Papers by Alessandro Di Nuovo
T he embodied cognition theory affirms that human intelligence is formed not only by the brain, b... more T he embodied cognition theory affirms that human intelligence is formed not only by the brain, but is also shaped by the body and the experiences acquired through it, such as manipulatives, gestures and movements . Research in developmental psychology has shown that embodied experiences help children in learning various cognitive skills by using limbs and senses to interact with the surrounding environment and other human beings 5 .
Cognitive robotics for the modelling of cognitive dysfunctions: A study on unilateral spatial neglect
2015 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob), 2015
Grounding fingers, words and numbers in a cognitive developmental robot
2014 Ieee Symposium on Computational Intelligence Cognitive Algorithms Mind and Brain, Dec 9, 2014
The young math learner must make the transition from a concrete number situation, such as that of... more The young math learner must make the transition from a concrete number situation, such as that of counting objects (fingers often being the most readily available), to that of using a written symbolic form that stands for the quantities the sets of objects come to represent. This challenging process is often coupled to that of learning a verbal number system that is not always transparent to children. A number of theoretical approaches have been advanced to explain aspects of how this transition takes place in cognitive development. The results obtained with the model presented here, show that a symbol grounding approach can be used to implement aspects of this transition in a cognitive robot. In the current extended version, the model develops finger and word representations, through the use of finger counting and verbal counting strategies, together with the visual representations of learned number symbols, which it uses to perform basic arithmetic operations. In the final training phases, the model is able to do this using only the number symbols as addends. We consider this an example of symbolic grounding, in that through the direct sensory experience with the body (finger counting), a category of linguistic symbol is learned (number words), and both types of representations subsequently serve to ground higher level (numerical) symbols, which are later used exclusively to perform the arithmetic operations.
Use of robotics to stimulate imitation in children with Autism Spectrum Disorder: A pilot study in a clinical setting
2015 24th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), 2015
ABSTRACT
Proceedings of the 5th Joint IEEE International Conference on Developmental Learning and Epigentic Robotics
The novel deep learning paradigm offers a highly biologically plausible way to train neural netwo... more The novel deep learning paradigm offers a highly biologically plausible way to train neural network architectures with many layers, inspired by the hierarchical organization of the human brain. Indeed, deep learning gives a new dimension to research modeling human cognitive behaviors, and provides new opportunities for applications in cognitive robotics. In this paper, we present a novel deep neural network architecture for number cognition by means of finger counting and number words. The architecture is composed of 5 layers and is designed in a way that allows it to learn numbers from one to ten by associating the sensory inputs (motor and auditory) coming from the iCub humanoid robotic platform. The architecture performance is validated and tested in two developmental experiments. In the first experiment, standard backpropagation is compared with a deep learning approach, in which weights and biases are pre-trained by means of a greedy algorithm and then refined with backpropagation. In the second experiment, six bi-cultural number learning conditions are compared to explore the impact of different languages (for number words) and finger counting strategies. The developmental experiments confirm the validity of the model and the increase in efficiency given by the deep learning approach. Results of the bi-cultural study are presented and discussed with respect to the neuro-psychological literature and implications of the results for learning situations are briefly outlined.
Benefits of Fuzzy Logic in the Assessment of Intellectual Disability
ABSTRACT Among the artificial intelligence techniques that successfully support computer assisted... more ABSTRACT Among the artificial intelligence techniques that successfully support computer assisted decision making, fuzzy logic has proved to be a powerful tool in various fields. In particular it is appreciated by clinical practitioners because of their approaches to take a decision require to deal with uncertainties and vagueness in the knowledge and information. One field in which fuzzy sets theory can be applied with great benefit is psychopathology due to the high prominence of sources of uncertainty, that should be taken into account when the diagnosis of intellectual disability must be formulated. Therefore clinical psychologists have often to deal with comorbidities that make the decision process harder because they must evaluate different assessment tools for a correct diagnosis. In our work we investigate the application of computational intelligence methods, and in particular of approaches based on fuzzy logic and its hybridizations, in the psychological assess-ment by means of theoretical studies and practical experiments with data collected from patients affected by different levels of intellectual disability. In this paper we present a detailed review of the experimental application, with patients under treatment in a clinical centre, of methodologies we propose to generate fuzzy expert systems for the assessment of intellectual disability. Specifically we highlight, with numerical results, how they can be beneficial for the diagnosis and improve efficacy of the administration of psycho-diagnostic instruments and the efficiency of the assessment.
A cross-cultural study of acceptance and use of robotics by future psychology practitioners
2015 24th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), 2015
ABSTRACT Socially Assistive Robotics has made available numerous possibilities and tools for furt... more ABSTRACT Socially Assistive Robotics has made available numerous possibilities and tools for further innovation in the psychological practice. For instance, recent research provided many examples of possible applications of robots in the education and rehabilitation of people with learning difficulties and/or intellectual disabilities. In this paper, we present a study on how cultural backgrounds can influence the perception and intention to use a robot as an tool in the future practice. The study involved 37 Italian and 37 UK students, as future professionals in the field of psychology, which experienced the actual capabilities of a humanoid robot through a live demo. In this work, we explored the main factors of the Unified Theory of Acceptance and Use of Technology (UTAUT) with the aim to reveal cultural differences. The instrument used was the UTAUT questionnaire, which was designed and validated to investigate the robot acceptance and use. A significant difference on the intention to use the robot is reported in our results: Italians are positive, vice versa British are negative, The discriminant analysis produced a very high degree of separation between the two groups, confirming that there is a different approach toward the use of robotics between the two cultures.
A Web Based Multi-Modal Interface for Elderly Users of the Robot-Era Multi-Robot Services
An Hybrid Soft Computing Approach for Automated Computer Design
Starting AI Researchers Symposium, 2006
ABSTRACT In this paper we present an intelligent approach for Computer Aided Design, that is capa... more ABSTRACT In this paper we present an intelligent approach for Computer Aided Design, that is capable to learn from its experience in order to speedup the design process. The proposed approach integrates two well known soft-computing techniques, Multi-Objective Genetic Algorithms (MOGAs) and Fuzzy Systems (FSs): MOGA smartly explores the design space, in the meanwhile the FS learn from the experience accumulated during the MOGA evolution, storing knowledge in fuzzy rules. The joined rules build the Knowledge Base through which the integrated system quickly predict the results of complex simulations thus avoiding their long execution times. The methodology is applied to a real case study and evaluated in terms of both efficiency and accuracy, demonstrating the superiority of the intelligent approach against brute force random search.
Evolving Fuzzy C-Means: An intelligent technique for efficient diagnosis of children mental retardation level from databases with missing values
ABSTRACT
In this paper we present an hybrid approach which integrate Fuzzy C-Means (FCM) algorithms and Ge... more In this paper we present an hybrid approach which integrate Fuzzy C-Means (FCM) algorithms and Genetic Algorithms (GAs) to design an optimal classifier for the specific classification problem. This integration allows automatic generation of an classifier system, with an optimized subset of features, from a database of examples. The generated classifier strongly outperform the classic FCM algorithm. A reasoned implementation of the hybrid algorithm, we called GFCM, is given along with a comparative study and performance evaluation results on several public benchmark databases. Results obtained show the efficiency of GFCM algorithm.
Knowledge Base Extraction for Fuzzy Diagnosis of Mental Retardation Level
... 4. Giovanna Castellano, Anna M. Fanelli, and Corrado Mencar, A Fuzzy Clustering Approach for ... more ... 4. Giovanna Castellano, Anna M. Fanelli, and Corrado Mencar, A Fuzzy Clustering Approach for Mining Diagnostic Rules, in IEEE International Conference on ... 15. J. Ross Quinlan, C4.5: programs for machine learning, Morgan Kaufmann Publishers Inc., San Francisco, CA, 1993. ...
An Efficient Approach for the Design of Transparent Fuzzy Rule-Based Classifiers
2006 IEEE International Conference on Fuzzy Systems, 2006
ABSTRACT
Model-based reinforcement learning for humanoids: A study on forming rewards with the iCub platform
2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB), 2013
An Intelligent Infrastructure for In-Flight Situation Awareness of Aviation Pilots
Lecture Notes in Computer Science, 2011
This paper presents an infrastructure that integrates intelligent agents in order to monitor, in ... more This paper presents an infrastructure that integrates intelligent agents in order to monitor, in real time, the attention of aviation pilots during training/operative flight missions. The primary goal of this infrastructure is to make the decision process easier and increase Situation ...
Talking About Task Progress: Towards Integrating Task Planning and Dialog for Assistive Robotic Services
Paladyn, Journal of Behavioral Robotics, 2015
The use of service robots to assist ageing people in their own homes has the potential to allow p... more The use of service robots to assist ageing people in their own homes has the potential to allow people to maintain their independence, increasing their health and quality of life. In many assistive applications, robots perform tasks on people’s behalf that they are unable or unwilling to monitor directly. It is important that users be given useful and appropriate information about task progress. People being assisted in homes and other realworld environments are likely be engaged in other activities while they wait for a service, so information should also be presented in an appropriate, nonintrusive manner. This paper presents a human-robot interaction experiment investigatingwhat type of feedback people prefer in verbal updates by a service robot about distributed assistive services. People found feedback about time until task completion more useful than feedback about events in task progress or no feedback. We also discuss future research directions that involve giving non-expert...
Computer-aided assessment of aviation pilots attention: Design of an integrated test and its empirical validation
Applied Computing and Informatics, 2015
ABSTRACT Attention has a key role in the flight performance of the aviation pilot, therefore it i... more ABSTRACT Attention has a key role in the flight performance of the aviation pilot, therefore it is among human factors commonly used in the evaluation of candidate pilots. In this context, our work aims to define a single integrated instrument able to measure all the distinctive attention factors and to assist the assessment and the training of aviation pilots. In this paper, we present a battery of seven computerized tests, encompassing classical and innovative solutions inspired by the literature in the field, for the integrated measurement of the attention factors of aviation pilots. The computer software is validated by means of an experimental trial with 50 experienced aviation pilots and 50 untrained people as controls. Statistical analyzes confirm that the instrument can effectively classify aviation pilots, and identify a subset of distinctive attention factors that could be used for monitoring their duty.
Benefits of fuzzy logic in the assessment of intellectual disability
2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 2014
ABSTRACT Among the artificial intelligence techniques that successfully support computer assisted... more ABSTRACT Among the artificial intelligence techniques that successfully support computer assisted decision making, fuzzy logic has proved to be a powerful tool in various fields. In particular it is appreciated by clinical practitioners because of their approaches to take a decision require to deal with uncertainties and vagueness in the knowledge and information. One field in which fuzzy sets theory can be applied with great benefit is psychopathology due to the high prominence of sources of uncertainty, that should be taken into account when the diagnosis of intellectual disability must be formulated. Therefore clinical psychologists have often to deal with comorbidities that make the decision process harder because they must evaluate different assessment tools for a correct diagnosis. In our work we investigate the application of computational intelligence methods, and in particular of approaches based on fuzzy logic and its hybridizations, in the psychological assess-ment by means of theoretical studies and practical experiments with data collected from patients affected by different levels of intellectual disability. In this paper we present a detailed review of the experimental application, with patients under treatment in a clinical centre, of methodologies we propose to generate fuzzy expert systems for the assessment of intellectual disability. Specifically we highlight, with numerical results, how they can be beneficial for the diagnosis and improve efficacy of the administration of psycho-diagnostic instruments and the efficiency of the assessment.
A Study on Evolutionary Multi-Objective Optimization with Fuzzy Approximation for Computational Expensive Problems
Lecture Notes in Computer Science, 2012
Genetic Tuning of Fuzzy Rule Deep Structures for Efficient Knowledge Extraction from Medical Data
2006 IEEE International Conference on Systems, Man and Cybernetics, 2006
In medical diagnosis, a correct disease classification is needed to choose the right treatment an... more In medical diagnosis, a correct disease classification is needed to choose the right treatment and to assure a quality of life that is suitable for a patient's condition. In order to meet this need we researched a technique that allows us to perform automatic diagnoses efficiently and reliably and at the same time is easy for practitioners to use. In
Uploads
Papers by Alessandro Di Nuovo