Claret Anderson Faria, Casali Karina Rabello, Cunha Tatiana Sousa, Moraes Matheus Cardoso
Institute of Science and Technology, Federal University of São Paulo, São José dos Campos, Brazil.
Ann Biomed Eng. 2023 Nov;51(11):2393-2414. doi: 10.1007/s10439-023-03341-8. Epub 2023 Aug 5.
Emotions play a pivotal role in human cognition, exerting influence across diverse domains of individuals' lives. The widespread adoption of artificial intelligence and machine learning has spurred interest in systems capable of automatically recognizing and classifying emotions and affective states. However, the accurate identification of human emotions remains a formidable challenge, as they are influenced by various factors and accompanied by physiological changes. Numerous solutions have emerged to enable emotion recognition, leveraging the characterization of biological signals, including the utilization of cardiac signals acquired from low-cost and wearable sensors. The objective of this work was to comprehensively investigate the current trends in the field by conducting a Systematic Literature Review (SLR) that focuses specifically on the detection, recognition, and classification of emotions based on cardiac signals, to gain insights into the prevailing techniques employed for signal acquisition, the extracted features, the elicitation process, and the classification methods employed in these studies. A SLR was conducted using four research databases, and articles were assessed concerning the proposed research questions. Twenty seven articles met the selection criteria and were assessed for the feasibility of using cardiac signals, acquired from low-cost and wearable devices, for emotion recognition. Several emotional elicitation methods were found in the literature, including the algorithms applied for automatic classification, as well as the key challenges associated with emotion recognition relying solely on cardiac signals. This study extends the current body of knowledge and enables future research by providing insights into suitable techniques for designing automatic emotion recognition applications. It emphasizes the importance of utilizing low-cost, wearable, and unobtrusive devices to acquire cardiac signals for accurate and accessible emotion recognition.
情绪在人类认知中起着关键作用，在个体生活的各个领域都产生影响。人工智能和机器学习的广泛应用激发了人们对能够自动识别和分类情绪及情感状态的系统的兴趣。然而，准确识别人类情绪仍然是一项艰巨的挑战，因为它们受到各种因素的影响并伴随着生理变化。为实现情绪识别，已出现众多解决方案，利用生物信号的特征，包括利用从低成本可穿戴传感器获取的心脏信号。这项工作的目的是通过进行系统文献综述（SLR）全面研究该领域的当前趋势，该综述特别关注基于心脏信号的情绪检测、识别和分类，以深入了解这些研究中用于信号采集、提取特征、诱发过程和分类方法的主流技术。使用四个研究数据库进行了系统文献综述，并根据提出的研究问题对文章进行了评估。27篇文章符合选择标准，并被评估了使用从低成本可穿戴设备获取的心脏信号进行情绪识别的可行性。文献中发现了几种情绪诱发方法，包括用于自动分类的算法，以及仅依靠心脏信号进行情绪识别的关键挑战。本研究扩展了当前的知识体系，并通过提供有关设计自动情绪识别应用的合适技术的见解来推动未来的研究。它强调了利用低成本、可穿戴且不引人注目的设备获取心脏信号以进行准确且可及的情绪识别的重要性。
