Social robots are increasingly being used in therapeutic contexts, especially as a complement in the therapy of children with Autism Spectrum Disorder (ASD). Because of this, the aim of this study is to understand how children with ASD perceive and interpret the gestures made by the robot Pepper versus human instructor, which can also be influenced by verbal communication. This study analyzes the impact of both conditions (verbal and nonverbal communication) and types of gestures (conversational and emotional) on gesture recognition through the study of the accuracy rate and examines the physiological responses of children with the Empatica E4 device. The results reveal that verbal communication is more accessible to children with ASD and neurotypicals (NT), with emotional gestures being more interpretable than conversational gestures. The Pepper robot was found to generate lower responses of emotional arousal compared to the human instructor in both ASD and neurotypical children. This study highlights the potential of robots like Pepper to support the communication skills of children with ASD, especially in structured and predictable nonverbal gestures. However, the findings also point to challenges, such as the need for more reliable robotic communication methods, and highlight the importance of changing interventions tailored to individual needs.

In a world where social interaction presents challenges for children with Autism Spectrum Disorder (ASD), robots are stepping in as allies in emotional learning. This study examined how affective interactions with a humanoid robot elicited physiological responses in children with ASD, using electrodermal activity (EDA) and heart rate variability (HRV) as key indicators of emotional arousal. The objectives were to identify emotionally salient moments during human-robot interaction, assess whether certain individual characteristics - such as age or ASD severity - modulate autonomic responses, and evaluate the usefulness of wearable devices for real-time monitoring. Thirteen children participated in structured sessions involving a range of social, cognitive, and motor tasks alongside the robot Pepper. The results showed that the hugging phase (HS2) often generated greater autonomic reactivity in children, especially among younger children and those with higher levels of restlessness or a higher level of ASD. Children with level 2 ASD displayed higher sympathetic activation compared to level 1 participants, who showed more HRV stability. Age also played a role, as younger children demonstrated lower autonomic regulation. These findings highlight the relevance of physiological monitoring in detecting emotional dysregulation and tailoring robot-assisted therapy. Future developments will explore adaptive systems capable of adjusting interventions in real time to better support each child's unique needs.

Extracellular recordings of neuronal spikes are crucial for studying brain activity. These signals are typically classified based on firing patterns and waveform shape, particularly trough-to-peak duration. While useful, this method oversimplifies the diversity of cortical neurons and discharge patterns. Recent advances in recording and analysis techniques allow for more precise waveform classification, though the main criteria remain waveform features. We aim to develop an automatic spike waveform classifier using advanced machine learning techniques selected from a range of candidate methods based on their optimized performance, such as Uniform Manifold Approximation and Projection (UMAP), Gaussian Mixture Model (GMM), and Random Forest (RF). The classifier is part of the working progress of a preprocessing pipeline previously developed. For the classifying step, we use all voltage samples that define each waveform, enabling a multi-dimensional analysis. To evaluate our approach, RF model was trained and tested on a subset of electrophysiological recordings from the human visual cortex achieving high [Formula: see text]-scores. The comparison of the classified neurons was carried out between our method and a waveform analysis toolbox described in the literature. Our method improves the characterization of the clusters of waveforms based on statistical measurements that found a third group while the accepted method categorizes just broad and narrow waveforms, labeling some as unclassifiable.

The large range of potential applications, not only for patients but also for healthy people, that could be achieved by affective brain-computer interface (aBCI) makes more latent the necessity of finding a commonly accepted protocol for real-time EEG-based emotion recognition. Based on wavelet package for spectral feature extraction, attending to the nature of the EEG signal, we have specified some of the main parameters needed for the implementation of robust positive and negative emotion classification. Twelve seconds has resulted as the most appropriate sliding window size; from that, a set of 20 target frequency-location variables have been proposed as the most relevant features that carry the emotional information. Lastly, QDA and KNN classifiers and population rating criterion for stimuli labeling have been suggested as the most suitable approaches for EEG-based emotion recognition. The proposed model reached a mean accuracy of 98% (s.d. 1.4) and 98.96% (s.d. 1.28) in a subject-dependent (SD) approach for QDA and KNN classifier, respectively. This new model represents a step forward towards real-time classification. Moreover, new insights regarding subject-independent (SI) approximation have been discussed, although the results were not conclusive.

In recent years, the important role of good mental health and the wide-ranging consequences of mental disorders have been increasingly recognized. The World Health Organization (WHO) claims that action is necessary across sectors to promote mental health and well-being, as is stated in the third Sustainable Development Goal (SDG), which advocates the need to ensure healthy lives and promote well-being for all at all ages. Mental health is a state of well-being in which an individual realizes his or her own abilities, can cope with the normal stresses of life, can work productively and is able to contribute to his or her community. On this basis, the promotion, protection and restoration of mental health can be regarded as a vital concern, and technology can play an important role in democratizing it to reach everyone. In this context, intelligent systems for cognitive training and assessment refer to artificial intelligence (AI) methodologies and techniques used to support the promotion, protection and restoration of mental health. AI seems to play an important role in the field of cognitive training and rehabilitation, as its adaptability and interactivity increase users' motivation and participation (Karyotaki & Drigas, 2015). The information technology tools mainly used are serious games, virtual worlds and virtual reality, wearable devices, brain imaging, assistance robotics, smart environments, smart homes, smart cities, data analysis, automated learning, approximated reasoning, natural language processing and many other techniques that characterize a system as intelligent. AI provides the means for flexible, robust and inexpensive applications mainly because the modelling phase is significatively simplified, with data collection for machine learning algorithms being the costliest part. Although mental health is not only the absence of disease but also the result of a complex process that includes biological, economic, social, political and environmental factors, we will focus on the biological part, brain health, which refers to how well a person's brain functions across several areas. Cognitive impairments may include problems with attention, memory recall, planning, organizing, reasoning and problem solving and are core features of mental health conditions. While some factors affecting brain health are innate, there are many lifestyle factors that can make a difference, such as being physically active, eating healthy, controlling blood pressure, keeping your mind active, being socially connected, and so forth. Evidence is not conclusive for promoting specific interventions, but at least it is encouraging (Arcara et al., 2017; Butler et al., 2018; National Academies of Sciences, Engineering, and Medicine, 2017). Therefore, health requires a continuum of care at all stages: when a person is in good health, they follow a healthy lifestyle and guidelines for effective prevention, when a pathology is detected, accurate diagnosis is needed, and personalized treatments are applied for recovery or overcoming disability. The target audience is everyone, from healthy people who want to keep their cognitive level in good conditions to those who have an impairment and want to overcome it. Similarly, intelligent systems can cover different business models such as coaching and training of cognitive functions and skills, assessment of cognitive functions, screening and assessment of cognitive diseases and disorders, cognitive intervention and rehabilitation, online assessment & training, multisensing monitoring of cognitive assessment, and so forth. In this special issue, we focus on the multiple possibilities of using AI within the health system to contribute to the well-being of the elderly, that is, to take advantage of current technologies to improve (personalize), reduce costs and democratize healthcare to reach more of the population. We selected some key contributions from the 8th International Conference on the Interplay between Natural and Artificial Computation—IWINAC—(Almería, Spain, 3–7 June 2019) and authors were invited to produce extended versions of their papers for consideration. These papers present a sample of the possibilities of AI to improve prediction, assessment, and training of patients with cognitive impairments. Machine learning techniques are used to assess and predict different cognitive impairments. In Cano-Escalera et al. (2022), the authors deal with the prediction of delirium as the main cause for hospital admittance, and the identification of the major risk factors for delirium, some of them associated with frailty of the patients. The paper explores the construction of machine learning based predictors from a broad set of demographic, clinical, and pharmacological variables. Building predictive models based on machine learning provides an alternative way to identify risk factors as the most important variables to improve predictive performance. They have found a strong association with frailty and dementia indices, and have also found strong pharmacological risks, especially the use of neuroleptics. A technique that has been frequently used to identify cognitive impairment is the monitoring of individuals' behaviour. In Gonzalez et al. (2022), the authors describe a novel method for the detection of anomalous behaviours by monitoring the power consumption of household appliances. The analysis of their daily consumption on normal days allows them to model the normal behaviour of the daily activity of people within that household. The detection of an anomalous consumption will trigger an alarm indicating that the behaviour is not the usual one, in order to communicate this incidence to those in charge. In this paper, auto-encoders and variational auto-encoders, which have a similar topological representation, are compared. From the corresponding latent layers, a classification algorithm based on Random Forest has been implemented. The results obtained show us how, for any type of household appliance, networks based on variational autoencoders obtain substantial improvements with respect to the versions based on autoencoders. This is due to the probabilistic representation of the variational autoencoders, allowing a better representation of the input data. This method is a non-intrusive way of caring for people with Dementia or Alzheimer, as it will be able to detect precisely situations in which the user requires attention and avoid possible dangerous situations derived from these diseases. In Ponticorvo et al. (2022), the authors describe Baldo, an integrated digital and physical system that relies on the findings and theories about numerical and arithmetical cognition, together with the related emotional aspects, to assess and train numerical abilities in the form of a game. They propose a mixed system, which focuses on player–game interaction, using both physical and digital cards as a highly effective way of assessing and training numeracy skills. Baldo has the same logic structure of Italian gaming cards, but it is also based on well-established theoretical contributions and allows recording almost every aspect of children game interaction or, more generally, player-game interaction, for example recording reaction times. Finally, given the increase in population ageing, we believe that research and development of applications in this field should be boosted, and the papers presented in this special issue are significant examples of where efforts are being directed.

The cortical and subcortical circuit regulating both cognition and cardiac autonomic interactions are already well established. This circuit has mainly been analyzed from cortex to heart. Thus, the heart rate variability (HRV) is usually considered a reflection of cortical activity. In this paper, we investigate whether HRV changes affect cortical activity. Short-term local autonomic changes were induced by three breathing strategies: spontaneous (Control), normal (NB) and slow paced breathing (SB). We measured the performance in two cognition domains: executive functions and processing speed. Breathing maneuvres produced three clearly differentiated autonomic states, which preconditioned the cognitive tasks. We found that the SB significantly increased the HRV low frequency (LF) power and lowered the power spectral density (PSD) peak to 0.1[Formula: see text]Hz. Meanwhile, executive function was assessed by the working memory test, whose accuracy significantly improved after SB, with no significant changes in the response times. Processing speed was assessed by a multitasking test. Consistently, the proportion of correct answers (success rate) was the only dependent variable affected by short-term and long-term breath pacing. These findings suggest that accuracy, and not timing of these two cognitive domains would benefit from short-term SB in this study population.

Speech is controlled by axial neuromotor systems, therefore, it is highly sensitive to the effects of neurodegenerative illnesses such as Parkinson's Disease (PD). Patients suffering from PD present important alterations in speech, which are manifested in phonation, articulation, prosody, and fluency. These alterations may be evaluated using statistical methods on features obtained from glottal, spectral, cepstral, or fractal descriptions of speech. This work introduces an evaluation paradigm based on Information Theory (IT) to differentiate the effects of PD and aging on glottal amplitude distributions. The study is conducted on a database including 48 PD patients (24 males, 24 females), 48 age-matched healthy controls (HC, 24 males, 24 females), and 48 mid-age normative subjects (NS, 24 males, 24 females). It may be concluded from the study that Hierarchical Clustering (HiCl) methods produce a clear separation between the phonation of PD patients from NS subjects (accuracy of 89.6% for both male and female subsets), but the separation between PD patients and HC subjects is less efficient (accuracy of 75.0% for the male subset and 70.8% for the female subset). Conversely, using feature selection and Support Vector Machine (SVM) classification, the differentiation between PD and HC is substantially improved (accuracy of 94.8% for the male subset and 92.8% for the female subset). This improvement was mainly boosted by feature selection, at a cost of information and generalization losses. The results point to the possibility that speech deterioration may affect HC phonation with aging, reducing its difference to PD phonation.

Visual neuroprosthesis, that provide electrical stimulation along several sites of the human visual system, constitute a potential tool for vision restoration for the blind. Scientific and technological progress in the fields of neural engineering and artificial vision comes with new theories and tools that, along with the dawn of modern artificial intelligence, constitute a promising framework for the further development of neurotechnology. In the framework of the development of a Cortical Visual Neuroprosthesis for the blind (CORTIVIS), we are now facing the challenge of developing not only computationally powerful tools and flexible approaches that will allow us to provide some degree of functional vision to individuals who are profoundly blind. In this work, we propose a general neuroprosthesis framework composed of several task-oriented and visual encoding modules. We address the development and implementation of computational models of the firing rates of retinal ganglion cells and design a tool - Neurolight - that allows these models to be interfaced with intracortical microelectrodes in order to create electrical stimulation patterns that can evoke useful perceptions. In addition, the developed framework allows the deployment of a diverse array of state-of-the-art deep-learning techniques for task-oriented and general image pre-processing, such as semantic segmentation and object detection in our system's pipeline. To the best of our knowledge, this constitutes the first deep-learning-based system designed to directly interface with the visual brain through an intracortical microelectrode array. We implement the complete pipeline, from obtaining a video stream to developing and deploying task-oriented deep-learning models and predictive models of retinal ganglion cells' encoding of visual inputs under the control of a neurostimulation device able to send electrical train pulses to a microelectrode array implanted at the visual cortex.

Understanding the neurophysiology of emotions, the neuronal structures involved in processing emotional information and the circuits by which they act, is key to designing applications in the field of affective neuroscience, to advance both new treatments and applications of brain-computer interactions. However, efforts have focused on developing computational models capable of emotion classification instead of on studying the neural substrates involved in the emotional process. In this context, we have carried out a study of cortical asymmetries and functional cortical connectivity based on the electroencephalographic signal of 24 subjects stimulated with videos of positive and negative emotional content to bring some light to the neurobiology behind emotional processes. Our results show opposite interhemispheric asymmetry patterns throughout the cortex for both emotional categories and specific connectivity patterns regarding each of the studied emotional categories. However, in general, the same key areas, such as the right hemisphere and more anterior cortical regions, presented higher levels of activity during the processing of both valence emotional categories. These results suggest a common neural pathway for processing positive and negative emotions, but with different activation patterns. These preliminary results are encouraging for elucidating the neuronal circuits of the emotional valence dimension.

Emotion estimation systems based on brain and physiological signals such as electro encephalography (EEG), blood-volume pressure (BVP), and galvanic skin response (GSR) are gaining special attention in recent years due to the possibilities they offer. The field of human-robot interactions (HRIs) could benefit from a broadened understanding of the brain and physiological emotion encoding, together with the use of lightweight software and cheap wearable devices, and thus improve the capabilities of robots to fully engage with the users emotional reactions. In this paper, a previously developed methodology for real-time emotion estimation aimed for its use in the field of HRI is tested under realistic circumstances using a self-generated database created using dynamically evoked emotions. Other state-of-the-art, real-time approaches address emotion estimation using constant stimuli to facilitate the analysis of the evoked responses, remaining far from real scenarios since emotions are dynamically evoked. The proposed approach studies the feasibility of the emotion estimation methodology previously developed, under an experimentation paradigm that imitates a more realistic scenario involving dynamically evoked emotions by using a dramatic film as the experimental paradigm. The emotion estimation methodology has proved to perform on real-time constraints while maintaining high accuracy on emotion estimation when using the self-produced dynamically evoked emotions multi-signal database.

Artificial intelligence and all its supporting tools, e.g. machine and deep learning in computational intelligence-based systems, are rebuilding our society (economy, education, life-style, etc.) and promising a new era for the social welfare state. In this paper we summarize recent advances in data science and artificial intelligence within the interplay between natural and artificial computation. A review of recent works published in the latter field and the state the art are summarized in a comprehensive and self-contained way to provide a baseline framework for the international community in artificial intelligence. Moreover, this paper aims to provide a complete analysis and some relevant discussions of the current trends and insights within several theoretical and application fields covered in the essay, from theoretical models in artificial intelligence and machine learning to the most prospective applications in robotics, neuroscience, brain computer interfaces, medicine and society, in general.

The development of suitable EEG-based emotion recognition systems has become a main target in the last decades for Brain Computer Interface applications (BCI). However, there are scarce algorithms and procedures for real-time classification of emotions. The present study aims to investigate the feasibility of real-time emotion recognition implementation by the selection of parameters such as the appropriate time window segmentation and target bandwidths and cortical regions. We recorded the EEG-neural activity of 24 participants while they were looking and listening to an audiovisual database composed of positive and negative emotional video clips. We tested 12 different temporal window sizes, 6 ranges of frequency bands and 60 electrodes located along the entire scalp. Our results showed a correct classification of 86.96% for positive stimuli. The correct classification for negative stimuli was a little bit less (80.88%). The best time window size, from the tested 1[Formula: see text]s to 12[Formula: see text]s segments, was 12[Formula: see text]s. Although more studies are still needed, these preliminary results provide a reliable way to develop accurate EEG-based emotion classification.

Neurodegenerative pathologies as Parkinson's Disease (PD) show important distortions in speech, affecting fluency, prosody, articulation and phonation. Classically, measurements based on articulation gestures altering formant positions, as the Vocal Space Area (VSA) or the Formant Centralization Ratio (FCR) have been proposed to measure speech distortion, but these markers are based mainly on static positions of sustained vowels. The present study introduces a measurement based on the mutual information distance among probability density functions of kinematic correlates derived from formant dynamics. An absolute kinematic velocity associated to the position of the jaw and tongue articulation gestures is estimated and modeled statistically. The distribution of this feature may differentiate PD patients from normative speakers during sustained vowel emission. The study is based on a limited database of 53 male PD patients, contrasted to a very selected and stable set of eight normative speakers. In this sense, distances based on Kullback-Leibler divergence seem to be sensitive to PD articulation instability. Correlation studies show statistically relevant relationship between information contents based on articulation instability to certain motor and nonmotor clinical scores, such as freezing of gait, or sleep disorders. Remarkably, one of the statistically relevant correlations point out to the time interval passed since the first diagnostic. These results stress the need of defining scoring scales specifically designed for speech disability estimation and monitoring methodologies in degenerative diseases of neuromotor origin.

Speech articulation is produced by the movements of muscles in the larynx, pharynx, mouth and face. Therefore speech shows acoustic features as formants which are directly related with neuromotor actions of these muscles. The first two formants are strongly related with jaw and tongue muscular activity. Speech can be used as a simple and ubiquitous signal, easy to record and process, either locally or on e-Health platforms. This fact may open a wide set of applications in the study of functional grading and monitoring neurodegenerative diseases. A relevant question, in this sense, is how far speech correlates and neuromotor actions are related. This preliminary study is intended to find answers to this question by using surface electromyographic recordings on the masseter and the acoustic kinematics related with the first formant. It is shown in the study that relevant correlations can be found among the surface electromyographic activity (dynamic muscle behavior) and the positions and first derivatives of the first formant (kinematic variables related to vertical velocity and acceleration of the joint jaw and tongue biomechanical system). As an application example, it is shown that the probability density function associated to these kinematic variables is more sensitive than classical features as Vowel Space Area (VSA) or Formant Centralization Ratio (FCR) in characterizing neuromotor degeneration in Parkinson's Disease.

Deep Learning offers flexible powerful tools that have advanced our understanding of the neural coding of neurosensory systems. In this work, a 3D Convolutional Neural Network (3D CNN) is used to mimic the behavior of a population of mice retinal ganglion cells in response to different light patterns. For this purpose, we projected homogeneous RGB flashes and checkerboards stimuli with variable luminances and wavelength spectrum to mimic a more naturalistic stimuli environment onto the mouse retina. We also used white moving bars in order to localize the spatial position of the recorded cells. Then recorded spikes were smoothed with a Gaussian kernel and used as the output target when training a 3D CNN in a supervised way. To find a suitable model, two hyperparameter search stages were performed. In the first stage, a trial and error process allowed us to obtain a system that is able to fit the neurons firing rates. In the second stage, a systematic procedure was used to compare several gradient-based optimizers, loss functions and the model's convolutional layers number. We found that a three layered 3D CNN was able to predict the ganglion cells firing rates with high correlations and low prediction error, as measured with Mean Squared Error and Dynamic Time Warping in test sets. These models were either competitive or outperformed other models used already in neuroscience, as Feed Forward Neural Networks and Linear-Nonlinear models. This methodology allowed us to capture the temporal dynamic response patterns in a robust way, even for neurons with high trial-to-trial variable spontaneous firing rates, when providing the peristimulus time histogram as an output to our model.

Intelligence in educational environmentsThe current maturity of the e-learning industry and continuous technological development based on cognitive computing and the cloud are challenging university and industry research

Stress remains a significant social problem for individuals in modern societies. This paper presents a machine learning approach for the automatic detection of stress of people in a social situation by combining two sensor systems that capture physiological and social responses. We compare the performance using different classifiers including support vector machine, AdaBoost, and [Formula: see text]-nearest neighbor. Our experimental results show that by combining the measurements from both sensor systems, we could accurately discriminate between stressful and neutral situations during a controlled Trier social stress test (TSST). Moreover, this paper assesses the discriminative ability of each sensor modality individually and considers their suitability for real-time stress detection. Finally, we present an study of the most discriminative features for stress detection.

The retina is a very complex neural structure, which contains many different types of neurons interconnected with great precision, enabling sophisticated conditioning and coding of the visual information before it is passed via the optic nerve to higher visual centers. The encoding of visual information is one of the basic questions in visual and computational neuroscience and is also of seminal importance in the field of visual prostheses. In this framework, it is essential to have artificial retina systems to be able to function in a way as similar as possible to the biological retinas. This paper proposes an automatic evolutionary multi-objective strategy based on the NSGA-II algorithm for tuning retina models. Four metrics were adopted for guiding the algorithm in the search of those parameters that best approximate a synthetic retinal model output with real electrophysiological recordings. Results show that this procedure exhibits a high flexibility when different trade-offs has to be considered during the design of customized neuro prostheses.

Intelligent monitoring for people assistance and safetyThis expert systems special issue on 'Intelligent Monitoring for People Assistance and Safety' contains the revised and extended best papers dealing with different issues concerning people assistance and safety through intelligent monitoring and activity interpretation, presented at 'IWINAC 2011: the fourth International Work-Conference on the Interplay between Natural and Artificial Computation'.People assistance and safety is a hot topic and of crucial importance in indoor environments such as homes, offices, hospitals and schools as well as in outdoor areas.Environments are increasingly well equipped with multiple sensing technologies that can monitor simple and complex activities and behaviours (Gascueña and Fernández-Caballero, 2011).Intelligent monitoring implies not only the analysis of the data captured from the various sensors but also their interpretation from the detection of the presence of certain events or actions previously defined (Rivas, Martínez-Tomás and Fernández-Caballero, 2011).From a historical perspective, it is acknowledged that the evolution of monitoring systems has gone through three generations.In the first generation , closedcircuit television analogue systems were used, which consisted of several cameras connected to a series of monitors.These systems do not process information and require a human operator to be permanently concentrated on analysing the situations observed on the monitors.However, in the second generation (1990)(1991)(1992)(1993)(1994)(1995)(1996)(1997)(1998)(1999)(2000), advances attained in digital video communication (e.g.digital compression, bandwidth reduction and robust transmission) were used to increase the efficiency of monitoring systems: closed-circuit television systems were combined with computer vision technology to process images automatically, in order to be proactive in the detection of alarm events during recording.These semiautomatic systems required a robust tracking and detection algorithm for behaviour analysis.Whereas these systems represented a clear improvement with respect to first generation systems by reducing the dependency on human operators to detect anomalous situations, their algorithms and techniques were responsible for triggering a high number of false positives.In the third generation (2000-today), a series of heterogeneous sensors (e.g.fixed cameras, pan-tilt-zoom (PTZ) cameras, audio sensors and RFID tags (radio-frequency identification) will be geographically distributed throughout the scenario to be observed.From the image processing point of view, these systems are based on distributed processing capabilities and the use of embedded signal processing devices to gain distributed scalability and robustness.The main problems that need to be solved in third generation

Expert Systems (ES) are computer programs that use the knowledge and analytical skills (heuristics) of one or more human experts to infer solutions to problems in a particular discipline. The original aim of ES was to be able to replace human expertise (Buchanan, 1986). Nowadays, the exponential increase in the volume, complexity, and diversification of data has lead to the combination of different artificial intelligence techniques to support data access, analysis, and exploitation (Russell & Norvig, 2009). The representation and reasoning capabilities provided by rule-based ES are of assistance in tasks related to information access, interpretation, and management (Liao, 2005). Despite the relative maturity of such rule-based systems, they still contribute a great deal in diverse domains, such as medicine (Kong et al., 2009; Mabotuwana & Warren, 2009), telecommunication network design (Monedero et al., 2008), product configuration (Yang et al., 2009), and ontological engineering (Biletskiy & Girish, 2010). Moreover, the most recent applications have adopted a broad-minded approach to the subject, integrating expertise-based tasks with other Artificial Intelligence approaches, such as natural language processing (Demner-Fushman et al., 2009), case-based reasoning (Aamodt & Plaza, 1994) and event recognition (Fialho et al., 2010). The huge advances in computer technology have increased the possibilities for real applications using knowledge and heuristics, and has accelerated the growth of the efficient knowledge-based systems that are demanded in many practical domains, including as healthcare, surveillance, virtual environments, and system configuration. This special issue, entitled ‘New Perspectives on the Application of Expert Systems’, focuses on new applications using human expertise as an integral part for reasoning. It consists of extended versions of the best papers from the 3rd International Conference on the Interplay between Natural and Artificial Computation, (IWINAC 2009). The selected papers cover the use of human expertise in vital areas of modern ESs, and integrating this knowledge with other AI techniques, such as such as fuzzy reasoning, case-based reasoning, temporal reasoning, agent modelling, and visual system configuration. In the paper ‘Communication in distributed tracking systems: an ontology-based approach to improve cooperation’, Gómez-Romero et al. (2011) present a formal ontology aimed at the symbolic representation of visual data, specifically tracking information in a video-surveillance system. The ontology is used by a cooperative surveillance multi-agent system to increase the coordination and cooperation between independent and heterogeneous cameras. Additionally, the use of the ontology improves system scalability and facilitates the development of new functionalities. In the paper ‘Knowledge modelling through computational agents: Application to surveillance Systems’, Gascueña et al. (2011) model highly dynamic visual surveillance systems using computational agents. The novel underlying assumption in this work is that an agent starts being a conceptual model, then it is reduced to a formal model, and finally to a physical machine with sensors, effectors, and a control program. This assumption emphasizes the computable aspects of agent theory, allowing a higher degree of autonomy and response of agents because of their capabilities to adapt and to cooperate In the paper ‘T-CARE: Temporal Case Retrieval System’, Juarez et al. (2011) assume that the temporal evolution of the patient is a key factor in providing effective healthcare. This paper introduces T-CARE, an innovative temporal case retrieval system in the specific domain of Intensive Care Burns Unit. The system combines classical and non-classical approaches to measure temporal similarity of cases, which are composed of temporal sequences of time point events and intervals. In ‘Adaptive Fuzzy Knowledge-Based Multi-Agent Systems in Virtual Environments’, Arroyo et al. (2011) deal with pioneering aspects such as the confluence of 3D virtual worlds with social networks. The authors explore the possibility of using metabots, metaverse robots, in complex virtual 3D worlds, with motion capabilities based on an Adaptive Fuzzy Knowledge-Based controller, and driven by social issues. In the last paper ‘ARDIS: Knowledge-based architecture for visual system configuration in dynamic surface inspection’, Martin Gomez et al. (2011) present an original approach to dynamic surface inspection in laminated materials. The work is based on the configuration of a visual system in order to obtain good quality control of the manufacturing surface. It also aims to overcome some of the limitations of the single-use visual inspections systems, by integrating and differentiating knowledge. All these works represent the best contributions in ESs to the International World-conference on the Interplay between Natural and Artificial Computation (IWINAC-2009). We hope that the contributions of this special issue facilitate the interplay of proposals between Natural Sciences and Computation. Finally, we dedicate this special issue to the memory of Professor Mira. We would like to thank Dr. Jon G. Hall, the Editor-in-Chief of Expert Systems, for his interest and ongoing help for this special issue. This special issue, done in honour of José Mira, would not have been possible without the support of the Ministerio de Ciencia e Innovación through the projects TIN2007-67586-C02-01, TIN2009-14159-C05-05, and TIN2010-20845-C03-02. M. Taboada M. Taboada is Associate Professor of Computer Science and Artificial Intelligence at University of Santiago de Compostela. Her current research interests include knowledge engineering, ontology and terminology mapping, and archetype modeling in medicine. R. Martínez-Tomás R. Martínez-Tomás is Associate Professor of Computer Science and Artificial Intelligence at Spanish National University of Distance Learning (UNED). He obtained his PhD degree in Artificial Intelligence from UNED in 2000. He has worked on several projects related to artificial intelligence in medicine and video-sequence identification in surveillance tasks. His current research interests include knowledge engineering, knowledge based systems, spatial-temporal logics, description logics and video-sequence semantic interpretation. He is voluntarily serving as a technical publication reviewer for several respected scientific journals and conferences. J. M. Ferrández J. M. Ferrández is Associate Professor of Computer Science at Universidad Politécnica de Cartagena. He is the coordinator of Spanish Thematic Network RTNAC (rtnac.org) and the Iberoamerican network CANS, related to Natural and Artificial Computation. He is also the General Chairman of the International Conference IWINAC, International Work Conference on the Interplay between Natural and Artificial Computation.

Our objective is to provide an enhanced algorithm for the FASTCAM instrument, developed by the Instituto de Astrofísica de Canarias in collaboration with the Universidad Politécnica de Cartagena. In this paper we propose an algorithm for the detection of astronomical objects and its implementation on a High Performance Reconfigurable Computer. Our algorithm introduces wavelet based preprocessing and post-processing stages that considerably enhance the image quality when compared to the initial algorithm.

This paper introduces an open-source real-time system that controls remotelly a robot using Human Neuroblastoma cultures and basic Braitenberg principles. Multielectrode Arrays Setups have been designed for direct culturing neural cells over silicon or glass substrates, providing the capability to stimulate and record simultaneously populations of neural cells. The main objective of this research is to modulate the natural physiologic responses of human neural cells by tetanic stimulation of the culture. If the system is able to modify the selective responses of some cells with a external pattern stimuli provided by a robot over different time scales, the neuroblastoma-cultured structure could be trained to process pre-programmed spatio-temporal patterns, controlling in this way the robotic behaviour.

A retinal model and its implementation on reconfigurable hardware are proposed in this paper. The model incorporates the neural circuits found in the different regions of the first synapse of the retina. The model is based on a Discrete-Time Cellular Neural Network (DTCNN) approach. The implementation on reconfigurable hardware makes it possible to carry out in real time the processing tasks implied in the model execution. Like in the first synapse of the retina, it has been observed that contrast detection and detail resolution are influenced by the convergence factor of neurons and by the lateral inhibition, which are specific parameters of each neural circuit.

This paper describes a novel architecture for the hardware implementation of non-linear multi-layer cellular neural networks. This makes it feasible to design CNNs with millions of neurons accommodated in low price FPGA devices, being able to process standard video in real time.

Augmented reality (AR) is a highly interdisciplinary field which has received increasing attention since late 90s. Basically, it consists of a combination of the real scene viewed by a user and a computer generated image, running in real time. So, AR allows the user to see the real world supplemented, in general, with some information considered as useful, enhancing the users perception and knowledge of the environment. Benefits of reconfigurable hardware for AR have been explored by Luk et al. [4]. However, the wide majority of AR systems have been based so far on PCs or workstations.

In the last decade, skin color has proven to be a useful cue for recognition and tracking of face and hand, and skin color segmentation has become the first step in several processing tasks. With the aim of overcoming the weak points that existing software solutions show in real time mobile applications, we propose an FPGA-based implementation of a skin classifier. The skin classification algorithm and its hardware architecture are herein described. Results in terms of classification performance, processing rate and hardware resources used are presented.

In this paper we propose an area-time efficient architecture for the realization of self-clocked MAC filters on FPGA. First, the self-timed 4-phase oscillator/counter is analyzed and characterized, showing experimental results in comparison with simulation foreseen. Next, the proposed filter architecture, based on circular memories, is described and efficiently implemented as an IP module using device primitives and relative location constraints. Finally, an example using the proposed architecture is implemented on an FPGA and compared with a standard IP filter of similar characteristics, pointing out the advantages of our approach.

In our work, an FPGA-based AR application is developed for people affected by tunnel vision. This consists of a loss of peripheral vision, while retaining a high resolution central vision, associated mainly to several eye diseases such as retinitis pigmentosa and glaucoma. The loss of the peripheral visual field affects considerably the patient's ability to localize objects or persons and navigate, and consequently, his relationship with people and the environment.