Narrow Results

A Facial Expression Recognition (FER) method based on Conv3D-ConvLSTM-SEnet in an online education environment is proposed to address the issue of low accuracy in current classroom expression recognition (FER) methods. Firstly, ConvLSTM is used to integrate the local feature extraction ability of CNN and the temporal modeling ability of LSTM, and based on this, the rich spatial features of the image are characterized. Then, by introducing Depth Separated Convolution (DSC) to change the number of output channels and separate each channel, the Feature Maps (F-M) are sequentially concatenated to obtain a multi-channel output F-M. Finally, based on ConvLSTM and SEnet modules, a Conv3D ConvLSTM-based FER model was proposed by redistributing the extracted abstract features and basic texture features, achieving high accuracy classroom FER. The proposed classroom FER method and the other five methods were compared and analyzed through simulation experiments using the CK$+$, FER2013 and JAFFE datasets, respectively. The results indicate that the proposed method achieves the highest accuracy, precision, recall, and F1 score, with improvements of at least 1.85%, 2.41%, 1.18% and 2.05%, respectively, compared to the other five methods on the FER2013 dataset. The proposed method can perform FER on students in online classroom teaching, detect their emotions in real-time, and help teachers make better course teaching adjustments based on this.

In this paper, a new deep learning framework named encoding convolution long short-term memory (encoding ConvLSTM) is proposed to build a surrogate structural model with spatiotemporal evolution of structure, estimate the structural spatiotemporal state and predict the dynamic response under similar future dynamic load conditions. The main work of this study includes: (a) The spatiotemporal response tensor database is developed using discrete-time history data of structural dynamic response. (b) As an extension of LSTM, convolution operation is combined with LSTM network to construct structural surrogate model from the spatiotemporal evolution structural performance. (c) To enhance the anti-interference ability of structural surrogate models, a new three-layer encoding layer is added for denoising autoencoders of the hybrid network. The influence of building types and input noise on the accuracy and antinoise performance of the surrogate models are analyzed through the dynamic response prediction of a frame-shear wall, a cylindrical, and a spherical reticulated shell structure. As a testbed for the proposed network, a case study is performed on a laboratory stadium structure. The results demonstrate that the developed surrogate model can predict the structural dynamic response precisely with more under 30% noise interference.

Traditionally, machine learning technologies with the methods and capabilities available, combined with a geospatial dimension, can perform predictive analyzes of air quality with greater accuracy. However, air pollution is influenced by many external factors, one of which has recently been caused by the restrictions applied to curb the relentless advance of COVID-19. These sudden changes in air quality levels can negatively influence current forecasting models. This work compares air pollution forecasts during a pandemic and non-pandemic period under the same conditions. The ConvLSTM algorithm was applied to predict the concentration of nitrogen dioxide using data from the air quality and meteorological stations in Madrid. The proposed model was applied for two scenarios: pandemic (January–June 2020) and non-pandemic (January–June 2019), each with sub-scenarios based on time granularity (1-h, 12-h, 24-h and 48-h) and combination of features. The Root Mean Square Error was taken as the estimation metric, and the results showed that the proposed method outperformed a reference model, and the feature selection technique significantly improved the overall accuracy.