Motor imagery BCI systems have demonstrated success in single-subject laboratory settings, where a classifier is trained using data from a single BCI user. Typically, multiple training sessions are needed to enhance the user's performance. To address this, the BCI community has developed Subject Transfer techniques, which reduce training time by leveraging data from other subjects, primarily as pretraining samples. This study introduces a novel subject transfer method that employs Wavelet Packet Decomposition (WPD) followed by Common Spatial Patterns (CSP) for feature extraction. Once the spatial features are extracted, binary particle swarm optimization (BPSO) is applied for feature selection. In this approach, 40% of the target subject's data is used to derive a BPSO filter, which is then applied to the data from all subjects before training and testing. The binary vector produced by BPSO acts as a filter, optimizing model performance by focusing on the most class-representative features. Classification is performed using linear support vector machines (SVMs) trained via Stochastic Gradient Descent (SGD), enabling the hyperplane to be pre-trained and allowing for the effective use of data collected outside of the user session in an interpretable way. The proposed method was evaluated using three benchmark BCI Competition datasets: III-IVa, IV-I, and IV-IIa. It outperformed the single-trial MI-EEG classification state-of-the-art by 3.4% on the BCI Competition III dataset IVa and by 8.4% on the BCI Competition IV dataset IIa. Additionally, it surpassed the subject-transfer MI-EEG classification state-of-the-art by 4.1 % on the BCI Competition III-IVa dataset.

Internet-based social engineering (SE) attacks are a major cyber threat. These attacks often serve as the first step in a sophisticated sequence of attacks that target, among other things, victims’ credentials and can cause financial losses. The problem has received mounting attention in recent years, with many publications proposing defenses against SE attacks. Despite this, the situation has not improved. In this article, we aim to understand and explain this phenomenon by investigating the root cause of the problem. To this end, we examine Internet-based SE attacks and defenses through a unique lens based on psychological factors (PFs) and psychological techniques (PTs). We find that there is a key discrepancy between attacks and defenses: SE attacks have deliberately exploited 46 PFs and 16 PTs in total, but existing defenses have only leveraged 16 PFs and seven PTs in total. This discrepancy may explain why existing defenses have achieved limited success and prompt us to propose a systematic roadmap for future research.

This study tracked eye movement in children with and without autism spectrum disorder (ASD) watching emotional biological and non-biological motion point-light-displays (PLDs). Older children with ASD focused on extremities while older typically developing (TD) children looked at figure’s heads, whereas not evident in the younger groups. These results suggest developmental advances in social-information biases in TD children not evident in children with ASD, together with atypical and potentially adaptive increases in attentional biases towards local motion cues with age in ASD. Potential avenues for future computational and methodological analyses are discussed.

Facial Expression Recognition (FER) plays a pivotal role in interpreting human emotions during social interactions. Using still facial images to recognize emotions presents challenges due to similarities between emotions and variations in lighting and poses. This study offers a fresh FER approach, harnessing VGG19 for extracting features and coupling it with an attention-focused residual block and an MLP for classifying emotions. When tested on prominent datasets like CK+, RAF-DB, and FER2013, the method achieved accuracies of 99.13%, 88.89%, and 89.06%, respectively. These results outpace current standards on CK+ and RAF-DB, and hold their own against top performances on FER2013, highlighting the efficacy of the proposed technique.

Emotion detection has become an increasingly important area of research in recent years, as it has numerous applications in fields such as psychology, marketing, and human-computer interaction. Deep learning has shown success in emotion recognition due to the availability of large amounts of data and the ability to learn complex patterns in facial expressions, speech, and physiological signals when recognizing emotions. However, there are challenges associated with variations in lighting, pose, and facial expressions. This study introduces a novel deep-learning approach for emotion detection, leveraging the power of VGGFace2 to classify six emotional poses in children. The proposed approach outperforms the state-of-the-art in the field, achieving a success rate of 96.3% on the CAFE dataset. A comprehensive evaluation of the findings and a detailed discussion of their potential implications is offered as part of the study. Facial Emotion Recognition (FER), VGGFace2, emotion detection

Background: Looking pattern differences are shown to separate individuals with Autism Spectrum Disorder (ASD) and Typically Developing (TD) controls. Recent studies have shown that, in children with ASD, these patterns change with intellectual and social impairments, suggesting that patterns of social attention provide indices of clinically meaningful variation in ASD. Method: We conducted a naturalistic study of children with ASD (n = 55) and typical development (TD, n = 32). A battery of eye-tracking video stimuli was used in the study, including Activity Monitoring (AM), Social Referencing (SR), Theory of Mind (ToM), and Dyadic Bid (DB) tasks. This work reports on the feasibility of spatial and spatiotemporal scanpaths generated from eye-gaze patterns of these paradigms in stratifying ASD and TD groups. Algorithm: This article presents an approach for automatically identifying clinically meaningful information contained within the raw eye-tracking data of children with ASD and TD. The proposed mechanism utilizes combinations of eye-gaze scan-paths (spatial information), fused with temporal information and pupil velocity data and Convolutional Neural Network (CNN) for stratification of diagnosis (ASD or TD). Results: Spatial eye-gaze representations in the form of scanpaths in stratifying ASD and TD (ASD vs. TD: DNN: 74.4%) are feasible. These spatial eye-gaze features, e.g., scan-paths, are shown to be sensitive to factors mediating heterogeneity in ASD: age (ASD: 2–4 y/old vs. 10–17 y/old CNN: 80.5%), gender (Male vs. Female ASD: DNN: 78.0%) and the mixture of age and gender (5–9 y/old Male vs. 5–9 y/old Female ASD: DNN:98.8%). Limiting scan-path representations temporally increased variance in stratification performance, attesting to the importance of the temporal dimension of eye-gaze data. Spatio-Temporal scan-paths that incorporate velocity of eye movement in their images of eye-gaze are shown to outperform other feature representation methods achieving classification accuracy of 80.25%. Conclusion: The results indicate the feasibility of scan-path images to stratify ASD and TD diagnosis in children of varying ages and gender. Infusion of temporal information and velocity data improves the classification performance of our deep learning models. Such novel velocity fused spatio-temporal scan-path features are shown to be able to capture eye gaze patterns that reflect age, gender, and the mixed effect of age and gender, factors that are associated with heterogeneity in ASD and difficulty in identifying robust biomarkers for ASD.

Motor Imagery (MI) based brain-computer inter-faces have diverse applications from providing communication capability to paralyzed and locked-in patients to controlling movement of wheelchairs for patients with lack of motor control/functionality. Lack of adequate number of samples to train predictive models due to reliance on Single Trial EEG (STE) study designs in which a large portion of EEG data from a participant/patient is used for training a classifier that is only able to somewhat reliably predict thought patterns of that participant during the same BCI recording session is one of the main bottlenecks of BCI studies. Not having enough training samples limit the use of advance classification methods such as deep neural networks, methods that are known to have better prediction accuracy. Session Transfer, using previous sessions EEG data of the same subject, and Subject Transfer, using EEG data of other participants performing the same task, are found as mechanisms to address the limitations of STE-based BCI systems and increase their practicality. This paper proposes two subject transfer protocols representing “Zero Trial” and “Target SUbject Re-tuned”. A Convolutional Neural Network (CNN) is used to develop a predictive model capable of reliably stratifying MI patterns in target subject. The CNN performance is assessed using 3 datasets from BCI competitions with 2 and 3 MI classes. The results indicated feasibility of”Zero Trial” in the sense of providing above chance level predictions across all subjects. “Target Subject without re-tuning” subject transfer performed worse than both the “Zero Trial” and “Target Subject Re-tuned” albeit still above chance level. Yet, “Target Subject Re-tuned” subject transfer protocol outperformed STE and “Zero Trial” in most subjects.

Motor Imagery (MI) based Brain Computer Interfaces (BCIs) are seen as effective mechanisms for motor rehabilitation. Aside from promises of MI based BCI systems, their utility are mainly limited to laboratory-based Single-Trial EEG studies where each participant/patient undergo a long and tedious EEG data recording session to train a classifier that can accurately stratify participant's MI patterns. Session and subject transfer frameworks are considered as liable solutions for this problem. This study assess the utility of deep learning models, trained on MI patterns from other subjects enrolled in a) the same study (Cross-Subject Within-Dataset (CSWD)) or b) across multiple studies (Cross-Subject Cross-Dataset (CSCD)), for stratifying EEG patterns representing 3 different MI tasks. The aim of the study is to a) highlight the effectiveness of subject transfer in MI-based BCI studies and b) evaluate the hypothesis that “there exist a set of unique MI patterns that are known to be impacted by differences across experiment design, EEG recording equipment, phenotype of participants and many other factors, but can be used to generate universal MI-based BCI systems”. Three well known dataset of BCI Competition IV Dataset I & IIa and BCI Competition III Dataset IVa are used to assess these hypothesises. First, results from Single Trial EEG analysis is considered as base-line and later a set of experiments are conducted to assess within dataset and across dataset subject transfer (CSWD & CSCD). The results indicate the proposed subject transfer methods achieved similar or higher performances compared to state-of-the-art.

Identifying oculomotor behaviors relevant for eye-tracking applications is a critical but often challenging task. Aiming to automatically learn and extract knowledge from existing eye-tracking data, we develop a novel method that creates rich representations of oculomotor scanpaths to facilitate the learning of downstream tasks. The proposed stimulus-agnostic Oculomotor Behavior Framework (OBF) model learns human oculomotor behaviors from unsupervised and semi-supervised tasks, including reconstruction, predictive coding, fixation identification, and contrastive learning tasks. The resultant pre-trained OBF model can be used in a variety of applications. Our pre-trained model outperforms baseline approaches and traditional scanpath methods in autism spectrum disorder and viewed-stimulus classification tasks. Ablation experiments further show our proposed method could achieve even better results with larger model sizes and more diverse eye-tracking training datasets, supporting the model’s potential for future eye-tracking applications. Open source code: http://github.com/BeibinLi/OBF.

This paper describes a reflexive multilayered mission planner with a mounted energy efficient local path planner for unmanned underwater vehicle's (UUV) navigation throughout complex subsea volume in a time variant semi-dynamic operation network. The UUV routing protocol in underwater wireless sensor network is generalized with a homogeneous dynamic knapsack-traveler salesman problem emerging with an adaptive path planning mechanism to address UUV's long-duration missions on dynamically changing subsea volume. The framework includes a base layer of global path planning, an inner layer of local path planning and an environmental sublayer. Such a multilayer integrated structure facilitates the framework to adopt any algorithm with real-time performance. The evolutionary technique known as differential evolution (DE) algorithm is employed by both base and inner layers to examine the performance of the framework in efficient mission timing and its resilience against the environmental disturbances. Relying on reactive nature of the framework and fast computational performance of the DE algorithm, the simulations show promising results and this new framework guarantees a safe and efficient deployment in a turbulent uncertain marine environment passing through a proper sequence of stations considering various constraint in a complex environment.

Most studies of executive function (EF) in Autism Spectrum Disorder (ASD) focus on cognitive information processing, emphasizing less the social interaction deficits core to ASD. We designed a mobile game that uses social and nonsocial stimuli to assess children's EF skills. The game comprised three components involving different EF skills: cognitive flexibility (shifting/inference), inhibitory control, and short-term memory. By recruiting 65 children with and without ASD to play the mobile game, we investigated the potential of such platforms for capturing important phenotypic characteristics of individuals with autism. Results highlighted between-diagnostic-group differences in playing patterns with children with ASD showing broad patterns of EF deficits, but with relative strengths in nonsocial short-term memory, and preserved response to emotional inhibition cues. We showed the system could predict IQ, an important target for clinical treatment, towards the goal of developing platforms to act as long-term, efficient, and effective behavioral biomarkers for ASD.

Augmentative and Alternative Communication (AAC) apps are apps that enable non-speech communicative forms. One class of AAC apps are speech-generating devices (SGDs), where icons/pictures are tapped to produce spoken words. These apps are widely used to support communication and language learning for individuals with disabilities such as autism spectrum disorder (ASD). Given that these apps are used in everyday scenarios, they can generate massive streams of data, providing a wealth of information regarding individual usage patterns and for developing usage model profiles. However, the utility and potential of these streams of data has been little explored from a data mining perspective. The objective of this study is to evaluate several feature representations of usage patterns, coupled with data mining and data modelling techniques, for identifying differences in AAC usage patterns between users with and without ASD. The study is conducted using data streams aggregated from an AAC app called FreeSpeech, specifically designed for individuals with learning disabilities and ASD. Several feature representations for modeling usage profiles based on temporal, behavioral and frequency of usage, are investigated. The potential of each usage representation is assessed using a collection of well-known and well-established learning methods such as support vector machine and ensemble learning. While, in general, prediction performance was only slightly above chance in most representations, results from unsupervised class labeling experiments showed promising results regarding the potential of stationary keypress usage representations with bootstrapped ensembles for separating ASD from non-ASD users.

Navigation in dynamic and uncertain environments in the absence of reliable environment map is challenging. In this study, we investigate the effectiveness of two variations of Particle Swarm Optimization (PSO) called Area Extended PSO (AEPSO) and Cooperative AEPSO (CAEPSO) in noisy environments in which the noise does not represent random noise originated from a single type of source but the combination of noises originating from different sources located in nearby or faraway positions. Knowledge Transfer and Transfer Learning that represent the use of the expertise and knowledge gained from previous experiments can improve the robots decision making and reduce the number of wrong decisions in such uncertain environments. This study investigates the impact of transfer learning on robots’ search in such hostile environment. The results highlight the feasibility of CAEPSO to be used as the movement controller and decision maker of a swarm of robots in the simulated uncertain environment when gained expertise from past trainings is transferred to the robots in the testing phase.

EEG signals usually have a high dimensionality which makes it difficult for classifiers to learn the difference of various classes in the underlying pattern in the signal. This paper investigates several evolutionary algorithms used to reduce the dimensionality of the data. The study presents electrode and feature reduction methods based on Genetic Algorithms (GA) and Particle Swarm Optimization (PSO). Evolution-based methods are used to generate a set of indexes presenting either electrode seats or feature points that maximizes the output of a weak classifier. The results are interpreted based on the dimensionality reduction achieved, the significance of the lost accuracy, and the possibility of improving the accuracy by passing the chosen electrode/feature sets to alternative classifiers.

EEG data contains high-dimensional data that requires considerable computational power for distinguishing different classes. Dimension reduction is commonly used to reduces the necessary training time of the classifiers with some degree of accuracy lost. The dimension reduction is usually performed on either feature or electrode space. In this study, a new dimension reduction method that reduce the number of electrodes and features using variations of Particle Swarm Optimization (PSO) is used. The variation is in terms of parameter adjustment and adding a mutation operator to the PSO. The results are assessed based on the dimension reduction percentage, the potential of selected electrodes and the degree of performance lost. An Extreme Learning Machine (ELM) is used as the primary classifier to evaluate the sets of electrodes and features selected by PSO. Two alternative classifiers such as Polynomial SVM and Perceptron are used for further evaluation of the reduced dimension data. The results indicate the potential of variations of PSO for reducing up to 99% of the data with minimal performance lost.

Dimension reduction is an important step toward asynchronous EEG based BCI systems, with EA based Feature/ Electrode Reduction (FR/ER) methods showing significant potential for this purpose. A PSO based approach can reduce 99% of the EEG data in this manner while demonstrating generalizability through the use of 3 new subsets of features/electrodes that are selected based on the best performing subset on the validation set, the best performing subset on the testing set, and the most commonly used features/electrodes in the swarm. This study is focused on applying the subsets generated from 4 subjects on a 5th one. Two schemes for this are implemented based on i) extracting separate subsets of feature/electrodes for each subject (out of 4 subjects) and combining the final products together for use with the 5th subject, and ii) concatenating the preprocessed EEG data of 4 subjects together and extracting the desired subset with PSO for use with the 5th subject. The results indicate the feasibility of generating subsets of feature/electrode indexes that are task specific and can be used on new subjects.

EEG recording involves having subjects sit on a chair for a couple of hours without being allowed to move and being asked to repeatedly perform various mental, computational, motor imaginary or any other tasks for some specific amount of time. This is a time consuming, boring and complicated procedure during which there is no guarantee that the subject will maintain the proper level of concentration on the requested task at all times, this is apart from the possible muscle activity that might be accidentally generated. This might cause complications in terms of generating signals that do not necessarily contain useful information for classification in the whole tasks time duration. This effect is more likely to appear on recordings in which the task period is longer than usual as in the dataset IVa from BCI competition III in which the task time duration is set to 3.5s. This study investigate the impact of various fragments of time on classification performance. The idea is to improve the classification performance by providing higher concentration on segments of the signal that we assume the subject had better concentration on the task. The results indicate the importance of the middle and end sub-epochs while it illustrate lower performance during the earlier sub-windows.

We report on the development of a new simulation environment for use in Multi-Robot Learning, Swarm Robotics, Robot Teaming, Human Factors and Operator Training. The simulator provides a realistic environment for examining methods for localization and navigation, sensor analysis, object identification and tracking, as well as strategy development, interface refinement and operator training (based on various degrees of heterogeneity, robot teaming, and connectivity). The simulation additionally incorporates real-time human-robot interaction and allows hybrid operation with a mix of simulated and real robots and sensor inputs.

Swarm Robotics is the study of simple, un-intelligent robots teaming up together to address complicated tasks using cooperation and knowledge/skills sharing factors. Particle Swarm Optimization (PSO) is an Evolutionary algorithm inspired by animals' social behaviors. PSO has been used in various problems due to its fast convergence capability. Area Extended PSO (AEPSO) is an enhanced version of PSO designed to address complications in the Swarm Robotics field. These complications include dynamicity of the environment, degree of cooperation, time dependency of the tasks, and uncertain nature of the environment. This study investigates advantages and shortcomings of the AEPSO method in the robotic domain.

Particle Swarm Optimization with Area Extension (AEPSO) is a modified PSO that performs better than basic PSO in static, dynamic, noisy, and real-time environments. This paper investigates the effectiveness of cooperative learning AEPSO in a simulated environment. The environment is a 2D landscape planted with various types of bombs with arbitrary explosion times and locations. The simulated-robots’ task (i.e., swarm particles) is to disarm these bombs. Different bombs must be disarmed with appropriate robots (i.e., disarming skills and bomb types must correspond) and the robots (hereafter, referred to as agents) do not have full observations of the environment due to uncertainties in their perceptions. In this study, each agent has the ability to disarm different type of bombs in heterogeneous scenario while each agent has the ability to disarm all types of bombs in homogeneous scenario. We found that AEPSO shows reliable performance in both heterogeneous and homogeneous scenarios as compared to the basic PSO. We also found that the proposed cooperative learning is robust in environment where agents’ perception are distorted with noise.

Particle swarm optimization (PSO) is one of the evolutionary algorithms which proved to be useful in solving multi-robots tasks. PSO outperforms other evolutionary algorithms, such as GA, in this area. In this paper we introduce a new modified version of PSO called area extension PSO (AEPSO). Information about the environment in extended area together with various heuristics improves the performance of each robot and the group. We believe this AEPSO is suitable to solve problems in environments with large area which have more similarity to real world robotic problems. The result of this study shows a magnificent improvement and the potential of AEPSO, especially in dynamic environments.