An energy screening and morphology characterization-based hybrid expert scheme for automatic identification of micro-sleep event K-complex

Exploring emotional climate recognition in peer conversations through bispectral features and affect dynamics

BACKGROUND AND OBJECTIVE

Emotion recognition in conversations using artificial intelligence (AI) has gained significant attention due to its potential to provide insights into human social behavior. This study extends AI-based emotion recognition to the recognition of emotional climate (EC), which reflects the joint emotional atmosphere dynamically created and perceived by peers during conversations. The objective is to propose and evaluate a novel approach, MLBispec, for EC recognition using speech signals.

METHODS

The MLBispec approach involves time-windowed bispectral analysis of conversational speech signals to extract features related to nonlinear harmonic interactions. These features are combined with peers' affect dynamics, derived from emotion labeling for the same time windows, to form an extended feature set. The combined feature set is then fed into machine learning (ML) classifiers. MLBispec was evaluated on the IEMOCAP, K-EmoCon, and SEWA open-access datasets, which provide 2D emotion annotations (arousal and valence) divided into low/high classes. Additionally, cross-lingual experiments were conducted to test the framework's generalization across languages.

RESULTS

Experimental results demonstrated that MLBispec outperformed previous deep learning-based state-of-the-art approaches in speech emotion recognition, achieving accuracies of 82.6% for arousal and 75.4% for valence. The framework's incorporation of both qualitative and quantitative EC measurements enhanced its ability to characterize the dynamic speech representations of conversational affective structures. Cross-lingual experiments further validated the robustness of MLBispec.

CONCLUSIONS

The findings highlight the effectiveness of MLBispec in objectively recognizing peers' EC during conversations, setting a new standard for practical emotionally-aware applications. These include point-of-care healthcare, human-computer interfaces (HCI), and large-language models (LLMs). By enabling dynamic and reliable EC recognition, MLBispec paves the way for advancements in emotionally intelligent systems.

Overview of a Sleep Monitoring Protocol for a Large Natural Population

A standard operating procedure for studying the sleep phenotypes in a large population cohort is proposed. It is intended for academic researchers in investigating the sleep phenotypes in conjunction with the clinical sleep disorders assessment guidelines. The protocol refers to the definitive American Academy of Sleep Medicine (AASM) manual for setting polysomnography (PSG) technical specifications, scoring of sleep and associated events, etc. On this basis, it not only provides a standardized procedure of sleep interview, sleep-relevant questionnaires, and laboratory-based PSG test, but also offers a comprehensive process of sleep data analysis, phenotype extraction, and data storage. Both the objective sleep data recorded by PSG test and subjective sleep information obtained by the sleep interview and sleep questionnaires are involved in the data acquisition procedure. Subsequently, sleep phenotypes can be characterized by observable/inconspicuous physiological patterns during sleep from PSG test or can be marked by sleeping habits like sleep quality, sleep latency, sleep duration, habitual sleep efficiency, sleep disturbances, daytime dysfunction, etc., from sleep interview or questionnaires derived. In addition, solutions to the problems that may be encountered during the protocol are summarized and addressed. With the protocol, it can significantly improve scientific research efficiency and reduce unnecessary workload in large population cohort studies. Moreover, it is also expected to provide a valuable reference for researchers to conduct systematic sleep research.