Riccardo Poli

• PhD Biomedical Engineering
• Professor (Full) at University of Essex

The use of electromagnetic fields to control a collection of magnetic nanoparticles, known as a microswarm, has many promising applications. Current research often makes use of accurate but time-consuming simulations lacking real-time human input. On the contrary, human interaction is possible with a real-time simulator, allowing the collection of...

Neuroimaging studies have reported the possibility of semantic neural decoding to identify specific semantic concepts from neural activity. This offers promise for brain-computer interfaces (BCIs) for communication. However, translating these findings into a BCI paradigm has proven challenging. Existing EEG-based semantic decoding studies often rel...

Making decisions is an important aspect of people’s lives. Decisions can be highly critical in nature, with mistakes possibly resulting in extremely adverse consequences. Yet, such decisions have often to be made within a very short period of time and with limited information. This can result in decreased accuracy and efficiency. In this paper, we...

Objective. We investigated whether a recently introduced transfer-learning technique based on meta-learning could improve the performance of brain–computer interfaces (BCIs) for decision-confidence prediction with respect to more traditional machine learning methods. Approach. We adapted the meta-learning by biased regularisation algorithm to the p...

Background: This study assessed the effectiveness of the NEVERMIND e-health system, consisting of a smart shirt and a mobile application with lifestyle behavioural advice, mindfulness-based therapy, and cognitive behavioural therapy, in reducing depressive symptoms among patients diagnosed with severe somatic conditions. Our hypothesis was that th...

The vanishing gradient problem (i.e., gradients prematurely becoming extremely small during training, thereby effectively preventing a network from learning) is a long-standing obstacle to the training of deep neural networks using sigmoid activation functions when using the standard back-propagation algorithm. In this paper, we found that an impor...

In our previous work at University of Essex, collaborative brain-computer interfaces (cBCIs) have been used to estimate the decision confidence of individuals from their brain signals and behavioral data, thereby making it possible to improve group decision-making. However, such studies used cBCIs in controlled lab conditions, where users were disc...

Neurotechnologies combine neuroscience and engineering to create tools for studying, repairing, and enhancing brain function. Traditionally, researchers have used neurotechnologies, such as Brain-Computer Interfaces (BCIs), as assistive devices, for example to allow locked-in patients to communicate. In the last few decades, non-invasive brain imag...

In this paper we present, and test in two realistic environments, collaborative Brain-Computer Interfaces (cBCIs) that can significantly increase both the speed and the accuracy of perceptual group decision-making. The key distinguishing features of this work are: (1) our cBCIs combine behavioural, physiological and neural data in such a way as to...

Objective. In many real-world decision tasks, the information available to the decision maker is incomplete. To account for this uncertainty, we associate a degree of confidence to every decision, representing the likelihood of that decision being correct. In this study, we analyse electroencephalography (EEG) data from 68 participants undertaking...

Objective. Semantic decoding refers to the identification of semantic concepts from recordings of an individual’s brain activity. It has been previously reported in functional magnetic resonance imaging and electroencephalography. We investigate whether semantic decoding is possible with functional near-infrared spectroscopy (fNIRS). Specifically,...

In this paper we present and test collaborative Brain-Computer Interfaces (cBCIs) that can significantly increase both the speed and the accuracy of group decision-making in realistic situations. The key distinguishing features of this work are: (1) our cBCIs combine behavioural, physiological and neural data in such a way as to be able to provide...

INTRODUCTION: Traditional personalised modelling typically requires sufficient personal data for training. This is a challenge in healthcare contexts, e.g. when using smartphones to predict well-being. OBJECTIVE: A method to produce incremental patient-specific models and forecasts even in the early stages of data collection when the data are spor...

We have uncovered serious flaws in handling EEG signals with a decreased rank in implementations of the common spatial patterns (CSP). The CSP algorithm assumes covariance matrices of the signal to have full rank. However, preprocessing techniques, such as artifact removal using independent component analysis, may decrease the rank of the signal, l...

Background: Depressive symptoms are common in individuals suffering from severe somatic conditions. There is a lack of interventions and evidence-based interventions aiming to reduce depressive symptoms in patients with severe somatic conditions. The aim of the NEVERMIND project is to address these issues and provide evidence by testing the NEVERM...

Smartphones and wearable sensors are increasingly used for personalised prediction and management in healthcare contexts. Personalisation requires tuning/learning a model of the user. However, traditional machine learning approaches for personalised modelling typically require the availability of sufficient personal data of a suitable nature for tr...

We present the SurfacE Electromyographic with hanD kinematicS (SEEDS) database. It contains electromyographic (EMG) signals and hand kinematics recorded from the forearm muscles of 25 non-disabled subjects while performing 13 different movements at normal and slow-paced speeds. EMG signals were recorded with a high-density 126-channel array centere...

We present a two-layered collaborative Brain-Computer Interface (cBCI) to aid groups making decisions under time constraints in a realistic video surveillance setting - the very first cBCI application of this type. The cBCI first uses response times (RTs) to estimate the decision confidence the user would report after each decision. Such an estimat...

[This corrects the article DOI: 10.1371/journal.pone.0212935.].

Recognizing a person in a crowded environment is a challenging, yet critical, visual-search task for both humans and machine-vision algorithms. This paper explores the possibility of combining a residual neural network (ResNet), brain-computer interfaces (BCIs) and human participants to create “cyborgs” that improve decision making. Human participa...

Recent advances in neuroscience have paved the way to innovative applications that cognitively augment and enhance humans in a variety of contexts. This paper aims at providing a snapshot of the current state of the art and a motivated forecast of the most likely developments in the next two decades. Firstly, we survey the main neuroscience technol...

The field of brain–computer interfaces (BCIs) has grown rapidly in the last few decades, allowing the development of ever faster and more reliable assistive technologies for converting brain activity into control signals for external devices for people with severe disabilities [...]

Game balancing has been an important area of academic research in the past few years, with various methods of approaching the task being proposed. At this point in time, however , industry impact has been minimal, with these approaches appearing overwhelming or expensive to game designers and developers. The work presented in this paper takes one o...

This paper aims to show a glimpse of the potential benefits of using genetic algorithms (GA's) in EEG data analysis. The system attempts machine-learning based classification of a mental state reached during competitive gameplay and an idle state. EEG activity from a large number of experienced players of League of Legends has been recorded during...

Predicting the severity and onset of depressive symptoms is of great importance. User-specific models have better performance than a general model but require significant amounts of training data from each individual, which is often impractical to obtain. Even when this is possible, there is a significant lag between the beginning of the data-colle...

Electromyographic (EMG) recordings of muscle activity using monopolar electrodes suffer from poor spatial resolution due to the crosstalk from neighbouring muscles. This effect has mainly been studied on surface EMG recordings. Here, we use Principal Component Analysis (PCA) to reduce the crosstalk in recordings from unipolar epimysial electrodes i...

Recognizing a person in a crowded environment is a challenging, yet critical, visual-search task for both humans and machine-vision algorithms. This paper explores the possibility of combining a residual neural network (ResNet), brain-computer interfaces (BCIs) and human participants to create "cyborgs" that improve decision making. Human participa...

Recent work has shown that genetic algorithms are a good choice for use in game design, particularly for finding improved versions of a game’s parameters to better fit a designer’s requirements. A significant issue with this approach to game optimisation is the very long time it can take to evaluate fitness, since this requires running the target g...

Groups have increased sensing and cognition capabilities that typically allow them to make better decisions. However, factors such as communication biases and time constraints can lead to less-than-optimal group decisions. In this study, we use a hybrid Brain-Computer Interface (hBCI) to improve the performance of groups undertaking a realistic vis...

Genetic Algorithms (GAs) can find game parameters that fit a designer's requirements. An issue with this is the long time taken to evaluate fitness, as this requires running the game many times. Here we use fitness predictors, currently neural networks, to speed up the process by reducing the number of fitness evaluations. The predictors are traine...

Assessment and recognition of perceived well-being has wide applications in the development of assistive healthcare systems for people with physical and mental disorders. In practical data collection, these systems need to be less intrusive, and respect users' autonomy and willingness as much as possible. As a result, self-reported data are not nec...

The N2pc is a lateralised Event-Related Potential (ERP) that signals a shift of attention towards the location of a potential object of interest. We propose a single-trial target-localisation collaborative Brain-Computer Interface (cBCI) that exploits this ERP to automatically approximate the horizontal position of targets in aerial images. Images...

This paper presents a hybrid collaborative brain- computer interface (cBCI) to improve group-based recognition of target faces in crowded scenes recorded from surveillance cameras. The cBCI uses a combination of neural features extracted from EEG and response times to estimate the decision confidence of the users. Group decisions are then obtained...

Games, particularly online games, have an ongoing requirement to exhibit the ability to react to player behaviour and change their mechanics and available tools to keep their audience both entertained and feeling that their strategic choices and in-game decisions have value. Game designers invest time both gathering data and analysing it to introdu...

In the recent years, collaborative Brain-Computer Interfaces (cBCIs) have shown the potential to be used in the context of neuroergonomics to augment human performance, for example in decision making. This study proposes an innovative hybrid cBCI to augment group performance in decision making.

Collaborative brain-computer interfaces (cBCIs) have shown potential to improve group decisions with visual stimuli. This paper proposes a cBCI that assists and improves group decisions in a speech perception task. Neural features extracted from left-temporal-lobe EEG signals and response times were used to estimate the confidence of each individua...

Objective: We aimed at improving group performance in a challenging visual search task via a hybrid collaborative brain-computer interface (cBCI). Methods: Ten participants individually undertook a visual search task where a display was presented for 250 ms, and they had to decide whether a target was present or not. Local temporal correlation c...

Efficient and accurate classification of event related potentials is a core task in brain-computer interfaces (BCI). This is normally obtained by first extracting features from the voltage amplitudes recorded via EEG at different channels and then feeding them into a classifier. In this paper we evaluate the relative benefits of using the first ord...

Objective: The N2pc event-related potential (ERP) appears on the opposite side of the scalp with respect to the visual hemisphere where an object of interest is located.We explored the feasibility of using it to extract information on the spatial location of targets in aerial images shown by means of a rapid serial visual presentation (RSVP) proto...

In this paper, we analyse the Event-Related Potentials (ERPs) produced by cuts where the scenes before and after the cut are narratively related. In tests with 6 participants and 930 cuts from 5 Hollywood feature movies we found that cuts produce a large negative ERP with an onset 100 ms after a cut and a duration of 600 ms, distributed over a very...

In this paper we use a collaborative brain- computer interface to integrate the decision confidence of multiple non-communicating observers as a mechanism to improve group decisions. In recent research we tested this idea with the decisions associated with a simple visual matching task and found that a collaborative BCI can outperform group decisio...

Detecting a target in a complex environment can be a difficult task, both for a single individual and a group, es- pecially if the scene is very rich of structure and there are strict time constraints. In recent research, we have demonstrated that collaborative Brain-Computer Interfaces (cBCIs) can use neural signals and response times to estimate...

Event-Related Potentials (ERPs) are electrical signals produced by the brain in response to external stimuli. Due to the enormous noise affecting them, traditionally, the analysis of ERPs has relied of averaging the signals recorded in many repetitions of an experiment. However, while averaging helps to improve the signal to noise ratio of an ERP,...

The parsimony pressure method is perhaps the simplest and most fre-quently used method to control bloat in genetic programming. In this chapter we first reconsider the size evolution equation for genetic programming developed in [28] and rewrite it in a form that shows its direct relationship to Price's theorem. We then use this new formulation to...

The N2pc event-related potential appears on the opposite side of the scalp with respect to the visual hemisphere where an object of interest is located. In this paper, we propose a 2-user collaborative brain-computer interface that exploits this component for the automatic localisation of specific lateral targets in real aerial images displayed by...

Large sparse symmetric matrices are typical characteristics of the linear systems found in various scientific and engineering disciplines, such as fluid mechanics, structural engineering, finite element analysis, and network analysis. In all such systems, the performance of solvers crucially depends on the sum of the distance of each matrix element...

We look at the possibility of integrating the percepts from multiple non-communicating observers as a means of achieving better joint perception and better group decisions. Our approach involves the combination of a brain-computer interface with human behavioural responses. To test ideas in controlled conditions, we asked observers to perform a sim...

Large sparse symmetric matrix problems arise in a number of scientific and engineering fields such as fluid mechanics, structural engineering, finite element analysis and network analysis. In all such problems, the performance of solvers depends critically on the sum of the row bandwidths of the matrix, a quantity known as envelope size. This can b...

Exploration and exploitation are considered essential notions in evolutionary algorithms. However, a precise interpretation of what constitutes exploration or exploitation is clearly lacking and so are specific measures for characterising such notions. In this paper, we start addressing this issue by presenting new measures that can be used as indi...

The study of complex adaptive systems is among the key modern tasks in science. Such systems show radically different behaviours at different scales and in different environments, and mathematical modelling of such emergent behaviour is very difficult, even at the conceptual level. We require a new methodology to study and understand complex, emerg...

The goal of getting computers to automatically solve problems is central to artificial intelligence, machine learning, and the broad area encompassed by what Turing called machine intelligence (Turing 1948, 1950).

The parsimony pressure method is perhaps the simplest and most frequently used method to control bloat in genetic programming (GP). In this chapter we first reconsider the size evolution equation for genetic programming developed in Poli andMcPhee (Evol Comput 11(2):169-206, 2003) and rewrite it in a form that shows its direct relationship to Price...

In this paper, we propose a collaborative brain-computer interface for the automatic discrimination of images containing specific targets. When a user looks at a stream of images that are displayed using the rapid serial visual presentation protocol, images containing targets elicit a P300 event-related potential that can be detected. This allows t...

A significant proportion of patients affected by Parkinson's disease (PD) suffer from drug-resistant tremor, which often eventually progresses to disabling and distressing levels. Recent literature on PD indicates that such tremor is associated with corresponding oscillations in the thalamus. In this research, we wanted to explore the possibility t...

Abstract Several previous studies have focused on modelling and analysing the collective dynamic behaviour of population-based algorithms. However, an empirical approach for identifying and characterising such a behaviour is surprisingly lacking. In this paper, we present a new model to capture this collective behaviour, and to extract and quantify...

In rapid serial visual presentation (RSVP) images shown extremely rapidly can still be parsed by the visual system, and the detection of specific targets triggers specific EEG response. Research funded by DARPA's Neurotechnology for Intelligence Analysts program has proven speed-ups in sifting through satellite images when EEG signals of an intelli...

We explored the possibility of controlling a spacecraft simulator using an analogue Brain-Computer Interface (BCI) for 2-D pointer control. This is a difficult task, for which no previous attempt has been reported in the literature. Our system relies on an active display which produces event-related potentials (ERPs) in the user's brain. These are...

In the presence of complex stimuli, in the absence of sufficient time to complete the visual parsing of a scene, or when attention is divided, an observer can only take in a subset of the features of a scene, potentially leading to poor decisions. In this paper we look at the possibility of integrating the percepts from multiple non-communicating o...

Abstract Modelling the behaviour of algorithms is the realm of Evolutionary Algorithm theory. From a practitioner's point of view, theory must provide some guidelines regarding which algorithm/parameters to use in order to solve a particular problem. Unfortunately, most theoretical models of evolutionary algorithms are difficult to apply to realist...

We propose the use of genetic programming (GP) as a means to evolve brain–computer interfaces for mouse control. Our objective is to synthesise complete systems, which analyse electrical brain signals and directly transform them into pointer movements, almost from scratch, the only input provided by us in the process being the set of visual stimuli...

Large sparse matrices characterise the linear systems found in various scientific and engineering domains such as fluid mechanics, structural engineering, finite element analysis and network analysis. The ordering of the rows and columns of a matrix determines how close to the main diagonal its non-zero elements are, which in turn greatly influence...

Sparse matrices emerge in a number of problems in science and engineering. Typically the efficiency of solvers for such problems depends crucially on the distances between the first non-zero element in each row and the main diagonal of the problem's matrix -- a property assessed by a quantity called the size of the envelope of the matrix. This depe...

In [3] we proposed a hyperheuristic (HH) driven by Genetic Programming (GP). In given, more or less problem-specific target languages, this GP-HH expresses its evolved metaheuristics (MH), which makes the HH a generic solver. Here, we demonstrate that, for larger search spaces, specific MHs, evolved over simple and less specific languages

Understanding the emergent collective behaviour (and the properties associated with it) of population-based algorithms is an important prerequisite for making technically sound choices of algorithms and also for designing new algorithms for specific applications. In this paper, we present an empirical approach to analyse and quantify the collective...

Kimura's neutral theory of evolution has inspired researchers from the evolutionary computation community to incorporate neutrality into evolutionary algorithms (EAs) in the hope that it can aid evolution. The effects of neutrality on evolutionary search have been considered in a number of studies, the results of which, however, have been highly co...

Genetic programming (GP) is an evolutionary approach that extends genetic algorithms to allow the exploration of the space of computer programs. Like other evolutionary algorithms, GP works by defining a goal in the form of a quality criterion (or fitness) and then using this criterion to evolve a set (or population) of candidate solutions (individ...

The oddball protocol is often used in brain-computer interfaces (BCIs) to induce P300 ERPs, although, recently, some issues have been shown to detrimentally effect its performance. In this paper, we study a new periodic protocol and explore whether it can compete with the standard oddball protocol within the context of a BCI mouse. We found that th...

We propose GP-zip2, a new approach to lossless data compression based on Genetic Programming (GP). GP is used to optimally combine well-known lossless compression algorithms to maximise data compres- sion. GP-zip2 evolves programs with multiple components. One component analyses statistical features extracted by sequentially scanning the data to be...

The Tarpeian method for bloat control has been shown to be a robust technique to control bloat. The covariant Tarpeian method introduced last year, solves the problem of optimally setting the parameters of the method so as to achieve full control over the dynamics of mean program size. However, the theory supporting such a technique is applicable o...

The bandwidth reduction problem is a well-known NP-complete graph-layout problem that consists of labeling the vertices of a graph with integer labels in such a way as to minimize the maximum absolute difference between the labels of adjacent vertices. The problem is isomorphic to the important problem of reorder-ing the rows and columns of a symme...

In a recent paper by Bradberry, Gentili and Contreras-Vidal published in Journal of Neural Engineering (2011, 8 036010), an interesting method for the control of a two-dimensional mouse cursor was proposed, which apparently attained excellent control and good speed with relatively simple techniques. We believe some of the results in the paper have...

Over the last years, the effects of neutrality have attracted the attention of many researchers in the Evolutionary Algorithms (EAs) community. A mutation from one gene to another is considered as neutral if this modification does not affect the phenotype. This article provides a general overview on the work carried out on neutrality in EAs. Using...

Evolutionary algorithms were originally designed to locate basins of optimum solutions in a stationary environment. Therefore, additional techniques and modifications have been introduced to deal with further requirements such as handling dynamic fitness functions or finding multiple optima. In this paper, we present a new approach for building evo...

This paper describes a new approach for building evolutionary optimisation algorithms inspired by concepts borrowed from evolution of social behaviour. The proposed approach utilises a set of behaviours used as operators that work on a population of individuals. These behaviours are used and evolved by groups of individuals to enhance the group ada...

This paper describes a new approach for building evolutionary optimisation algorithms inspired by concepts borrowed from evolution of social behaviour. The proposed approach utilises a set of behaviours used as operators that work on a population of individuals. These behaviours are used and evolved by groups of individuals to enhance a group adapt...

Over the last few years there has been considerable activity around P300-based BCI protocols. Much of this has been focused on trying to overcome observed irregularities in ERP classification due to temporal proximity of target events. In this paper we explore three novel protocols which utilise a consistent temporal interval between targets. This...

We propose the use of genetic programming as a means to evolve brain-computer interfaces for mouse control. Our objective is to synthesise complete systems, which analyse electroencephalographic signals and directly transform them into pointer movements, almost from scratch, the only input provided by us in the process being the set of visual stimu...

Recently significant steps have been made towards effective EEG-based brain-computer interfaces for mouse control. A major obstacle in this line of research, however, is the integration of the noisy and contradictory information provided at each time step by the signal processing systems into a coherent and precise trajectory for the mouse pointer....

In this paper we use genetic programming an evolutionary program-induction technology to evolve algorithms that accurately approximate the behaviour of two standard detectors of ocular movement based on Electro-oculogram (EOG). The prediction is based entirely on EEG signals, i.e., without using EOG, making it possible to detect eye movements even...

Geometric crossovers are a class of representation-independent search operators for evolutionary algorithms that are well-defined once a notion of distance over a solution space is defined. In this paper we explore the specialisation of geometric crossovers to the permutation representation analysing the consequences of the availability of more tha...

In this paper a simple modification of the Tarpeian bloat-control method is presented which allows one to dynamically set the parameters of the method in such a way to guarantee that the mean program size will either keep a particular value (e.g., its initial value) or will follow a schedule chosen by the user. The mathematical derivation of the te...

Evolutionary computation techniques have seen a considerable popularity as problem solving and optimisation tools in recent years. Theoreticians have developed a variety of both exact and approximate models for evolutionary program induction algorithms. However, these models are often criticised for being only applicable to simplistic problems or a...

The P300 is an endogenous event-related potential (ERP) that is naturally elicited by rare and significant external stimuli. P300s are used increasingly frequently in brain-computer interfaces (BCIs) because the users of ERP-based BCIs need no special training. However, P300 waves are hard to detect and, therefore, multiple target stimulus presenta...