Multimodal Sentiment Classification(MSC)uses multimodal data,such as images and texts,to identify the users'sentiment polarities from the information posted by users on the Internet.MSC has attracted considerable ...Multimodal Sentiment Classification(MSC)uses multimodal data,such as images and texts,to identify the users'sentiment polarities from the information posted by users on the Internet.MSC has attracted considerable attention because of its wide applications in social computing and opinion mining.However,improper correlation strategies can cause erroneous fusion as the texts and the images that are unrelated to each other may integrate.Moreover,simply concatenating them modal by modal,even with true correlation,cannot fully capture the features within and between modals.To solve these problems,this paper proposes a Cross-Modal Complementary Network(CMCN)with hierarchical fusion for MSC.The CMCN is designed as a hierarchical structure with three key modules,namely,the feature extraction module to extract features from texts and images,the feature attention module to learn both text and image attention features generated by an image-text correlation generator,and the cross-modal hierarchical fusion module to fuse features within and between modals.Such a CMCN provides a hierarchical fusion framework that can fully integrate different modal features and helps reduce the risk of integrating unrelated modal features.Extensive experimental results on three public datasets show that the proposed approach significantly outperforms the state-of-the-art methods.展开更多
A promising scheme for coal-fired power plants in which biomass co-firing and carbon dioxide capture technologies are adopted and the low-temperature waste heat from the CO_(2) capture process is recycled to heat the ...A promising scheme for coal-fired power plants in which biomass co-firing and carbon dioxide capture technologies are adopted and the low-temperature waste heat from the CO_(2) capture process is recycled to heat the condensed water to achieve zero carbon emission is proposed in this paper.Based on a 660 MW supercritical coal-fired power plant,the thermal performance,emission performance,and economic performance of the proposed scheme are evaluated.In addition,a sensitivity analysis is conducted to show the effects of several key parameters on the performance of the proposed system.The results show that when the biomass mass mixing ratio is 15.40%and the CO_(2) capture rate is 90%,the CO_(2) emission of the coal-fired power plant can reach zero,indicating that the technical route proposed in this paper can indeed achieve zero carbon emission in coal-fired power plants.The net thermal efficiency decreases by 10.31%,due to the huge energy consumption of the CO_(2) capture unit.Besides,the cost of electricity(COE)and the cost of CO_(2) avoided(COA)of the proposed system are 80.37/MWhand41.63/tCO_(2),respectively.The sensitivity analysis demonstrates that with the energy consumption of the reboiler decreasing from 3.22 GJ/tCO_(2) to 2.40 GJ/tCO_(2),the efficiency penalty is reduced to 8.67%.This paper may provide reference for promoting the early realization of carbon neutrality in the power generation industry.展开更多
基金supported by the National Key Research and Development Program of China(No.2020AAA0104903)。
文摘Multimodal Sentiment Classification(MSC)uses multimodal data,such as images and texts,to identify the users'sentiment polarities from the information posted by users on the Internet.MSC has attracted considerable attention because of its wide applications in social computing and opinion mining.However,improper correlation strategies can cause erroneous fusion as the texts and the images that are unrelated to each other may integrate.Moreover,simply concatenating them modal by modal,even with true correlation,cannot fully capture the features within and between modals.To solve these problems,this paper proposes a Cross-Modal Complementary Network(CMCN)with hierarchical fusion for MSC.The CMCN is designed as a hierarchical structure with three key modules,namely,the feature extraction module to extract features from texts and images,the feature attention module to learn both text and image attention features generated by an image-text correlation generator,and the cross-modal hierarchical fusion module to fuse features within and between modals.Such a CMCN provides a hierarchical fusion framework that can fully integrate different modal features and helps reduce the risk of integrating unrelated modal features.Extensive experimental results on three public datasets show that the proposed approach significantly outperforms the state-of-the-art methods.
基金supported by the National Natural Science Foundation of China(Grant No.51806062)the Science Fund for Creative Research Groups of the National Natural Science Foundation of China(Grant No.51821004)the Fundamental Research Funds for the Central Universities(Grant No.2020MS006).
文摘A promising scheme for coal-fired power plants in which biomass co-firing and carbon dioxide capture technologies are adopted and the low-temperature waste heat from the CO_(2) capture process is recycled to heat the condensed water to achieve zero carbon emission is proposed in this paper.Based on a 660 MW supercritical coal-fired power plant,the thermal performance,emission performance,and economic performance of the proposed scheme are evaluated.In addition,a sensitivity analysis is conducted to show the effects of several key parameters on the performance of the proposed system.The results show that when the biomass mass mixing ratio is 15.40%and the CO_(2) capture rate is 90%,the CO_(2) emission of the coal-fired power plant can reach zero,indicating that the technical route proposed in this paper can indeed achieve zero carbon emission in coal-fired power plants.The net thermal efficiency decreases by 10.31%,due to the huge energy consumption of the CO_(2) capture unit.Besides,the cost of electricity(COE)and the cost of CO_(2) avoided(COA)of the proposed system are 80.37/MWhand41.63/tCO_(2),respectively.The sensitivity analysis demonstrates that with the energy consumption of the reboiler decreasing from 3.22 GJ/tCO_(2) to 2.40 GJ/tCO_(2),the efficiency penalty is reduced to 8.67%.This paper may provide reference for promoting the early realization of carbon neutrality in the power generation industry.