State-of-the-art architectures of convolutional neural networks (CNN) are widely used by authors for facial expression recognition (FER). There are many variants of these models with positive results in studies for FER and successful applications, some well-known models are VGG, ResNet, Xception, EfficientNet, DenseNet. However, these models have considerable complexity for some real-world applications with limitations of computational resources. This paper proposes a lightweight CNN model based on a modern architecture of dense-connectivity with moderate complexity but still ensures quality and efficiency for facial expression recognition. Then, it is designed to be integrated into learning management systems (LMS) for recording and evaluation of online learning activities. The proposed model is to run experiments on some popular datasets for testing and evaluation, the results show that the model is effective and can be used in practice.

Using convolution neural network (CNN) for face recognition is being widely research with a promising significant in applications and it is interested by many authors. Moreover, the CNN model has brought successful applications in practice such as detection and identification face of people on Facebook users' photos application, they use DeepFace model. There are many articles which proposed CNN models for face recognition with using some modifications of popular models of large architectures such as VGG, ResNet, OpenFace or FaceNet. However, these models are large complexity for some applications in reality with limitations of computing resources. This paper proposes a design of CNN model with moderate complexity but still ensures the quality and efficiency of face recognition. We run experiments for evaluating the model on some popular datasets, the experiment shows effective results and indicates that the proposed model can be practically used.