Search

The construction of complex networks from electroencephalography (EEG) proves to be an effective method for representing emotion patterns in affection computing as it offers rich spatiotemporal EEG features associated with brain emotions. In this paper, we propose a novel method for constructing complex networks from EEG signals for emotion recognition, which begins with phase space reconstruction to obtain ordinal patterns and subsequently forms a graph network representation from the sequence of ordinal patterns based on the visibility graph method, named ComNet-PSR-VG. For the proposed ComNet-PSR-VG, the initial step involves mapping EEG signals into a series of ordinal partitions using phase space reconstruction, generating a sequence of ordinal patterns. These ordinal patterns are then quantified to form a symbolized new sequence. Subsequently, the resulting symbolized sequence of ordinal patterns is transformed into a graph network using the visibility graph method. Two types of network node measures, average node degree (AND) and node degree entropy (NDE), are extracted from the graph networks as the inputs of machine learning for EEG emotion recognition. To evaluate the effectiveness of the proposed construction method of complex networks based on the visibility graph of ordinal patterns, comparative experiments are conducted using two types of simulated signals (random and Lorenz signals). Subsequently, EEG emotion recognition is performed on the SEED EEG emotion dataset. The experimental results show that, with AND as the feature, our proposed method is 4.88% higher than the existing visibility graph method and 12.23% higher than the phase space reconstruction method. These findings indicate that our proposed novel method for constructing complex networks from EEG signals not only achieves effective emotional EEG pattern recognition but also exhibits the potential for extension to other EEG pattern learning tasks, suggesting broad adaptability and application potential for our method. [ABSTRACT FROM AUTHOR]

Diversified ion-selective separation applications have dramatically incentivized the exploitation and performance modulation of highly ion-selective nanofiltration (NF) membranes. However, the ion selectivity of NF membranes is synergistically governed by multi-scale factors of membrane structural parameters and operational parameters, with the intrinsic ion-selective mechanism still ambiguous. Herein, we proposed an ensemble machine learning (ML) method to decouple key factors affecting the ionic selectivity of polyamide NF membranes. Membrane structural parameters and operational parameters were typically extracted as input variables and linked to mono−/divalent ion selectivity by model training based on Random Forest and XGBoost algorithms. The feature importance assessment indicated the critical role of membrane structure parameters on ion selectivity, wherein pore radius dominated the mono−/divalent anionic selectivity while zeta potential for mono−/divalent cationic selectivity. Partial dependence analyses further depicted intensive insights regarding the influence of membrane structural parameters on ion selectivity. Moreover, stochastic dataset splitting measurements demonstrated the accurate predictive capability of the model simultaneously possessing excellent stability and reliability. We anticipated that the implementation of ensemble ML in explicating the intricate ion-selective mechanism created platforms for understanding the structure-membrane performance correlation and orientally manufacturing highly ion-selective NF membranes. [Display omitted] • Ensemble machine learning was implemented to decouple the key features affecting ion selectivities of polyamide membranes. • RF and XGBoost algorithms were adopted to learn from relevant variables and evaluate permutation features importance. • Mono-/divalent anionic selectivity was dominated by pore size while zeta potential for mono-/divalent cationic selectivity. [ABSTRACT FROM AUTHOR]

Nanofiltration (NF) plays an increasingly central role in water/salts separation, which puts forward tailored requirements on NF membranes in a variety of application scenarios. However, the ambiguous separation mechanisms of NF including membrane structure parameters and operating conditions hinder the rational design of versatile NF membranes. Herein, machine learning was used to explore the correlation between membrane structure parameters and operating conditions with water/salts selectivity, and reveal the importance of the diverse features based on literature data. Two structural features of polyamide NF membrane (pore radius and zeta potential) and two operating parameters (pressure and feed concentration) were typically extracted and associated with water/salts selectivity. Random Forest and XGBoost models were employed to learn from relevant variables and assess their importance. The results showed that membrane structure parameters attached more importance to water/salts selectivity than that of operating conditions accompanying the variable influence for different typed salts, where symmetrical salts were mainly governed by size sieving while Donnan exclusion for asymmetrical salts. Structure-performance relationships between pore radius, zeta potential and diverse water/salts selectivity were established using partial dependence plot analysis. It is anticipated that the constructed comprehensive insights can be further leveraged to tackle performance modulation and oriented design of multi-scenarios NF membranes. [Display omitted] • Machine learning was used to understand NF separation mechanisms. • Random Forest and XGBoost models were employed to learn from relevant variables and assess features importance. • Symmetrical salts were mainly governed by size sieving while Donnan exclusion for asymmetrical salts. • The integrated management of pore size and zeta potential for the oriented design of versatile NF membranes was highlighted. [ABSTRACT FROM AUTHOR]