Pattern Recognition of Cognitive Load Using EEG and ECG Signals

Xiong, Ronglong; Kong, Fanmeng; Yang, Xuehong; Liu, Guangyuan; Wang, Wen

doi:10.3390/s20185122

Cited by 34 publications

(18 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used eight algorithms based on feature selection to classify the datasets, which included K-nearest neighbor (KNN), neural network (NN), linear discriminant analysis (LDA) [ 40 ], logistic regression (LR) [ 41 ], random forest (RF) [ 27 , 41 , 42 ], decision tree (DT) [ 42 , 43 ], support vector machines (SVM) [ 23 ] and gradient boost decision tree (GBDT). All algorithms were implemented with Python sklearn library.…”

Section: Resultsmentioning

confidence: 99%

Emotion Recognition Based on Skin Potential Signals with a Portable Wireless Device

Chen

et al. 2021

Sensors

View full text Add to dashboard Cite

Emotion recognition is of great importance for artificial intelligence, robots, and medicine etc. Although many techniques have been developed for emotion recognition, with certain successes, they rely heavily on complicated and expensive equipment. Skin potential (SP) has been recognized to be correlated with human emotions for a long time, but has been largely ignored due to the lack of systematic research. In this paper, we propose a single SP-signal-based method for emotion recognition. Firstly, we developed a portable wireless device to measure the SP signal between the middle finger and left wrist. Then, a video induction experiment was designed to stimulate four kinds of typical emotion (happiness, sadness, anger, fear) in 26 subjects. Based on the device and video induction, we obtained a dataset consisting of 397 emotion samples. We extracted 29 features from each of the emotion samples and used eight well-established algorithms to classify the four emotions based on these features. Experimental results show that the gradient-boosting decision tree (GBDT), logistic regression (LR) and random forest (RF) algorithms achieved the highest accuracy of 75%. The obtained accuracy is similar to, or even better than, that of other methods using multiple physiological signals. Our research demonstrates the feasibility of the SP signal’s integration into existing physiological signals for emotion recognition.

show abstract

Section: Resultsmentioning

confidence: 99%

Emotion Recognition Based on Skin Potential Signals with a Portable Wireless Device

Chen

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Classification algorithms include classifying between discrete MWL states (i.e., resting, low and high) with the use of ML models, such as Artificial Neural Networks (ANN) [47,48], Support Vector Machines (SVM) [38,49] or Linear Discriminant Analysis (LDA) [19,41] (or extended variants). In addition to this, some studies compare several classification models when performing MWL estimations [50,51]. The use of regression models, such as Neuro Fuzzy Systems (NFS) [46,52,53] and Gaussian process regression [44], provides a continuous estimation of MWL but is less reported.…”

Section: Multimodal Fusion For Inferring Mwlmentioning

confidence: 99%

“…Whereas studies by Zhang et al and Wang et al [46,58,59] demonstrated large time intervals, Lim et al [52] lacked the ability to demonstrate an inference of MWL during an online validation. Moreover, recent studies have outlined the importance of investigating the features contributing to the performance of the respective model used [50,51]. This is also an area that was not investigated for NFS in previous studies.…”

Section: Multimodal Fusion For Inferring Mwlmentioning

confidence: 99%

Online Multimodal Inference of Mental Workload for Cognitive Human Machine Systems

et al. 2021

View full text Add to dashboard Cite

With increasingly higher levels of automation in aerospace decision support systems, it is imperative that the human operator maintains a high level of situational awareness in different operational conditions and a central role in the decision-making process. While current aerospace systems and interfaces are limited in their adaptability, a Cognitive Human Machine System (CHMS) aims to perform dynamic, real-time system adaptation by estimating the cognitive states of the human operator. Nevertheless, to reliably drive system adaptation of current and emerging aerospace systems, there is a need to accurately and repeatably estimate cognitive states, particularly for Mental Workload (MWL), in real-time. As part of this study, two sessions were performed during a Multi-Attribute Task Battery (MATB) scenario, including a session for offline calibration and validation and a session for online validation of eleven multimodal inference models of MWL. The multimodal inference model implemented included an Adaptive Neuro Fuzzy Inference System (ANFIS), which was used in different configurations to fuse data from an Electroencephalogram (EEG) model’s output, four eye activity features and a control input feature. The results from the online validation of the ANFIS models demonstrated that five of the ANFIS models (containing different feature combinations of eye activity and control input features) all demonstrated good results, while the best performing model (containing all four eye activity features and the control input feature) showed an average Mean Absolute Error (MAE) = 0.67 ± 0.18 and Correlation Coefficient (CC) = 0.71 ± 0.15. The remaining six ANFIS models included data from the EEG model’s output, which had an offset discrepancy. This resulted in an equivalent offset for the online multimodal fusion. Nonetheless, the efficacy of these ANFIS models could be seen with the pairwise correlation with the task level, where one model demonstrated a CC = 0.77 ± 0.06, which was the highest among all the ANFIS models tested. Hence, this study demonstrates the ability for online multimodal fusion from features extracted from EEG signals, eye activity and control inputs to produce an accurate and repeatable inference of MWL.

show abstract

“…Moreover, the multivariate pattern analysis method can discover potential biomarkers based on multimodal physiological signals to distinguish patients from normal controls at the individual level and further highlight the physiological mechanism of PD behavioral symptoms. Recently, many researchers combine multimodal physiological data with machine learning methods and have obtained many valuable results [15][16][17][18]. Kyle Ross et al used ECG and galvanic skin response (GSR) signals to classify professional trauma patients and novices at a professional level and achieved an accuracy of 79.84% [15].…”

Section: Introductionmentioning

confidence: 99%

“…Kyle Ross et al used ECG and galvanic skin response (GSR) signals to classify professional trauma patients and novices at a professional level and achieved an accuracy of 79.84% [15]. Rong L et al used EEG and ECG signals combined with the SVM model to classify cognitive load, which yielded an accuracy of 97.2% [16]. Sara et al used electromyogram (EMG) and ECG data combined with feature selection and machine learning algorithms to detect the psychological stress of healthy people, and the four levels of pressure recognition accuracy reached 96.2% [17].…”

Section: Introductionmentioning

confidence: 99%

Diagnosing Parkinson’s Disease Using Multimodal Physiological Signals

Guo

Wang

et al. 2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

Parkinson's disease (PD) is the second most common neurodegenerative disease after Alzheimer's disease. Due to the complex etiology and diverse clinical symptoms, it's difficult to accurately diagnose PD. In this study, we applied multimodal physiological signals, which include electroencephalography (EEG), electrocardiogram (ECG), photoplethysmography (PPG), and respiratory (RA), to classify PD and healthy control (HC) based on a multimodal support vector machine (SVM). Our experiments achieved an accuracy of 96.03%. Besides, we performed statistical analysis on the four types of physiological data of the PD group and the HC group. Results showed that the EEG of non-dementia PD patients had a significant decrease in high-frequency power, and the high-frequency energy distribution of the normalized PPG signal increased compared with HC. The current study suggests that combining the physiological information of multiple models and machine learning methods could improve the diagnosis accuracy of PD disease and be a potentially effective method of clinical diagnosis.

show abstract

Pattern Recognition of Cognitive Load Using EEG and ECG Signals

Cited by 34 publications

References 40 publications

Emotion Recognition Based on Skin Potential Signals with a Portable Wireless Device

Emotion Recognition Based on Skin Potential Signals with a Portable Wireless Device

Online Multimodal Inference of Mental Workload for Cognitive Human Machine Systems

Diagnosing Parkinson’s Disease Using Multimodal Physiological Signals

Contact Info

Product

Resources

About