Features Of EEG Signals Research Articles

Multiscale Hjorth Descriptor on Epileptic EEG Classification

The electroencephalogram (EEG) examination provides information on the brain’s electricity, especially in cases of epilepsy. Since the characteristics of EEG signals are nonlinear and nonstationary, visual inspection becomes very difficult. To overcome this problem, digital EEG signal processing was developed. Automatic epileptic EEG recognition is an area of interest on which much research focuses. The complexity approach to EEG signal analysis is interesting to be used as feature extraction, referring to the nonlinear characteristics of the signal. This study proposed an automatic epileptic EEG classification method based on the multiscale Hjorth descriptor measurement. EEG signals consisting of normal, interictal, and seizure (ictal) were simulated. The signal is scaled into new signals using the coarse-grained procedure on a scale of 1–20. Then, the Hjorth parameter which consists of activity, mobility, and complexity is calculated on the new signal. This process produces a feature vector that is used in the classification stage. Support vector machine (SVM) is used to evaluate the proposed feature extraction method. Simulation results showed that the Hjorth parameter on a scale of 1–15 yields 99.5% accuracy. The proposed method is expected to be applied to digital EEG for seizure detection and prediction.

Automatic epileptic seizure detection based on persistent homology.

Epilepsy is a prevalent brain disease, which is quite difficult-to-treat or cure. This study developed a novel automatic seizure detection method based on the persistent homology method. In this study, a Vietoris-Rips (VR) complex filtration model was constructed based on the EEG data. And the persistent homology method was applied to calculate the VR complex filtration barcodes to describe the topological changes of EEG recordings. Afterward, the barcodes as the topological characteristics of EEG signals were fed into the GoogLeNet for classification. The persistent homology is applicable for multi-channel EEG data analysis, where the global topological information is calculated and the features are extracted by considering the multi-channel EEG data as a whole, without the multiple calculations or the post-stitching. Three databases were used to evaluate the proposed approach and the results showed that the approach had high performances in the epilepsy detection. The results obtained from the CHB-MIT Database recordings revealed that the proposed approach can achieve a segment-based averaged accuracy, sensitivity and specificity values of 97.05%, 96.71% and 97.38%, and achieve an event-based averaged sensitivity value of 100% with 1.22s average detection latency. In addition, on the Siena Scalp Database, the proposed method yields averaged accuracy, sensitivity and specificity values of 96.42%, 95.23% and 97.6%. Multiple tasks of the Bonn Database also showed achieved accuracy of 99.55%, 98.63%, 98.28% and 97.68%, respectively. The experimental results on these three EEG databases illustrate the efficiency and robustness of our approach for automatic detection of epileptic seizure.

EEG Topography Amplification Using FastGAN-ASP Method

Electroencephalogram (EEG) signals are bioelectrical activities generated by the central nervous system. As a unique information factor, they are correlated with the genetic information of the subjects, exhibiting robustness against forgery. The development of biometric identity recognition based on EEG signals has significantly improved the security and accuracy of biometric recognition. However, EEG signals obtained from incompatible acquisition devices have low universality and are prone to noise, making them challenging for direct use in practical identity recognition scenarios. Employing deep learning network models for data augmentation can address the issue of data scarcity. Yet, the time–frequency–space characteristics of EEG signals pose challenges for extracting features and efficiently generating data with deep learning models. To tackle these challenges, this paper proposes a data generation method based on channel attention normalization and spatial pyramid in a generative adversative network (FastGAN-ASP). The method introduces attention mechanisms in both the generator and discriminator to locate crucial feature information, enhancing the training performance of the generative model for EEG data augmentation. The EEG data used here are preprocessed EEG topographic maps, effectively representing the spatial characteristics of EEG data. Experiments were conducted using the BCI Competition IV-Ⅰ and BCI Competition IV-2b standard datasets. Quantitative and usability evaluations were performed using the Fréchet inception distance (FID) metric and ResNet-18 classification network, validating the quality and usability of the generated data from both theoretical and applied perspectives. The FID metric confirmed that FastGAN-ASP outperforms FastGAN, WGAN-GP, and WGAN-GP-ASP in terms of performance. Moreover, utilizing the dataset augmented with this method for classification recognition achieved an accuracy of 95.47% and 92.43%.

Research on Emotional Improvement of Product Design Based on Emotion Recognition Technology

Abstract In this paper, we first extracted the time-domain features, frequency-domain features and spatial-domain features of EEG signals, combined with the three-stage feature selection algorithm applicable to the binary classification problem and the multi-classification problem, and constructed the SEE model for emotion recognition based on EEG signals. Then, based on the three-level design model of emotion, emotion decoding and labeling are carried out on the instinctive layer, behavioral layer and reflective layer of product design, and the constructed model is combined to improve the product design emotionally. Finally, after analyzing the results of product emotion annotation, we explore the performance of the EEG-based emotion recognition model and the improvement effect of product design emotionalization. The results showed that the average accuracy of the EEG signal emotion recognition model for various emotion recognition was about 0.99, and the intensity of emotion intensity in Dahe was 0.32 and 0.25, respectively, accounting for 0.57 of the total sample, and the performance evaluation indicators of the eight emotions were greater than 0.85. Ninety percent of product experiencers had pre- and post-improvement differences between [0.12, 0.22] for happiness and [-0.20, -0.04] for dissatisfaction.

The Effect of Transcranial Direct Current Stimulation on Linear and Nonlinear EEG Signal Characteristics in Contamination Obsessive-Compulsive Disorder Patients

The Effect of Transcranial Direct Current Stimulation on Linear and Nonlinear EEG Signal Characteristics in Contamination Obsessive-Compulsive Disorder Patients

Cross-subject emotion EEG signal recognition based on source microstate analysis

Electroencephalogram (EEG) signals are very weak and have low spatial resolution, which has led to less satisfactory accuracy in cross-subject EEG-based emotion classification studies. Microstate analyses of EEG sources can be performed to determine the important spatiotemporal characteristics of EEG signals. Such analyses can be used to cluster rapidly changing EEG signals into multiple brain prototype topographies, fully utilizing the spatial information contained in the EEG signals and providing a neural representation for emotional dynamics. To better utilize the spatial information of brain signals, source localization analysis on the EEG signals was first conducted. Then, a microstate analysis on the source-reconstructed EEG signals is conducted to extract the microstate features of the data. We conducted source microstate analysis on the participant data from the odor-video physiological signal database (OVPD-II) dataset. The experimental results show that the source microstate feature topologies of different participants under the same emotion exhibited a high degree of correlation, which was proven by the analysis of microstate feature topographic maps and the comparison of two-dimensional feature visualization maps of the differential entropy (DE) and power spectral density (PSD). The microstate features represent more abstract emotional information and are more robust. The extracted microstate features were then used with the style transfer mapping method to transfer the feature data from the source domain to the target domain and were then used in support vector machines (SVMs) and convolutional neural networks (CNNs) for emotion recognition. The experimental results show that the cross-subject classification accuracies of the microstate features in SVMs were 84.90 ± 8.24% and 87.43 ± 7.54%, which were 7.19 and 6.95% higher than those obtained with the PSD and 0.51 and 1.79% higher than those obtained with the DE features. In CNN, the average cross-subject classification accuracies of the microstate features were 86.44 and 91.49%, which were 7.71 and 19.41% higher than those obtained with the PSD and 2.7 and 11.76% higher than those obtained with the DE features.

A Fine-Grained Approach for EEG-Based Emotion Recognition Using Clustering and Hybrid Deep Neural Networks

Emotion recognition, as an important part of human-computer interaction, is of great research significance and has already played a role in the fields of artificial intelligence, healthcare, and distance education. In recent times, there has been a growing trend in using deep learning techniques for EEG emotion recognition. These methods have shown higher accuracy in recognizing emotions when compared with traditional machine learning methods. However, most of the current EEG emotion recognition performs multi-category single-label prediction, and is a binary classification problem based on the dimensional model. This simplifies the fact that human emotions are mixed and complex. In order to adapt to real-world applications, fine-grained emotion recognition is necessary. We propose a new method for building emotion classification labels using linguistic resource and density-based spatial clustering of applications with noise (DBSCAN). Additionally, we integrate the frequency domain and spatial features of emotional EEG signals and feed these features into a serial network that combines a convolutional neural network (CNN) and a long short-term memory (LSTM) recurrent neural network (RNN) for EEG emotion feature learning and classification. We conduct emotion classification experiments on the DEAP dataset, and the results show that our method has an average emotion classification accuracy of 92.98% per subject, validating the effectiveness of the improvements we have made to our emotion classification method. Our method for emotion classification holds potential for future use in the domain of affective computing, such as mental health care, education, social media, and so on. By constructing an automatic emotion analysis system using our method to enable the machine to understand the emotional implications conveyed by the subjects’ EEG signals, it can provide healthcare professionals with valuable information for effective treatment outcomes.

Research on MI EEG signal classification algorithm using multi-model fusion strategy coupling

To enhance the accuracy of motor imagery(MI)EEG signal recognition, two methods, namely power spectral density and wavelet packet decomposition combined with a common spatial pattern, were employed to explore the feature information in depth in MI EEG signals. The extracted MI EEG signal features were subjected to series feature fusion, and the F-test method was used to select features with higher information content. Here regarding the accuracy of MI EEG signal classification, we further proposed the Platt Scaling probability calibration method was used to calibrate the results obtained from six basic classifiers, namely random forest (RF), support vector machines (SVM), Logistic Regression (LR), Gaussian naïve bayes (GNB), eXtreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM). From these 12 classifiers, three to four with higher accuracy were selected for model fusion. The proposed method was validated on Datasets 2a of the 4th International BCI Competition, achieving an average accuracy of MI EEG data of nine subjects reached 91.46%, which indicates that model fusion was an effective method to improve classification accuracy, and provides some reference value for the research on MI brain-machine interface.

Functional connectivity-enhanced feature-grouped attention network for cross-subject EEG emotion recognition

Electroencephalogram (EEG)-based automatic emotion recognition technologies are gaining significant attention and have become crucial in the field of brain–computer interfaces (BCIs). In particular, deep learning methods have been widely used in emotion recognition in recent years. However, most existing methods generally tend to focus on EEG spatiotemporal information, which ignores the potential relationships between brain activity signals and the differences in functional connectivity under different emotions. Here, we raise a functional connectivity-enhanced feature-grouped attention network (FC-FAN) for cross-subject emotion recognition. The FC-FAN model developed is a dual-input model. One input consists of the differential entropy data derived from the original EEG signals, while the other input comprises the functional connectivity data obtained through the calculation of the phase synchronization index. Then the primary EEG features of the two groups’ input data are extracted through two specific residual blocks. Next, the designed time-series feature grouped attention module (TFGAM) and functional connectivity feature grouped attention model (F2GAM) are utilized to mark interested information or suppress uninterested features for the two groups’ features, respectively. Finally, generated information interacts through a fusion operator. The designed framework could not only sufficiently learn the spatiotemporal features of EEG signals but also clearly analyze nonlinear correlations between electrode signals. Comprehensive tests confirm that the FC-FAN has an excellent effect on subject-independent emotion recognition tasks.

Diagnosis of Alzheimer's disease via resting-state EEG: integration of spectrum, complexity, and synchronization signal features.

Alzheimer's disease (AD) is the most common neurogenerative disorder, making up 70% of total dementia cases with a prevalence of more than 55 million people. Electroencephalogram (EEG) has become a suitable, accurate, and highly sensitive biomarker for the identification and diagnosis of AD. In this study, a public database of EEG resting state-closed eye recordings containing 36 AD subjects and 29 normal subjects was used. And then, three types of signal features of resting-state EEG, i.e., spectrum, complexity, and synchronization, were performed by applying various signal processing and statistical methods, to obtain a total of 18 features for each signal epoch. Next, the supervised machine learning classification algorithms of decision trees, random forests, and support vector machine (SVM) were compared in categorizing processed EEG signal features of AD and normal cases with leave-one-person-out cross-validation. The results showed that compared to normal cases, the major change in EEG characteristics in AD cases was an EEG slowing, a reduced complexity, and a decrease in synchrony. The proposed methodology achieved a relatively high classification accuracy of 95.65, 95.86, and 88.54% between AD and normal cases for decision trees, random forests, and SVM, respectively, showing that the integration of spectrum, complexity, and synchronization features for EEG signals can enhance the performance of identifying AD and normal subjects. This study recommended the integration of EEG features of spectrum, complexity, and synchronization for aiding the diagnosis of AD.

MS-FTSCNN: An EEG emotion recognition method from the combination of multi-domain features

Electroencephalography (EEG), as a physiological cue, is more objective and reliable in identifying emotions than non-physiological cues. Previous methods only consider one or two relationships among frequency, time and spatial domain features of EEG signals, and the designed models may still be relatively large in terms of parameters. Meanwhile, the training process of the previous networks is troublesome during algorithm optimization. To address these challenges, we design a simple and efficient feature preprocessing method to obtain a 3D feature structure that contains EEG signal information in the frequency, time and spatial domains simultaneously. Then, we propose a multiscale frequency–time–spatial convolutional model, MS-FTSCNN, which is able to capture frequency, time and spatial features from the input signals and fuse three features more efficiently. Moreover, the multi-scale one-dimensional convolutional kernel in our method can reduce network parameters, providing possibilities for real-time online applications. Finally, the recognition accuracies of arousal and valence of our proposed model are 93.82%, 94.48% on DEAP dataset and 92.64%, 92.15% on MOHNOB-HCI dataset, which is higher than most existing methods.

An IoT-Based Intelligent Selection of Multidomain Feature for Smart Healthcare Using Reinforcement Learning in Schizophrenia

Currently, the health industry by the Internet of Things (IoT) is developing rapidly, and Electroencephalogram (EEG) signal has become a bridge for human-machine communication. EEG signal feature selection is a key link in brain nerves research and has important practical application value. Therefore, we propose an IoT-based Intelligent Selection of Multi-domain Feature for multimodal transformer EEG signal using reinforcement learning in Schizophrenia. First of all, the features of the multimodal EEG signal sequence by the IoT were extracted from time domain, frequency domain, and spatial domain; Second, the average pooling layer was added to improve the design of the transformer model for deep feature extraction of EEG signal; finally, reinforcement learning was introduced to run operation with the extracted features as input and the improved transformer model as agent. At the same time, entropy and Pearson correlation coefficient calculation were introduced to select feature subsets, and feature intelligent selection of EEG signal in multiple domains was completed through interaction between the agent and the environment. Experiments were performed on DEAP, EEG Motor Movement/Imagery Data set, BCI2008 competition data set and data set of a hospital. The results show that the feature extraction and feature visualization effect of the proposed algorithm is good, and the feature selection precision is as high as about 90%, and the average time is only about 13 seconds. These findings indicate the feasibility of the proposed feature intelligent selection algorithm in the study of EEG signal in schizophrenia, which provides a good basis for further study on the integration of IoT with the healthy industry.

Chebyshev polynimal dempster convolutional hearing sensitivity level detection with auditory evoked potentials

The EEG-based HTR utilizing AEP responses of both group of participants with normal hearing and abnormal hearing are managed with the objective of detecting hearing sensitivity level using Chebyshev Recurrence Polynomial and Dempster Convolutional Neural Network (CRP-DCNN) is designed. The CRP-DCNN method is split into three sections. They are preprocessing using Chebyshev Recurrence Polynomial Filter, feature extraction by employing Orthogonalized Singular Value and Median Skewed Wavelet. Here, both Orthogonalized Singular Value Decomposition-based parametric and Median Skewness-based non-parametric modeling techniques are employed for first obtaining the hearing threshold factors and then extracting statistical features for further processing. Finally Dempster Convolutional Neural Network-based Classification for detecting hearing sensitivity level is presented. Hence, the objective to determine the significant correlations between the brain dynamics and the auditory responses and detect the hearing sensitivity level of the group of participants with normal hearing and with the group of participants with hearing loss are designed on accordance with the features of EEG signals. Simulations are performed in MATLAB to validate the features of EEG signals.

AMGCN-L: an adaptive multi-time-window graph convolutional network with long-short-term memory for depression detection

Objective. Depression is a common chronic mental disorder characterized by high rates of prevalence, recurrence, suicide, and disability as well as heavy disease burden. An accurate diagnosis of depression is a prerequisite for treatment. However, existing questionnaire-based diagnostic methods are limited by the innate subjectivity of medical practitioners and subjects. In the search for a more objective diagnostic methods for depression, researchers have recently started to use deep learning approaches. Approach. In this work, a deep-learning network, named adaptively multi-time-window graph convolutional network (GCN) with long-short-term memory (LSTM) (i.e. AMGCN-L), is proposed. This network can automatically categorize depressed and non-depressed people by testing for the existence of inherent brain functional connectivity and spatiotemporal features contained in electroencephalogram (EEG) signals. AMGCN-L is mainly composed of two sub-networks: the first sub-network is an adaptive multi-time-window graph generation block with which adjacency matrices that contain brain functional connectivity on different time periods are adaptively designed. The second sub-network consists of GCN and LSTM, which are used to fully extract the innate spatial and temporal features of EEG signals, respectively. Main results. Two public datasets, namely the patient repository for EEG data and computational tools, and the multi-modal open dataset for mental-disorder analysis, were used to test the performance of the proposed network; the depression recognition accuracies achieved in both datasets (using tenfold cross-validation) were 90.38% and 90.57%, respectively. Significance. This work demonstrates that GCN and LSTM have eminent effects on spatial and temporal feature extraction, respectively, suggesting that the exploration of brain connectivity and the exploitation of spatiotemporal features benefit the detection of depression. Moreover, the proposed method provides effective support and supplement for the detection of clinical depression and later treatment procedures.

Convolutional gated recurrent unit-driven multidimensional dynamic graph neural network for subject-independent emotion recognition

Electroencephalogram (EEG) could directly reflect human brain activities. Recently, EEG-based emotion recognition technology has attracted widespread attention. However, although most of the existing methods can extract temporal and spatial features of EEG signals, the extraction process of the time-series information and spatial features is separate from each other. Some spatial features may be lost when extracting time-series information, and vice versa. Additionally, the non-Euclidean representations between the EEG electrodes cannot be ignored. In response to these issues, we construct a convolutional gated recurrent unit-driven multidimensional dynamic graph neural network (CGRU-MDGN), which mines its local spatial characteristics of EEG signals while learning the temporal information and captures non-Euclidean spatial features between EEG channels to classify emotions more accurately. Specifically, we substitute the fully connected layers of the GRU with convolution layers, which can take into account both the local spatial features and time-series information of EEG signals. Next, multiple non-Euclidean spatial representations are generated using multidimensional dynamic graph convolution. Furthermore, the characteristics of different dimensions or views are merged through the adaptive-weighted summation technique to realize the maximized feature extraction as much as possible. Comprehensive experiments reveal that the constructed CGRU-MDGN could achieve competitive recognition results on subject-independent emotion recognition tasks.

An EEG-based cross-subject interpretable CNN for game player expertise level classification

Electroencephalogram (EEG) signals have been demonstrated to be an effective method for game player expertise level classification, as it can reflect the activity state of the player’s brain during the game task. Although many efforts have been made to classify the expertise level of game players based on EEG signals, existing methods still need to be improved in identifying common brain patterns across different subjects. In this article, we propose a Spatiotemporal-Based Brain Pattern Recognition Network (BPR-STNet), which uses depthwise separable convolution to extract the spatiotemporal features of EEG signals and incorporates Gradient-weighted Class Activation Mapping (Grad-CAM) interpretable technology to explore common brain patterns among different subjects. To evaluate the model’s performance, we use non-invasive wearable devices to collect EEG signals from 19 subjects during the game process. The results of the leave-one-out cross-subject experiments demonstrate that the average accuracy of the model’s game player expertise level classification is 82%–86.32% in the five frequency bands (δ, θ, α, β, γ). Among them, the γ frequency band has the highest accuracy of 86.32%. More importantly, the average accuracy of our method is 1.56%–5.79% higher than the state-of-the-art deep learning methods. Moreover, interpretable results indicate the model can learn biologically significant features from EEG frequency bands. Overall, this study can offer a new idea of using deep learning to explore common brain patterns and features among different subjects at the same level. The BPR-STNet code is available at https://github.com/L000077/BPR-STNet.

Classification of attention deficit/hyperactivity disorder based on EEG signals using a EEG-Transformer model ∗ ∗This work was supported in part by the National Key R&D Program of China (2022YFE0197500), National Natural Science Foundation of China (#81927804, #62101538), Science and Technology Planning Project of Shenzhen (#JSGG20210713091808027, #JSGG20211029095801002), China Postdoctoral Science Foundation (2022M710968), and the Science and Technology Program of Guangdong Province

Objective. Attention-deficit/hyperactivity disorder (ADHD) is the most common neurodevelopmental disorder in adolescents that can seriously impair a person’s attention function, cognitive processes, and learning ability. Currently, clinicians primarily diagnose patients based on the subjective assessments of the Diagnostic and Statistical Manual of Mental Disorders-5, which can lead to delayed diagnosis of ADHD and even misdiagnosis due to low diagnostic efficiency and lack of well-trained diagnostic experts. Deep learning of electroencephalogram (EEG) signals recorded from ADHD patients could provide an objective and accurate method to assist physicians in clinical diagnosis. Approach. This paper proposes the EEG-Transformer deep learning model, which is based on the attention mechanism in the traditional Transformer model, and can perform feature extraction and signal classification processing for the characteristics of EEG signals. A comprehensive comparison was made between the proposed transformer model and three existing convolutional neural network models. Main results. The results showed that the proposed EEG-Transformer model achieved an average accuracy of 95.85% and an average AUC value of 0.9926 with the fastest convergence speed, outperforming the other three models. The function and relationship of each module of the model are studied by ablation experiments. The model with optimal performance was identified by the optimization experiment. Significance. The EEG-Transformer model proposed in this paper can be used as an auxiliary tool for clinical diagnosis of ADHD, and at the same time provides a basic model for transferable learning in the field of EEG signal classification.

PolyCosGraph: A Privacy-Preserving Cancelable EEG Biometric System

Recent findings confirm that biometric templates derived from electroencephalography (EEG) signals contain sensitive information about registered users, such as age, gender, cognitive ability, mental status and health information. Existing privacy-preserving methods such as hash function and fuzzy commitment are not cancelable, where raw biometric features are vulnerable to hill-climbing attacks. To address this issue, we propose the PolyCosGraph, a system based on <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Poly</b> nomial transformation embedding <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Cos</b> ine functions with <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Graph</b> features of EEG signals, which is a privacy-preserving and cancelable template design that protects EEG features and system security against multiple attacks. In addition, a template corrupting process is designed to further enhance the security of the system, and a corresponding matching algorithm is developed. Even when the transformed template is compromised, attackers cannot retrieve raw EEG features and the compromised template can be revoked. The proposed system achieves the authentication performance of 1.49% EER with a resting state protocol, 0.68% EER with a motor imagery task, and 0.46% EER under a watching movie condition, which is equivalent to that in the non-encrypted domain. Security analysis demonstrates that our system is resistant to attacks via record multiplicity, preimage attacks, hill-climbing attacks, second attacks and brute force attacks.

Electroencephalogram Emotion Recognition Using Combined Features in Variational Mode Decomposition Domain

Using Electroencephalogram (EEG) to recognize human emotion has attracted increasing attention. However, features extraction from EEG is a challenging work because it is a non-stationary continuous sequential signal. To obtain more pattern information, a combined features extraction method in Variational Mode Decomposition (VMD) domain is proposed, which can extract local features of EEG signals to overcome the effects caused by non-stationarity. This method first decomposes EEG into several components using VMD, and then combined features of Differential Entropy (DE) and Short-Time Energy (STE) are extracted from each component. To optimize combined features, the important features are selected by tree modes, and the feature set is dimensionally reduced by further using Linear Discriminant Analysis (LDA). Moreover, an XGBoost classifier with Bayesian optimization is presented to classify different emotional states. Binary-class and multi-class EEG emotion recognition are conducted on the DEAP dataset, from which the experimental results show that accuracy of binary-class classification is 81.77% for High/Low Valence and 80.47% for High/Low Arousal, and accuracy of 91.41%, 94.27%, 94.27% and 93.49% are obtained for HVHA, LVHA, LVLA and HVLA, respectively, which demonstrate its effectiveness.

VRNPT: A Neuropsychological Test Tool for Diagnosing Mild Cognitive Impairment Using Virtual Reality and EEG Signals

Mild cognitive impairment is associated with many neurodegenerative diseases. It is essential to detect mild cognitive impairment on time to reduce the prevalence of such disorders. Nevertheless, present clinically employed test scales and biomarkers are time-consuming, user-unfriendly, and expensive. Hence, we developed a neuropsychological test system based on virtual reality in this study, the Virtual Reality Neuropsychological Mild Cognitive Impairment Test (VRNPT). The diagnosis and classification of MCI were achieved by effectively combining digital cognitive parameters and EEG signal features obtained during the VRNPT cognitive task. The VRNPT contains three head-mounted display-based cognitive tasks that assess participants’ attention, memory, spatial perception, working memory, and visuospatial executive ability across multiple cognitive domains of functioning. We investigated how to design and optimize these tasks. We conducted a field study by recruiting 80 participants (40 MCI patients and 40 normal older adults). The results showed that the classification accuracy of combining digitized cognitive parameters and EEG signals during VRNPT was 91.3%, higher than using only digitized parameters from VRNPT and applying EEG signals alone, demonstrating the validity and feasibility of this method for diagnosing MCI. The user satisfaction survey showed that the subjects were satisfied with VRNPT.