Multimodal sentiment analysis (MSA) aims to use a variety of sensors to obtain and process information to predict the intensity and polarity of human emotions. The main challenges faced by current multi-modal sentiment analysis include: how the model extracts emotional information in a single modality and realizes the complementary transmission of multimodal information; how to output relatively stable predictions even when the sentiment embodied in a single modality is inconsistent with the multi-modal label; how can the model ensure high accuracy when a single modal information is incomplete or the feature extraction performance not good. Traditional methods do not take into account the interaction of unimodal contextual information and multi-modal information. They also ignore the independence and correlation of different modalities, which perform poorly when multimodal sentiment representations are asymmetric. To address these issues, this paper first proposes unimodal feature extraction network (UFEN) to extract unimodal features with stronger representation capabilities; then introduces multi-task fusion network (MTFN) to improve the correlation and fusion effect between multiple modalities. Multilayer feature extraction, attention mechanisms and Transformer are used in the model to mine potential relationships between features. Experimental results on MOSI, MOSEI and SIMS datasets show that the proposed method achieves better performance on multimodal sentiment analysis tasks compared with state-of-the-art baselines.

The non-line of sight (NLOS) propagation caused by the building shielding and background interference will lead to large error when applying Ultra-Wideband (UWB) technology to indoor positioning. In order to reduce the positioning error, a joint simulated annealing algorithm and a bat algorithm is proposed in the paper. First, based on the Bat Algorithm (BA), transform the problem of the target into the problem of difference between the estimated position and the actual position to establish an iterative optimization model. Then introduce random perturbation factor to improve the search ability of the bat individual; Aiming at BA is easy to fall into local optimum, a Simulate Anneal (SA) algorithm is integrated to improve the classification and search ability of the algorithm. Finally, we use Chan-Taylor algorithm to determine the accurate position of the target. The research result shows that proposed algorithm improves positioning accuracy by 11∼23cm which can effectively improve the positioning accuracy of the positioning algorithm under the LOS/NLOS environment.