Tong Li

Emotion recognition plays an important part in human-computer interaction. Currently, the main challenge in electroencephalogram -based emotion recognition is the non-stationarity of EEG signals, which causes performance of the trained model decreasing over time. In this paper, we propose a two-level domain adaptation neural network to construct a transfer model for EEG-based emotion recognition. Specifically, deep features from the topological graph, which preserve topological information from EEG signals, are extracted using a deep neural network. These features are then passed through TDANN for two-level domain confusion. The first level uses the maximum mean discrepancy to reduce the distribution discrepancy of deep features between source domain and target domain, and the second uses the domain adversarial neural network to force the deep features closer to their corresponding class centers. We evaluated the domain-transfer performance of the model on both our self-built data set and the public data set SEED. In the cross-day transfer experiment, the ability to accurately discriminate joy from other emotions was high: sadness, anger, and fear on the self-built data set. The accuracy reached 74.93% on the SEED data set. In the cross-subject transfer experiment, the ability to accurately discriminate joy from other emotions was equally high: sadness, anger, and fear on the self-built data set. The average accuracy reached 87.9% on the SEED data set, which was higher than WGAN-DA. The experimental results demonstrate that the proposed TDANN can effectively handle the domain transfer problem in EEG-based emotion recognition.

This paper presents a numerical investigation of bird attitude angles affecting the soft-impact damage of a full fan assembly. Firstly, considering the geometry of a mallard, a real bird model is established by the Smoothed Particle Hydrodynamics method and calibrated with available test data. Then, complying with airworthiness requirements, simulations of a full-bladed fan assembly subjected to a real bird were conducted to determine the critical ingestion parameters. Furthermore, a real bird with different attitude angles aimed at a full fan assembly was simulated. Results show that attitude angles of the bird produce a significant impact on the effect of the bird strike on rotating blades and would increase the possibility of blade failures, especially for the yaw angle of -45° and the pitch angle of −60°. It is invaluable for commercial airlines and engine manufactures to provide safe flight and landing by adopting the real bird model with critical yaw and pitch angles in the design for resistance to bird ingestion.