Sparse optimization assisted adaptive and smart hybrid data-driven modeling for process systems

• An adaptive modular hybrid modeling approach for a building-integrated GSHP-DH system. • A physics-guided, event-triggered mechanism enables real-time adaptation to changes. • An Accuracy Recovery Gradient (ARG) metric quantifies the model’s adaptability rate. • White-box and black-box models were compared across modules for accuracy and runtime. • The physics-guided all-black-box configuration delivered the best overall performance. Accurate and efficient building energy models with high adaptability are essential for online energy management of multi-energy heating systems in complex buildings. Although various modeling approaches were utilized to balance accuracy and computational efficiency, they remain limited in flexibility, interpretability, and adaptability to changing control conditions. This study develops an adaptive modular hybrid modeling approach for a cold-climate, multi-purpose building supplied by a hybrid ground-source heat pump (GSHP) and district heating (DH) system. Within the proposed framework, white-box and black-box models were developed for each component using measured data and tested in all-white-box, all-black-box, and hybrid configurations to evaluate trade-offs between accuracy and computational time. A physics-guided, event-triggered adaptation mechanism was introduced and validated with measurements from real-world scenarios representing varying operating conditions to ensure real-time adaptability. Adaptability was quantified using the novel accuracy recovery gradient factor (ARG), which demonstrated fast and effective performance recovery after disruptions. The all-black-box model, guided by the building white-box model for synchronization, achieved the best overall performance. It estimated hourly electrical consumption with a CVRMSE of 7.5% while running over 1000 times faster than the hybrid configuration. It could also automatically detect deviations, trigger adaptation, and regain acceptable accuracy in 28 and 170 minutes under minor and major changes in operating conditions, respectively. The results demonstrated the potential of the proposed modular hybrid model, supported by an event-triggered adaptation mechanism, for real-time energy management in complex multi-energy buildings.

In this paper, an uncertainty optimization method based on the adaptive hybrid correlation Kriging surrogate model is proposed to optimize the ply angles of laminated spherical-conical shells. First, equations of motion of laminated spherical-conical shells are constructed to calculate the vibration characteristics. Then, this paper proposes a Kriging surrogate model with adaptive weight hybrid correlation functions and validates its accuracy. Based on this framework, the weight distribution of the surrogate model for uncertain parameters in laminated spherical-conical shells under different ply angles is analyzed. To address the uncertainty optimization problem in laminated spherical-conical shell structures, an Improved Multi-objective Salp Swarm Algorithm is developed, and its optimization efficacy is systematically validated. Furthermore, an adaptive hybrid correlation Kriging surrogate model is reconstructed, incorporating both uncertainty parameters and design variables as inputs, with the peak vibration displacement and fundamental frequency serving as the output responses. The uncertainty optimization results confirm that the proposed methodology, along with the enhanced Kriging modeling strategy, exhibits both applicability and computational efficiency for such engineering applications.

Hybrid surrogate model for online temperature and pressure predictions in data centers

Different emerging threats highlighted the relevance of recovery and adaptation modelling in the functioning of societal systems. However, as modelling of systems becomes more complex, its effort increases challenging the practicality of the engineering analyses required for efficient recovery and adaptation. In the present work, metamodels are researched as a tool to enable these analyses in traffic networks. One of the main advantages of metamodeling is their synergy with the short decision times required in recovery and adaptation. A sequential global metamodeling technique is proposed and applied to three macroscopic day-to-day user-equilibrium models. Two reference contexts of application are researched: optimal recovery to a perturbation (with response times reduced by 98% with loss of accuracy lower than 1%) and adaptation under uncertainty with perturbation-dependent optimality. Results show that metamodeling-based metaheuristics enable fast resource-intensive engineering analyses of traffic recovery and adaptation, which may change the paradigm of decision-making in this field

This paper proposes a step-by-step technique for combining basic models that forecast electricity consumption in an artificial neural network by the method of preliminary selection and further hybridization. The reported experiments were conducted using data on hourly electricity consumption at the metallurgical plant AO ArcelorMittal Temirtau in the period from January 1, 2019, to November 30, 2021. The current research is related to the planned introduction of a balancing electricity market. 96 combinations of basic models were compiled, differing in the type of neural network, the set of initial data, the order of lag, the learning algorithm, and the number of neurons in the hidden layer. It has been determined that the NARX-type network is the most optimal architecture to forecast electricity consumption. Based on experimental studies, the number of hidden neurons needed to form a planned daily profile should equal 3 or 4; it is recommended to use the conjugate gradient method as a learning algorithm. When selecting models from three groups, it was revealed that the conjugate gradient method produces better results compared to the Levenberg-Marquardt algorithm. It is determined that the values of the selected RMSE error indicator take values of 23.17, 22.54, and 22.56, respectively, for the first, second, and third data groups. The adaptive hybridization method has been shown to reduce the RMSE error rate to 21.73. However, the weights of the best models with values of 0.327 for the first group of data, and 0.336 for the second and third ones, show that the individual use of a separate combination of models is also applicable. The devised forecasting electricity consumption model can be integrated into an automated electricity metering system

The study addresses the critical importance of teacher skills and competences in shaping educational quality and future generations, focusing on revealing the essence and structure of professionally-based competences that prospective foreign language teachers should acquire to work effectively with digital adaptive technologies in their future profession. The research recognizes that improving teacher training programs and maintaining high teaching standards are essential for sustainable national development. Methodology and Methods. Data was collected using a structured Likert Scale questionnaire administered to 68 participants who rated a set of 25 competences. The research employed descriptive statistical analysis as the primary analytical approach, with the Friedman test utilized to reveal essential differences between professionally-based competences of prospective foreign language teachers. Results. The findings demonstrated that in-service teachers considered methodical competence as the most important professionally-based competence. The Friedman test revealed significant differences between various competences, with highest ranks assigned to competences related to effective lesson planning and classroom time management, while contemporary approaches such as hybrid learning models received the lowest rankings. The lower ranking of competences related to adaptive learning models indicated gaps in current teacher training programs. Scientific novelty. The research provides comprehensive analysis of the competence structure required for prospective foreign language teachers working with digital adaptive technologies, establishing a hierarchy of professional competences and identifying previously unrecognized gaps between traditional teaching skills and contemporary digital approaches in teacher preparation. Practical significance. The study reveals the need for focused professional development in teacher training programs, particularly in areas related to adaptive learning models and hybrid teaching approaches, providing evidence-based recommendations for improving the quality of foreign language teacher preparation to meet modern educational demands.

Recently, network security has become an extremely vital issue that beckons the development of accurate and efficient solutions capable of effectively defending our network systems and the valuable information journeying through them. In this article, a distributed multiagent intrusion detection system (IDS) architecture is proposed, which attempts to provide an accurate and lightweight solution to network intrusion detection by tackling issues associated with the design of a distributed multiagent system, such as poor system scalability and the requirements of excessive processing power and memory storage. The proposed IDS architecture consists of (i) the Host layer with lightweight host agents that perform anomaly detection in network connections to their respective hosts, and (ii) the Classification layer whose main functions are to perform misuse detection for the host agents, detect distributed attacks, and disseminate network security status information to the whole network. The intrusion detection task is achieved through the employment of the lightweight Adaptive Sub-Eigenspace Modeling (ASEM)-based anomaly and misuse detection schemes. Promising experimental results indicate that ASEM-based schemes outperform the KNN and LOF algorithms, with high detection rates and low false alarm rates in the anomaly detection task, and outperform several well-known supervised classification methods such as C4.5 Decision Tree, SVM, NN, KNN, Logistic, and Decision Table (DT) in the misuse detection task. To assess the performance in a real-world scenario, the Relative Assumption Model, feature extraction techniques, and common network attack generation tools are employed to generate normal and anomalous traffic in a private LAN testbed. Furthermore, the scalability performance of the proposed IDS architecture is investigated through the simulation of the proposed agent communication scheme, and satisfactory linear relationships for both degradation of system response time and agent communication generated network traffic overhead are achieved.

Modeling is essential to integrating knowledge of human physiology. Comprehensive self-consistent descriptions expressed in quantitative mathematical form define working hypotheses in testable and reproducible form, and though such models are always "wrong" in the sense of being incomplete or partly incorrect, they provide a means of understanding a system and improving that understanding. Physiological systems, and models of them, encompass different levels of complexity. The lowest levels concern gene signaling and the regulation of transcription and translation, then biophysical and biochemical events at the protein level, and extend through the levels of cells, tissues and organs all the way to descriptions of integrated systems behavior. The highest levels of organization represent the dynamically varying interactions of billions of cells. Models of such systems are necessarily simplified to minimize computation and to emphasize the key factors defining system behavior; different model forms are thus often used to represent a system in different ways. Each simplification of lower level complicated function reduces the range of accurate operability at the higher level model, reducing robustness, the ability to respond correctly to dynamic changes in conditions. When conditions change so that the complexity reduction has resulted in the solution departing from the range of validity, detecting the deviation is critical, and requires special methods to enforce adapting the model formulation to alternative reduced-form modules or decomposing the reduced-form aggregates to the more detailed lower level modules to maintain appropriate behavior. The processes of error recognition, and of mapping between different levels of model complexity and shifting the levels of complexity of models in response to changing conditions, are essential for adaptive modeling and computer simulation of large-scale systems in reasonable time.

This chapter presents an adaptive modeling and control scheme for drug delivery systems based on a Generalized Fuzzy Neural Network (G-FNN). The proposed G-FNN is a novel intelligent modeling tool, which can model the unknown nonlinearities of complex drug delivery systems and adapt to changes and uncertainties in these systems on line. It offers salient features, such as dynamic fuzzy neural structure, fast online learning ability and adaptability, etc. System approximation formulated by the G-FNN is thus employed in the adaptive controller design for drug infusion. In particular, this chapter investigates automated regulation of Mean Arterial Pressure (MAP) through the intravenous infusion of Sodium NitroPrusside (SNP), which is one of the attractive applications in automation of drug delivery. Simulation study demonstrates superior performance of the proposed approach for estimating the drug’s effect and regulating blood pressure at a prescribed level.

ID: 371 Patient dose calculation systems in diagnostic radiology: State of the art and conscious use

Daily land surface temperature (LST) forecasting is of great significance for application in climate-related, agricultural, eco-environmental, or industrial studies. Hybrid data-driven prediction models using Ensemble Empirical Mode Composition (EEMD) coupled with Machine Learning (ML) algorithms are useful for achieving these purposes because they can reduce the difficulty of modeling, require less history data, are easy to develop, and are less complex than physical models. In this article, a computationally simple, less data-intensive, fast and efficient novel hybrid data-driven model called the EEMD Long Short-Term Memory (LSTM) neural network, namely EEMD-LSTM, is proposed to reduce the difficulty of modeling and to improve prediction accuracy. The daily LST data series from the Mapoling and Zhijiang stations in the Dongting Lake basin, central south China, from 1 January 2014 to 31 December 2016 is used as a case study. The EEMD is firstly employed to decompose the original daily LST data series into many Intrinsic Mode Functions (IMFs) and a single residue item. Then, the Partial Autocorrelation Function (PACF) is used to obtain the number of input data sample points for LSTM models. Next, the LSTM models are constructed to predict the decompositions. All the predicted results of the decompositions are aggregated as the final daily LST. Finally, the prediction performance of the hybrid EEMD-LSTM model is assessed in terms of the Mean Square Error (MSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), Pearson Correlation Coefficient (CC) and Nash-Sutcliffe Coefficient of Efficiency (NSCE). To validate the hybrid data-driven model, the hybrid EEMD-LSTM model is compared with the Recurrent Neural Network (RNN), LSTM and Empirical Mode Decomposition (EMD) coupled with RNN, EMD-LSTM and EEMD-RNN models, and their comparison results demonstrate that the hybrid EEMD-LSTM model performs better than the other five models. The scatterplots of the predicted results of the six models versus the original daily LST data series show that the hybrid EEMD-LSTM model is superior to the other five models. It is concluded that the proposed hybrid EEMD-LSTM model in this study is a suitable tool for temperature forecasting.

Accurate and interpretable arrhythmia detection is essential for timely diagnosis and intervention, particularly in Medical Decision Support Systems (MDSS). Fuzzy logic, known for its ability to handle uncertainty and enhance interpretability, has emerged as a promising approach. This systematic literature review (SLR) investigates the role of fuzzy logic in advancing arrhythmia detection, focusing on accuracy, interpretability, and integration with computational intelligence. Following the PRISMA guidelines, 13 studies published between 2019 and 2024 were analysed to address four key questions: (Q1) the accuracy and reliability of fuzzy logic systems, (Q2) the effectiveness of hybrid systems combining fuzzy logic with computational intelligence, (Q3) the challenges in developing multi-class fuzzy logic systems, and (Q4) the impact of fuzzy logic on interpretability in MDSS. Techniques such as Adaptive Neural Fuzzy Inference Systems (ANFIS) and hybrid models with neural networks and bio-inspired algorithms were evaluated. ANFIS demonstrated near-perfect accuracy, while hybrid systems enhanced scalability and addressed multi-class classification challenges. Limitations included reliance on benchmark datasets, limited real-world validation, and insufficient focus on explainable artificial intelligence (XAI). Fuzzy logic shows strong potential for developing interpretable and robust MDSS for arrhythmia detection. Future research should prioritise advancing XAI, incorporating diverse datasets, and addressing real-world challenges to improve clinical applicability.

Underwater Image Enhancement via Domain Adaptive Transfer Learning and Hybrid Reinforcement Model

Closed-form seismic earth pressure solutions via adaptive limit analysis and hybrid learning models

The need of the aerospace industry, at national or European level, of faster yet reliable computational fluid dynamics models is the main drive for the application of model reduction techniques. This need is linked to the time cost of high-fidelity models, rendering them inefficient for applications like multi-disciplinary optimization. With the goal of testing and applying model reduction to computational fluid dynamics models applicable to lifting surfaces, a bibliographical research covering reduction of nonlinear, dynamic, or steady models was conducted. This established the prevalence of projection and least mean squares methods, which rely on solutions of the original high-fidelity model and their proper orthogonal decomposition to work. Other complementary techniques such as adaptive sampling, greedy sampling, and hybrid models are also presented and discussed. These projection and least mean squares methods are then tested on simple and documented benchmarks to estimate the error and speed-up of the reduced order models thus generated. Dynamic, steady, nonlinear, and multiparametric problems were reduced, with the simplest version of these methods showing the most promise. These methods were later applied to single parameter problems, namely the lid-driven cavity with incompressible Navier–Stokes equations and varying Reynolds number, and the elliptic airfoil at varying angles of attack for compressible Euler flow. An analysis of the performance of these methods is given at the end of this article, highlighting the computational speed-up obtained with these techniques, and the challenges presented by multiparametric problems and problems showing point singularities in their domain.