Trust is a critical factor in effective human–automation interaction, influencing user reliance, acceptance, and system performance. As automated systems become increasingly complex and computationally advanced, real-time trust quantification is essential. This review systematically examines the literature using a PRISMA-guided approach, integrating studies on neural mechanisms, physiological measures, and computational modelling. Relevant studies were collected from multiple databases, screened according to inclusion criteria, and categorised by experimental paradigms, neural modalities, preprocessing pipelines, feature types, and machine/deep learning frameworks. We critically evaluate classical machine learning and deep learning approaches, highlighting consistent neural correlates, including oscillatory activity, connectivity patterns, and frontal and temporoparietal activations. The review also reveals a critical misalignment between psychological theories of trust, how trust is labelled in experiments, and how computational models are trained, raising concerns about the specificity and interpretability of many reported trust markers. Key challenges include limited feature exploration, dataset scarcity, real-time assessment strategies, and underutilisation of multimodal fusion across feature-, decision-, and network-level representations. By synthesising current evidence and identifying key gaps, this work provides a roadmap for developing adaptive, interpretable, and generalisable trust models that support safer and more reliable human–automation systems in complex, real-world scenarios.

In today’s world, intelligent machines play increasingly important roles in collaboration with humans, necessitating a deeper level of trust between individuals and technology. However, there is a significant research gap in understanding how humans calibrate their trust in automation, which is crucial for optimising system usage and preventing the misuse or disuse of automated systems. In this article, we introduce an artificial neural network (ANN) framework designed to classify trust and distrust in automation based on electroencephalogram (EEG) signals. Our objective is to develop an effective model that can accurately differentiate between states of trust and distrust exhibited by individuals towards automated systems. In this research, we utilised an existing online dataset specifically focused on eliciting trust and distrust states. This dataset served as the foundation for feature extraction and selection, training, and validation of the proposed ANN framework, which is aimed at robustly classifying trust and distrust based on EEG data. To evaluate the effectiveness, the performance of the proposed ANN framework was compared with three traditional machine learning methods: Naive Bayes, K-Nearest Neighbour, and Support Vector Machine. Performance metrics such as accuracy, sensitivity, and specificity were used for trust and distrust classification. The results demonstrated the efficacy of the ANN approach in leveraging EEG data to enhance the classification of trust and distrust towards automation. This research contributes to advancing the understanding of human trust dynamics in human-machine interaction, which is essential for developing more reliable and trustworthy automated systems.

The increasing sophistication of autonomous systems and robotics has spurred research into the unique dynamics of human-autonomy teaming (HAT). These advanced technologies aim to enhance decision-making, situational awareness, mutual understanding, and interpersonal relationships, thereby minimizing risks in collaborative endeavors. However, achieving effective HAT requires careful attention to team trust, particularly in scenarios that move beyond simple human–machine dyads to involve complex, multiagent systems and distributed teams. This review undertakes a comprehensive exploration and evaluation of trust measurement techniques within the domain of HAT, focusing on methods that are sensitive to the nuances of these complex team dynamics. Emphasising the significance of trust measurement in optimising team performance, the review categorizes existing empirical works into subjective (e.g., self-report, questionnaires, surveys) and objective (e.g., behavioral, physiological) indices. Drawing insights from recent literature (2019–2024), the article explores the complexities of trust measurement, addressing methodologies employed by researchers and synthesizing their findings. The study suggests directions for further investigation into improving trust assessment techniques and developing practical models to better suit the evolving context of human-autonomy collaboration. The review highlights gaps in current methods and suggests avenues for future research, particularly in refining trust calibration models for dynamic, evolving contexts in human-autonomy collaboration and for understanding how trust is distributed and managed across complex team structures.

Abstract Reinforcement learning (RL) has emerged as an effective approach for building an intelligent system, which involves multiple self-operated agents to collectively accomplish a designated task. More importantly, there has been a renewed focus on RL since the introduction of deep learning that essentially makes RL feasible to operate in high-dimensional environments. However, there are many diversified research directions in the current literature, such as multi-agent and multi-objective learning, and human-machine interactions. Therefore, in this paper, we propose a comprehensive software architecture that not only plays a vital role in designing a connect-the-dots deep RL architecture but also provides a guideline to develop a realistic RL application in a short time span. By inheriting the proposed architecture, software managers can foresee any challenges when designing a deep RL-based system. As a result, they can expedite the design process and actively control every stage of software development, which is especially critical in agile development environments. For this reason, we design a deep RL-based framework that strictly ensures flexibility, robustness, and scalability. To enforce generalization, the proposed architecture also does not depend on a specific RL algorithm, a network configuration, the number of agents, or the type of agents.

Measuring team performance and physiological compliance (PC) within a team have gained interest in the last few decades. The team’s performance or functioning of a team is overseen by attributes such as collaboration, coordination, attitudes and motivation. Team emergent states such as situational awareness, trust, emotions and mutual understanding influence the attributes of teams. This study examines the relationship between PC and collaboration. It also investigates how the cognitive state influences this relationship. Seventeen teams, each with three members, participated in a collaborative simulated task, while their electrocardiogram (ECG) activity was recorded via a chest strap device. Short-term time-domain measures of heart rate variability (HRV) were derived for each participant. PC was established using the mean of the cross-correlation (CC) between dyads within a team. A linear regression model was employed to examine the relationship between PC and self-reported measures of team collaboration. This in turn will be applied to investigate how cognitive state between team members influences that relationship. The results have shown a statistically significant (p<0.05) positive relationship between PC and collaboration. In conclusion, PC has the potential to be an objective method to quantity teamwork effectiveness where it can be assessed via self-reported collaboration.

In this research, we present a new emotion recognition model using wavelet packet energy features using electroencephalography (EEG) data. Wavelet packets has been widely used as a means of time-frequency analysis of EEG in many different applications including brain computer interface systems. Features for emotion recognition are extracted from the EEG signals using a depth 6 wavelet packet tree. Wavelet packet energy of the sub-bands corresponding to delta (0-4Hz), theta (4-8Hz), alpha (8-13Hz), beta (13-30Hz), and gamma (30-49Hz) are taken as emotional features. Feature selection based on feature ranking is applied to select the most prominent EEG channel-frequency combinations for emotion recognition. Four classical classifiers such as linear discriminant analysis, support vector machine, K nearest neighbor and naive Bayes were used to detect the emotional states from the extracted features. To evaluate the effectiveness and validation of the proposed model, the SEED database has been employed. Based on the experiment results obtained, our method demonstrates that the LDA is more suitable for emotion recognition as compared to other classical classifier, which achieving the best average accuracy of 90.9386. Emotion recognition systems with high accuracy give opportunities to study real world applications such as mental state and fatigue monitoring.

Employing electroencephalography (EEG) data for classifying emotion has attracted a significant interest among researchers. With the ever advancing machine learning and neural network computational power, several models have been proposed for classifying the emotion states. Training an efficient classifier requires selection of appropriate features demanding complex computations. The present article investigates whether dense convolutional neural networks can extract the features from just pre-processed raw EEG signals enabling a suitability for online classification. The article presents a fully connected multi-channel neural network model comprising of dense con-volutional layers coupled with sparse autoencoder and dense perceptron layers for classifying emotions from 62-channel EEG data. The proposed model uses the dense convolution layers to learn emotion features directly from each channel. The cascaded SAE layer coupled with dense perceptron network learns correlations between the channels for efficient classification. In addition, different methods exist to generate training and testing sets for validating classifier models. In this light, the article discusses three most recent methods to generate training and testing sets employed in emotion classification. The proposed model achieves a best testing accuracy of 97.42%.

Spike sorting of electrophysiological data plays an important role in deciphering useful information from the brain. Unsupervised clustering of brain data relative to respective neurons is important to understand single cell and networks dynamics. A large number of clustering techniques exist in the literature; however, the dependency of these clustering algorithms on the selection of appropriate parameters, such as, bandwidth or threshold window size is critical. Iterative methods are generally employed to estimate optimal parameters, however, significant computational time and associated large number of iterations make the clustering inefficient to implement. To address this issue, we introduce a robust Optimal Parameter Estimation (OPE) Algorithm that can estimate the optimized parameters in a fast and efficient way. The performance of the OPE algorithm is tested on MeanShift and DBSCAN clustering algorithms. Three different extracellular recorded datasets including two simulated and one single human cell, as well as two feature sets including PCA and Haar Wavelets are used for validation purposes.

Multi-screens or wide screen setup is becoming increasingly popular in many work places and training environments. However, there has been limited studies of their effect on human health and performance. In this study, we investigate individuals performance and eye movement characteristics while performing a visual task on multi-screen setup consisting of three monitors. During the task, subjects had to share their attention among three screens to identify the location of the visual stimulus and respond accordingly. Subjects' score was calculated based on validity of input to stimulus and response time, while fixation characteristics were investigated with respect to eye movements. The results show that the use of 3-screens added extra demand on the individual causing a decrease on the score and decrease in reaction time. In a further investigation, we found statistically significant negative correlation between the task score and the participant's age while a statistically significant positive correlation between the response time and the participant's age. In addition, the use of multi-screens to perform the tasks caused both fixation occurrences and duration to decrease, denoting an increased alertness since respond was given with less fixation duration and occurrences and less response time.

The development of eye tracking-based applications has witnessed a number of advancements over the past few years. As a result, a number of low cost commercial remote vision-based eye trackers started to appear in the market. Consequently, a number of research communities started to explore the feasibility of extending the eye-tracking capabilities beyond single computer screen and utilize it in multi-screen setup. One of the main challenges for the wide adoption of such eye trackers in multi-screen setup, is their limitations when it comes to an intuitive and reliable way for tracking human eye movements across these multiple screens without losing much of the eye tracking data itself. In this work, a novel data-driven approach based on deep recurrent neural networks for a reliable and responsive switching mechanism between low cost multi-screen eye trackers is proposed. Our approach has achieved a competent results in terms of higher accuracy and lower positive rate in detecting accurately the screen the subject is attending to with F1 measure score of 85%.

The purpose of this study is to investigate the possibility to use eye movements to control the laparoscope during a laparoscopic surgery. Laparoscopic surgery usually needs at least two doctors, a surgeon and a laparoscope assistant. The view of the operating surgeon is provided by the laparoscope assistant. As misunderstandings or conflicts of cooperation may happen, an ideal way is that the surgeon has a full control of all the instruments including the surgical tools and laparoscope. To achieve it, an eye based interaction method is introduced in this paper that allows surgeons to control the view by themselves. With recent developments in the eye tracker platforms and associated eye tracking technologies, many non-contact eye tracking systems are available. It can record where a person is looking at any time and a sequence of eye movements. This information can be used to know where is the attention and interest of the person on a display. As such, surgeon's attention can be captured and then be followed by moving the laparoscope to the region of interest. To have a safe and efficient evaluation on the usability, a virtual reality based laparoscopic surgery simulation is built. It is based on Unity with two haptic devices simulating the surgical tools, a 3D mouse providing 6 degrees-of-freedom control of the camera and an eye tracker capturing eyes' positions on a display. Experiments on moving a camera left, right, up, down, in, out and to specified locations using eyes are conducted, and moreover the performances of the proposed eye based self-control and the 3D mouse based other-control are compared. The results are promising where the proposed pointing method leads to 43.6% faster completion of the tasks against the traditional other-control method using the 3D mouse.

This paper presents an approach to analysis of multiclass EEG data obtained from the brain computer interface (BCI) applications. The proposed approach comprises two stages including feature extraction using the common spatial pattern (CSP) and classification using fuzzy logic systems (FLS). CSP is used to extract significant features that are then fed into FLS as inputs for classification. The metaheuristic population-based particle swarm optimization method is used to train parameters of the FLS. The multiclass motor imagery dataset IIa from the BCI competition IV is used for experiments to highlight the superiority of the proposed approach against competing methods, which include linear discriminant analysis, naïve bayes, k-nearest neighbour, ensemble learning AdaBoost and support vector machine. Results from experiments show the great accuracy of the combination of CSP and FLS. Therefore, the proposed approach can be implemented effectively in the practical BCI systems, which would be helpful for people with impairments and rehabilitation.

Spike sorting plays an important role in analysing electrophysiological data and understanding neural functions. Developing spike sorting methods that are highly accurate and computationally inexpensive is always a challenge in the biomedical engineering practice. This paper proposes an automatic unsupervised spike sorting method using the landmark-based spectral clustering (LSC) method in connection with features extracted by the locality preserving projection (LPP) technique. Gap statistics is employed to evaluate the number of clusters before the LSC can be performed. Experimental results show that LPP spike features are more discriminative than those of the popular wavelet transformation (WT). Accordingly, the proposed method LPP-LSC demonstrates a significant dominance compared to the existing method that is the combination between WT feature extraction and the superparamagnetic clustering. LPP and LSC are both linear algorithms that help reduce computational burden and thus their combination can be applied into realtime spike analysis.

This study developed and tested a research model which examined the impact of user perceptions of self-efficacy (SE) and virtual environment (VE) efficacy on the effectiveness of VE training systems. The model distinguishes between the perceptions of one's own capability to perform trained tasks effectively and the perceptions of system performance, regarding the established parameters from literature. Specifically, the model posits that user perceptions will have positive effects on task performance and memory. Seventy-six adults participated in a VE in a controlled experiment, designed to empirically test the model. Each participant performed a series of object assembly tasks. The task involved selecting, rotating, releasing, inserting and manipulating 3D objects. Initially, the results of factor analysis demonstrated dimensionality of two user perception measures and produced a set of empirical validated factors underlining the VE efficacy. The results of regression analysis revealed that SE had a significant positive effect on perceived VE efficacy. No significant effects were found of perceptions on performance and memory. Furthermore, the study provided insights into the relationships between the perception measures and performance measures for assessing the efficacy of VE training systems. The study also addressed how well users learn, perform, adapt to and perceive the VE training, which provides valuable insight into the system efficacy. Research and practical implications are presented at the end of the paper.

In this research, we study the effect of feature selection in the spike detection and sorting accuracy. We introduce a new feature representation for neural spikes from multichannel recordings. The features selection plays a significant role in analyzing the response of brain neurons. The more precise selection of features leads to a more accurate spike sorting, which can group spikes more precisely into clusters based on the similarity of spikes. Proper spike sorting will enable the association between spikes and neurons. Different with other threshold-based methods, the cepstrum of spike signals is employed in our method to select the candidates of spike features. To choose the best features among different candidates, the Kolmogorov-Smirnov (KS) test is utilized. Then, we rely on the super paramagnetic method to cluster the neural spikes based on KS features. Simulation results demonstrate that the proposed method not only achieve more accurate clustering results but also reduce computational burden, which implies that it can be applied into real-time spike analysis.

The fact that medical images have redundant information is exploited by researchers for faster image acquisition. Sample set or number of measurements were reduced in order to achieve rapid imaging. However, due to inadequate sampling, noise artefacts are inevitable in Compressive Sensing (CS) MRI. CS utilizes the transform sparsity of MR images to regenerate images from under-sampled data. Locally sparsified Compressed Sensing is an extension of simple CS. It localises sparsity constraints for sub-regions rather than using a global constraint. This paper, presents a framework to use local CS for improving image quality without increasing sampling rate or without making the acquisition process any slower. This was achieved by exploiting local constraints. Localising image into independent sub-regions allows different sampling rates within image. Energy distribution of MR images is not even and most of noise occurs due to under-sampling in high energy regions. By sampling sub-regions based on energy distribution, noise artefacts can be minimized. Experiments were done using the proposed technique. Results were compared with global CS and summarized in this paper.

Super-resolution is a method of post-processing image enhancement that increases the spatial resolution of video or images. Existing super-resolution techniques apply only to images captured of a planar scene. This paper aims to extend super-resolution concepts from the 2D domain to the 3D domain, drawing on ideas from both super-resolution and multi-view geometry, two fields of research that until now have predominantly been studied in isolation. 2D super-resolution methods are not without their complexities and limitations. However, once multiple views of a scene are considered within a super-resolution framework, a new range of issues arise that must also be resolved. For example, when input images of a scene with variation in depth are considered, it is no longer clear how and where the images should be registered. This paper describes the use of sparse 3D reconstruction in order to `register' the input images, which are then transferred to a novel image plane and combined to increase the perceived detail in the scene. Experimental results using real images captured from generally positioned input cameras are presented.

Magnetic Resonance Imaging (MRI) is one of the prominent medical imaging techniques. This process is time-consuming and can take several minutes to acquire one image. The aim of this research is to reduce the imaging process time of MRI. This issue is addressed by reducing the number of acquired measurements using theory of Compressive Sensing (CS). Compressive Sensing exploits sparsity in MR images. Randomly under sampled k-space generates incoherent noise which can be handled using a nonlinear image reconstruction method. In this paper, a new framework is presented based on the idea to exploit non-uniform nature of sparsity in MR images, where local sparsity constrains were used instead of traditional global constraint, to further reduce the sample set. Experimental results and comparison with CS using global constraint are demonstrated.

Correspondence estimation in one of the most active research areas in the field of computer vision and number of techniques has been proposed, possessing both advantages and shortcomings. Among the techniques reported, multiresolution analysis based stereo correspondence estimation has gained lot of research focus in recent years. Although, the most widely employed medium for multiresolution analysis is wavelets and multiwavelets bases, however, relatively little work has been reported in this context. In this work we have tried to address some of the issues regarding the work done in this domain and the inherited shortcomings. In the light of these shortcomings, we propose a new technique to overcome some of the flaws that could have significantly impact on the algorithm performance and has not been addressed in the earlier propositions. Proposed algorithm uses multiresolution analysis enforced with wavelets/multiwavelts transform modulus maxima to establish correspondences between the stereo pair of images. Variety of wavelets and multiwavelets bases, possessing distinct properties such as orthogonality, approximation order, short support and shape are employed to analyse their effect on the performance of correspondence estimation. The idea is to provide knowledge base to understand and establish relationships between wavelets and multiwavelets properties and their effect on the quality of stereo correspondence estimation.

Mobile robots are providing great assistance operating in hazardous environments such as nuclear cores, battlefields, natural disasters, and even at the nano-level of human cells. These robots are usually equipped with a wide variety of sensors in order to collect data and guide their navigation. Whether a single robot operating all sensors or a swarm of cooperating robots operating their special sensors, the captured data can be too large to be transferred across limited resources (e.g. bandwidth, battery, processing, and response time) in hazardous environments. Therefore, local computations have to be carried out on board the swarming robots to assess the worthiness of captured data and the capacity of fused information in a certain spatial dimension as well as selection of proper combination of fusion algorithms and metrics. This paper introduces to the concepts of Type-I and Type-II fusion errors, fusion capacity, and fusion worthiness. These concepts together form the ladder leading to autonomous fusion systems.

A multiresolution technique based on multiwavelets scale-space representation for stereo correspondence estimation is presented. The technique uses the well-known coarse-to-fine strategy, involving the calculation of stereo correspondences at the coarsest resolution level with consequent refinement up to the finest level. Vector coefficients of the multiwavelets transform modulus are used as corresponding features, where modulus maxima defines the shift invariant high-level features (multiscale edges) with phase pointing to the normal of the feature surface. The technique addresses the estimation of optimal corresponding points and the corresponding 2D disparity maps. Illuminative variation that can exist between the perspective views of the same scene is controlled using scale normalization at each decomposition level by dividing the details space coefficients with approximation space. The problems of ambiguity, explicitly, and occlusion, implicitly, are addressed by using a geometric topological refinement procedure. Geometric refinement is based on a symbolic tagging procedure introduced to keep only the most consistent matches in consideration. Symbolic tagging is performed based on probability of occurrence and multiple thresholds. The whole procedure is constrained by the uniqueness and continuity of the corresponding stereo features. The comparative performance of the proposed algorithm with eight famous existing algorithms, presented in the literature, is shown to validate the claims of promising performance of the proposed algorithm.

A simple method for constructing M-band multi-wavelets using the super function idea is presented. The method is based on formulating the approximation order requirement in terms of a matrix equation and recognizing the generalized left eigenvectors of the matrix Lf a finite portion of the down sampled convolution matrix L as the coefficients that linearly combine to form the desired M-band spline super function with the desired approximation order. Several 3-band multi-wavelets with approximation orders two and three with multiplicity two and three are constructed.

A unified approach for constructing a large class of multi-wavelets is presented. This class includes Geranimo Hardin Massopust, Alpert and Daubechies-like multi-wavelets. The main emphasis is on approximation order of the resulting multi-scaling functions. The unified approach involves formulating the approximation order condition in the framework of super functions and recognizing that the generalized left eigenvectors of the resulting finite down-sampled convolution matrix gives the coefficients that enter the finite linear combination of scaling functions which produces the desired super function from which polynomials of desired degree can be locally approximated.

For multi-wavelets generalized left eigenvectors of the matrix H/sub f/ a finite portion of down-sampled convolution matrix H determine the combinations of scaling functions that produce the desired spline or scaling function from which polynomials of desired degree can be reproduced. This condition is used to construct Alpert's multi-wavelets with multiplicity two, three and four and with approximation orders two, three and four respectively. Higher-multiplicity Alpert multi-wavelets can also be constructed using this new method.