Tesis por compendio / [ES] Las funciones cognitivas incluyen todos los procesos a través de los cuales un individuo percibe, registra, mantiene, manipula, usa y expresa información que está involucrada en cualquier actividad cotidiana. Las principales herramientas estandarizadas se pueden dividir en tres grupos principales: escalas cortas de pruebas de seguimiento cognitivo: cuestionarios, baterías neuropsicológicas generales y pruebas específicas. Estas herramientas están bien validadas y son confiables, pero, en la última década, varias investigaciones han demostrado que algunos pacientes pueden realizar bien estas pruebas neuropsicológicas, incluso cuando tienen dificultades significativas para adaptar sus comportamientos a las actividades de la vida diaria. De acuerdo con esto, más recientemente, un nuevo enfoque ha aumentado sustancialmente, lo que podría proporcionar una mayor validez ecológica en la evaluación de las capacidades cognitivas funcionales que el enfoque estandarizado: el uso de sistemas tecnológicos avanzados para la evaluación neuropsicológica (STAEN). STAEN se refiere a un conjunto de dispositivos y aplicaciones de software tales como pruebas computarizadas, juegos divertidos e interactivos de fantasía (JS) y / o sistemas de realidad virtual simulada (RV) y / o aumentada (RA) que van más allá de las pruebas de evaluación tradicionales y que Brindar la posibilidad de entregar estímulos controlados y dinámicos, en entornos ecológicamente válidos y seguros. Partiendo de estas premisas, el objetivo principal de la tesis era diseñar, desarrollar y validar un SG 2D no inmersivo versus un JS 3D inmersivo y una actividad de la vida diaria en un entorno 3D RV inmersivo versus un RA para la evaluación de funciones cognitivas, comparando la eficacia y efectividad de ellos. El primer estudio 2D incluyó 354 sujetos sanos y se encontraron correlaciones entre el juego y los métodos tradicionales, lo que sugiere que el juego podría ser una herramienta válida para evaluar las funciones cognitivas en adultos. El segundo estudio, comparó la versión 2D versus una versión 3D STAEN, involucró a 94 sujetos sanos y mostró que la versión 3D fue capaz de generar tiempos más bajos y respuestas correctas más altas que la 2D, lo que sugiere evidencia inicial de la eficacia de un sistema más inmersivo en comparación con un sistema no-inmersivo. Aunque este resultado destaca una posible limitación en el uso de diferentes sistemas tecnológicos debido a las diferencias en los dos métodos de interacción (el sistema 2D aplicó el mouse y el teclado; los controladores de dos manos virtuales 3D) y el registro de datos de latencia de hardware y software. Con respecto a la variabilidad individual en edad, género y educación, los hallazgos mostraron consistencia con la literatura de referencia. Específicamente, los más jóvenes mostraron un mayor rendimiento que los mayores; niveles educativos más altos reflejados en una mejor puntuación y sobre género, los resultados mostraron un panorama más compuesto. Además, para mejorar la validez ecológica de la evaluación, el último estudio de esta tesis comparó el rendimiento conductual y las respuestas fisiológicas, durante una tarea de cocina ecológica, entre un sistema virtual y un sistema aumentado en 50 sujetos sanos. La tarea de cocinar consistió en 4 niveles que aumentaron en dificultad. A medida que el nivel aumentó, aparecieron actividades adicionales. Los resultados de comportamiento mostraron que los tiempos son siempre más bajos en realidad virtual que en RA, aumentando constantemente de acuerdo con la dificultad de las tareas. Con respecto a las respuestas fisiológicas, los hallazgos mostraron que la condición RA produjo más excitación y activación individual que la realidad virtual. Para concluir, STAEN está demostrando ser herramientas confiables y efectivas para la evaluación de las funciones cognitivas en adultos, proporcionando más validez ec / [CA] Les funcions cognitives inclouen tots els processos a través dels quals un individu percep, registra, manté, manipula, usa i expressa informació que està involucrada en qualsevol activitat quotidiana. Les principals ferramentes estandarditzades es poden dividir en tres grups principals: escales curtes de proves de seguiment cognitiu: qüestionaris, bateries neuropsicológiques generals i proves específiques. Estes ferramentes estan ben validades i són confiables, però, en l'última dècada, diverses investigacions han demostrat que alguns pacients poden realitzar bé estes proves neuropsicológiques, inclús quan tenen dificultats significatives per a adaptar els seus comportaments a les activitats de la vida diària. D'acord amb açò, més recentment, un nou enfocament ha augmentat substancialment, la qual cosa podria proporcionar una major validesa ecològica en l'avaluació de les capacitats cognitives funcionals que l'enfocament estandarditzat: l'ús de sistemes tecnològics avançats per a l'avaluació neuropsicológica (STAEN). STAEN es referix a un conjunt de dispositius i aplicacions de software com ara proves computaritzades, jocs divertits i interactius de fantasia (JS) i / o sistemes de realitat virtual simulada (RV) i / o augmentada (RA) que van més enllà de les proves d'avaluació tradicionals i que brinden la possibilitat de presentar estímuls controlats i dinàmics, en entorns ecològicament vàlids i segurs. Partint d'estes premisses, l'objectiu principal de la tesi era dissenyar, desenrotllar i validar un SG 2D no inmersiu versus un JS 3D inmersiu i una activitat de la vida diària en un entorn 3D RV inmersiu versus un RA per a l'avaluació de funcions cognitives, comparant l'eficàcia i efectivitat d'ells. El primer estudi 2D va incloure 354 subjectes sans i es van trobar correlacions entre el joc i els mètodes tradicionals, la qual cosa suggerix que el joc podria ser una ferramenta vàlida per a avaluar les funcions cognitives en adults. El segon estudi, va comparar la versió 2D versus una versió 3D STAEN, va involucrar a 94 subjectes sans i va mostrar que la versió 3D va ser capaç de generar temps més baixos i respostes correctes més altes que la 2D, la qual cosa suggerix evidència inicial de l'eficàcia d'un sistema més inmersiu en comparació amb un sistema no-inmersiu. Encara que este resultat destaca una possible limitació en l'ús de diferents sistemes tecnològics a causa de les diferències en els dos mètodes d'interacció (el sistema 2D va aplicar el ratolí i el teclat; els controladors de dos mans virtuals 3D) i el registre de dades de latència de hardware i software. Respecte a la variabilitat individual en edat, gènere i educació, les troballes van mostrar consistència amb la literatura de referència. Específicament, els més jóvens van mostrar un major rendiment que els majors; nivells educatius més alts reflectits en una millor puntuació i sobre gènere, els resultats van mostrar un panorama més compost. A més, per a millorar la validesa ecològica de l'avaluació, l'últim estudi d'esta tesi va comparar el rendiment conductual i les respostes fisiològiques, durant una tasca de cuina ecològica, entre un sistema virtual i un sistema augmentat en 50 subjectes sans. La tasca de cuinar va consistir en 4 nivells que van augmentar en dificultat. A mesura que el nivell va augmentar, van aparéixer activitats addicionals. Els resultats de comportament van mostrar que els temps són sempre més baixos en realitat virtual que en RA, augmentant constantment d'acord amb la dificultat de les tasques. Respecte a les respostes fisiològiques, les troballes van mostrar que la condició RA va produir més excitació i activació individual que la realitat virtual. Per a concloure, STAEN està demostrant ser ferramentes confiables i efectives per a l'avaluació de les funcions cognitives en adults, proporcionant més validesa ecològica i objectivitat que els mètodes tradicio / [EN] Cognitive functions include all the processes through which an individual perceives, records, maintains, manipulates, uses and expresses information that are involved in any everyday activity. The main standardized tools can be divided in three main groups: short scales of cognitive tracking tests - questionnaires, general neuropsychological batteries, and specific tests. These tools are well-validated and reliable but, in the last decade, several research have shown that some patients can perform these neuropsychological tests well, even when they have significant difficulties in adapting their behaviours to daily life activities. According to this, more recently, a new approach has substantially increased, potentially providing a higher ecological validity in functional cognitive abilities assessment than standardized approach: the use of advanced technological systems for neuropsychological assessment (ATSNA). ATSNA refer to a set of devices and software applications such as computerized tests, fun and interactive fantasy serious games (SG), and/or simulated virtual (VR) and/or augmented (AR) reality systems that go beyond traditional assessment tests and that supply the possibility to deliver controlled and dynamic stimuli, in ecologically valid, and secure environments. Starting from these premises, the main objective of the thesis was to design, develop, and validate a non-immersive 2D SG versus an immersive 3D SG and a daily life activity in an immersive 3D VR environment versus an AR for the assessment of cognitive functions, comparing the efficacy and effectiveness of them. The first 2D study involved 354 healthy subjects and correlations were found between the game and traditional methods, suggesting that the game could be a valid tool for assessing cognitive functions in adults. The second study, compared 2D versus a 3D ATSNA version, it involved 94 healthy subjects and showed that 3D version was able to generate lower times and higher correct answers that the 2D, suggesting initial evidence of efficacy of a more immersive system compared to a non-immersive system. Although this result highlights a potential limitation on using different technological systems due to the differences on the two interaction methods (the 2D system applied mouse and keyboard; the 3D two virtual hands' controllers) and hardware and software latency data recording. Regarding individual variability on age, gender, and education, the findings showed consistency with the reference literature. Specifically, younger showed higher performance that older; higher educational levels reflected on a better score and about gender, results showed a more composite panorama. Furthermore, to enhance the ecological validity of assessment, the last study of this thesis compared the behavioural performance and physiological responses, during an ecological cooking task, between a virtual and an augmented system on 50 healthy subjects. The cooking task consisted of 4 levels that increased in difficulty. As the level increased, additional activities appeared. The behavioural results showed that times are always lower in VR than in AR, increasing constantly in accordance with the difficulty of the tasks. Regarding physiological responses, the findings showed that AR condition produced more individual excitement and activation than VR. To conclude, ATSNA are proving to be reliable and effective tools for the assessment of cognitive functions in adults, providing more ecological validity and objectivity than traditional methods of assessment. / Chicchi Giglioli, IAM. (2020). Novel supports to the assessment of cognitive functions through the combined use of technologies and subjective and objective measurements [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/139075 / Compendio

Yes / Assessment of children for school readiness is a crucial process that requires extensive effort to select the sequence of tests most appropriate for the particular case to be investigated. Indeed, the success of the assessment depends highly on the diversity, flexibility, and comprehensiveness of the tests available and the ability of the applied system to decide on the specific sequence of tests to be utilized for each child based on his/her skills which should be discovered dynam- ically as the assessment progresses. Given the huge search space for the test cases to be utilized in the assessment process, it is preferred to apply an optimization technique capable of finding an appropriate test case that better fits the skills of a given child. It was decided to use a genetic algorithm (GA)-based approach for the optimization process. Any other optimization technique could have been used and utilizing the GA is a personal decision to complement the framework developed for this paper. GAs have been widely and successfully used in various application domains. Fortunately, the results reported in this paper demonstrate the effective- ness of the utilized GA in handling the assessment process to decide on school readiness. Assessment of a person’s abilities and skills is an important task for organizations. Examples include evaluating a child’s readiness for school or determining an employee’s aptitude for a position. The assessment involves various parameters related to the test subject’s aptitude, such as motor skills, linguistic development, or deductive capabilities, among others. The assessment may be conducted by various bodies, such as public education systems, commercial testing companies, and recruiters. To facilitate the assessment process in a systematic way less influenced by the attitude of a specific domain expert, it is preferred to develop and employ web-based assessment systems which integrate the skills of professional domain experts. A recent innovation is an adaptive web-based stealth assessment that analyzes the subject’s skill and dynamically adapts the assessment tests accordingly. A web-based stealth assessment is used for evaluating school readiness of a child by having the child play a series of games comparing the child’s per- formance with a database of performance results for a population. The web-based stealth assessment includes a processor for processing the child’s performance data, for comparing the performance data with the performance results of the population, and for applying a GA to determine the most appropriate next test for the child.

A major challenge that faces most families is effectively anticipating how ready to start school a given child is. Traditional tests are not very effective as they depend on the skills of the expert conducting the test. It is argued that automated tools are more attractive especially when they are extended with games capabilities that would be the most attractive for the children to be seriously involved in the test. The first part of this thesis reviews the school readiness approaches applied in various countries. This motivated the development of the sophisticated system described in the thesis. Extensive research was conducted to enrich the system with features that consider machine learning and social network aspects. A modified genetic algorithm was integrated into a web-based stealth assessment tool for school readiness. The research goal is to create a web-based stealth assessment tool that can learn the user's skills and adjust the assessment tests accordingly. The user plays various sessions from various games, while the Genetic Algorithm (GA) selects the upcoming session or group of sessions to be presented to the user according to his/her skills and status. The modified GA and the learning procedure were described. A penalizing system and a fitness heuristic for best choice selection were integrated into the GA. Two methods for learning were presented, namely a memory system and a no-memory system. Several methods were presented for the improvement of the speed of learning. In addition, learning mechanisms were introduced in the social network aspect to address further usage of stealth assessment automation. The effect of the relatives and friends on the readiness of the child was studied by investigating the social communities to which the child belongs and how the trend in these communities will reflect on to the child under investigation. The plan is to develop this framework further by incorporating more information related to social network construction and analysis. Also, it is planned to turn the framework into a self adaptive one by utilizing the feedback from the usage patterns to learn and adjust the evaluation process accordingly.

A major challenge that faces most families is effectively anticipating how ready to start school a given child is. Traditional tests are not very effective as they depend on the skills of the expert conducting the test. It is argued that automated tools are more attractive especially when they are extended with games capabilities that would be the most attractive for the children to be seriously involved in the test. The first part of this thesis reviews the school readiness approaches applied in various countries. This motivated the development of the sophisticated system described in the thesis. Extensive research was conducted to enrich the system with features that consider machine learning and social network aspects. A modified genetic algorithm was integrated into a web-based stealth assessment tool for school readiness. The research goal is to create a web-based stealth assessment tool that can learn the user's skills and adjust the assessment tests accordingly. The user plays various sessions from various games, while the Genetic Algorithm (GA) selects the upcoming session or group of sessions to be presented to the user according to his/her skills and status. The modified GA and the learning procedure were described. A penalizing system and a fitness heuristic for best choice selection were integrated into the GA. Two methods for learning were presented, namely a memory system and a no-memory system. Several methods were presented for the improvement of the speed of learning. In addition, learning mechanisms were introduced in the social network aspect to address further usage of stealth assessment automation. The effect of the relatives and friends on the readiness of the child was studied by investigating the social communities to which the child belongs and how the trend in these communities will reflect on to the child under investigation. The plan is to develop this framework further by incorporating more information related to social network construction and analysis. Also, it is planned to turn the framework into a self adaptive one by utilizing the feedback from the usage patterns to learn and adjust the evaluation process accordingly.