Emotion Aware Voice-Casting Robot for Rehabilitation Evaluated with Bio-signal Index

Constructing an Emotion Estimation Model Based on EEG/HRV Indexes Using Feature Extraction and Feature Selection Algorithms

“…Macro F1 is an extension of F1-score, which is an accuracy verification index used in binary classification to multi-label classification. The calculation method of F1-score is expressed by Equations ( 6)- (8). precision = TP TP + FP (6) recall = TP TP + FN (7) F1 − score = 2×recall × precision recall + precision (8) In the binary classification of positive and negative examples, the denotations of the variables in the equation is described as follows: TP denotes the amount of data for which the predicted value is a positive example and the prediction is correct; TN denotes the amount of data for which the predicted value is a negative example and the predicted value is correct; FP denotes the amount of data for which the predicted value is a positive example and the prediction is incorrect; FN denotes the amount of data for which the prediction is incorrect using the predicted value as a negative example; precision is an accuracy index that is emphasized when you want to reduce false positives; and recall is an accuracy index that is important when you want to avoid overlooking positive examples; F1-score is a balanced index by taking the harmonic mean of these accuracy indexes.…”

“…In recent years, there has been a number of studies on estimating human emotions in the engineering field, and there are a wide variety of fields where this technology is expected to be applied [ 1 , 2 , 3 ]. In human–robot interactions (HRI), emotion estimation technology is used to facilitate communication between humans and robots in real-life settings, such as schools [ 4 ], homes [ 5 ], ambient assisted living [ 6 ], hospitals [ 7 ], and in rehabilitation [ 8 ]. In the field of marketing, the best advertisements [ 9 ] for a customer are presented by estimating a customer’s emotion.…”