effect on the dynamic performance of the aeroengine. Therefore, a neural network-based parameter estimation and a multi-loop neural network-based predictive control (ML-NNPC) method for aeroengine inlet guide vane (IGV) servo systems (SVS) were proposed. In this study, the time delay estimation of the servo system was treated as a classification problem, and an SE (squeeze-and-excitation)-GRU (gated recurrent unit) network was proposed to estimate the time delay by using the selected dynamic data of the servo system. The estimated delay was embedded into an online sequential extreme learning machine, and a nonlinear model predictive controller was designed to obtain an optimal control sequence. The compensation control loop was designed to reduce the impact of the model and delay mismatch problems of the control system. The proposed method was applied to the IGV SVS control of a turboshaft engine. The simulation results demonstrate that the time delay is estimated accurately and compensated effectively. Compared to the existing PI and PI with Smith predictor methods, the ML-NNPC method achieves better control performance in the control of both the SVS and the engine rotor speed system. The stability and robustness of the ML-NNPC also show superiority. The results verify the effectiveness of the proposed time delay estimation method and the ML-NNPC method. Full article

When autonomous underwater vehicles (AUVs) perform underwater tasks, the absence of GPS position assistance can lead to a decrease in the accuracy of traditional navigation systems, such as the extended Kalman filter (EKF), due to the accumulation of errors. To enhance the navigation accuracy of AUVs in the absence of position assistance, this paper proposes an innovative navigation method that integrates a position correction model and a velocity model. Specifically, a velocity model is developed using a dynamic model and the Optimal Pruning Extreme Learning Machine (OP-ELM) method. This velocity model is trained online to provide velocity outputs during the intervals when the Doppler Velocity Log (DVL) is not updating, ensuring more consistent and reliable velocity estimation. Additionally, a position correction model (PCM) is constructed, based on a hybrid gated recurrent neural network (HGRNN). This model is specifically designed to correct the AUV’s navigation position when GPS data are unavailable underwater. The HGRNN utilizes historical navigation data and patterns learned during training to predict and adjust the AUV’s estimated position, thereby reducing the drift caused by the lack of real-time position updates. Experimental results demonstrate that the proposed VM-PCM-EKF algorithm can significantly improve the positioning accuracy of the navigation system, with a maximum accuracy improvement of 87.2% compared to conventional EKF algorithms. This method not only improves the reliability and accuracy of AUV missions but also opens up new possibilities for more complex and extended underwater operations. Full article

This paper presents a systematic approach for solving complex prediction problems with a focus on energy efficiency. The approach involves using neural networks, specifically recurrent and sequential networks, as the main tool for prediction. In order to test the methodology, a case study was conducted in the telecommunications industry to address the problem of energy efficiency in data centers. The case study involved comparing four recurrent and sequential neural networks, including recurrent neural networks (RNNs), long short-term memory (LSTM), gated recurrent units (GRUs), and online sequential extreme learning machine (OS-ELM), to determine the best network in terms of prediction accuracy and computational time. The results show that OS-ELM outperformed the other networks in both accuracy and computational efficiency. The simulation was applied to real traffic data and showed potential energy savings of up to 12.2% in a single day. This highlights the importance of energy efficiency and the potential for the methodology to be applied to other industries. The methodology can be further developed as technology and data continue to advance, making it a promising solution for a wide range of prediction problems. Full article

Concept drift (CD) in data streaming scenarios such as networking intrusion detection systems (IDS) refers to the change in the statistical distribution of the data over time. There are five principal variants related to CD: incremental, gradual, recurrent, sudden, and blip. Genetic programming combiner (GPC) classification is an effective core candidate for data stream classification for IDS. However, its basic structure relies on the usage of traditional static machine learning models that receive onetime training, limiting its ability to handle CD. To address this issue, we propose an extended variant of the GPC using three main components. First, we replace existing classifiers with alternatives: online sequential extreme learning machine (OSELM), feature adaptive OSELM (FA-OSELM), and knowledge preservation OSELM (KP-OSELM). Second, we add two new components to the GPC, specifically, a data balancing and a classifier update. Third, the coordination between the sub-models produces three novel variants of the GPC: GPC-KOS for KA-OSELM; GPC-FOS for FA-OSELM; and GPC-OS for OSELM. This article presents the first data stream-based classification framework that provides novel strategies for handling CD variants. The experimental results demonstrate that both GPC-KOS and GPC-FOS outperform the traditional GPC and other state-of-the-art methods, and the transfer learning and memory features contribute to the effective handling of most types of CD. Moreover, the application of our incremental variants on real-world datasets (KDD Cup ‘99, CICIDS-2017, CSE-CIC-IDS-2018, and ISCX ‘12) demonstrate improved performance (GPC-FOS in connection with CSE-CIC-IDS-2018 and CICIDS-2017; GPC-KOS in connection with ISCX2012 and KDD Cup ‘99), with maximum accuracy rates of 100% and 98% by GPC-KOS and GPC-FOS, respectively. Additionally, our GPC variants do not show superior performance in handling blip drift. Full article

In order to effectively solve the problem of low accuracy of seawater water quality prediction, an optimized water quality parameter prediction model is constructed in this paper. The model first screened the key factors of water quality data with the principal component analysis (PCA) algorithm, then realized the de-noising of the key factors of water quality data with an ensemble empirical mode decomposition (EEMD) algorithm, and the data were input into the two-dimensional convolutional neural network (2D-CNN) module to extract features, which were used for training and learning by attention, gated recurrent unit, and an encoder–decoder (attention–GRU–encoder–decoder, attention–GED) integrated module. The trained prediction model was used to predict the content of key parameters of water quality. In this paper, the water quality data of six typical online monitoring stations from 2017 to 2021 were used to verify the proposed model. The experimental results show that, based on short-term series prediction, the root mean square error (RMSE), mean absolute percentage error (MAPE), and decision coefficient (R²) were 0.246, 0.307, and 97.80%, respectively. Based on the long-term series prediction, RMSE, MAPE, and R² were 0.878, 0.594, and 92.23%, respectively, which were all better than the prediction model based on an enhanced clustering algorithm and adam with a radial basis function neural network (ECA–Adam–RBFNN), a prediction model based on a softplus extreme learning machine method with partial least squares and particle swarm optimization (PSO–SELM–PLS), and a wavelet transform-depth Bi–S–SRU (Bi-directional Stacked Simple Recurrent Unit) prediction model. The PCA–EEMD–CNN–attention–GED prediction model not only has high prediction accuracy but can also provide a decision-making basis for the water quality control and management of aquaculture in the waters around Zhanjiang Bay. Full article

Accurate forecast of PM_2.5 pollution is highly needed for the timely prevention of haze pollution in many cities suffered from frequent haze pollution. In this work, an online recurrent extreme learning machine (OR-ELM) technique with online data update was used in the forecast of PM_2.5 pollution for the first time, and a hybrid model (OR-ELM-AR) by combining autoregressive (AR) model was proposed to enhance its forecast ability to capture the variations of hourly PM_2.5 concentration. Evaluation of forecast performances in terms of pollution levels, forecast times, spatial distributions were conducted over the Yangtze River Delta (YRD) region, China. Results indicated that the OR-ELM-AR model could quickly respond to short-term changes and had better forecast performance. Therefore, the OR-ELM-AR model is a promising tool for air pollution forecast of supporting the government to take urgent actions to reduce the frequency and severity of haze pollution in cities or regions. Full article

Control moment gyroscopes (CMG) are crucial components in spacecrafts. Since the anomaly of bearing temperature of the CMG shows apparent correlation with nearly all critical fault modes, temperature prediction is of great importance for health management of CMGs. However, due to the complicity of thermal environment on orbit, the temperature signal of the CMG has strong intrinsic nonlinearity and chaotic characteristics. Therefore, it is crucial to study temperature prediction under the framework of chaos time series theory. There are also several other challenges including poor data quality, large individual differences and difficulty in processing streaming data. To overcome these issues, we propose a new method named Chaotic Ensemble of Online Recurrent Extreme Learning Machine (CE-ORELM) for temperature prediction of control moment gyroscopes. By means of the CE-ORELM model, this proposed method is capable of dynamic prediction of temperature. The performance of the method was tested by real temperature data acquired from actual CMGs. Experimental results show that this method has high prediction accuracy and strong adaptability to the on-orbital temperature data with sudden variations. These superiorities indicate that the proposed method can be used for temperature prediction of control moment gyroscopes. Full article

The learning speed of online sequential extreme learning machine (OS-ELM) algorithms is much higher than that of convolutional neural networks (CNNs) or recurrent neural network (RNNs) on regression and simple classification datasets. However, the general feature extraction of OS-ELM makes it difficult to conveniently and effectively perform classification on some large and complex datasets, e.g., CIFAR. In this paper, we propose a flexible OS-ELM-mixed neural network, termed as fnnmOS-ELM. In this mixed structure, the OS-ELM can replace a part of fully connected layers in CNNs or RNNs. Our framework not only exploits the strong feature representation of CNNs or RNNs, but also performs at a fast speed in terms of classification. Additionally, it avoids the problem of long training time and large parameter size of CNNs or RNNs to some extent. Further, we propose a method for optimizing network performance by splicing OS-ELM after CNN or RNN structures. Iris, IMDb, CIFAR-10, and CIFAR-100 datasets are employed to verify the performance of the fnnmOS-ELM. The relationship between hyper-parameters and the performance of the fnnmOS-ELM is explored, which sheds light on the optimization of network performance. Finally, the experimental results demonstrate that the fnnmOS-ELM has a stronger feature representation and higher classification performance than contemporary methods. Full article

The online sequential extreme learning machine with persistent regularization and forgetting factor (OSELM-PRFF) can avoid potential singularities or ill-posed problems of online sequential regularized extreme learning machines with forgetting factors (FR-OSELM), and is particularly suitable for modelling in non-stationary environments. However, existing algorithms for OSELM-PRFF are time-consuming or unstable in certain paradigms or parameters setups. This paper presents a novel algorithm for OSELM-PRFF, named “Cholesky factorization based” OSELM-PRFF (CF-OSELM-PRFF), which recurrently constructs an equation for extreme learning machine and efficiently solves the equation via Cholesky factorization during every cycle. CF-OSELM-PRFF deals with timeliness of samples by forgetting factor, and the regularization term in its cost function works persistently. CF-OSELM-PRFF can learn data one-by-one or chunk-by-chunk with a fixed or varying chunk size. Detailed performance comparisons between CF-OSELM-PRFF and relevant approaches are carried out on several regression problems. The numerical simulation results show that CF-OSELM-PRFF demonstrates higher computational efficiency than its counterparts, and can yield stable predictions. Full article