Enhancing early autism diagnosis through machine learning: Exploring raw motion data for classification.

In recent years, research has been demonstrating that movement analysis, utilizing machine learning methods, can be a promising aid for clinicians in supporting autism diagnostic process. Within this field of research, we aim to explore new models and delve into the detailed observation of certain features that previous literature has identified as prominent in the classification process. Our study employs a game-based tablet application to collect motor data. We use artificial neural networks to analyze raw trajectories in a "drag and drop" task. We compare a two-features model (utilizing only raw coordinates) with a four-features model (including velocities and accelerations). The aim is to assess the effectiveness of raw data analysis and determine the impact of acceleration on autism classification. Our results revealed that both models demonstrate promising accuracy in classifying motor trajectories. The four-features model consistently outperforms the two-features model, as evidenced by accuracy values (0.90 vs. 0.76). However, our findings support the potential of raw data analysis in objectively assessing motor behaviors related to autism. While the four-features model excels, the two-features model still achieves reasonable accuracy. Addressing limitations related to sample size and noise is essential for future research. Our study emphasizes the importance of integrating intelligent solutions to enhance and assist autism traditional diagnostic process and intervention, paving the way for more effective tools in assessing motor skills.

Artificial Neural Networks for Short-Form Development of Psychometric Tests: A Study on Synthetic Populations Using Autoencoders.

Short-form development is an important topic in psychometric research, which requires researchers to face methodological choices at different steps. The statistical techniques traditionally used for shortening tests, which belong to the so-called exploratory model, make assumptions not always verified in psychological data. This article proposes a machine learning-based autonomous procedure for short-form development that combines explanatory and predictive techniques in an integrative approach. The study investigates the item-selection performance of two autoencoders: a particular type of artificial neural network that is comparable to principal component analysis. The procedure is tested on artificial data simulated from a factor-based population and is compared with existent computational approaches to develop short forms. Autoencoders require mild assumptions on data characteristics and provide a method to predict long-form items' responses from the short form. Indeed, results show that they can help the researcher to develop a short form by automatically selecting a subset of items that better reconstruct the original item's responses and that preserve the internal structure of the long-form.

A Systematic Review of Mobile Apps as an Adjunct to Psychological Interventions for Emotion Dysregulation.

BACKGROUND: Mental health care has been enriched with the progressive use of technology during the last ten years, in particular after the COVID-19 pandemic. Mobile applications (apps) and smartphones have become the most widespread access point for many people who look for self-help in the psychological domain. OBJECTIVE: We focused on a systematic review of mobile apps for mental health, focusing on the blending of apps with psychotherapy contexts, with a specific focus on emotional dysregulation. METHODS: A comprehensive literature search (January 2017 to August 2022) in PubMed, PsycInfo, Web of Science, and the Cochrane Library was conducted. Abstracts were included if they described mental health mobile apps targeting emotional dysregulation and their use during ongoing psychological or psychotherapy treatment for adults and adolescents. RESULTS: In total, 397 abstracts were identified; of these, 19 publications describing apps targeting borderline personality disorder, depression, anxiety, suicidal behaviors, and post-traumatic stress disorders met the inclusion criteria. CONCLUSIONS: App-enhanced psychotherapy might be a winning combination in many scenarios, but at the same time, many issues must still be faced in this yet emerging scientific field. In conclusion, we tried to put together some major guidelines for mental health mobile app development in the context of psychological treatments.

Organization measures in the Enhanced Baking Tray Task.

Introduction: The ecological assessment and the analysis of spatial organization behaviors, like the organization of objects in an empty space, in clinical and neurotypical conditions, is crucial. The Enhanced-Baking Tray Task (E-BTT) is as simple as that - placing objects inside a frame as evenly as possible, as if they were "cookies" to be baked in the oven. The E-BTT is the enhanced version of a task for neglect assessment, the Baking Tray Task, and has the advantage to register the coordinates of each object and their temporal order, meaning that it is easy to reconstruct the sequence of their placement. This sequence could be further analyzed, and, in this paper, we aim to do that with a series of indexes. Moreover, since they investigate the visual search organization of the sequence itself, their validity will be tested with a convergent measure of subjective organization. Methods: Therefore, we asked 100 observers (76 women) to evaluate the subjective organization of each of 97 E-BTT plots, on a scale that ranged from 0 = not at all to 100 = well organized. Results: A multiple regression model showed a significant association between subjective organization ratings (dependent variable) and Intersection rate, Total time of performance and distance to both optimal sequences (independent variables). Discussion: Therefore the above-mentioned indexes can be considered measures of the overall organization in the E-BTT.

Coding and educational robotics with peers: The C0D1NC experience to foster inclusion.

In the present paper, the experience of the C0D1NC project (Coding for inclusion) is described. In this project an innovative methodology based on peer-education is the core of the educational approach. High school students become "teachers" as they are trained to teach coding and robotics to younger students. This approach favors inclusion and digital inclusion. To affirm this, we evaluated different aspects: relations between peers, perceived self-efficacy, and attitude towards technology at the beginning of activities (pre-test) and the end (post-test). Results indicate that this approach can be effective to favor personal growth, improved relations between peers, and increased self-efficacy too.

Hyper-Activity Books and Serious Games: How to Promote Experiential Learning beyond Distance.

The COVID-19 pandemic has accelerated the adoption of digital tools for learning. Experiential learning, a crucial process in the educational pathway, can also be promoted at a distance. This paper describes HAB, hyper-activity books and serious games (SG) as methodologies to be used for assessment and training that overcome physical distancing due to COVID-19 in learning. We introduce some examples of these methodologies. The experiences and results represent a pool of resources for experiential learning in everyday educational practice and not merely for responding to emergencies caused by pandemics.

The Ability to Manage Unexpected Events and the Vocational Identity in Young People: The Italian Validation of Planned Happenstance Career Inventory.

The present study had two goals: to test the validity of Planned Happenstance Career Inventory (PHCI) in the Italian context and to explore the relations between PHC skills and vocational identity processes within a sample of 472 undergraduate students attending university in the southern of Italy. Moreover, we examined relations between the PHCI and measures of vocational identity processes. With regard to the first goal, results show that for the Italian version of the instrument was confirmed the multifactor structure of the original version. The multi-group analyses showed that invariance between genders is supported. Convergent validity and divergent validity of the measure were reported. Concerning the second goal, the skills of planned happenstance show different associations with Vocational Identity Dimensions. As hypothesized, the exploration and commitment dimensions of vocational identity status are positive related to Planned Happenstance Skills. These findings suggest implications for career guidance and counseling.

Indexes for the E-Baking Tray Task: A Look on Laterality, Verticality and Quality of Exploration.

The Baking Tray Task is an ecological task developed for the assessment of unilateral neglect that can also be used for research on neurotypical participants. In this task, participants are asked to place 16 objects inside a board as evenly as possible. In the case of impaired spatial exploration, consequent to right attentional networks damage, asymmetrical object disposition is observed as more objects are placed on the ipsilesional side (typically the right side). The E-BTT is a technology-enhanced version of the Baking Tray Task, implemented with a software platform, E-TAN, which detects the objects and automatically computes their spatial coordinates. This allows a complement to the traditional scoring methods with new measures to extract richer information from the data. In this study, we focus on neurotypical participants to explore if some new indexes, derived from the literature review on similar tasks, can be applied to BTT and E-BTT for research aims. A principal component analysis (PCA) was then performed to verify if these new indexes reflect some common dimensions. Results indicate the emergence of two principal dimensions: spatiality, which summarizes both laterality and verticality, and quality, which regards the explored space and (dis)organization in placing the items.

E-TAN, a technology-enhanced platform with tangible objects for the assessment of visual neglect: A multiple single-case study.

Visual neglect is a frequent and disabling consequence of right brain damage. Traditional paper-and pencil tests of neglect have limited sensitivity and ecological validity. The Baking Tray Task (BTT), instead, approaches real-life situations, because it requires participants to place 16 physical objects on a board. The number of objects placed on the left and right portions of the board provides a clinical index of visual neglect. Here we present E-TAN, a technology-enhanced platform for BTT (E-BTT). E-BTT automatically determines the object locations on the board, and also records the sequence and timing of their placement. We used E-BTT to test 9 patients with right hemisphere damage and compared their performance with that obtained by 115 healthy participants. To this end, we developed a new method of analysis of participants' performance, based on the use of the convex hull described by the objects on the board. This measure provides an estimate of the portion of space processed by each participant and can effectively discriminate neglect patients from patients without neglect. E-TAN allows clinicians to assess visuospatial performance by using a convenient, fast, and relatively automatized procedure, that patients can even perform at home to follow-up the effects of rehabilitation.

On the Edge Between Digital and Physical: Materials to Enhance Creativity in Children. An Application to Atypical Development.

The 4 P's creativity model (person, process, press, and product) underlines how creativity is strongly connected with the materials employed to conceive and realize a creative outcome. As a multiform construct, it invites a wide variety of approaches to the study of it. One of the most promising ways to address this issue is to connect it with cognitive development and related educational pathways, as creativity can be enhanced and stimulated in every child, leading to an improvement both at personal and societal level. Even if creativity is recognized and highly valued, there is still a lack of methods which can stimulate creativity in an effective way. Useful hints may come from the outstanding contributions of Piaget and Montessori who underlined that interaction with the physical world is a fundamental building block for cognitive development. In this paper, starting from these fixed points, we describe some creativity enhancing methods for children which give importance to the edge between digital and physical materials. Digital materials open new ways to the use and integration of physical materials with hybrid platforms which can be used in educational contexts. Together with this perspective we provide a description of the application of these methodologies to enhance creativity in children with Autistic Spectrum Disorder.

Educational Robotics to Foster and Assess Social Relations in Students' Groups.

Robotics has gained, in recent years, a significant role in educational processes that take place in formal, non-formal, and informal contexts, mainly in the subjects related to STEM (science, technology, engineering, and mathematics). Indeed, educational robotics (ER) can be fruitfully applied also to soft skills, as it allows promoting social links between students, if it is proposed as a group activity. Working in a group to solve a problem or to accomplish a task in the robotics field allows fostering new relations and overcoming the constraints of the established links associated to the school context. Together with this aspect, ER offers an environment where it is possible to assess group dynamics by means of sociometric tools. In this paper, we will describe an example of how ER can be used to foster and assess social relations in students' group. In particular, we report a study that compares: (1) a laboratory with robots, (2) a laboratory with Scratch for coding, and (3) a control group. This study involved Italian students attending middle school. As the focus of this experiment was to study relations in students' group, we used the sociometric tools proposed by Moreno. Results show that involving students in a robotics lab can effectively foster relations between students and, jointly with sociometric tools, can be employed to portrait group dynamics in a synthetic and manageable way.

The Number Interval Position Effect (NIPE) in the mental bisection of numerical intervals might reflect the influence of the decimal-number system on the Gaussian representations of numerosities: A combined developmental and computational-modeling study.

Healthy adults show typical error biases when they mentally bisect number intervals without exact calculations. For a given number interval length, the bisection bias is in fact modulated by the position that the interval occupies within a ten. For intervals positioned at the beginning of tens the error bias is directed toward values that are higher than those of the true interval midpoint whereas for intervals at the end of tens the direction of the error bias is reversed toward values that are lower than that of the true midpoint (Doricchi et al., 2009; Rotondaro et al., 2015). This effect has been defined Number Interval Position Effect (NIPE). The NIPE recurs over consecutive tens and it is not found when intervals are bisected through exact calculations. For this reasons we have hypothesized that the NIPE reflects the influence that the habit of counting in tens has on the neural representations of numerosities that humans share with other species. Here, in a developmental study we demonstrate that children from preschool to fifth-grade display a NIPE that is comparable to that of healthy adults. Then, through a computational-modeling study we investigated whether the NIPE might reflect specific patterns in the Gaussian representations of numerosities that are found in the parietal and pre-frontal neuronal populations of macaque monkeys and that underlie approximate numerosity estimations also in humans. The findings of computational simulations suggest that the NIPE might reflect the influence that the learning and use of the decimal numerical system has on the phylogenetically and ontogenetically older representation of numerosities that humans share with other species. These changes in the representation of numerosities have an influence on approximate numerical estimations even when these, like in the case of the mental bisection of number intervals, are elicited by numerical symbols or words.

Basic emotions and adaptation. A computational and evolutionary model.

The core principles of the evolutionary theories of emotions declare that affective states represent crucial drives for action selection in the environment and regulated the behavior and adaptation of natural agents in ancestrally recurrent situations. While many different studies used autonomous artificial agents to simulate emotional responses and the way these patterns can affect decision-making, few are the approaches that tried to analyze the evolutionary emergence of affective behaviors directly from the specific adaptive problems posed by the ancestral environment. A model of the evolution of affective behaviors is presented using simulated artificial agents equipped with neural networks and physically inspired on the architecture of the iCub humanoid robot. We use genetic algorithms to train populations of virtual robots across generations, and investigate the spontaneous emergence of basic emotional behaviors in different experimental conditions. In particular, we focus on studying the emotion of fear, therefore the environment explored by the artificial agents can contain stimuli that are safe or dangerous to pick. The simulated task is based on classical conditioning and the agents are asked to learn a strategy to recognize whether the environment is safe or represents a threat to their lives and select the correct action to perform in absence of any visual cues. The simulated agents have special input units in their neural structure whose activation keep track of their actual "sensations" based on the outcome of past behavior. We train five different neural network architectures and then test the best ranked individuals comparing their performances and analyzing the unit activations in each individual's life cycle. We show that the agents, regardless of the presence of recurrent connections, spontaneously evolved the ability to cope with potentially dangerous environment by collecting information about the environment and then switching their behavior to a genetically selected pattern in order to maximize the possible reward. We also prove the determinant presence of an internal time perception unit for the robots to achieve the highest performance and survivability across all conditions.

Encoding geometric and non-geometric information: a study with evolved agents.

Vertebrate species use geometric information and non-geometric or featural cues to orient. Under some circumstances, when both geometric and non-geometric information are available, the geometric information overwhelms non-geometric cues (geometric primacy). In other cases, we observe the inverse tendency or the successful integration of both cues. In past years, modular explanations have been proposed for the geometric primacy: geometric and non-geometric information are processed separately, with the geometry module playing a dominant role. The modularity issue is related to the recent debate on the encoding of geometric information: is it innate or does it depend on environmental experience? In order to get insight into the mechanisms that cause the wide variety of behaviors observed in nature, we used Artificial Life experiments. We demonstrated that agents trained mainly with a single class of information oriented efficiently when they were exposed to one class of information (geometric or non-geometric). When they were tested in environments that contained both classes of information, they displayed a primacy for the information that they had experienced more during their training phase. Encoding and processing geometric and non-geometric information was run in a single cognitive neuro-representation. These findings represent a theoretical proof that the exposure frequency to different spatial information during a learning/adaptive history could produce agents with no modular neuro-cognitive systems that are able to process different types of spatial information and display various orientation behaviors (geometric primacy, non-geometric primacy, no primacy at all).

Artificial organisms as tools for the development of psychological theory: Tolman's lesson.

In the 1930s and 1940s, Edward Tolman developed a psychological theory of spatial orientation in rats and humans. He expressed his theory as an automaton (the "schematic sowbug") or what today we would call an "artificial organism." With the technology of the day, he could not implement his model. Nonetheless, he used it to develop empirical predictions which tested with animals in the laboratory. This way of proceeding was in line with scientific practice dating back to Galileo. The way psychologists use artificial organisms in their work today breaks with this tradition. Modern "artificial organisms" are constructed a posteriori, working from experimental or ethological observations. As a result, researchers can use them to confirm a theoretical model or to simulate its operation. But they make no contribution to the actual building of models. In this paper, we try to return to Tolman's original strategy: implementing his theory of "vicarious trial and error" in a simulated robot, forecasting the robot's behavior and conducting experiments that verify or falsify these predictions.