ABSTRACT Attention Deficit Hyperactivity Disorder (ADHD) is a neurodevelopmental disorder that is challenging to diagnose and requires advanced approaches for reliable and transparent identification and classification. It is characterised by a pattern of inattention, hyperactivity and impulsivity that is more severe and more frequent than in individuals with a comparable level of development. In this paper, an explainable framework based on a fine‐tuned hybrid Deep Neural Network (DNN) and Recurrent Neural Network (RNN) called HyExDNN‐RNN model is proposed for ADHD detection, multi‐class categorization and decision interpretation. This framework not only detects ADHD but also provides interpretable insights into the diagnostic process so that psychologists can better understand and trust the results of the diagnosis. We use the Pearson correlation coefficient for optimal feature selection and machine and deep learning models for experimental analysis and comparison. We use a standardised technique for feature reduction, model selection and interpretation to accurately determine the diagnosis rate and ensure the interpretability of the proposed framework. Our framework provided excellent results on binary classification, with HyExDNN‐RNN achieving an F1‐score of 99% and 94.2% on multi‐class categorization. XAI approaches, in particular SHapley Additive exPlanations (SHAP) and Permutation Feature Importance (PFI), provided important insights into the importance of features and the decision logic of models. By combining AI with human expertise, we aim to bridge the gap between advanced computational techniques and practical psychological applications. These results demonstrate the potential of our framework to assist in ADHD diagnosis and interpretation.

Self Supervised Representation Learning (SSRepL) can capture meaningful and robust representations of the Attention Deficit Hyperactivity Disorder (ADHD) data and have the potential to improve the model’s performance on also downstream different types of Neurodevelopmental disorder (NDD) detection. In this paper, a novel SSRepL and Transfer Learning (TL)-based framework that incorporates a Long Short-Term Memory (LSTM) and a Gated Recurrent Units (GRU) model is proposed to detect children with potential symptoms of ADHD. This model uses Electroencephalogram (EEG) signals extracted during visual attention tasks to accurately detect ADHD by preprocessing EEG signal quality through normalization, filtering, and data balancing. For the experimental analysis, we use three different models: 1) SSRepL and TL-based LSTM-GRU model named as SSRepL-ADHD, which integrates LSTM and GRU layers to capture temporal dependencies in the data, 2) lightweight SSRepL-based DNN model (LSSRepL-DNN), and 3) Random Forest (RF). In the study, these models are thoroughly evaluated using well-known performance metrics (i.e., accuracy, precision, recall, and F1-score). The results show that the proposed SSRepL-ADHD model achieves the maximum accuracy of 81.11% while admitting the difficulties associated with dataset imbalance and feature selection.

This paper focuses on developing a framework for uncovering insights about NDD children’s performance (e.g., raw gaze cluster analysis, duration analysis & area of interest for sustained attention, stimuli expectancy, loss of focus/motivation, inhibitory control) and informing their teachers. The hypothesis behind this work is that self-adaptation of games can contribute to improving students’ well-being and performance by suggesting personalized activities (e.g., highlighting stimuli to increase attention or choosing a difficulty level that matches students’ abilities). The aim is to examine how AI can be used to help solve this problem. The results would not only contribute to a better understanding of the problems of NDD children and their teachers but also help psychologists to validate the results against their clinical knowledge, improve communication with patients and identify areas for further investigation, e.g., by explaining the decision made and preserving the children’s private data in the learning process.

Computer-based applications incorporating eye-tracking technologies (ETs) and serious games (SGs) promise support for managing health problems. ETs can help to understand better how the eyes function, and SGs can contribute to higher user experiences and increased engagement. Collecting and aligning data on eye functions and games can provide evidence for professionals to diagnose or plan rehabilitation. However, it is difficult to understand how data from ET and SG and information on health problems can be combined to provide trustworthy evidence. Solutions that combine these technologies can provide more engaging training and reliable gaze-based measures for a variety of problems. This paper investigates this question for supporting children with neurodevelopmental disorder (NDD). Based on examining the scientific literature indexed in the Web of Science databases for visualizing bibliometric indicators from 2008 to 2023, it identifies promising studies examining research utilizing ET and SG technologies for NDD diagnoses or support. The results highlight an increased interest and publication trends. However, there is no go-to journal for the topic, and reporting of ET aspects varies greatly. There is a distinct lack of reporting on calibration methods and detailed descriptions of connections between major eye movements and specific psychology-based NDD measures.

The vision behind this research is to develop a platform that supports children with neurodevelopmental disorders (NDD) in handling their difficulties. This will be done by informing their teachers about each child's NDD specificity, personal ability, and learning progress through standardized tasks that allow tailoring the tasks to personalized requirements. The aim of this work in progress is to 1) examine the role of using eye tracking (ET) technologies to inform teachers to support NDD children through a platform, 2) provide an example for using ET data, and 3) show how ET data can be combined with Serious Games (SG) output in a pipeline. The results show the necessary requirements for the experimental setup with a focus on informing the teachers, the influence of inherent limitations of the participant pool, and illustrate how the ET and SG results can be used to communicate status for sustained attention.

Developing accessible tools that support the identification of functional vision problems with reliable measurements of eye movements is a common interest. To develop such an open source tool considering eye tracker data needs automatic processing of eye data, handling time stamps, dynamic data generation, and parameter adaptation. This paper illustrates the possibility of such a tool for saccadic, smooth pursuit and circular eye movements and discusses future steps.

Spatial hashing is an efficient technique to speed up proximity queries on moving objects in the space domain, suitable for computer entertainment applications and simulations. This paper presents an efficient three-step algorithm for building a 1D hash table for spatial hashing needed to perform fast queries on objects for location and proximity detection. In contrast to existing solutions, this algorithm uses fixed-size vectors and pivots instead of dynamic data structures to deal with collisions in the hash table. This also enables iterating through entities and performing proximity queries in a linear memory. Experiments conducted shows that the proposed algorithm is, on average, at least 3 times faster than existing solutions based on dynamic data structures. This contributes to realizing interactive frame rates with massive number of moving entities.

This study presents the Thesis Steering Model (TSM), an instrument supporting systematic communication and collaboration between the different stakeholders involved in industrial doctoral projects. The results describe TSM and illustrate its introduction for seven doctoral projects within a postgraduate school in applied informatics. The experiences from the first two years in use are: enhanced communication, mutual understanding of academic and business values, and opportunity to the doctoral students to build a research identity associated to their own project.

Under which conditions has collaboration added value over individual work? How does performance change when using different technologies? These are important questions for industry and for research. This paper addresses them for pairs versus individuals using physical objects and virtual representations for object-focused task-solving. Based upon previous research on pair's performance and experiences for collaboration in a real setting and four different distributed virtual environments (VEs), single-user experimental studies were carried out. The results show that in relation to performance, pairs working in networked CAVE™ technologies are superior compared to individuals, or pairs working in other distributed settings. In general, social interaction works as a facilitator for this type of task solving in networked VEs. Though, best performance was found in the real setting, with no major difference when comparing individuals versus pairs, working in VEs often were appreciated higher than working with physical objects.

Collaboration at a distance has long been a research goal of distributed virtual environments.A number of recent technologies, including immersive projection technology systems (IPTs) and head-mounted displays (HMDs), promise a new generation of technologies that are more intuitive to use than desktop-based systems.This paper presents an experiment that compares collaboration in five different settings.Pairs collaborated on the same puzzle-solving task using one of: an IPT connected to another IPT, an IPT connected to an HMD, an IPT connected to a desktop system, two connected desktop systems, or face-to-face collaboration with real objects.The findings demonstrate the benefits of using immersive technologies, and show the advantages of using symmetrical settings for better performance.Some usability problems of the different distributed settings are addressed, as well as factors such as "presence" and "copresence" and how these contribute to the participants' overall experiences.

This study examines pairs of subjects who used networked immersive projection technology systems to collaborate on five tasks over an extended period of time (210+ minutes). The aim was to compare zero history and mutual history partners, to examine how their experience changed over time, and compare their experience of different tasks. Analysis yields a number of interesting findings for these comparisons. Overall, the study shows that users could collaborate effectively over an extended period of time, but that understanding the intentions and activities of the other person remained a hindrance.