Search

Models of seven discrete expressions developed using macro-level facial muscle variations would suffice identifying macro-level expressions of affective states. These models won’t discretise continuous and dynamic micro-level variations in facial expressions. We present a Hierarchical Separation and Classification Network (HSCN) for discovering dynamic, continuous and macro- and micro-level variations in facial expressions of affective states. In the HSCN, we first invoke an unsupervised cosine similarity-based separation method on continuous facial expression data to extract twenty-one dynamic facial expression classes from the seven common discrete affective states. The between-clusters separation is then optimised for discovering the macro-level changes resulting from facial muscle activations. A following step in the HSCN separates the upper and lower facial regions for realizing changes pertaining to upper and lower facial muscle activations. Data from the two separated facial regions are then clustered in a linear discriminant space using similarities in muscular activation patterns. Next, the actual dynamic expression data are mapped onto discriminant features for developing a rule-based expert system that facilitates classifying twenty-one upper and twenty-one lower micro-expressions. Invoking the random forest algorithm would classify twenty-one macro-level facial expressions with 76.11\% accuracy. A support vector machine (SVM), used separately on upper and lower facial regions in tandem, could classify them with respective accuracies of 73.63\% and 87.68\%. This work demonstrates a novel and effective method of dynamic assessment of affective states. The HSCN further demonstrates that facial muscle variations gathered from either upper-, lower- or full-face would suffice classifying affective states. We also provide new insight into discovery of micro-level facial muscle variations and their utilization in dynamic assessment of facial expressions of affec

Autistic individuals experience poor vocational outcomes internationally. Transition planning and interventions during adolescence may assist in improving outcomes in adulthood. Strength-based technology clubs show promise in improving outcomes for autistic adolescents by developing skills specific to the Information and Communication Technology industry, and fostering positive traits, such as self-determination. Although strength-based technology clubs have been examined with autistic adolescents, to date, no framework has been proposed to underpin their design and delivery. In this conceptual analysis, we propose a practical framework for delivering strength-based technology clubs for autistic adolescents. The framework builds on work from a previous systematic review of qualitative research and a realist evaluation study of technology clubs for autistic adolescents, combined with theoretical understandings from three health models. The new framework comprised the components of interests, value, autonomy, and requirements, forming the acronym IVAR. Interests refer to strategies drawing on adolescents' areas of interest. Value represents a culture of valuing autistic adolescents as individuals for their unique strengths and skills. Autonomy refers to providing opportunities for adolescents to make decisions, and Requirements refers to aspects of the social and physical environment. Practical recommendations of the framework are discussed, including design and delivery of future strength-based technology clubs, facilitator training, and design activities. The proposed IVAR framework may be useful in guiding the development of strength-based technology clubs. Future research is needed to validate the feasibility and efficacy of the IVAR framework in underpinning the delivery of strength-based technology clubs to autistic adolescents. Community brief Why is this topic important? The shift from adolescence to adulthood can be challenging for young people on the autism

Independent, discrete models like Paul Ekman’s six basic emotions model are widely used in affective state assessment (ASA) and facial expression classification. However, the continuous and dynamic nature of human expressions often needs to be considered for accurately assessing facial expressions of affective states. This paper investigates how mutual information-carrying continuous models can be extracted and used in continuous and dynamic facial expression classification systems for improving the efficacy and reliability of ASA systems. A novel, hybrid learning model that projects continuous data onto a multidimensional hyperplane is proposed. Through cosine similarity-based clustering (unsupervised) and classification (supervised) processes, our hybrid approach allows us to transform seven, discrete facial expression models into twenty-one facial expression models that include micro-expressions. The proposed continuous, dynamic classifier was able to achieve greater than 73% accuracy when experimented with Random Forest, Support Vector Machine (SVM) and Neural Network classification architectures. The presented system was validated using the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) and the extended Cohn-Kanade (CK+) dataset.

Background: Strength-based technology clubs for adolescents with autism spectrum disorder (ASD) have become increasingly popular; however, they remain poorly described in the literature. Before the impact and benefit of strength-based technology clubs can be measured, consistency in their design and delivery must be established. This study aimed to identify the essential components of strength-based technology clubs by exploring context, mechanisms, and outcomes of existing strength-based technology clubs. Method: Twenty-three adolescents with ASD (mean age 12.96 years, SD = 1.86, range = 10–18 years), 25 parents (mean age 46.08 years, SD = 8.27, range = 33–69 years), and 20 facilitators (mean age 27.93 years, SD = 6.55, range = 20–46 years) were purposively sampled from three established strength-based technology clubs. Data were obtained via ethnographic methods, including participant observations, interviews, and focus groups. Data analysis was underpinned by a realist evaluation, which provided the context-mechanism-outcome framework. Results: Data analysis revealed that strength-based technology clubs had four context themes (personal factors of adolescents, personal factors of facilitators, personal factors of parents, institution), three mechanism themes (activity design, strengths and abilities, environment), and three outcome themes (skill building, connection with others, emotion). Conclusion: The results highlighted the importance of understanding the personal context of adolescents, providing an individualized approach, leveraging individual interests, and modifying the environment to suit the individual. The findings contributed to defining a strength-based approach within ASD, and have demonstrated that positive outcomes can be achieved by focusing on strengths rather than deficits. Future ASD services can use the results as a framework for applying a strength-based approach. The efficacy of newly designed strength-based programs can then be tested.

Purpose: This research explored the challenges of public transport use for individuals on the autism spectrum. It, subsequently, proposed a mobile application solution, coproduced by individuals on the autism spectrum, to facilitate public transport use. Methods: We, first, conducted a review of the literature to highlight the challenges people on the autism spectrum face when utilizing public transport. We, then, designed a list of mobile application functionalities that address the identified problems. To validate these functionalities, 27 young autistic adults and 19 families of autistic individuals were employed. Finally, based on the findings, we designed a mobile application that helps facilitate public transport use for those on the autism spectrum. Results: We found that the most prevalent concerns, in public transport use, amongst autistic individuals and their families are safety and spatial awareness. Specific problems include finding one’s way to the bus stop, boarding the correct service and disembarking at the correct stop. Interestingly, anxiety about unexpected events was also a barrier. Sensory sensitivity, similarly, was found to be an obstacle. Conclusions: This study defined the challenges of public transport use for autistic individuals and proposed a technological solution. The findings can also inform innovators, public transport providers and policymakers to improve public transport accessibility. Implications for rehabilitation: People on the autism spectrum heavily rely on other individuals, namely family and friends, for their transportation needs. This dependence results in immobility for the autistic individuals and significant time and economical sacrifice for the person responsible for the transportation. Public transport, a cheap and widely available form of transportation, has not yet been clearly studied with individuals on the autism spectrum. We clearly define the challenges of using public transport and put forward a trip planner