脉搏血氧饱和度测定（SpO2）的进展（下）

三、准确使用SpO2测定。一些情况会使SpO2测定的读数不可靠、不正确或缺乏可信性：应注意判断和解决（表3）。

Cognitive Emotion Model for Eldercare Robot in Smart Home

Based on the smart home and facial expression recognition, this paper presents a cognitive emotional model for eldercare robot. By combining with Gabor filter, Local Binary Pattern algorithm(LBP) and k-Nearest Neighbor algorithm(KNN) are facial emotional features extracted and recognized. Meanwhile, facial emotional features put influence on robot's emotion state, which is described in AVS emotion space. Then the optimization of smart home environment on the cognitive emotional model is specially analyzed using simulated annealing algorithm(SA). Finally, transition probability from any emotional state to a state of basic emotions is obtained based on the cognitive reappraisal strategy and Euclidean distance. The simulation and experiment have tested and verified the effective in reducing negative emotional state.

Facial Robot Expression Simulator(FRESi)——A Simulator to Implement Dynamic Facial Expression

Most of the robots are nowadays evolving and imitating huiron social skills to achieve sociable interaction with humanas. Socially interactive robots require different characteristics than conventional robots. Likewise human-human interaction, human-robot interaction is also accompanied with emotional interaction. Therefore, the robot＇s emotional expression is very important for human, especially facial expressions play an important role among the whole part of the human body. In this paper, we introduce a facial robot expression simulator FRESi.

Transfer learning with deep sparse auto-encoder for speech emotion recognition

In order to improve the efficiency of speech emotion recognition across corpora,a speech emotion transfer learning method based on the deep sparse auto-encoder is proposed.The algorithm first reconstructs a small amount of data in the target domain by training the deep sparse auto-encoder,so that the encoder can learn the low-dimensional structural representation of the target domain data.Then,the source domain data and the target domain data are coded by the trained deep sparse auto-encoder to obtain the reconstruction data of the low-dimensional structural representation close to the target domain.Finally,a part of the reconstructed tagged target domain data is mixed with the reconstructed source domain data to jointly train the classifier.This part of the target domain data is used to guide the source domain data.Experiments on the CASIA,SoutheastLab corpus show that the model recognition rate after a small amount of data transferred reached 89.2%and 72.4%on the DNN.Compared to the training results of the complete original corpus,it only decreased by 2%in the CASIA corpus,and only 3.4%in the SoutheastLab corpus.Experiments show that the algorithm can achieve the effect of labeling all data in the extreme case that the data set has only a small amount of data tagged.

Robot’s Emotion Decision by Energy and Entropy Concepts

This study is to introduce concepts of energy and entropy to describe a robot＇s emoton decisien. It chooses the dimensional approach based on factors of pleasure and arousal for the merit of the interpolation between enotions. Especially, Circumplex model which has also two axes： pleasure and arousal is used. Besides, the model indicates how emotions are distributed in the two-dimensional plane. Then by the definition of psychodynamicsthe energy states （mental energy and physical energy） are matched to pleasure and arousal respectively that are the basis of Circumplex model. The mental energy is updated by the result of Prospect theory which measures the value of gain and loss as pleasure factor. And the physical energy is updated by the result of hedonic scaling which measures levels of arousal from pleasure computed by Prospect theory, and the result of intensity of stimuli. Then the energy states are fed by entropy. The feedback loop by entropy satisfies the 2nd law of thermodynamics. The energy states generated by stimuli and fed by entropy take a position in the plane of Circumplex model. Then distances between the current position and other emotions are cornputed to get a level of each emotion, proportional to the inverse of the distance.

Affective rating ranking based on face images in arousal-valence dimensional space

In dimensional affect recognition, the machine learning methods, which are used to model and predict affect, are mostly classification and regression. However, the annotation in the dimensional affect space usually takes the form of a continuous real value which has an ordinal property. The aforementioned methods do not focus on taking advantage of this important information. Therefore, we propose an affective rating ranking framework for affect recognition based on face images in the valence and arousal dimensional space. Our approach can appropriately use the ordinal information among affective ratings which are generated by discretizing continuous annotations.Specifically, we first train a series of basic cost-sensitive binary classifiers, each of which uses all samples relabeled according to the comparison results between corresponding ratings and a given rank of a binary classifier. We obtain the final affective ratings by aggregating the outputs of binary classifiers. By comparing the experimental results with the baseline and deep learning based classification and regression methods on the benchmarking database of the AVEC 2015 Challenge and the selected subset of SEMAINE database, we find that our ordinal ranking method is effective in both arousal and valence dimensions.