Soft sensors are mathematical models of industrial processes that are often used for monitoring and control. Data-driven techniques based on artificial intelligence are generally used for identifying these models. Data scarcity is a challenging problem that occurs when the variable to be estimated must be measured by laboratory analysis. Here, a difference-based neural network called Δ -Net is proposed to develop dynamic nonlinear soft sensors when only a few hundred labeled data are available. The Δ -Net, which exploits the case difference heuristic approach, is based on two parallel neural networks responsible for processing pairs of input samples. The Δ -Net is trained on an augmented dataset obtained by pairwise ordering the small original dataset. The outputs of the subnets are then combined to estimate the difference between the corresponding outputs of the pairs. The reconstruction of the output sample is computed as the mean of the distances from the sample to a set of anchor points, to increase the robustness of the prediction. The proposed approach has been applied to well-known industrial benchmarking datasets. The obtained results show superior performance compared to other data augmentation approaches, including bootstrap resampling, variational autoencoders and Wasserstein generative adversarial networks.

In this work, black-box modeling techniques are applied to Bacterial Cellulose-based sensors to characterize their dynamic behavior. Several classes of linear and nonlinear models, including Finite Impulse Response, AutoRegressive with eXogenous Input, Nonlinear Finite Impulse Response, Nonlinear AutoRegressive with eXogenous Input, and Long Short-Term Memory networks, are developed and compared. The performance of each model is evaluated based on a one-step-ahead prediction and a ∞-step-ahead simulation using standard performance metrics such as Root Mean Square Error, Mean Absolute Error and the coefficient of determination. The results show the strengths and limitations of the different modeling approaches in capturing the dynamics of BC-based transducers. The ARX model showed the best results for the prediction in one step, but poor results were obtained when the prediction was considered in ∞ steps. The NFIR model is instead the best choice for long-term prediction.

Bacterial Cellulose (BC) functionalized with Ionic Liquids (ILs) is a promising candidate for sustainable electroactive sensors. While single-carrier transport models are well-established in piezoionic electroactive polymers, their applicability to BC-IL systems remains unverified. This study introduces a simplified 1D finite element model, significantly improving computational efficiency while preserving key physical insights. A detailed parametric analysis investigates the impact of different charge transport assumptions, revealing that single-carrier models are insufficient to fully describe the mechanoelectric transduction behavior. The results emphasize the necessity of a dual-carrier framework to accurately model BC-based transducers, offering a deeper understanding of multi-ionic interactions within the porous BC structure. By highlighting key mechanisms and limitations, this work provides a foundation for optimizing BC-IL sensors, preparing the way for more reliable and scalable bioelectronic applications.

This paper presents a novel Clinical Decision Support System based on eXplainable Artificial Intelligence (XAI-CDSS) as a comprehensive structured tool consisting of three main parts: predictive models, XAI interpretation, and a graph-based visualization of non-communicable pathologies. Machine learning models are proposed to predict the risk factors related to the direct association between obesity and comorbidities such as cardiovascular, heart disease, and diabetes. Multilayer perceptron and extreme gradient boosting are chosen among different machine learning algorithms as the best performing for the risk factors prediction of the selected comorbidities. They perform prediction with an accuracy of 0.72 for diabetes, and 0.73 for cardiovascular and heart disease. The intuitive XAI interface gives the end-user insight into the machine learning decision process, while the graph visualization links such co-occurrent pathologies to many other non-communicable diseases and provides a global view to healthcare professionals, usable for obesity and associated pathologies prevention and long-term treatment and care.

Accurate Remaining Useful Life (RUL) prediction of machines is important for condition-based maintenance, in order to improve the reliability and costs of maintenance. The rotor is one of the most important equipment parts and is one of the most common failure points. To assess the degradation life of rotating machines, this paper proposes a data-driven prognostic technique that utilizes an unsupervised trend extraction and an exponential degradation model to obtain an accurate RUL prediction of rotor failures. The main steps of the proposed prognostic technique are condition monitoring data acquisition, feature extraction using signal processing techniques, feature selection based on the monotonicity technique to quantify the merit of the best representative features for prognosis purposes. The selected features are then combined using the principal component analysis technique to get the most appropriate component health indicator. Finally, an exponential degradation model is used to estimate the RUL using this health indicator. The suitability of the proposed approach in component monitoring is demonstrated on a degradation dataset of a faulty rotor acquired from a Simulink model of an induction motor.

In this paper a dielectric structure made with Carbon Black has been designed to realize a Fractional Order Element (FOE). This device is hence used as capacitor to build a fractional-order Wien oscillator. FOE experimental frequency characterization, theoretical and experimental simulations on Wien oscillator are provided.

In this paper, a graphical method to analyze the stability of LTI systems, with multiple commensurate time delays, is proposed. It is based on the determination of the purely imaginary roots of the pseudo-polynomial characteristic equation of the system. The proposed technique offers a number of unique features: it allows to have an immediate analysis stability i.e. it allows to verify if the stability of the system is delay-dependent or independent. Also, in the case of delay dependent stability, the method shows immediately all the existing imaginary roots, without solving many equations, as required by analytical methods. Advantages and drawbacks of the method are analyzed in the paper along with some numerical examples.

Deep Neural Network (DNN) based Soft Sensors (SSs) have been demonstrated as successful alternatives to other data-driven structures. Here, a dynamic DNN based SS is proposed for the estimation of the Research Octane Number (RON) for a Reformer Unit in a refinery. The SS is required to estimate the RON when the plant operates in two different working conditions. Nonlinear Finite Inputs Response (NFIR) models have been investigated. The regressors in the models have been selected according to a cross-correlation analysis between candidate inputs and the RON value. The performance of the proposed SSs has been compared with previously designed deep structures, based on different dynamic first level models, coupled with a fuzzy algorithm.

In this paper, the model identification of the temperature over the surface of the limiter adopted in the Frascati Tokamak Upgrade (FTU) is presented. Tokamaks are considered as the most interesting facilities to study self-sustained nuclear fusion reactions. Recently, a Liquid Lithium Limiter (LLL) has been introduced in the FTU with the aim of reducing impurities in the plasma. However, the performance of the LLL are maximized when temperature over its surface is uniformly distributed. In this paper, we face the problem of modeling the thermal behavior of the limiter surface following two different data-driven approaches: a linear autoregressive model, and a nonlinear autoregressive model. A comparison among the two models will be given, showing also which physical quantities are relevant to the specific modeling problem.

In this paper the problem of regressor selection in virtual sensor design is addressed. In particular nonlinear models designed by experimental data are used to estimate relevant process variables of an industrial plant. The plant considered is a Sulphur Recovery Unit of a large refinery settled in Sicily. The proposed approach is used to face with the problem of input regressor selection of NMA models. The approach is based on a recursive evaluation of the cross correlation function between input variables and model residuals. The obtained results are compared with corresponding estimation obtained by using a reference model. Significant improvements in the model estimation capability show the suitability of the proposed method

In this paper a CNNs based circuit for the generation of hyperchaotic signals is proposed. The circuit has been developed for applications in secure communication systems. An Saito oscillator has been designed by using a suitable configuration of a four-cells State-Controlled CNNs. A cryptography system based on the Saito oscillator has been implemented by using inverse system synchronization. The proposed circuit implementation and experimental results are given.

This paper proposes an experimental analysis on the convergence of evolutionary algorithms (EAs). The effect of introducing chaotic sequences instead of random ones during all the phases of the evolution process is investigated. The approach is based on the substitution of the random number generator (RNG) with chaotic sequences. Several numerical examples are reported in order to compare the performance of the EA using random and chaotic generators as regards to both the results and the convergence speed. The results obtained show that some chaotic sequences are always able to increase the value of some measured algorithm-performance indexes with respect to random sequences. Moreover, it is shown that EAs can be extremely sensitive to different RNGs. Some t-tests were performed to confirm the improvements introduced by the proposed strategy.

In this paper the problem of controlling the attitude of a rigid body, such as a Spacecraft, in three-dimensional space is approached by introducing two new control strategies developed in hypercomplex algebra. The proposed approaches are based on two parallel controllers, both derived in quaternion algebra. The first is a feedback controller of the proportional derivative (PD) type, while the second is a feedforward controller, which is implemented either by means of a hypercomplex multilayer perceptron (HMLP) neural network or by means of a hypercomplex radial basis function (HRBF) neural network. Several simulations show the performance of the two approaches. The results are also compared with a classical PD controller and with an adaptive controller, showing the improvements obtained by using neural networks, especially when an external disturbance acts on the rigid body. In particular the HMLP network gave better results when considering trajectories not presented during the learning phase.

Natural circulation loops represent important elements of many technologically relevant systems. For this reason, their instability represents a major concern, as it consists of oscillations leading to flow reversal. The analysis of these processes was addressed in various theoretical works, mainly based on mathematical approaches to the problem. The models obtained in this way suffers a poor correspondence between simulated and experimental data. To solve this problem, the identification of the system was adopted in this paper, and a neural network model was obtained by means of input-output measurements detected on an experimental natural circulation loop. Moreover, the neural model was used in a predictive scheme, in order to allow long term prediction of the birth of unstable behaviors.

In this paper it is shown that, with slight modifications, State Controlled CNNs (SC-CNNs) are able to approximate the behaviour of a class of complex dynamics with multivariable nonlinearities. In particular, in the so-called Extended SC-CNN defined in this work, the output nonlinearity shape has been modified, and a new template acting on the output function of the cell has been introduced. The needed circuitry to extend SC-CNNs, together with SPICE simulations of the new system, are here reported in order to confirm the suitability of the approach.

The methodology proposed in the paper applies artificial intelligence (AI) techniques to the modeling and control of some climate variables within a greenhouse. The nonlinear physical phenomena governing the dynamics of temperature and humidity in such systems are, in fact, difficult to model and control using traditional techniques. The paper proposes a framework for the development of soft computing-based controllers in modern greenhouses.

In the paper a strategy in order to decrease the learning time without affecting the learning efficiency for a complex valued Multi Layer Perceptron (CMLP) is proposed. The methodology makes use of auxiliary devices that enable one to predict the connections trend of the principal neural network whose learning phase is not damaged since the auxiliary devices run concurrently with it. A numerical example is reported which shows the suitability of the proposed approach.

In this paper the approximation capabilities of different structures of complex feedforward neural networks, reported in the literature, have been theoretically analyzed. In particular a new density theorem for Complex Multilayer Perceptrons with complex valued non-analytical sigmoidal activation functions has been proven. Such a result makes Multilayer Perceptrons with complex valued neurons universal interpolators of continuous complex valued functions. Moreover the approximation properties of superpositions of analytic activation functions have been investigated, proving that such combinations are not dense in the set of continuous complex valued functions. Several numerical examples have also been reported in order to show the advantages introduced by Complex Multilayer Perceptrons in terms of computational complexity with respect to the classical real MLP.

In the paper a new structure of a Multi-Layer Perceptron, able to deal with quaternion-valued signals, is proposed. A learning algorithm for the proposed Quaternion MLP (QMLP) is also derived. Such a neural network allows one to interpolate functions of a quaternion variable with a smaller number of connections with respect to the corresponding real valued MLP.>

In the paper it is proposed the use of a complex valued multi-layer perceptron neural network (MLP) with complex activation functions and complex connection strengths in order to perform the estimation of chaotic time series. In particular, the Ikeda map is taken into consideration. A comparison between the behavior of the real MLP and the complex one is also reported, showing that the complex valued MLP requires a smaller topology as well as a lower number of parameters in order to reach comparable performance.>