解读fmri情感类型的机器学习方法分析-analysis of machine learning methods for interpreting fmri emotional types.docxVIP

DECODING EMOTION FROM FMRl BASED ONMACHINE LEARNINGABSTRAC TImagcs contain very rich cmotion meanings. Image cmotion meaning recogn ition is a hot spot in many research fields which incJude digital image processing ，artificial emotion ， machine leaming and cognitive psychology. lmage emotion is an active，interna l and implicit emotional reflection of the manwhen he or she watches the image. Most of the existing literature are selected based on low-level features of image itself，through machine learning methods ， and cstablish the rclationship bctween low-lcvel features and semantics ofimage emotion. The emotional meaning annotated image library is the key point of this kind of researches. However，in the most of existing image libraries，the emotional meanings are manually annotated based on the statistics. Themanually annotated image library is very expensive and hardly ref1ects theintemal and implicít emotion of human being.Functional magnetic resonance imaging is an imaging technology ，mainlyby measuring the blood oxygen level dependent sígnal activation of the brain. With fMR1 study of the emotional process of the appJication ，the researchers found that different emotions will have di ffercnt activatio l1 patterns. 1n this paper，the 如IíRI is used to observe the brain reactions to the images and the Machine Learning method is introduced to establish the map between brain activationpattems and the human emotions. After practice ，a cJassifier can be gotten toautomatically annotate the emotional meanings 011 the new images based on the map.This research is a part of the project Images Annotation Based On 附[RI forPersona lized Emotion and Ontology Library research that is supported by the111大 !京现工大学硕士研究生学校论艾national natural scienc巳 foundalion of china und er granl No. and isthe exploratory research . Th is project majorly researches on the differcnt brain activalion patterns reflecled by diff