Recently, the study of emotion recognition has received increasing attentions by the rapid development of noninvasive sensor technologies, machine learning algorithms and compute capability of computers. Compared with single modal emotion recognition, the multimodal paradigm introduces complementary information for emotion recognition. Hence, in this work, we presented a decision level fusion framework for detecting emotions continuously by fusing the Electroencephalography (EEG) and facial expressions. Three types of movie clips (positive, negative, and neutral) were utilized to elicit specific emotions of subjects, the EEG and facial expression signals were recorded simultaneously. The power spectrum density (PSD) features of EEG were extracted by time-frequency analysis, and then EEG features were selected for regression. For the facial expression, the facial geometric features were calculated by facial landmark localization. Long short-term memory networks (LSTM) were utilized to accomplish the decision level fusion and captured temporal dynamics of emotions. The results have shown that the proposed method achieved outstanding performance for continuous emotion recognition, and it yields 0.625±0.029 of concordance correlation coefficient (CCC). From the results, the fusion of two modalities outperformed EEG and facial expression separately. Furthermore, different numbers of time-steps of LSTM was applied to analyze the temporal dynamic capturing.INDEX TERMS Continuous emotion recognition, EEG, facial expressions, signal processing, decision level fusion, temporal dynamics.
Owing to the high charge mobility and low processing temperature, ZnO is regarded as an ideal candidate for electron transport layer (ETL) material in thin-film solar cells. For the film preparation, the presently dominated sol-gel (SG) and hydrolysis-condensation (HC) methods show great potential; however, the effect of these two methods on the performance of the resulting devices has not been investigated in the same frame. In this study, the ZnO films made through SG and HC methods were applied in perovskite solar cells (Pero-SCs), and the performances of corresponding devices were compared under parallel conditions. We found that the surface morphologies and the conductivities of the films prepared by SG and HC methods showed great differences. The HC-ZnO films with higher conductivity led to relatively higher device performance, and the best power conversion efficiencie (PCE) of 12.9% was obtained; meanwhile, for Pero-SCs based on SG-ZnO, the best PCE achieved was 10.9%. The better device performance of Pero-SCs based on HC-ZnO should be attributed to the better charge extraction and transportation ability of HC-ZnO film. Moreover, to further enhance the performance of Pero-SCs, a thin layer of pristine C was introduced between HC-ZnO and perovskite layers. By doing so, the quality of perovskite films was improved, and the PCE was elevated to 14.1%. The preparation of HC-ZnO film involves relatively lower-temperature (maximum 100 °C) processing; the films showed better charge extraction and transportation properties and can be a more promising ETL material in Pero-SCs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.