*Entropy and the Emotional Brain: Overview of a Research Field DOI: http://dx.doi.org/10.5772/intechopen.98342*


*1 SVM: Support vector machine.*

*2 DEAP: Database for emotion analysis using physiological signals.*

*3 DT: Decision tree.*

*4 MLP: Multi-layer perceptron.*

*5 DST: Dempster-Shafer theory.*

*6 PSAE: Parallel stacked autoencoders. 7*

*DBN: Deep belief networks. 8*

*LDA: Linear discriminant analysis. 9*

*SEED: SJTU emotion EEG database. 10DySampEn: Dynamic SampEn.*

*11CSampEn: Cross-sample entropy.*

**Table 1.**

*Studies of emotions recognition from EEG recordings with regularity-based entropy indices.*

main studies that have used these entropy metrics for that purpose are included in **Tables 2** and **3**. It can be observed that only a few works studied these indices between 2011 and 2015 [49–52, 63]. Nevertheless, the interest in these predictability measures has notably increased since 2017 until nowadays. More precisely, DEn is the predictability-based metric that has gained a considerable visibility since 2018, thus **Table 3** only includes studies based on the application of DEn. The rest of predictability-based entropy metrics, i.e. ShEn, REn, SpEn, and permutation indices, are contained in **Table 2**. It is interesting to note that the majority of these works in **Table 2** analyzed the EEG signals contained in the DEAP database, whereas only a few


*SP: Spectral power.*

*2 KNN: K-nearest neightbor.*

*3 ANOVA: Analysis of variance.*

*4 MC-LSSVM: Multiclass least-square support vector machine.*

*5 CFNN: Cascade-forward neural network.*

*6 LSSVM: Least-square support vector machine.*

*7 D-RFE: Dynamical recursive feature elimination.*

*8 NB: Naive Bayes.*

*9 CEn: Conditional entropy.*

*10ANN: Artificial neural network.*

#### **Table 2.**

*Studies of emotions recognition from EEG recordings with predictability-based entropy indices (ShEn, SpEn, REn, PerEn, AAPE.*

tested those metrics with different experiments. As for the regularity-based indices, the number of emotions identified in works in **Table 2** ranged from 2 to 4, and only one study recognized 5 emotional states [49]. In terms of the classifiers implemented, SVM approaches were preferred over other models in the majority of the studies. The results obtained presented inconsistent Acc values, ranging from 65–99%, being the


*1 GELM: Graph-regularized extreme learning machine.*

*2 HCNN: Hierarchical convolutional neural network.*

*3 GRSLR: Graph regularized sparse linear regression.*

*4 DGCNN: Dynamical graph convolutional neural network.*

*5 STNN: Spatial–temporal neural network. <sup>6</sup>*

*9 SRU: Simple recurrent unit network.*

### **Table 3.**

*Studies of emotions recognition from EEG recordings with predictability-based entropy indices (DEn).*

frontal and parietal/occipital lobes the most relevant in emotional processes. With respect to the studies in **Table 3**, it can be noticed that the majority of them followed the same experimental procedure, but in this case, another public dataset different from DEAP was selected. Indeed, recordings from the SJTU Emotion EEG Dataset (SEED) were chosen and assessed for the detection of three emotional states, namely

*LR: Linear regression.*

*<sup>7</sup> MTL: Multisource transfer learning.*

*<sup>8</sup> LORSAL: Logistic regression via variable splitting and augmented Lagragian.*


*3*

*CMAAPE: Composite multiscale AAPE. 4*

*FCM: Fuzzy cognitive map. 5*

*DPerEn: Delayed PerEn. 6*

*MSpEn: Multiscale SpEn. 7*

*ARF: Autoencoder based random forest. 8*

*RVM: Relevance vector machine.*

#### **Table 4.**

*Studies of emotions recognition from EEG recordings with multiscale and multilag entropy indices.*

positive, neutral and negative [63]. This database contained EEG recordings with 62 channels from 15 subjects during the visualization of film clips with emotional content [63]. The selection of the classification approaches was quite inconsistent across the different studies. However, it can be observed that deep learning approaches like convolutional neural networks (CNN) have been progressively introduced in the literature for their application in emotion recognition researches. The accuracy results reported in these works were between 68% and 99%. Furthermore, some of them demonstrated that DEn was more suitable than some linear metrics for the identification of emotions [63, 68].

Finally, **Table 4** shows the main works focused on the application of multiscale and multilag entropy approaches for detecting emotions with EEG recordings. As can be observed, the study of these indices has emerged in the last few years, especially since 2019 until nowadays. In these works, the number of emotional states studied ranged from 2 to 5, which is in line with the rest of entropy metrics evaluated. Furthermore, the signals from the DEAP database were also chosen by some of the studies included in the table. It can be noticed that the selection of the classification models was slightly inconsistent among the different studies, although SVM and deep learning approaches were the most selected. As in the previous cases, the final outcomes obtained presented accuracy values with a high variability, ranging from 73–98%.
