首页|Findings from University of Naples Federico II Reveals New Findings on Machine L earning (Toward Cross-subject and Cross-session Generalization In Eeg-based Emot ion Recognition: Systematic Review, Taxonomy, and Methods)
Findings from University of Naples Federico II Reveals New Findings on Machine L earning (Toward Cross-subject and Cross-session Generalization In Eeg-based Emot ion Recognition: Systematic Review, Taxonomy, and Methods)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News-Researchers detail new data in Machine Learning. According to news reporting fromNaples, Italy, by NewsRx journalists , research stated, "A systematic review on machine-learning strategiesfor impro ving generalization in electroencephalographybased emotion classification was re alized. Inparticular, cross-subject and cross-session generalization was focuse d."Financial supporters for this research include Italian Ministry of Enterprise an d Made in Italy, EuropeanUnion-FSE-REACT-EU, Ministry of Education, Universitie s and Research (MIUR), PhD GrantAR4ClinicSur-Augmented Reality for Clinical Sur gery (INPS-National Social Security Institution - Italy).The news correspondents obtained a quote from the research from the University o f Naples FedericoII, "In this context, the non-stationarity of electroencephalo graphic (EEG) signals is a critical issue andcan lead to the Dataset Shift prob lem. Several architectures and methods have been proposed to addressthis issue, mainly based on transfer learning methods. In this review, 449 papers were retr ieved fromthe Scopus, IEEE Xplore and PubMed databases through a search query f ocusing on modern machinelearning techniques for generalization in EEG-based em otion assessment. Among these papers, 79 werefound eligible based on their rele vance to the problem. Studies lacking a specific cross-subject or crosssessionvalidation strategy, or making use of other biosignals as support were excluded. On the basis ofthe selected papers' analysis, a taxonomy of the studies employ ing Machine Learning (ML) methods wasproposed, together with a brief discussion of the different ML approaches involved. The studies reportingthe best results in terms of average classification accuracy were identified, supporting that tr ansfer learningmethods seem to perform better than other approaches."
NaplesItalyEuropeCyborgsEmerging TechnologiesMachine LearningUniversity of Naples Federico II
NETL
NSTL
