Emotion recognition based on facial expressions is one of the most critical elements of human-machine interfaces.Most conventional methods for emotion recognition using facial expressions use the entire facial image t...Emotion recognition based on facial expressions is one of the most critical elements of human-machine interfaces.Most conventional methods for emotion recognition using facial expressions use the entire facial image to extract features and then recognize specific emotions through a pre-trained model.In contrast,this paper proposes a novel feature vector extraction method using the Euclidean distance between the landmarks changing their positions according to facial expressions,especially around the eyes,eyebrows,nose,andmouth.Then,we apply a newclassifier using an ensemble network to increase emotion recognition accuracy.The emotion recognition performance was compared with the conventional algorithms using public databases.The results indicated that the proposed method achieved higher accuracy than the traditional based on facial expressions for emotion recognition.In particular,our experiments with the FER2013 database show that our proposed method is robust to lighting conditions and backgrounds,with an average of 25% higher performance than previous studies.Consequently,the proposed method is expected to recognize facial expressions,especially fear and anger,to help prevent severe accidents by detecting security-related or dangerous actions in advance.展开更多
Rivers originating from the Tibetan Plateau(TP)provide water to almost one-fifth of the global population[1,2].Due to its high elevation,the TP features high dependence on cryospheric meltwater,including meltwater fro...Rivers originating from the Tibetan Plateau(TP)provide water to almost one-fifth of the global population[1,2].Due to its high elevation,the TP features high dependence on cryospheric meltwater,including meltwater from snow,glaciers,and ground ice[3].In a warming climate,the sustainability of cryospheric meltwater on the TP has raised concerns because of its importance for the fragile ecosystems in the headwater regions.Existing studies mainly focused on glacier melt and snow melt on the TP[1,4,5],while the hydrological implications of thawing permafrost remain elusive.The TP has the world’s largest area of elevational permafrost,which features long-term preservation of ground ice that has formed since the Late Pleistocene[6].With ongoing climate warming,a large quantity of ground ice is likely to be mobilized and the meltwater could contribute to river runoff(Q)[7],which might also transport sediment and organic carbon fluxes[2].Existing large-scale hydrological modelling studies on the TP rarely include permafrost dynamics in their models[8,9].Therefore,the fate of ground ice and its hydrological implications across the entire TP remain largely unknown.展开更多
基金supported by the Healthcare AI Convergence R&D Program through the National IT Industry Promotion Agency of Korea(NIPA)funded by the Ministry of Science and ICT(No.S0102-23-1007)the Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(NRF-2017R1A6A1A03015496).
文摘Emotion recognition based on facial expressions is one of the most critical elements of human-machine interfaces.Most conventional methods for emotion recognition using facial expressions use the entire facial image to extract features and then recognize specific emotions through a pre-trained model.In contrast,this paper proposes a novel feature vector extraction method using the Euclidean distance between the landmarks changing their positions according to facial expressions,especially around the eyes,eyebrows,nose,andmouth.Then,we apply a newclassifier using an ensemble network to increase emotion recognition accuracy.The emotion recognition performance was compared with the conventional algorithms using public databases.The results indicated that the proposed method achieved higher accuracy than the traditional based on facial expressions for emotion recognition.In particular,our experiments with the FER2013 database show that our proposed method is robust to lighting conditions and backgrounds,with an average of 25% higher performance than previous studies.Consequently,the proposed method is expected to recognize facial expressions,especially fear and anger,to help prevent severe accidents by detecting security-related or dangerous actions in advance.
基金the National Natural Science Foundation of China(42041004 and 52209027)the Strategic Priority Research Program of Chinese Academy of Sciences(XDA20100103)+3 种基金the support from the China Postdoctoral Science Foundation(2022M711857)the Postdoctoral Innovation Talents Support Program of China(BX2021166)the Shuimu Tsinghua Scholar Programthe financial support from the National Natural Science Foundation of China(42071029)。
文摘Rivers originating from the Tibetan Plateau(TP)provide water to almost one-fifth of the global population[1,2].Due to its high elevation,the TP features high dependence on cryospheric meltwater,including meltwater from snow,glaciers,and ground ice[3].In a warming climate,the sustainability of cryospheric meltwater on the TP has raised concerns because of its importance for the fragile ecosystems in the headwater regions.Existing studies mainly focused on glacier melt and snow melt on the TP[1,4,5],while the hydrological implications of thawing permafrost remain elusive.The TP has the world’s largest area of elevational permafrost,which features long-term preservation of ground ice that has formed since the Late Pleistocene[6].With ongoing climate warming,a large quantity of ground ice is likely to be mobilized and the meltwater could contribute to river runoff(Q)[7],which might also transport sediment and organic carbon fluxes[2].Existing large-scale hydrological modelling studies on the TP rarely include permafrost dynamics in their models[8,9].Therefore,the fate of ground ice and its hydrological implications across the entire TP remain largely unknown.
