Virtual Reality (VR) provides immersive and interactive experiences in healthcare, education, entertainment, and defense. However, cybersickness remains a major barrier to its widespread adoption, reducing user comfort and engagement. Early and accurate detection of cybersickness is critical to developing adaptive VR systems that ensure safety and improve usability. In this study, we propose a novel real-time cybersickness detection approach using Bidirectional Long Short-Term Memory (Bi-LSTM) networks trained on electroencephalography (EEG) signals. Power Spectral Density (PSD) and Signal Magnitude Area (SMA) features were extracted to capture frequency- and amplitude-related characteristics of cybersickness. EEG data were collected from six electrodes across frontal (F3–F4), prefrontal (FP1–FP2), and central parietal (P3–P4) regions during VR exposure. The proposed Bi-LSTM model achieved 95% classification accuracy, significantly outperforming baseline methods. Results indicate that cybersickness can be reliably detected with a compact EEG setup, supporting resource-efficient, real-time monitoring for adaptive VR environments.

The diffusion of virtual reality (VR) technology has highlighted several user experiences challenges, including cybersickness (CS), mental workload (MWL), eye fatigue (EF), and physical fatigue (PHF). To address these issues, a comprehensive human factors and ergonomics (HFE) tool is necessary. This study developed a specialized HFE questionnaire to assess primary issues in VR environments. Ninety-three participants used VR headsets to test the questionnaire, which was validated through expert opinions and statistical analysis. The questionnaire consists of 19 questions categorized into four groups: MWL (4 items), PHF (5 items), CS (5 items), and EF (5 items). The questionnaire showed high reliability and validity, with a Cronbach’s alpha coefficient of 0.91, a mean content validity index of 0.83, and a content validity ratio of 0.81. Structural validity was also confirmed with acceptable Chi-square and root mean square error of approximation scores. The results support the validity and reliability of the questionnaire, making it a useful tool for assessing and improving VR user experiences.

This study examined the effects of two locomotion methods (joystick and teleportation) and two postures (sitting and standing) on mental workload (MWL) in virtual reality (VR). Sixty participants played a VR game using a 2 × 2 experimental design, with assessments including Electroencephalography (alpha and theta bands), Electrocardiography (heart rate and heart-rate variability indices), and the NASA Task Load Index (NASA-TLX). The results showed lower theta activities and higher alpha activities in the joystick condition, indicating higher MWL in the teleportation condition, primarily due to time demand and effort. Sitting posture resulted in lower mental load and higher heart rate with increased Standard Deviation of Normal-to-Normal intervals (SDNN) compared to standing, suggesting higher MWL in the standing posture. The NASA-TLX highlighted physical demand, effort, and time demand as crucial factors in MWL related to posture. These findings provide a basis for developing human factors and ergonomics (HF/E) guidelines for VR, emphasizing the importance of locomotion methods and user posture in reducing mental workload.

Abstract. Image forensics and counter forensics (CF) are two competing fields that have experienced significant developments in recent years. Interestingly, the use of histogram is popular in both forensic detectors and counter-forensic methods. In this work, we focus on the histogram-based CF methods; in particular, we propose a quasi-convex version of SSIM and MSSIM as the cost function of CF which helps in restricting search domain for optimal solution to the CF problem. Also, we propose two sub-optimal methods for this problem: (1) a gradient descent version of the optimal counter-forensics method (OCM) with the cost function MSSIM instead of MSE (which we call GDOCM), and (2) another method that employs unitary matrices as the transfer matrix (which we call UMM). We numerically compare the proposed methods with the OCM method in different settings including the common JPEG compression detection scenario. Our experiments confirm superiority of the proposed methods compared to OCM.

A variety of human factors/ergonomics (HFE) problems have been studied by researchers and developers in VR environments. This systematic review aimed to summarize important HFE issues and classify the validated instruments used to quantify them in virtual reality environments. The most representative electronic databases for this review (2013–2022) were searched for original articles. The results showed that aspects, such as cybersickness, visual fatigue, mental workload, performance, spatial presence, and usability were the most relevant HFE issues assessed, whereas some aspects, such as physical workload, posture, stress, and discomfort, were consider less often. Previous studies have neglected some human factors and ergonomic issues, such as physical ergonomics, stress, and aftereffects, such as fatigue and human error. In virtual environments, presence was an emerging human factor compared to real environments. Most techniques were unidimensional and subjective. Future studies should focus on more factors and risks associated with HFE by emphasizing objective techniques and multidimensional subjective methods.

This study investigated the effects of the target size and movement distance on user performance and workload in a virtual reality (VR) environment. In a repeated-measures laboratory study, 36 participants (18 male and 18 female) performed the drag-and-drop task as a standard human–computer interaction (HCI) task with different target sizes (1, 1.5, 2, 2.5, and 3 cm) and movement distances (5, 9, 13, 17, and 20 cm). Task completion time (TCT), error rate, and movement time (MT) were measured as performance indices, whereas physical load and effort were assessed as workload indices. The results demonstrated that the target size and movement distance significantly affected all performance measures and workload indices. Large target sizes produced better performance and lower workloads; however, large movement distances decreased performance and increased workload. However, sex had no significant effect on the performance or workload during the drag-and-drop tasks. The best target sizes were 2.5 and 3 cm, and the worst size was 1 cm. The best movement distances were 5 and 9 cm, and the worst distance was 20 cm. The results of this study can provide useful reference information for developing VR technology based on human factors and demonstrate that additional basic research is required to reflect the distinctive features of VR in the future.

Repetitive Transcranial Magnetic Stimulation (rTMS) is proposed as an effective treatment for major depressive disorder (MDD). However, because of the suboptimal treatment outcome of rTMS, the prediction of response to this technique is a crucial task. We developed a deep learning (DL) model to classify responders (R) and non-responders (NR). With this aim, we assessed the pre-treatment EEG signal of 34 MDD patients and extracted effective connectivity (EC) among all electrodes in four frequency bands of EEG signal. Two-dimensional EC maps are put together to create a rich connectivity image and a sequence of these images is fed to the DL model. Then, the DL framework was constructed based on transfer learning (TL) models which are pre-trained convolutional neural networks (CNN) named VGG16, Xception, and EfficientNetB0. Then, long short-term memory (LSTM) cells are equipped with an attention mechanism added on top of TL models to fully exploit the spatiotemporal information of EEG signal. Using leave-one subject out cross validation (LOSO CV), Xception-BLSTM-Attention acquired the highest performance with 98.86% of accuracy and 97.73% of specificity. Fusion of these models as an ensemble model based on optimized majority voting gained 99.32% accuracy and 98.34% of specificity. Therefore, the ensemble of TL-LSTM-Attention models can predict accurately the treatment outcome.

This paper presents an accurate modeling technique for inclusion of the frequency-dependent characteristics of a wind turbine grounding system into time-domain codes for lightning transient studies. In this technique, first, the frequency response of grounding system is determined using an electromagnetic approach based on the method-of-moment solutions of the governing Maxwell's equations. A time-domain state-space model of the resultant frequency response of the grounding system is then obtained by making use of the vector fitting technique. The proposed technique is used to analyze the effects of wide-band modeling of grounding system on predicted lightning transient overvoltages in a typical wind power plant. It is shown that the predicted overvoltage by the conventional resistive model of the grounding system gives an underestimation of those obtained accurately using the proposed model.

Nowadays, among the microscopic traffic flow modeling approaches, the car-following models are increasingly used by transportation experts to utilize appropriate intelligent transportation systems. Unlike previous works, where the reaction delay is considered to be fixed, in this paper, a modified neural network approach is proposed to simulate and predict the car-following behavior based on the instantaneous reaction delay of the driver-vehicle unit as the human effects. This reaction delay is calculated based on a proposed idea, and the model is developed based on this feature as an input. In this modeling, the inputs and outputs are chosen with respect to the reaction delay to train the neural network model. Using the field data, the performance of the model is calculated and compared with the responses of some existing neural network car-following models. Considering the difference between the responses of the actual plant and the predicted model as the error, comparison shows that the error in the proposed model is significantly smaller than that that in the other models.

Nowadays, simulation has become a cost-effective option for the evaluation of infrastructure improvements, on-road traffic management systems, and in vehicle driver support systems due to the fast evolution of computational modeling techniques. This paper presents a Locally Linear Neuro-Fuzzy (LLNF) model to simulate and predict the future behavior of a Driver-Vehicle-Unit (DVU). Local Linear Model Tree (LOLIMOT) learning algorithm is applied to train the model using real traffic data. This model was developed based on a new idea for estimating the instantaneous reaction of DVU, as an input of LLNF model. The model?s performance was evaluated based on real observed traffic data and also through comparisons with the results of LLNF models based on constant reaction delay. The results showed that LLNF model based on instantaneous reaction delay input outperformed the other car following models.

A driving simulator experiment is presented investigating different road departure prevention (RDP) setups. To induce the risk of road departure, thirty test drivers were asked to avoid a pylon-confined area (obstacle) while keeping the vehicle within the road limits. The RDP system intervened by applying a haptic-feedback (i.e., haptic shared control) and/or correcting the steering angle (i.e., drive-by-wire (DBW) input-mixing shared control) in the event that a vehicle road departure was likely to occur. The system that determines the correcting steering input is a RDP controller based on the driver's inputs. The results showed that DBW effectively helped drivers to stay within road limits and reduced workload. The haptic shared control had a significant influence on the measured steering torque, but limited effect on the steering wheel angle and the vehicle path. The DBW system resulted in drivers making counter-corrections demoting their performance. In conclusion, shared control for RDP is effective, although more research needs to be conducted regarding the human response in situations where the relationship between the steering wheel angle and the front wheels' steering angle is altered while driving.