Waseda University · Computer Science
Professor Jinglu Hu's research lab specializes in intelligent modeling, system identification, and control for nonlinear and complex systems, with a strong focus on hybrid modeling techniques that combine linear structures with nonlinear learning components. The lab develops advanced data-driven models—such as quasi-ARMAX and neurofuzzy systems—tailored for applications in renewable energy (e.g., wind turbines), brain-computer interfaces (BCIs), and signal processing. Key innovations include the integration of deep learning, graph neural networks, and stochastic optimization (e.g., PSO) to enhance model accuracy, stability, and real-time performance. The lab also emphasizes feature selection and signal representation techniques to improve decoding in EEG-based systems and other high-dimensional data applications.
Figures are computed from collected data and may differ slightly.
This paper proposes a class of quasi-ARMAX models for non-linear systems. Similar to ordinary non-linear ARMAX models, the quasi-ARMAX models are flexible black-box models, but they have various linearity properties similar to those of linear ARMAX models. A modelling scheme is introduced to construct models consisting of two parts: a macro-part and a kernel-part. By using Taylor expansion and other mathematical transformation techniques, it is first constructed as a class of quasi-ARMAX interfa
This paper proposes a hybrid quasi-ARMAX modeling and identification scheme for nonlinear systems. The idea is to incorporate a group of certain nonlinear nonparametric models (NNMs) into a linear ARMAX structure. Particular effort is made to find a better compromise to the trade-off between the model flexibility and the model simplicity by using knowledge information efficiently. As the result, we obtain a model equipped with a linear. ARMAX structure, flexibility and simplicity. The effectiven
To develop an efficient brain-computer interface (BCI) system, electroencephalography (EEG) measures neuronal activities in different brain regions through electrodes. Many EEG-based motor imagery (MI) studies do not make full use of brain network topology. In this paper, a deep learning framework based on a modified graph convolution neural network (M-GCN) is proposed, in which temporal-frequency processing is performed on the data through modified S-transform (MST) to improve the decoding perf
Abstract The central criterion of feature selection is that good feature sets contain features that are highly correlated with the output, yet uncorrelated with each other. Based on this criterion, we address the problem of feature selection through correlation‐based feature clustering and support vector machine (SVM) based feature ranking. Correlation‐based clustering is proposed to group features into some clusters based on the correlation between two features. As a result, a feature is highly
By itself, a wind turbine is already a fairly complex system with highly nonlinear dynamics. Changes in wind speed can affect the dynamic parameters of wind turbines, thus rendering the parameters uncertain. However, we can identify the dynamics of the wind energy conversion system (WECS) online by a quasi‐ARX neural network (QARXNN) model. A QARXNN presents a problem in searching for the coefficients of the regression vector (input vector). A multilayer perceptron neural network (MLPNN) is an e
Abstract An improved Elman neural network ( IENN ) controller with particle swarm optimization ( PSO ) is presented for nonlinear systems. The proposed controller is composed of a quasi‐ ARX neural network ( QARXNN ) prediction model and a switching mechanism. The switching mechanism is used to guarantee that the prediction model works well. The primary controller is designed based on IENN using the backpropagation ( BP ) learning algorithm with PSO . PSO is used to adjust the learning rates in
Open papers in the app to read, cite, and organize with AI.
