Graph Representation Integrating Signals for Emotion Recognition and Analysis

Abstract

Data reusability is an important feature of current research, just in every field of science. Modern research in Affective Computing, often rely on datasets containing experiments-originated data such as biosignals, video clips, or images. Moreover, conducting experiments with a vast number of participants to build datasets for Affective Computing research is time-consuming and expensive. Therefore, it is extremely important to provide solutions allowing one to (re)use data from a variety of sources, which usually demands data integration. This paper presents the Graph Representation Integrating Signals for Emotion Recognition and Analysis (GRISERA) framework, which provides a persistent model for storing integrated signals and methods for its creation. To the best of our knowledge, this is the first approach in Affective Computing field that addresses the problem of integrating data from multiple experiments, storing it in a consistent way, and providing query patterns for data retrieval. The proposed framework is based on the standardized graph model, which is known to be highly suitable for signal processing purposes. The validation proved that data from the well-known AMIGOS dataset can be stored in the GRISERA framework and later retrieved for training deep learning models. Furthermore, the second case study proved that it is possible to integrate signals from multiple sources (AMIGOS, ASCERTAIN, and DEAP) into GRISERA and retrieve them for further statistical analysis.

EDA-Graph: Graph Signal Processing of Electrodermal Activity for Emotional States Detection

“…Comparative analysis showed that conventional EDA features can detect changes but have limitations in characterizing nuanced emotional states. In contrast, graph features demonstrated greater sensitivity to subtle state variations, aligning with evidence on complementarity of physiological signals and network representations [103]. Overall, this pioneering study introduced an EDA-graph framework that captures complex nonlinear emotion-signal relationships and enables granular state differentiation.…”

“…The suitability of GSP for processing EDA signals was suggested by previous studies that showed that graph representations better characterize discrete structural patterns rather than just amplitude differences [77], [103]. In particular, three features capturing node-level information, TLC and THC, and three features capturing graph-level information, GNC, Diameter, and Radius, exhibited significant differences between the five emotional states.…”

“…By quantifying the frequency of different graphlet motifs, this metric captures the distribution of small-scale topological structures embedded within the global network. The graphlet profile provides a more granular characterization of network architecture than summary metrics like density or degree distribution [4], [27], [100], [102], [103]. In contrast, node-level features like centralities and clustering coefficients characterize the local topology and regional signal variations.…”

“…However, they lack sensitivity to the overall graph organization. While degree distributions reveal local connection density, they fail to summarize the full graph [62], [70], [103].…”

Ontological Model for Contextual Data Defining Time Series for Emotion Recognition and Analysis

“…The distinction of a time series is based on the distinction used in [14] and [85]. In Figure 6, the two independent divisions are presented.…”