MOTIVATION: G-quadruplex-binding proteins (G4BPs) play key roles in RNA metabolism and stress response, yet their identification remains experimentally challenging. Here, we present a deep learning (DL) framework for the prediction of RNA G4BPs (RG4BPs), integrating diverse encoding strategies and neural architectures. Our best-performing model, which includes ESM-2 protein language model embeddings and consists of an LSTM architecture, achieved 86% accuracy in distinguishing RG4BPs from non-binder proteins. The application of this model to the human proteome uncovered 2160 high-confidence RG4BP candidates, many of which display intrinsically disordered regions (IDRs) and enrichment in stress granule organelles. These findings reveal a potential link between G-quadruplex recognition and cellular stress responses. To enable easy and broad access to the framework, we developed G4REP, a web server for RG4BP prediction and analysis. Overall, an effective approach to explore the RG4BPs landscape and uncover novel players in RNA regulation is provided. AVAILABILITY: Source code for the G4REP Model training and evaluation is available at: https://github.com/G4REP/G4REPmodel and at https://doi.org/10.5281/zenodo.17963046. G4REP Server is hosted at: https://schubert.bio.uniroma1.it/g4/.

• Innovative unsupervised approach for discovering anomalies in multivariate time series. • Data attribution by using explainability and data-driven learning. • Initial training on a self-supervised task to capture normal data behavior. • Data attribution to identify potential anomalies at the time step. • Experiments on several synthetic and real-world datasets. Anomaly detection is a challenging task that manifests in several forms depending on its context (e.g., fraud detection, network security, fault monitoring): given a collection of data, the goal is discovering the anomalous patterns diverging from the majority. The time dimension adds complexity to defining an anomaly, especially with multivariate time series, where each channel represents possibly distinct quantities. Classical unsupervised anomaly detection approaches have been based on differences in data, sequences of data, distributions, or also by inspecting the prediction deviation errors. In this work, we propose an innovative unsupervised approach for discovering anomalies in multivariate time series by leveraging the concept of data attribution from the explainability literature. Our proposed method is flexible and data-driven, and it can be used across multiple scenarios without the necessity of domain experts. By training initially on a self-supervised task (e.g., forecasting), a model captures normal data behavior; then, by using a data attribution technique we identify potential anomalies at the time step level. We conduct experiments on several synthetic and real-world datasets, comparing the results with state-of-the-art unsupervised anomaly detection methods, achieving competitive or better performance on most datasets, with notable improvements on synthetic data and promising results on real-world data, despite certain challenges in highly anomalous scenarios. Finally, we show an in-depth investigation of this methodology, along different dimensions, in order to gain a greater understanding of the application of these functions and their characteristics within the anomaly detection landscape.

Generating images from brain waves is gaining increasing attention due to its potential to advance brain-computer interface (BCI) systems by understanding how brain signals encode visual cues. Most of the literature has focused on fMRI-to-Image tasks as fMRI is characterized by high spatial resolution. However, fMRI is an expensive neuroimaging modality and does not allow for real-time BCI. On the other hand, electroencephalography (EEG) is a low-cost, non-invasive, and portable neuroimaging technique, making it an attractive option for future real-time applications. Nevertheless, EEG presents inherent challenges due to its low spatial resolution and susceptibility to noise and artifacts, which makes generating images from EEG more difficult. In this paper, we address these problems with a streamlined framework based on the ControlNet adapter for conditioning a latent diffusion model (LDM) through EEG signals. We conduct experiments and ablation studies on popular benchmarks to demonstrate that the proposed method beats other state-of-the-art models. Unlike these methods, which often require extensive preprocessing, pretraining, different losses, and captioning models, our approach is efficient and straightforward, requiring only minimal preprocessing and a few components. The code is available at https://github.com/LuigiSigillo/GWIT.

In this work, we introduce a hybrid quantum-classical framework to address anomaly detection problems in time series data using an innovative Quadratic Unconstrained Binary Optimization formulation. The proposed approach integrates density-based and statistical methodologies with the Quantum Approximate Optimization Algorithm, providing a versatile tool for anomaly detection. Moreover, the underlying model is transversal to different kinds of anomalies and can be directly applied to diverse applications, ranging from fault detection to novelty discovery. Experimental results prove that this architecture achieves competitive accuracy compared to classical techniques, with the unique advantage of exploring alternative solutions in parallel due to the properties of quantum computing. This capability enables a deeper understanding of patterns in time series data.

Gait analysis is an important technique for diagnosing, monitoring and rehabilitating neurological conditions such as Autism Spectrum Disorder, also known as ASD. With the increasing employment of AI in the medical domain, gait analysis allows researchers and doctors to improve their ability in modeling and interpreting complex structured data. In this delicate domain, explainable models become essential to build medical frameworks that can fasten and objectify the diagnosis procedure which is generally slow and ineffective. This study explores the use of explainability techniques applied to graph neural networks to enhance the understanding of decisions made by gait analysis models to detect ASD. The findings demonstrate that integrating explainability AI tools in this particular domain increases the accuracy of ASD detection and improves model transparency of the entire diagnosis process, allowing specialists to interpret and validate the extracted information and facilitating the adoption of these models in clinical settings.

In this work, we introduce new quantum machine learning models that combine both quantum and hyperdimensional computing. We focus our effort on two novel architectures that are first theoretically demonstrated, and then applied for testing to prototypical machine learning tasks, namely for pattern completion, classification, and clustering. We obtained accurate and promising results that prove, for the first time, the synergies between two of the most innovative computational approaches such as quantum computing and hyperdimensional computing.

Knowledge distillation is a widely explored technique in classical machine learning, in which a smaller or more efficient model is trained to mimic the behavior of a larger, more complex model. In this study, we extend the concept of knowledge distillation from classical architectures to quantum architectures, with the goal of improving the training of quantum models while potentially reducing the number of parameters compared to their classical counterparts. Given the inherent challenges in training quantum neural networks, leveraging knowledge from well-established classical models could provide valuable insights and advantages, particularly in terms of model efficiency and performance. In this work we explore the potential benefits of this approach, evaluating a hybrid quantum model against a non-hybrid quantum baseline. While the proposed study is still in the preliminary stage, it aims to set the scene for further investigation into the most appropriate architecture for classical-to-quantum knowledge distillation in order to enhance the development and optimization of quantum neural networks more generally.

This paper investigates the potential of quantum-enhanced models for time series forecasting in environments where time is a fundamental constraint. The focus is on on the quantum long short term memory networks with reservoir (QR-LSTM), and our proposed novel extension, the Autoencoded Quantum Reservoir LSTM Model (QR-LSTM-AE). The QR-LSTM, while offering substantial computational benefits in terms of time and resource efficiency, incurs a slight decrease in performance relative to the fully trainable quantum LSTM model. To address this trade-off, we introduce the QR-LSTM-AE, which utilizes an autoencoder-based strategy to recover performance lost in the reservoir alone, achieving superior accuracy without the need for full retraining. This approach not only maintains the efficiency of the QR-LSTM but also significantly reduces the computational cost associated with adapting to new data or time series, making it ideal for real-time forecasting applications. The experiments are carried out on a energy-related, highly volatile dataset, and results underscore the importance of balancing predictive accuracy with computational efficiency, highlighting the potential of quantum models to offer practical solutions in time-constrained environments. Our findings demonstrate that the QR-LSTM-AE effectively balances predictive accuracy and computational efficiency, paving the way for future advancements in quantum-enhanced forecasting through self-adaptive models, quantum autoencoders, and attention-based reservoir computing.

Early detection and accurate diagnosis of Autism Spectrum Disorder are critical for enabling timely interventions and personalized support. However, conventional diagnostic approaches remain largely subjective, posing challenges in achieving consistency and reliability. Recent clinical studies suggest that eye gaze patterns offer valuable insights into cognitive and attentional mechanisms underlying Autism Spectrum Disorder, highlighting their potential as biomarkers for objective assessment. In this work, we introduce a patch-based Graph Neural Network framework designed to analyze eye-tracking data by integrating fixation maps with the corresponding visual stimuli observed by both neurotypical and neurodivergent individuals. The proposed method constructs a hierarchical graph representation of image patches, progressively aggregating visual and attentional information to enhance feature extraction. A combination of Graph and Convolutional Neural Networks are employed for classification, capturing spatial and contextual dependencies between regions of interest respectively. Experimental evaluations and analysis demonstrate the effectiveness of our approach in distinguishing Autism Spectrum Disorder from neurotypical behavior, underscoring the potential of graph-based learning for neurodevelopmental assessments.

This paper explores the integration of quantum tools into classical cryptographic systems to assess their impact on the feasibility-efficiency trade-off in the context of Noisy Intermediate-Scale Quantum technology. By focusing on the hybridization of classical low-level primitives and high level cryptographic tools, the study investigates the effect of quantum contributions on encryption schemes corresponding to trapdoor permutations, revealing significant insights into the intersection of cryptography, quantum computing, and Boolean circuit theory.

Deep Learning models, and specifically Recurrent Neural Networks, have been successfully applied to time series classification in many applications, including Structural Health Monitoring. A relatively new field of research is the implementation of Deep Learning techniques for damage identification via measured time series in space systems, which proves chal-lenging in case of Structural Health Monitoring of large flexible structures. In this work, we propose a novel approach exploiting a symbolic time series representation as an additional data pre-processing step for data dimensionality reduction. The strategy is applied to a real world-scenario of a spacecraft hosting large solar panels equipped with distributed accelerometers at structural level, and compared against a previous benchmark case developed by the authors. Obtained results prove that the strategy has the potential to further improve classification quality towards an ideal 100% accuracy envisioned for space systems.

This paper introduces a novel variational quantum algorithm built upon the established Quantum Approximate Optimization Algorithm also known as QAOA. Since the known parameter fixing strategy imposes constraints on QAOA to enhance tractability at the cost of some expressive power, the proposed layerwise approach integrates it with the existing Multi-Angle QAOA technique, which is characterized in turn by height-ened expressiveness through an increased number of parameters, albeit with increased optimization challenges. Consequently, the proposed layerwise-Multi-Angle QAOA combines the strengths of one variant with the limitations of the other, striking a balance in algorithmic design. The effectiveness of the proposed algorithm is assessed through experimental evaluations on the Maximum Cut problem. This study reveals promising results in heuristic predictions, with robustness both in terms of approximation ratio and optimization capabilities.

Autism Spectrum Disorder (ASD) is a complex and heterogeneous neurodevelopmental disorder which affects a significant proportion of the population, with estimates suggesting that about 1 in 100 children worldwide are affected by ASD. This study introduces a new Deep Neural Network for identifying ASD in children through gait analysis, using features extracted from frames composing video recordings of their walking patterns. The innovative method presented herein is based on imagery and combines gait analysis and deep learning, offering a noninvasive and objective assessment of neurodevelopmental disorders while delivering high accuracy in ASD detection. Our model proposes a bimodal approach based on the concatenation of two distinct Convolutional Neural Networks processing two feature sets extracted from the same videos. The features obtained from the convolutions of both networks are subsequently flattened and merged into a single vector, serving as input for the fully connected layers in the binary classification process. This approach demonstrates the potential for effective ASD detection in children through the combination of gait analysis and deep learning techniques.

Multilayer neural networks set the current state of the art for many technical classification problems. But, these networks are still, essentially, black boxes in terms of analyzing them and predicting their performance. Here, we develop a statistical theory for the one-layer perceptron and show that it can predict performances of a surprisingly large variety of neural networks with different architectures. A general theory of classification with perceptrons is developed by generalizing an existing theory for analyzing reservoir computing models and connectionist models for symbolic reasoning known as vector symbolic architectures. Our statistical theory offers three formulas leveraging the signal statistics with increasing detail. The formulas are analytically intractable, but can be evaluated numerically. The description level that captures maximum details requires stochastic sampling methods. Depending on the network model, the simpler formulas already yield high prediction accuracy. The quality of the theory predictions is assessed in three experimental settings, a memorization task for echo state networks (ESNs) from reservoir computing literature, a collection of classification datasets for shallow randomly connected networks, and the ImageNet dataset for deep convolutional neural networks. We find that the second description level of the perceptron theory can predict the performance of types of ESNs, which could not be described previously. Furthermore, the theory can predict deep multilayer neural networks by being applied to their output layer. While other methods for prediction of neural networks performance commonly require to train an estimator model, the proposed theory requires only the first two moments of the distribution of the postsynaptic sums in the output neurons. Moreover, the perceptron theory compares favorably to other methods that do not rely on training an estimator model.

Nowadays, solving time series prediction problems is an open and challenging task. Many solutions are based on the implementation of deep neural architectures, which are able to analyze the structure of the time series and to carry out the prediction. In this work, we present a novel deep learning scheme based on an adaptive embedding mechanism. The latter is exploited to extract a compressed representation of the input time series that is used for the subsequent forecasting. The proposed model is based on a two-layer bidirectional Long Short-Term Memory network, where the first layer performs the adaptive embedding and the second layer acts as a predictor. The performances of the proposed forecasting scheme are compared with several models in two different scenarios, considering both well-known time series and real-life application cases. The experimental results show the accuracy and the flexibility of the proposed approach, which can be used as a prediction tool for any actual application.

This paper aims at solving time series prediction problems by means of a hybrid quantum-classical recurrent neural network. We propose a novel architecture based on stacked Long Short-Term Memory layers and a variational quantum layer. The latter employs a quantum feature map to embed input data into quantum states, which are then processed by a circuit ansatz. Finally, the expectation value of the circuit's outcome is taken over Pauli observables. Quantum properties such as superposition and entanglement are exploited to perform computations efficiently in a high-dimensional feature space. The proposed hybrid quantum-classical neural network is applied to a real-life challenging problem pertaining to the prediction of renewable energy time series. The comparison between the proposed approach and the classical counterpart shows that the former achieves better results in terms of prediction error, thus demonstrating better approximation of stochastic fluctuations and an overall effectiveness of the quantum variational approach also for prediction tasks.

The recent interest in federated learning has initiated the investigation for efficient models deployable in scenarios with strict communication and computational constraints. Furthermore, the inherent privacy concerns in decentralized and federated learning call for efficient distribution of information in a network of interconnected agents. Therefore, we propose a novel distributed classification solution that is based on shallow randomized networks equipped with a compression mechanism that is used for sharing the local model in the federated context. We make extensive use of hyperdimensional computing both in the local network model and in the compressed communication protocol, which is enabled by the binding and the superposition operations. Accuracy, precision, and stability of our proposed approach are demonstrated on a collection of datasets with several network topologies and for different data partitioning schemes.

Climate change has prompted the energy sector to shift its focus to renewable energy sources, which are environmentally friendly but less in terms of cost, complexity, and plants' management. It becomes critical to have a reliable method for estimating the output power of these systems, which are dispersed across the country and vary in kind and technology, and whose output power is mostly determined by meteorological factors. In this paper, we exploit the capability of modeling dynamic graph-like data of a specific type of graph neural network, spatio-temporal graph neural network, which can process spatial information about plants' distribution in a particular region as well as temporal data on individual plant power production. Plants in the same region can share information and make more accurate forecasts in this way. The suggested model was evaluated on two types of datasets: one with data gathered from real photovoltaic systems and the other with synthesized power time series reconstructed from data acquired by satellite detection. Our studies discovered how these systems can estimate the production outputs of photovoltaic stations simultaneously and with higher accuracy with respect to previous state-of-the-art models, performing effectively even in the absence of meteorological data.

Nowadays, deep learning is gaining attraction as one of the most successful paradigm for a plethora of machine learning applications. While its benefits are undoubted, the high computational burden associated with its training algorithms and cross-validation procedures is stimulating new lines of research. To this end, randomized deep neural networks are one of the best alternatives in terms of efficiency-to-accuracy balance. In this paper, we present a deep neural architecture that uses randomization of some parameters in a complex structure whose novelty is twofold: it embeds past samples of the time series by using daily blocks in the input frame of a convolutional layer; it predicts a day on the whole by solving a suitable regression problem. The proposed randomized approach is compared with state-of-the-art prediction algorithms on the challenging context related to energy time series, where the day-ahead prediction is usual, obtaining comparable or even better results in terms of forecasting accuracy and training time.

In the supervised learning domain, considering the recent prevalence of algorithms with high computational cost, the attention is steering towards simpler, lighter, and less computationally extensive training and inference approaches. In particular, randomized algorithms are currently having a resurgence, given their generalized elementary approach. By using randomized neural networks, we study distributed classification, which can be employed in situations were data cannot be stored at a central location nor shared. We propose a more efficient solution for distributed classification by making use of a lossy compression approach applied when sharing the local classifiers with other agents. This approach originates from the framework of hyperdimensional computing, and is adapted herein. The results of experiments on a collection of datasets demonstrate that the proposed approach has usually higher accuracy than local classifiers and getting close to the benchmark - the centralized classifier. This work can be considered as the first step towards analyzing the variegated horizon of distributed randomized neural networks.

The need of reliable prediction algorithms of energy production is increasing due to the spread of smart solution for grid, plant and resource management. Recurrent neural networks are a viable solution for prediction but their performance is somewhat insufficient when the time series is generated by an underlying process that behaves in a complex manner. In this paper, a new combination of echo state network and genetic algorithms is employed in order to improve the prediction accuracy of photovoltaic time series. The genetic algorithm is used to embed past samples of the time series to be used for predicting a new one. It aims at a feature extraction in order to regularize data being fed into a neural network model, so that it is able to learn more robust and generalizable prediction models. The experimental tests prove that the proposed approach is suited to the application focused in this paper.

In this paper, we introduce Random Weights Fuzzy Neural Networks as a suitable tool for solving prediction problems. The generalization capability of these randomized fuzzy neural networks is exploited in order to estimate accurately the sample be predicted from a multidimensional input. The latter is obtained by applying an embedding technique to the time series, which selects only the meaningful past samples to be used for prediction. We tested the proposed approach on real-world time series pertaining to the application context of power delivery. We proved the efficacy of the proposed approach by comparing its forecasting accuracy with respect to other prediction systems based on well-known data-driven regression models.

In modern real-world applications, the need of using a decentralized data processing approach has progressively increased, facing complexity and handling issues. Pervasive data and ubiquitous computational capacity have enabled the proficient use of distributed implementation of machine learning algorithms, especially for forecasting problems. We provide in this paper a new, fully distributed prediction approach based on the Long Short-Term Memory deep neural network. When placed in a network of interconnected agents, the single predictors are able to improve the prediction accuracy by means of the Alternating Direction Method of Multipliers consensus procedure on some network parameters. Experimental tests on real-world time series prove the efficacy of the proposed approach, which regulates the information exchange in the network through high-level structures in the considered models.

Quantum computing ideally allows designers to build much more efficient computers than the existing classical ones. By exploiting quantum parallelism and entanglement, it is possible to solve signal processing tasks on high throughput data coming from multiple sources. Random Vector Functional-Link is a neural network model usually adopted in such contexts, although quantum implementations have not been considered so far. This paper proposes a quantum version of this neural model, by introducing a specific learning algorithm to find the coefficients of the adopted quantum gates and focusing on the finite precision arithmetic imposed by the qubit strings that are used to represent the model parameters.

This paper introduces a sparse learning strategy that is suited for any fuzzy inference model, in particular to the Adaptive Neuro-Fuzzy Inference System, in order to optimize the generalization capability of the resulting model. This depends on two main issues: the estimate of numerical parameters of each fuzzy rule and the whole number of rules to be used. In this work, the former problem is solved by considering a random weight fuzzy neural network, where the fuzzy rule parameters of antecedents (i.e., membership functions) are randomly generated and the ones of rule consequents are estimated using a Regularized Least Squares algorithm. The second problem is solved by pruning the coefficients of fuzzy rules following a procedure based on sparse Bayesian learning theory. Experimental results on well-known datasets prove the effectiveness of the proposed approach.

Wavelet artificial neural networks and remote sensing techniques can be used to estimate water quality variables such as Chlorophyll-a, turbidity and suspended solids. This paper describes empirical algorithms for the estimation of these variables incorporating information from the Operational Land Imager Sensor on board the Landsat-8 satellite. Neural networks are seasonally trained using data from the Cefni reservoir (Anglesey, U.K.), covering a variety of physical trophic status. Chlorophyll-a levels and the suspended solids are estimated from the reflectance in band-2 and band-4, while the turbidity values from reflectance in band-4. Experimental results show the potential of Landsat-8 as a substitute of Landsat-7 in water bodies quality monitoring. Moreover, predicted values obtained by using wavelet artificial neural networks fit well measured data and hence, such models provide accurate results therefore improving the efficiency in monitoring water quality parameters and contributing to possible decision making processes in the environmental management.

In this paper, a new algorithm for on-line learning of Random Vector Functional-Link neural network is proposed. It is specifically tailored to hardware implementations with finite precision arithmetic in distributed computing scenarios, where the massive use of low-cost hardware resources for sensor networks or computing agents is necessary in order to deal with big data, IoT paradigms and multiple sources of information. The proposed algorithm does not require any specific DSP operation to be implemented in hardware, like matrix inversions or multiplications, for real-time learning. However, experimental results prove that the algorithm outperforms commonly adopted recursive least-squares algorithms optimized for hardware implementation, while the loss of performance with respect to batch training is reduced, as the proposed approach is proved to be very efficient when a reduced number of bits is adopted for finite precision hardware implementation.

In this paper, we present a study on the use of fuzzy neural networks and their application to the prediction of times series generated by complex processes of the real-world. The new learning strategy is suited to any fuzzy inference model, especially in the case of higher-order Sugeno-type fuzzy rules. The data considered herein are real-world cases concerning chaotic benchmarks as well as environmental time series. The comparison with respect to well-known neural and fuzzy neural models will prove that our approach is able to follow the behavior of the underlying, unknown process with a good prediction of the observed time series.

The Random-Weight Fuzzy Neural Network is an inference system where the fuzzy rule parameters of antecedents (i.e., membership functions) are randomly generated and the ones of consequents are estimated using a Regularized Least Squares algorithm. In this regard, we propose an on-line learning algorithm under the hypothesis of training data distributed across a network of interconnected agents. In particular, we assume that each agent in the network receives a stream of data as a sequence of mini-batches. When receiving a new chunk of data, each agent updates its estimate of the consequent parameters and, periodically, all agents agree on a common model through the Distributed Average Consensus protocol. The learning algorithm is faster than a solution based on a centralized training set and it does not rely on any coordination authority. The experimental results on well-known datasets validate our proposal.

Distributed learning refers to the problem of inferring a function when the training data are distributed among different nodes. While significant work has been done in the contexts of supervised and unsupervised learning, the intermediate case of Semi-supervised learning in the distributed setting has received less attention. In this paper, we propose an algorithm for this class of problems, by extending the framework of manifold regularization. The main component of the proposed algorithm consists of a fully distributed computation of the adjacency matrix of the training patterns. To this end, we propose a novel algorithm for low-rank distributed matrix completion, based on the framework of diffusion adaptation. Overall, the distributed Semi-supervised algorithm is efficient and scalable, and it can preserve privacy by the inclusion of flexible privacy-preserving mechanisms for similarity computation. The experimental results and comparison on a wide range of standard Semi-supervised benchmarks validate our proposal.

This paper deals with the opportunity of extracting useful information from medical data retrieved directly from a stereophotogrammetric system applied to gait analysis, which aims at controlling movements of patients affected by neurological diseases. The proposed approach is intended to a feature selection procedure as an optimization strategy based on genetic algorithms, where the misclassification error of healthy/diseased patients is adopted as the fitness function. This procedure will be used for estimating the performance of widely used classification algorithms, whose performance has been ascertained in many real-world problems with respect to well-known classification benchmarks, both in terms of number of selected features and classification accuracy. Moreover, the technique herein described will provide a useful tool in the context of medical diagnosis. In fact, we will prove that for the classification problem at hand the whole set of features is redundant and it can be significantly pruned. The obtained results on a real dataset acquired in our biomechanics laboratory show a very interesting classification accuracy using six features only among the sixteen acquired by the stereophotogrammetric system.

In this paper, we propose a scalable, decentralized learning algorithm for Random Weights Fuzzy Neural Networks, when training data is distributed through a network of interconnected computing agents. In this scenario, the aim is for all the agents to converge to a single model, with the requirement that only local communications between the agents are permitted. In this work we assume that all the agents know the parameters of the antecedents, while the parameters of the consequents are estimated by using the Alternating Direction Method of Multipliers strategy. Experimental results show that the performance of the proposed algorithm is comparable to that of a centralized model, where all the data is collected by a single agent before the training process. To this date, this is the first publication that addressed the problem of training a fuzzy neural network over a fully decentralized infrastructure.

Management of air quality is an important task in many human activities. It is carried out mainly by installing ventilation and filtering facilities. In order to ensure efficiency, these systems must be designed after the knowledge of key environmental parameters, such as size and type of particles and fibres present in the air. In this paper, we propose a new method for the classification of dust particles and fibres based on a minimal set of geometric features extracted from binary images of dust elements, captured by a very cheap imaging system. The proposed technique is discussed and tested. Experimental results obtained by real-measured data are presented, showing satisfactory performance by using several well-known classifiers.

In this paper, we consider the problem of distributed spectral clustering, wherein the data to be clustered is (horizontally) partitioned over a set of interconnected agents with limited connectivity. In order to solve it, we consider the equivalent problem of reconstructing the Euclidean distance matrix of pairwise distances among the joint set of datapoints. This is obtained in a fully decentralized fashion, making use of an innovative distributed gradient-based procedure, where at every agent we interleave gradient steps on a low-rank factorization of the distance matrix, with local averaging steps considering all its neighbors' current estimates. The procedure can be applied to any spectral clustering algorithm, including normalized and unnormalized variations, for multiple choices of the underlying Laplacian matrix. Experimental evaluations demonstrate that the solution is competitive with a fully centralized solver, where data is collected beforehand on a (virtual) coordinating agent.

Autonomous poststroke rehabilitation systems which can be deployed outside hospital with no or reduced supervision have attracted increasing amount of research attentions due to the high expenditure associated with the current inpatient stroke rehabilitation systems. To realize an autonomous systems, a reliable patient monitoring technique which can automatically record and classify patient's motion during training sessions is essential. In order to minimize the cost and operational complexity, the combination of nonvisual-based inertia sensing devices and pattern recognition algorithms are often considered more suitable in such applications. However, the high motion irregularity due to stroke patients' body function impairment has significantly increased the classification difficulty. A novel fuzzy kernel motion classifier specifically designed for stroke patient's rehabilitation training motion classification is presented in this paper. The proposed classifier utilizes geometrically unconstrained fuzzy membership functions to address the motion class overlapping issue, and thus, it can achieve highly accurate motion classification even with poorly performed motion samples. In order to validate the performance of the classifier, experiments have been conducted using real motion data sampled from stroke patients with a wide range of impairment level and the results have demonstrated that the proposed classifier is superior in terms of error rate compared to other popular algorithms.

A novel fuzzy clustering algorithm is presented in this paper, which removes the constraints generally imposed to the cluster shape when a given model is adopted for membership functions. An on-line, sequential procedure is proposed where the cluster determination is performed by using suited membership functions based on geometrically unconstrained kernels and a point-to-shape distance evaluation. Since the performance of on-line algorithms suffers from the pattern presentation order, we also consider the problem of cluster validity aiming at proving the minimal dependence and the robustness with respect to the initialization of inner parameters in the proposed algorithm. The numerical results reported in the paper prove that the proposed approach is able to improve the performances of well-known algorithms on some reference benchmarks.

In this paper we present a new approach for time series forecasting, called Maximum Length Weighted Nearest Neighbor (MLWNN), which combines prediction based on sequence similarity with optimization techniques. MLWNN predicts the 24 hourly electricity loads for the next day, from a time sequence of previously electricity loads up to the current day. We evaluate MLWNN using electricity load data for two years, for three countries (Australia, Portugal and Spain), and compare its performance with three state-of-the-art methods (weighted nearest neighbor, pattern sequence-based forecasting and iterative neural network) and with two baselines. The results show that MLWNN is a promising approach for one day ahead electricity load forecasting.

In this paper, we investigate the problem of music classification when training data is distributed throughout a network of interconnected agents (e.g. computers, or mobile devices), and it is available in a sequential stream. Under the considered setting, the task is for all the nodes, after receiving any new chunk of training data, to agree on a single classifier in a decentralized fashion, without reliance on a master node. In particular, in this paper we propose a fully decentralized, sequential learning algorithm for a class of neural networks known as Random Vector Functional-Link nets. The proposed algorithm does not require the presence of a single coordinating agent, and it is formulated exclusively in term of local exchanges between neighboring nodes, thus making it useful in a wide range of realistic situations. Experimental simulations on four music classification benchmarks show that the algorithm has comparable performance with respect to a centralized solution, where a single agent collects all the local data from every node and subsequently updates the model.

This work investigates on the widespread use of fuzzy neural networks in time series forecasting, concerning in particular the energy commodity markets. We propose a new learning strategy suited to any neural model. The proposed approach is further assessed in the case of higher-order Sugeno-type fuzzy rules, which are able to replicate the daily data and to reproduce the same statistical features for various Commodity time series. The data used are obtained from the daily return series of specific energy commodities, such as coal, natural gas, crude oil and electricity, over the period 2001-2010 for both the European and US markets. We will prove that our approach can obtain interesting results in terms of prediction accuracy and volatility estimation, compared to well-known neural and fuzzy neural models and to the ARMA-GARCH statistical paradigm.

A valid model of a rechargeable battery is required in several applications, especially to determine its internal charge. Due to the excessive variability of battery behavior, a large amount of data, experimentally obtained and suitably coded, should accompany the model. Exploiting the power of the fuzzy neural approach is a usual methodology to meet this requirement. However, also a strictly circuital approach is feasible, as proposed in the present paper. We suggest the use of a simple circuit model constituted by the series of a nonlinear capacitor and a memristor. Their different characteristics, experimentally determined, are compacted under the form of two small sets of vectors to be associated with the battery model.

In this paper, a new approach is presented for the evaluation of membership functions in fuzzy clustering algorithms. Starting from the geometrical representation of clusters by polygons, the fuzzy membership is evaluated through a suited point-to-polygon distance estimation. Three different methods are proposed, either by using the geometrical properties of clusters in the data space or by using Gaussian or cone-shaped kernel functions. They differ from the basic trade-off between computational complexity and approximation accuracy. By the proposed approach, fuzzy clusters of any geometrical complexity can be used, since there is no longer required to impose constraints on the shape of clusters resulting from the choice of computationally affordable membership functions. The methods illustrated in the paper are validated in terms of speed and accuracy by using several numerical simulations.

In the last decade the increasing volatility of petroleum markets has challenged time series analysts to produce highly predictive models. Crude Oil is a major driver of the global economy and its price fluctuations are a key indicator for producers, consumers and investors. With investors following the longerterm upward trend in Energy prices Commodity investments, we believe this will drive an increasing importance for methodologies like neurofuzzy networks for risk quantification, measurement and management. The data used is Crude Oil prices for both Brent and WTI in the 10 year period from 2001 to 2010. We will prove that the neurofuzzy approach based on ANFIS networks compare favorably with respect to other standard and neural models and it is able to achieve useful performances in terms of accurate prediction of prices and their probability distribution.

Damping of vibrations in piezo-electromechanical structures relies on a good design of the related electric networks. The most interesting solutions, from the complexity point of view, make use of two operational amplifiers for each piezo-electric transducer. Although the behavior of such circuits coincides with the ideal controller when the two operational amplifiers are assumed to be ideal, damping and stability issues arise when real active components are used. In this paper, it is shown how the actual performance of these circuits can be improved by modifying the interconnection among components.

Nonlinear quantum processing allows the solution of an optimization problem by the exhaustive search on all its possible solutions. Hence, it can replace advantageously the algorithms for learning from a training set. In order to pursue this possibility in the case of neurofuzzy networks, we propose in this paper to tailor their architectures to the requirements of quantum processing. In particular, superposition is introduced to pursue parallelism and entanglement to associate the network performance with each solution present in the superposition. Two aspects of the proposed method are considered in detail: the binary structure of membership functions and fuzzy reasoning and the use of a particular nonlinear quantum algorithm for extracting the optimal neurofuzzy network by exhaustive search.

This paper deals with the musical genre classification problem, starting from a set of features extracted directly from MPEG-1 layer III compressed audio data. The automatic classification of compressed audio signals into a short hierarchy of musical genres is explored. More specifically, three feature sets for representing timbre, rhythmic content and energy content are proposed for a four leafs tree genre hierarchy. The adopted set of features are computed from the spectral information available in the MPEG decoding stage. The performance and relative importance of the proposed approach is investigated by training a classification model using the audio collections proposed in musical genre contests. We also used an optimization strategy based on genetic algorithms. The results are comparable to those obtained by PCM-based musical genre classification systems.

Acoustic source localization in the presence of reverberation is a difficult task. Conventional approaches, based on time delay estimation performed by generalized cross correlation (GCC) on a set of microphone pairs, followed by geometric triangulation, are often unsatisfactory. Prefiltering is usually adopted to reduce the spurious peaks due to reflections. In this work an alternative strategy is proposed, based on the concept that secondary peaks of the GCCs can be crucial in order to correctly locate the source. More specifically, an iterative weighting procedure is introduced, based on the rationale that peaks corresponding to the actual source position should be consistently weighted. The position estimate is then refined by use of an effective and fast clustering technique. Experimental results on simulated data demonstrate the effectiveness of the proposed solution.

In this paper, we introduce a symbolic tool able to characterize the basic elements of a piezo-electromechanical structure. This tool gives us the opportunity to develop a useful procedure for investigating the properties of the whole electromechanical system and, in particular, the non-ideal behavior of the RC-active network connected to the structure. The main goal of this procedure is to determine the stability of the system for a given choice of active components and to introduce a criterion for the optimization of the related parameters.

A useful neural network paradigm for the solution of function approximation problems is represented by adaptive neuro-fuzzy inference systems (ANFIS). Data driven procedures for the synthesis of ANFIS networks are typically based on clustering a training set of numerical samples of the unknown function to be approximated. Some serious drawbacks often affect the clustering algorithms adopted in this context, according to the particular data space where they are applied. To overcome such problems, we propose a new ANFIS synthesis procedure where clustering is applied in the joint input-output data space. Using this approach, it is possible to determine the consequent part of Sugeno first-order rules and therefore the hyperplanes characterizing the local structure of the function to be approximated. Successively, the fuzzy antecedent part of each rule is determined using a particular fuzzy min-max classifier, which is based on the adaptive resolution mechanism. The generalization capability of the resulting ANFIS architecture is optimized using a constructive procedure for the automatic determination of the optimal number of rules. Simulation tests and comparisons with respect to other neuro-fuzzy techniques are discussed in the paper, in order to assess the efficiency of the proposed approach.

We propose a low cost prevention strategy for osteoporosis. Osteoporosis is a disease consisting in the structural deterioration of bones. This disease has a very high cost for the public health expense all over the world. Its main diagnostic tool is a radiographic analysis called computerized bone mineralometry, by which it is possible to measure the bone mineral density (BMD). Starting from the BMD value it is possible to estimate the risk of contracting osteoporosis. Although the cost of this clinical analysis is not high, a wide screening of the population can be not affordable. The proposed prevention strategy is based on the assumption that BMD can be estimated by a neural model, on the basis of some objective individual characteristics to be determined by the patient itself. We propose the use of MoG (mixture of Gaussian) neural model, trained by an automatic procedure based on maximum likelihood approach.

Classification can be considered as a basic data driven modeling problem, which allows us to define and design more complex modeling systems. The choice of an adequate classification system should take into account the automation degree of the learning procedure, especially if it must be employed as a core inference engine. Fuzzy min-max neural networks are very effective and flexible classification models, since they easily allow the design of constructive learning techniques, such as the ARC/PARC one. In this paper we propose a classification system able to generate automatically a fuzzy min-max classifier. It holds the capability to optimize both the number of neurons in the hidden layer and the set of features used to classify a pattern, without any knowledge about the test set. Its performances are evaluated through a toy problem and two real data benchmarks.

A high automation degree is one of the most important features of data driven modeling tools and it should be taken into consideration in classification systems design. In this regard, constructive training algorithms are essential to improve the automation degree of a modeling system. Among neuro-fuzzy classifiers, Simpson's (1992) min-max networks have the advantage of being trained in a constructive way. The use of the hyperbox, as a frame on which different membership functions can be tailored, makes the min-max model a flexible tool. However, the original training algorithm evidences some serious drawbacks, together with a low automation degree. In order to overcome these inconveniences, in this paper two new learning algorithms for fuzzy min-max neural classifiers are proposed: the adaptive resolution classifier (ARC) and its pruning version (PARC). ARC/PARC generates a regularized min-max network by a succession of hyperbox cuts. The generalization capability of ARC/PARC technique mostly depends on the adopted cutting strategy. By using a recursive cutting procedure (R-ARC and R-PARC) it is possible to obtain better results. ARC, PARC, R-ARC, and R-PARC are characterized by a high automation degree and allow to achieve networks with a remarkable generalization capability. Their performances are evaluated through a set of toy problems and real data benchmarks. The paper also proposes a suitable index that can be used for the sensitivity analysis of the classification systems under consideration.

An algorithm to train min-max neural models is proposed. It is based on the adaptive resolution classifier (ARC) technique, which overcomes some undesired properties of the original Simpson's (1992) algorithm. In particular, training results do not depend on pattern presentation order and hyperbox expansion is not limited by a fixed maximum size, so that it is possible to have different covering resolutions. ARC generates the optimal min-max network by a succession of hyperbox cuts. The generalization capability of the ARC technique depends mostly on the adopted cutting strategy. A new recursive cutting procedure allows ARC technique to yield a better performance. Some real data benchmarks are considered for illustration.