Next Issue
Volume 18, October
Previous Issue
Volume 18, August
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.5
2.1
Journals
Algorithms
Volume 18
Issue 9
share announcement

Algorithms, Volume 18, Issue 9 (September 2025) – 59 articles

Cover Story (view full-size image): How can optimization be guided with minimal prior knowledge but maximum efficiency? We propose an algorithm that combines classical Bayesian optimization with prior distributions constructed using UQ techniques based on a Hilbert basis. This technique facilitates the inference of probability distributions from limited data. A metamodel approximates the objective function throughout the domain by exploiting spatial correlations between samples. Our data-driven priors learn from these limited initial data automatically, assigning weight to different regions of the search space, highlighting promising ones, and downweighting less favorable ones. This approach guides the optimization process, leading to a 30% volume reduction in our application, with no added expensive evaluations. View this paper
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Order results
Result details
Section
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
18 pages, 393 KB  
Article
A Comparison of Energy Consumption and Quality of Solutions in Evolutionary Algorithms
by Francisco Javier Luque-Hernández, Sergio Aquino-Britez, Josefa Díaz-Álvarez and Pablo García-Sánchez
Algorithms 2025, 18(9), 593; https://doi.org/10.3390/a18090593 - 22 Sep 2025
Abstract
Evolutionary algorithms are extensively used to solve optimisation problems. However, it is important to consider and reduce their energy consumption, bearing in mind that programming languages also significantly affect energy efficiency. This research work compares the execution of four frameworks—ParadisEO (C++), ECJ (Java), [...] Read more.
Evolutionary algorithms are extensively used to solve optimisation problems. However, it is important to consider and reduce their energy consumption, bearing in mind that programming languages also significantly affect energy efficiency. This research work compares the execution of four frameworks—ParadisEO (C++), ECJ (Java), DEAPand Inspyred (Python)—running on two different architectures: a laptop and a server. The study follows a design that combines three population sizes (26, 210, 214 individuals) and three crossover probabilities (0.01; 0.2; 0.8) applied to four benchmarks (OneMax, Sphere, Rosenbrock and Schwefel). This work makes a relevant methodological contribution by providing a consistent implementation of the metric η=fitness/kWh. This metric has been systematically applied in four different frameworks, thereby setting up a standardized and replicable protocol for the evaluation of the energy efficiency of evolutionary algorithms. The CodeCarbon software was used to estimate energy consumption, which was measured using RAPL counters. This unified metric also indicates the algorithmic productivity. The experimental results show that the server speeds up the number of generations by a factor of approximately 2.5, but the energy consumption increases four- to sevenfold. Therefore, on average, the energy efficiency of the laptop is five times higher. The results confirm the following conclusions: the computer power does not guarantee sustainability, and population size is a key factor in balancing quality and energy. Full article
(This article belongs to the Special Issue Swarm Intelligence and Evolutionary Algorithms for Real World Applications (2nd Edition))
►▼ Show Figures

Figure 1

28 pages, 4443 KB  
Article
UCINet: A Multi-Task Network for Umbilical Coiling Index Measurement in Obstetric Ultrasound
by Zhuofu Liu, Lichen Niu, Zhixin Di and Meimei Liu
Algorithms 2025, 18(9), 592; https://doi.org/10.3390/a18090592 - 22 Sep 2025
Viewed by 36
Abstract
The umbilical coiling index (UCI), which quantifies the degree of vascular coiling in the umbilical cord, is a crucial indicator for assessing fetal intrauterine development and predicting perinatal outcomes. However, the existing methods for measuring the UCI primarily rely on manual assessment, which [...] Read more.
The umbilical coiling index (UCI), which quantifies the degree of vascular coiling in the umbilical cord, is a crucial indicator for assessing fetal intrauterine development and predicting perinatal outcomes. However, the existing methods for measuring the UCI primarily rely on manual assessment, which suffers from low efficiency and susceptibility to inter-observer variability. In response to the challenges in measuring the umbilical coiling index during obstetric ultrasound, we propose UCINet, a multi-task neural network engineered explicitly for this purpose. UCINet demonstrates enhanced operational efficiency and significantly improved accuracy in detection, catering to the nuanced requirements of obstetric imaging. Firstly, this paper proposes a Frequency–Spatial Domain Downsampling Module (FSDM) to extract features in both the frequency and spatial domains, thereby reducing the loss of umbilical cord features and enhancing their representational capacity. The proposed Multi-Receptive Field Feature Perception Module (MRPM) employs receptive fields of varying sizes across different stages of the feature maps, enhancing the richness of feature representation. This approach allows the model to capture a more diverse set of spatial information, contributing to improved overall performance in feature extraction. A Multi-Scale Feature Aggregation Module (MSAM) comprehensively leverages multi-scale features via a dynamic fusion mechanism, optimizing the integration of disparate feature scales for enhanced performance. In addition, the UCI dataset, which consisted of 2018 annotated ultrasound images, was constructed, each labeled with the number of vascular coils and keypoints at both ends of the umbilical cord. Compared with state-of-the-art methods, UCINet achieves consistent improvements across two tasks. In object detection, UCINet outperforms Deformable DETR-R50 with an improvement of 1.2% points in mAP@50. In keypoint localization, it further exceeds YOLOv11 with a 3.0% gain in mAP@50, highlighting its effectiveness in both detection accuracy and fine-grained keypoint prediction. Full article
(This article belongs to the Special Issue Machine Learning for Pattern Recognition (3rd Edition))
►▼ Show Figures

Figure 1

28 pages, 2942 KB  
Article
Interactive Fuzzy Logic Interface for Enhanced Real-Time Water Quality Index Monitoring
by Amar Lokman, Wan Zakiah Wan Ismail, Nor Azlina Ab Aziz and Anith Khairunnisa Ghazali
Algorithms 2025, 18(9), 591; https://doi.org/10.3390/a18090591 - 21 Sep 2025
Viewed by 86
Abstract
Surface water resources are under growing pressure from urbanization, industrial activity, and agriculture, making effective monitoring essential for safeguarding ecological integrity and human use. Conventional monitoring methods, which rely on manual sampling and rigid Water Quality Index (WQI) categories, often provide delayed feedback [...] Read more.
Surface water resources are under growing pressure from urbanization, industrial activity, and agriculture, making effective monitoring essential for safeguarding ecological integrity and human use. Conventional monitoring methods, which rely on manual sampling and rigid Water Quality Index (WQI) categories, often provide delayed feedback and oversimplify conditions near classification thresholds, limiting their usefulness for timely management. To overcome these shortcomings, we have developed an interactive fuzzy logic-based water quality monitoring interface or dashboard that integrates the WQI developed by Malaysia’s Department of Environment with the National Water Quality Standards (NWQS) Class I–V framework. The interface combines conventional WQI computation with advanced visualization tools such as dynamic gauges, parameter tables, fuzzy membership graphs, scatter plots, heatmaps, and bar charts. Then, triangular membership functions map six key parameters to NWQS classes, providing smoother and more nuanced interpretation compared to rigid thresholds. In addition to that, the dashboard enables clearer communication of trends, supports timely decision-making, and demonstrates adaptability for broader applications since it is implemented on the Replit platform. Finally, evaluation results show that the fuzzy interface improves interpretability by resolving ambiguities in over 15% of cases near class boundaries and facilitates faster assessment of pollution trends compared to conventional reporting. Thus, these contributions highlight the necessity and value of the research on advancing Malaysia’s national water quality monitoring and providing a scalable framework for international contexts. Full article
(This article belongs to the Special Issue Development of Machine Learning and Artificial Intelligence Algorithms in Environmental Retrieval Tasks)
14 pages, 3062 KB  
Article
Self-Supervised Monocular Depth Estimation Based on Differential Attention
by Ming Zhou, Hancheng Yu, Zhongchen Li and Yupu Zhang
Algorithms 2025, 18(9), 590; https://doi.org/10.3390/a18090590 - 19 Sep 2025
Viewed by 135
Abstract
Depth estimation algorithms are widely applied in various fields, including 3D reconstruction, autonomous driving, and industrial robotics. Monocular self-supervised algorithms for depth prediction offer a cost-effective alternative to acquiring depth through hardware devices such as LiDAR. However, current depth prediction networks, predominantly based [...] Read more.
Depth estimation algorithms are widely applied in various fields, including 3D reconstruction, autonomous driving, and industrial robotics. Monocular self-supervised algorithms for depth prediction offer a cost-effective alternative to acquiring depth through hardware devices such as LiDAR. However, current depth prediction networks, predominantly based on conventional encoder–decoder architectures, often encounter two critical limitations: insufficient feature fusion mechanisms during the upsampling phase and constrained receptive fields. These limitations result in the loss of high-frequency details in the predicted depth maps. To overcome these issues, we introduce differential attention operators to enhance global feature representation and refine locally upsampled features within the depth decoder. Furthermore, we equip the decoder with a deformable bin-structured prediction head; this lightweight design enables per-pixel dynamic aggregation of local depth distributions via adaptive receptive field modulation and deformable sampling, enhancing the decoder’s fine-grained detail processing by capturing local geometry and holistic structures. Experimental results on the KITTI and Make3D datasets demonstrate that our proposed method produces more accurate depth maps with finer details compared to existing approaches. Full article
(This article belongs to the Special Issue Algorithms for Feature Selection (3rd Edition))
►▼ Show Figures

Figure 1

13 pages, 836 KB  
Article
Importance Assessment of Distribution Network Nodes Based on an Improved MBCC-HITS Algorithm
by Jie Wu, Zhengwei Chang, Wei Zhang, Haina Rong and Tingting Zeng
Algorithms 2025, 18(9), 589; https://doi.org/10.3390/a18090589 - 17 Sep 2025
Viewed by 209
Abstract
By accurately identifying important nodes in the distribution network and implementing priority protection measures or optimizing the network layout, a system’s anti-interference capability can be effectively enhanced while reducing the probability of failures. Inspired by the MBCC-HITS algorithm, this paper proposes an improved [...] Read more.
By accurately identifying important nodes in the distribution network and implementing priority protection measures or optimizing the network layout, a system’s anti-interference capability can be effectively enhanced while reducing the probability of failures. Inspired by the MBCC-HITS algorithm, this paper proposes an improved MBCC-HITS algorithm based on node degree centrality (DCHITS) for evaluating important nodes in distribution networks. Building upon the MBCC-HITS algorithm, the DCHITS algorithm incorporates node degree centrality to enhance the evaluation framework, supplementing the influence of topological structure factors on node importance assessment, thereby more accurately reflecting the actual conditions of the distribution network. In the IEEE 33 system, the DCHITS algorithm was compared with the node degree and node betweenness algorithms, as well as the MBCC-HITS algorithm, using two indicators: the scale of load loss and the maximum subgroup size. The results demonstrate that the DCHITS algorithm outperforms the others in both indicators. Specifically, compared to the MBCC-HITS algorithm, the scale of load loss increased by 0.55%, and the maximum subgroup size decreased by 8.21%. compared to the node degree and node betweenness algorithm, the scale of load loss increased by 6.63%, and the maximum subgroup size decreased by 5.38%. These findings indicate that the DCHITS algorithm is more rational and effective in identifying the important nodes in distribution networks. Full article
(This article belongs to the Section Evolutionary Algorithms and Machine Learning)
►▼ Show Figures

Figure 1

28 pages, 45524 KB  
Article
A Comparative Analysis of U-Net Architectures with Dimensionality Reduction for Agricultural Crop Classification Using Hyperspectral Data
by Georgios Dimitrios Gkologkinas, Konstantinos Ntouros, Eftychios Protopapadakis and Ioannis Rallis
Algorithms 2025, 18(9), 588; https://doi.org/10.3390/a18090588 - 17 Sep 2025
Viewed by 248
Abstract
The inherent high dimensionality of hyperspectral imagery presents both opportunities and challenges for agricultural crop classification. This study offers a rigorous comparative evaluation of three U-Net-based architectures, i.e., U-Net, U-Net++, and Atrous U-Net, applied to EnMAP hyperspectral data over the heterogeneous agricultural region [...] Read more.
The inherent high dimensionality of hyperspectral imagery presents both opportunities and challenges for agricultural crop classification. This study offers a rigorous comparative evaluation of three U-Net-based architectures, i.e., U-Net, U-Net++, and Atrous U-Net, applied to EnMAP hyperspectral data over the heterogeneous agricultural region of Lake Vegoritida, Greece. To address the spectral redundancy, we integrated multiple dimensionality-reduction strategies, including Linear Discriminant Analysis, SHAP-based model-driven feature selection, and unsupervised clustering approaches. Results reveal that model performance is contingent on (a) the network’s architecture and (b) the features’ space provided by band selection. While U-Net++ consistently excels when the full spectrum or ACS-derived subsets are employed, standard U-Net achieves great performance under LDA reduction, and Atrous U-Net benefits from SHAP-driven compact representations. Importantly, band selection methods such as ACS and SHAP substantially reduce spectral dimensionality without sacrificing accuracy, with the U-Net++–ACS configuration delivering the highest F1-score (0.77). These findings demonstrate that effective hyperspectral crop classification requires a joint optimization of architecture and spectral representation, underscoring the potential of compact, interpretable pipelines for scalable and operational precision agriculture. Full article
(This article belongs to the Special Issue Data Sensing Techniques and Processing Algorithms for Smart and Sustainable Agriculture)
►▼ Show Figures

Figure 1

23 pages, 993 KB  
Review
Exploring Kalman Filtering Applications for Enhancing Artificial Neural Network Learning
by Alma Y. Alanis
Algorithms 2025, 18(9), 587; https://doi.org/10.3390/a18090587 - 17 Sep 2025
Viewed by 319
Abstract
Kalman filter is a widely used estimation algorithm with numerous applications, including parameter estimation, classification, prediction, pattern recognition, tuning, and filtering. Recently, it has gained attention in artificial intelligence and machine learning as a mathematical framework for the learning process. As a methodology [...] Read more.
Kalman filter is a widely used estimation algorithm with numerous applications, including parameter estimation, classification, prediction, pattern recognition, tuning, and filtering. Recently, it has gained attention in artificial intelligence and machine learning as a mathematical framework for the learning process. As a methodology designed for stochastic environments, the Kalman filter effectively manages noise and unstructured data with incomplete information while preventing premature stagnation, enabling faster learning and reducing the need for extensive pre-processing. These characteristics make it ideal for training artificial neural networks and other machine learning techniques. Given its significance, this paper presents a review of Kalman filter applications for artificial neural network learning. Full article
(This article belongs to the Section Evolutionary Algorithms and Machine Learning)
►▼ Show Figures

Figure 1

24 pages, 5250 KB  
Systematic Review
Reclaiming XAI as an Innovation in Healthcare: Bridging Rule-Based Systems
by Hanvedes Daovisan, Charin Suwanwong, Pitchada Prasittichok, Narulmon Prayai and Phaktada Choowan
Algorithms 2025, 18(9), 586; https://doi.org/10.3390/a18090586 - 17 Sep 2025
Viewed by 300
Abstract
The adoption of explainable artificial intelligence (XAI) in healthcare has been increasingly framed as dependent on transparency, trustworthiness, and accountability. The objective of this study was the reclamation of rule-based systems within XAI as innovations aligned with healthcare accountability. A scientometric mapping analysis [...] Read more.
The adoption of explainable artificial intelligence (XAI) in healthcare has been increasingly framed as dependent on transparency, trustworthiness, and accountability. The objective of this study was the reclamation of rule-based systems within XAI as innovations aligned with healthcare accountability. A scientometric mapping analysis was conducted using publications indexed in Scopus between 1 January 2018 and 20 May 2025. The search strategy was applied to 1034 records. From these, 892 were screened, 238 duplicates were removed, and 654 studies were retained in accordance with the PRISMA 2020 framework. Thematic cluster analysis, co-authorship structures, and keyword co-occurrence patterns were visualised through VOSviewer 1.6.20. Transparency, accountability, and trustworthiness were established as central values for clinical integration. Expanding domains were identified in smart healthcare, digital health, healthcare technology, and mHealth, while interpretability was observed to remain underrepresented. Rule-based systems, frequently in hybrid forms, were demonstrated to bridge algorithmic complexity with interpretability. This bridging was interpreted as reinforcing physician confidence, regulatory compliance, and patient safety. It was concluded that the advancement of XAI in healthcare has been shaped by the interplay of ethical principles, methodological innovation, and digital health applications. Practical implications, theoretical contributions, and potential limitations were systematically addressed. Full article
(This article belongs to the Special Issue AI-Assisted Medical Diagnostics)
►▼ Show Figures

Figure 1

21 pages, 6585 KB  
Article
2D/3D Pattern Formation Comparison Using Spectral Methods to Solve Nonlinear Partial Differential Equations of Condensed and Soft Matter
by Marco A. Morales, Dania A. Pérez-Muñoz, J. Alejandro Hernández-González, Miguel Alvarado-Flores and Sinuhé Ruiz-Salgado
Algorithms 2025, 18(9), 585; https://doi.org/10.3390/a18090585 - 16 Sep 2025
Viewed by 241
Abstract
It is well known that nonlinear partial differential equations (NLPDEs) can only be solved numerically and that fourth-order NLPDEs in their derivatives require unconventional methods. This paper explains spectral numerical methods for obtaining a numerical solution by Fast Fourier Transform (FFT), implemented under [...] Read more.
It is well known that nonlinear partial differential equations (NLPDEs) can only be solved numerically and that fourth-order NLPDEs in their derivatives require unconventional methods. This paper explains spectral numerical methods for obtaining a numerical solution by Fast Fourier Transform (FFT), implemented under Python in tis version 3.1 and their libraries (NumPy, Tkinter). Examples of NLPDEs typical of Condensed Matter Physics to be solved numerically are the conserved Cahn–Hilliard, Swift–Hohenberg and conserved Swift–Hohenberg equations. The last two equations are solved by the first- and second-order exponential integrator method, while the first of these equations is solved by the conventional FFT method. The Cahn–Hilliard equation, a phase-field model with an extended Ginzburg–Landau-like functional, is solved in two-dimensional (2D) to reproduce the evolution of the microstructure of an amorphous alloy Ce75Al25 − xGax, which is compared with the experimental micrography of the literature. Finally, three-dimensional (3D) simulations were performed using numerical solutions by FFT. The second-order exponential integrator method algorithm for the Swift–Hohenberg equation implementation is successfully obtained under Python by FFT to simulate different 3D patterns that cannot be obtained with the conventional FFT method. All these 2D/3D simulations have applications in Materials Science and Engineering. Full article
(This article belongs to the Section Algorithms for Multidisciplinary Applications)
►▼ Show Figures

Figure 1

15 pages, 1126 KB  
Article
PISI: Physical Information Based Solver-Interactive Network Structure Reconstruction
by Juan Liu and Guofeng Mei
Algorithms 2025, 18(9), 584; https://doi.org/10.3390/a18090584 - 16 Sep 2025
Viewed by 250
Abstract
Inference of the interactive network structure of the physical world that is captured by nonlinear dynamic systems is a long-standing goal for machine learning. Existing inference methods have shown limited incorporation of physical system information and solver interaction capabilities. We present a comprehensive [...] Read more.
Inference of the interactive network structure of the physical world that is captured by nonlinear dynamic systems is a long-standing goal for machine learning. Existing inference methods have shown limited incorporation of physical system information and solver interaction capabilities. We present a comprehensive Physical Information based Solver-Interactive (PISI) network structure identification framework that incorporates network topology, physical constraints, and bidirectional solver interaction in nonlinear dynamical systems. To this end, we first develop a physical information-based graphical neural network (PIGNN). The PIGNN cells are embedded as the basic integration units to iterative interact with dynamical solver. The dynamical systems’s physical information can be flexibly added to the iterative interaction for PIGNN training. The above stages are trained end-to-end using a Runge–Kutta solver. The network structure inferring capability of the proposed framework is demonstrated through two kuramoto systems. Our PISI methodology, integrating graph topology, physical constraints, and solver interactivity shows advantages in trajectory prediction and structure reconstruction compared to state-of-the-art methods. Full article
(This article belongs to the Section Evolutionary Algorithms and Machine Learning)
►▼ Show Figures

Figure 1

36 pages, 6566 KB  
Article
Algorithmic Optimal Control of Screw Compressors for Energy-Efficient Operation in Smart Power Systems
by Kassym Yelemessov, Dinara Baskanbayeva, Leyla Sabirova, Nikita V. Martyushev, Boris V. Malozyomov, Tatayeva Zhanar and Vladimir I. Golik
Algorithms 2025, 18(9), 583; https://doi.org/10.3390/a18090583 - 14 Sep 2025
Viewed by 523
Abstract
This work presents the results of a research study focused on the development and evaluation of an algorithmic optimal control framework for energy-efficient operation of screw compressors in smart power systems. The proposed approach is based on the Pontryagin maximum principle (PMP), which [...] Read more.
This work presents the results of a research study focused on the development and evaluation of an algorithmic optimal control framework for energy-efficient operation of screw compressors in smart power systems. The proposed approach is based on the Pontryagin maximum principle (PMP), which enables the synthesis of a mathematically grounded regulator that minimizes the total energy consumption of a nonlinear electromechanical system composed of a screw compressor and a variable-frequency induction motor. Unlike conventional PID controllers, the developed algorithm explicitly incorporates system constraints, nonlinear dynamics, and performance trade-offs into the control law, allowing for improved adaptability and energy-aware operation. Simulation results obtained using MATLAB/Simulink confirm that the PMP-based regulator outperforms classical PID solutions in both transient and steady-state regimes. Experimental tests conducted in accordance with standard energy consumption evaluation methods showed that the proposed PMP-based controller provides a reduction in specific energy consumption of up to 18% under dynamic load conditions compared to a well-tuned basic PID controller, while maintaining high control accuracy, faster settling, and complete suppression of overshoot under external disturbances. The control system demonstrates robustness to parametric uncertainty and load variability, maintaining a statistical pressure error below 0.2%. The regulator’s structure is compatible with real-time execution on industrial programmable logic controllers (PLCs), supporting integration into intelligent automation systems and smart grid infrastructures. The discrete-time PLC implementation of the regulator requires only 103 arithmetic operations per cycle and less than 102 kB of RAM for state, buffers, and logging, making it suitable for mid-range industrial controllers under 2–10 ms task cycles. Fault-tolerance is ensured via range and rate-of-change checks, residual-based plausibility tests, and safe fallbacks (baseline PID or torque-limited speed hold) in case of sensor faults. Furthermore, the proposed approach lays the groundwork for hybrid extensions combining model-based control with AI-driven optimization and learning mechanisms, including reinforcement learning, surrogate modeling, and digital twins. These enhancements open pathways toward predictive, self-adaptive compressor control with embedded energy optimization. The research outcomes contribute to the broader field of algorithmic control in power electronics, offering a scalable and analytically justified alternative to heuristic and empirical tuning approaches commonly used in industry. The results highlight the potential of advanced control algorithms to enhance the efficiency, stability, and intelligence of energy-intensive components within the context of Industry 4.0 and sustainable energy systems. Full article
(This article belongs to the Special Issue AI-Driven Control and Optimization in Power Electronics)
►▼ Show Figures

Figure 1

14 pages, 1027 KB  
Article
A Hybrid Steffensen–Genetic Algorithm for Finding Multi-Roots of Nonlinear Equations and Applications to Biomedical Engineering
by Fiza Zafar, Alicia Cordero, Sadia Mujtaba and Juan R. Torregrosa
Algorithms 2025, 18(9), 582; https://doi.org/10.3390/a18090582 - 13 Sep 2025
Viewed by 255
Abstract
A new hybrid of a Steffensen-type method and genetic algorithm is developed for the efficient simultaneous computation of roots of nonlinear equations, particularly in all cases involving non-differentiable functions and multiple roots. Traditional numerical methods often fail to handle these complexities effectively, highlighting [...] Read more.
A new hybrid of a Steffensen-type method and genetic algorithm is developed for the efficient simultaneous computation of roots of nonlinear equations, particularly in all cases involving non-differentiable functions and multiple roots. Traditional numerical methods often fail to handle these complexities effectively, highlighting the need for a more robust solution. The proposed algorithm combines the global search strength of the genetic algorithm (GA) with the local refinement capabilities of a derivative-free optimal fourth-order Steffensen method. This integration enhances both exploration and exploitation capabilities, leading to improved convergence and computational accuracy. By uniting the GA’s global optimization with the local refinement of iterative solvers, the algorithm forms a higher-order framework capable of locating all roots concurrently. This study validates the performance of this hybrid strategy through diverse applications in biomedical engineering problems. Full article
(This article belongs to the Special Issue Mathematical Modelling in Engineering and Human Behaviour (3rd Edition))
►▼ Show Figures

Figure 1

19 pages, 2352 KB  
Article
Detecting Very Weak Signals: A Mixed Strategy to Deal with Biologically Relevant Information
by Alessandro Vici, Ann Zeuner and Alessandro Giuliani
Algorithms 2025, 18(9), 581; https://doi.org/10.3390/a18090581 - 13 Sep 2025
Viewed by 362
Abstract
In many biological investigations, the relevant information does not coincide with the most powerful signals (most elevated eigenvalues, dominant frequencies, most populated clusters...), but very often hides in minor features that are difficult to discriminate from random noise. Here we propose an algorithm [...] Read more.
In many biological investigations, the relevant information does not coincide with the most powerful signals (most elevated eigenvalues, dominant frequencies, most populated clusters...), but very often hides in minor features that are difficult to discriminate from random noise. Here we propose an algorithm that, by the combined use of a non-linear cluster analysis procedure and a strategy to discriminate minor signal components from noise, allows singling out biologically relevant hidden information. We tested the algorithm on a sparse data set corresponding to single-cell RNA-Seq measures, being able to identify a very small population of cells in charge of the immune response toward cancer tissue. Full article
(This article belongs to the Special Issue Advances in Algorithms Through Heuristics: Theory, Applications, and Innovations)
►▼ Show Figures

Figure 1

19 pages, 1484 KB  
Article
Data-Efficient Sleep Staging with Synthetic Time Series Pretraining
by Niklas Grieger, Siamak Mehrkanoon and Stephan Bialonski
Algorithms 2025, 18(9), 580; https://doi.org/10.3390/a18090580 - 13 Sep 2025
Viewed by 225
Abstract
Analyzing electroencephalographic (EEG) time series can be challenging, especially with deep neural networks, due to the large variability among human subjects and often small datasets. To address these challenges, various strategies, such as self-supervised learning, have been suggested, but they typically rely on [...] Read more.
Analyzing electroencephalographic (EEG) time series can be challenging, especially with deep neural networks, due to the large variability among human subjects and often small datasets. To address these challenges, various strategies, such as self-supervised learning, have been suggested, but they typically rely on extensive empirical datasets. Inspired by recent advances in computer vision, we propose a pretraining task termed “frequency pretraining” to pretrain a neural network for sleep staging by predicting the frequency content of randomly generated synthetic time series. Our experiments demonstrate that our method surpasses fully supervised learning in scenarios with limited data and few subjects, and matches its performance in regimes with many subjects. Furthermore, our results underline the relevance of frequency information for sleep stage scoring, while also demonstrating that deep neural networks utilize information beyond frequencies to enhance sleep staging performance, which is consistent with previous research. We anticipate that our approach will be advantageous across a broad spectrum of applications where EEG data is limited or derived from a small number of subjects, including the domain of brain-computer interfaces. Full article
(This article belongs to the Special Issue Machine Learning and Signal Processing for EEG, ECG, EDA, and Other Biosignals)
►▼ Show Figures

Figure 1

14 pages, 549 KB  
Article
Poroelastic Medium with Non-Penetrating Crack Driven by Hydraulic Fracture: FEM Approximation Using HHT-α and Semi-Smooth Newton Methods
by Victor A. Kovtunenko and Olena M. Atlasiuk
Algorithms 2025, 18(9), 579; https://doi.org/10.3390/a18090579 - 13 Sep 2025
Viewed by 263
Abstract
A new class of poroelastic dynamic contact problems stemming from hydraulic fracture theory is introduced and studied. The two-phase medium consists of a solid phase and pores which are saturated with a Newtonian fluid. The porous body contains a fluid-driven crack endowed with [...] Read more.
A new class of poroelastic dynamic contact problems stemming from hydraulic fracture theory is introduced and studied. The two-phase medium consists of a solid phase and pores which are saturated with a Newtonian fluid. The porous body contains a fluid-driven crack endowed with non-penetration conditions for the opposite crack surfaces. The poroelastic model is described by a coupled system of hyperbolic–parabolic partial differential equations under the unilateral constraint imposed on displacement. After full discretization using finite-element and Hilber–Hughes–Taylor methods, the well-posedness of the resulting variational inequality is established. Formulation of the complementarity conditions with the help of a minimum-based merit function is used for the semi-smooth Newton method of solution presented in the form of a primal–dual active set algorithm which is tested numerically. Full article
(This article belongs to the Special Issue Nonsmooth Optimization and Its Applications)
►▼ Show Figures

Graphical abstract

27 pages, 6213 KB  
Article
Mathematical Modelling and Numerical Analysis of Turbulence Models (In a Two-Stage Laboratory Turbine)
by Vesna Antoska Knights, Tatjana Atanasova-Pacemska and Jasenka Gajdoš Kljusurić
Algorithms 2025, 18(9), 578; https://doi.org/10.3390/a18090578 - 13 Sep 2025
Viewed by 239
Abstract
This paper presents a mathematical modeling and numerical analysis of fluid-thermal processes in a two-stage steam turbine cascade, focusing on the application and comparative assessment of turbulence models in computational fluid dynamics (CFD) simulations. Using the finite volume method implemented in the ANSYS [...] Read more.
This paper presents a mathematical modeling and numerical analysis of fluid-thermal processes in a two-stage steam turbine cascade, focusing on the application and comparative assessment of turbulence models in computational fluid dynamics (CFD) simulations. Using the finite volume method implemented in the ANSYS CFX-Task Flow (ANSYS CFX 2022 R2) workflow, the study investigates the performance of standard k-ε, k-ω, and SST turbulence models in predicting flow structures, pressure fields, and velocity distributions within the turbine flow passages. The governing equations, including the Reynolds-Averaged Navier–Stokes (RANS) equations and associated energy and constitutive relations, are solved in conservative form under compressible flow conditions. Experimental data from turbine tests performed at the Institute of Fluid Machinery at Lodz University of Technology are used for validation. Results demonstrate that turbulence modeling significantly influences the accuracy of predicted flow phenomena. The study identifies strengths and limitations of the models in capturing complex three-dimensional flow structures and provides quantitative error margins and practical guidance for their application in industrial turbine flow simulations. Full article
(This article belongs to the Special Issue Mathematical Modelling in Engineering and Human Behaviour (3rd Edition))
►▼ Show Figures

Figure 1

18 pages, 2904 KB  
Article
Multiscale Average Absolute Difference (MSAAD): A Computationally Efficient and Nonparametric Adaptation of Line Length for Noisy, Uncontrolled Wearables Time Series
by Jamison H. Burks, Wendy Hartogensis, Stephan Dilchert, Ashley E. Mason and Benjamin L. Smarr
Algorithms 2025, 18(9), 577; https://doi.org/10.3390/a18090577 - 12 Sep 2025
Viewed by 325
Abstract
With the rise in physiological data sampled from wearable devices, efficient methods must be developed to encode temporal information for the comparison of time series arising from uncontrolled monitoring. We present a fast, nonparametric method called Multiscale Average Absolute Difference (MSAAD) to extract [...] Read more.
With the rise in physiological data sampled from wearable devices, efficient methods must be developed to encode temporal information for the comparison of time series arising from uncontrolled monitoring. We present a fast, nonparametric method called Multiscale Average Absolute Difference (MSAAD) to extract multiscale temporal features from wearable device data for purposes ranging from statistical analysis to machine learning inference. MSAAD outperforms comparable algorithms like multiscale sample entropy (MSSE) and multiscale Katz Fractal Dimension (MS-KFD) in terms of calculation stability on short realizations and faster runtime. MSAAD outperforms MSSE and MS-KFD by being able to separate diabetic and non-diabetic cohorts with moderate and large effect sizes in both sexes. Furthermore, it is capable of capturing “critical slowing down” in the temperature dynamics of aging populations, a phenomenon that has been previously observed in controlled settings. We propose that MSAAD is a scalable, interpretable time series feature that is capable of identifying meaningful differences in physiological time series data without making assumptions regarding underlying process models. MSAAD could improve the ability to derive insight from time series data mining for health applications. Full article
(This article belongs to the Section Algorithms for Multidisciplinary Applications)
►▼ Show Figures

Figure 1

18 pages, 4873 KB  
Article
Optimized GRU with Self-Attention for Bearing Fault Diagnosis Using Bayesian Hyperparameter Tuning
by Zongchao Liu, Shuai Teng and Shaodi Wang
Algorithms 2025, 18(9), 576; https://doi.org/10.3390/a18090576 - 12 Sep 2025
Viewed by 280
Abstract
Rolling bearing failures cause significant production downtime and economic losses. Traditional diagnostic methods suffer from low efficiency, suboptimal accuracy, and susceptibility to human subjectivity. To address these limitations, this paper proposes a novel bearing fault diagnosis (BFD) approach leveraging a Gated Recurrent Unit [...] Read more.
Rolling bearing failures cause significant production downtime and economic losses. Traditional diagnostic methods suffer from low efficiency, suboptimal accuracy, and susceptibility to human subjectivity. To address these limitations, this paper proposes a novel bearing fault diagnosis (BFD) approach leveraging a Gated Recurrent Unit (GRU) network. Key contributions include: (1) Employing Bayesian optimization to automate the search for the optimal GRU architecture (layers, hidden units) and hyperparameters (learning rate, batch size, epochs), significantly enhancing diagnostic performance (achieving 97.9% accuracy). (2) Integrating a self-attention mechanism to further improve the GRU’s feature extraction capability from vibration signals, boosting accuracy to 99.6%. (3) Demonstrating the robustness of the optimized GRU with self-attention across varying motor speeds (1772 rpm, 1750 rpm, 1730 rpm), consistently maintaining diagnostic accuracy above 97%. Comparative studies with Bayesian-optimized Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) models confirm the superior accuracy (97.9% vs. 95.1% and 90.0%) and faster inference speed (0.27 s) of the proposed GRU-based method. The results validate that the combination of Bayesian optimization, GRU, and self-attention provides an efficient, accurate, and robust intelligent solution for automated BFD. Full article
(This article belongs to the Special Issue Intelligent Algorithms and Signal Processing Techniques for Fault Diagnosis in Mechanical and Electrical Systems)
►▼ Show Figures

Figure 1

28 pages, 16152 KB  
Article
A Smooth-Delayed Phase-Type Mixture Model for Human-Driven Process Duration Modeling
by Dongwei Wang, Sally McClean, Lingkai Yang, Ian McChesney and Zeeshan Tariq
Algorithms 2025, 18(9), 575; https://doi.org/10.3390/a18090575 - 11 Sep 2025
Viewed by 212
Abstract
Activities in business processes primarily depend on human behavior for completion. Due to human agency, the behavior underlying individual activities may occur in multiple phases and can vary in execution. As a result, the execution duration and nature of such activities may exhibit [...] Read more.
Activities in business processes primarily depend on human behavior for completion. Due to human agency, the behavior underlying individual activities may occur in multiple phases and can vary in execution. As a result, the execution duration and nature of such activities may exhibit complex multimodal characteristics. Phase-type distributions are useful for analyzing the underlying behavioral structure, which may consist of multiple sub-activities. The phenomenon of delayed start is also common in such activities, possibly due to the minimum task completion time or prerequisite tasks. As a result, the distribution of durations or certain components does not start at zero but has a minimum value, and the probability below this value is zero. When using phase-type models to fit such distributions, a large number of phases are often required, which exceed the actual number of sub-activities. This reduces the interpretability of the parameters and may also lead to optimization difficulties due to overparameterization. In this paper, we propose a smooth-delayed phase-type mixture model that introduces delay parameters to address the difficulty of fitting this kind of distribution. Since durations shorter than the delay should have zero probability, such hard truncation renders the parameter not estimable under the Expectation–Maximization (EM) framework. To overcome this, we design a soft-truncation mechanism to improve model convergence. We further develop an inference framework that combines the EM algorithm, Bayesian inference, and Sequential Least Squares Programming for comprehensive and efficient parameter estimation. The method is validated on a synthetic dataset and two real-world datasets. Results demonstrate that the proposed approach maintains a suitable performance comparable to purely data-driven methods while providing good interpretability to reveal the potential underlying structure behind human-driven activities. Full article
(This article belongs to the Special Issue Mathematical Modelling in Engineering and Human Behaviour (3rd Edition))
►▼ Show Figures

Graphical abstract

27 pages, 1844 KB  
Article
A Quantum Frequency-Domain Framework for Image Transmission with Three-Qubit Error Correction
by Udara Jayasinghe, Thanuj Fernando and Anil Fernando
Algorithms 2025, 18(9), 574; https://doi.org/10.3390/a18090574 - 11 Sep 2025
Viewed by 362
Abstract
Quantum communication enables high-fidelity image transmission but is vulnerable to channel noise, and while advanced quantum error correction (QEC) can reduce such effects, its complexity and time-domain dependence limit practical efficiency. This paper presents a novel, low-complexity, and noise-resilient quantum image transmission framework [...] Read more.
Quantum communication enables high-fidelity image transmission but is vulnerable to channel noise, and while advanced quantum error correction (QEC) can reduce such effects, its complexity and time-domain dependence limit practical efficiency. This paper presents a novel, low-complexity, and noise-resilient quantum image transmission framework that operates in the frequency domain using the quantum Fourier transform (QFT) combined with the three-qubit QEC code. In the proposed system, input images are first source-encoded (JPEG/HEIF) and mapped to quantum states using single-qubit superposition encoding. Three-qubit QEC is then applied for channel protection, effectively safeguarding the encoded data against quantum errors. The channel-encoded quantum data are subsequently transformed via QFT for transmission over noisy quantum channels. At the receiver, the inverse QFT recovers the frequency-domain representation, after which three-qubit error correction, quantum decoding, and corresponding source decoding are performed to reconstruct the image. Results are analyzed using bit error rate (BER), peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and universal quality index (UQI). Experimental results show that the proposed quantum frequency-domain approach achieves up to 4 dB channel SNR gain over equivalent quantum time-domain methods and up to 10 dB over an equivalent-bandwidth classical communication system, regardless of the image format. These findings highlight the practical advantages of integrating QFT-based transmission with lightweight QEC, offering an efficient, scalable, and noise-tolerant solution for future quantum communication networks. Full article
(This article belongs to the Section Combinatorial Optimization, Graph, and Network Algorithms)
►▼ Show Figures

Graphical abstract

32 pages, 1828 KB  
Review
Recent Trends in the Optimization of Logistics Systems Through Discrete-Event Simulation and Deep Learning
by Róbert Skapinyecz
Algorithms 2025, 18(9), 573; https://doi.org/10.3390/a18090573 - 11 Sep 2025
Viewed by 388
Abstract
The main objective of the study is to present the latest trends and research directions in the field of optimization of logistics systems with Discrete-Event Simulation (DES) and Deep Learning (DL). This research area is highly relevant from several aspects: on the one [...] Read more.
The main objective of the study is to present the latest trends and research directions in the field of optimization of logistics systems with Discrete-Event Simulation (DES) and Deep Learning (DL). This research area is highly relevant from several aspects: on the one hand, in the modern Industry 4.0 concept, simulation tools, especially Discrete-Event Simulations, are increasingly used for the modelling of material flow processes; on the other hand, the use of Artificial Intelligence (AI)—especially Deep Neural Networks (DNNs)—to evaluate the results of the former significantly enhances the potential applicability and effectiveness of such simulations. At the same time, the results obtained from Discrete-Event Simulations can also be used as synthetic datasets for the training of DNNs, which creates entirely new opportunities for both scientific research and practical applications. As a result, the interest in the combination of Discrete-Event Simulation with Deep Learning in the field of logistics has significantly increased in the recent period, giving rise to multiple different approaches. The main contribution of the current paper is that, through a review of the relevant literature, it provides an overview and systematization of the state-of-the-art methods and approaches in this developing field. Based on the results of the literature review, the study also presents the evolution of the research trends and identifies the most important research gaps in the field. Full article
(This article belongs to the Section Evolutionary Algorithms and Machine Learning)
►▼ Show Figures

Figure 1

33 pages, 5041 KB  
Article
Multimodal Video Summarization Using Machine Learning: A Comprehensive Benchmark of Feature Selection and Classifier Performance
by Elmin Marevac, Esad Kadušić, Nataša Živić, Nevzudin Buzađija, Edin Tabak and Safet Velić
Algorithms 2025, 18(9), 572; https://doi.org/10.3390/a18090572 - 10 Sep 2025
Viewed by 389
Abstract
The exponential growth of user-generated video content necessitates efficient summarization systems for improved accessibility, retrieval, and analysis. This study presents and benchmarks a multimodal video summarization framework that classifies segments as informative or non-informative using audio, visual, and fused features. Sixty hours of [...] Read more.
The exponential growth of user-generated video content necessitates efficient summarization systems for improved accessibility, retrieval, and analysis. This study presents and benchmarks a multimodal video summarization framework that classifies segments as informative or non-informative using audio, visual, and fused features. Sixty hours of annotated video across ten diverse categories were analyzed. Audio features were extracted with pyAudioAnalysis, while visual features (colour histograms, optical flow, object detection, facial recognition) were derived using OpenCV. Six supervised classifiers—Naive Bayes, K-Nearest Neighbors, Logistic Regression, Decision Tree, Random Forest, and XGBoost—were evaluated, with hyperparameters optimized via grid search. Temporal coherence was enhanced using median filtering. Random Forest achieved the best performance, with 74% AUC on fused features and a 3% F1-score gain after post-processing. Spectral flux, grayscale histograms, and optical flow emerged as key discriminative features. The best model was deployed as a practical web service using TensorFlow and Flask, integrating informative segment detection with subtitle generation via beam search to ensure coherence and coverage. System-level evaluation demonstrated low latency and efficient resource utilization under load. Overall, the results confirm the strength of multimodal fusion and ensemble learning for video summarization and highlight their potential for real-world applications in surveillance, digital archiving, and online education. Full article
(This article belongs to the Special Issue Visual Attributes in Computer Vision Applications)
►▼ Show Figures

Figure 1

12 pages, 1554 KB  
Article
Enhancing Wireless Sensor Networks with Bluetooth Low-Energy Mesh and Ant Colony Optimization Algorithm
by Hussein S. Mohammed, Hayam K. Mustafa and Omar A. Abdulkareem
Algorithms 2025, 18(9), 571; https://doi.org/10.3390/a18090571 - 10 Sep 2025
Viewed by 980
Abstract
Wireless Sensor Networks (WSNs) face persistent challenges of uneven energy depletion, limited scalability, and reduced network lifetime, all of which hinder their effectiveness in Internet of Things (IoT) applications. This paper introduces a hybrid framework that integrates Bluetooth Low-Energy (BLE) mesh networking with [...] Read more.
Wireless Sensor Networks (WSNs) face persistent challenges of uneven energy depletion, limited scalability, and reduced network lifetime, all of which hinder their effectiveness in Internet of Things (IoT) applications. This paper introduces a hybrid framework that integrates Bluetooth Low-Energy (BLE) mesh networking with Ant Colony Optimization (ACO) to deliver energy-aware, adaptive routing over a standards-compliant mesh fabric. BLE mesh contributes a resilient many-to-many topology with Friend/Low-Power Node roles that minimize idle listening, while ACO dynamically selects next hops based on residual energy, distance, and link quality to balance load and prevent hot spots. Using large-scale simulations with 1000 nodes over a 1000 × 1000 m field, the proposed BLE-ACO system reduced overall energy consumption by approximately 35%, extended network lifetime by 40%, and improved throughput by 25% compared with conventional BLE forwarding, while also surpassing a LEACH-like clustering baseline. Confidence interval analysis confirmed the statistical robustness of these results. The findings demonstrate that BLE-ACO is a scalable, sustainable, and standards-aligned solution for energy-constrained IoT deployments, particularly in smart cities, industrial automation, and environmental monitoring, where long-term performance and adaptability are critical. Full article
(This article belongs to the Section Combinatorial Optimization, Graph, and Network Algorithms)
►▼ Show Figures

Figure 1

18 pages, 9177 KB  
Article
Understanding Physiological Responses for Intelligent Posture and Autonomic Response Detection Using Wearable Technology
by Chaitanya Vardhini Anumula, Tanvi Banerjee and William Lee Romine
Algorithms 2025, 18(9), 570; https://doi.org/10.3390/a18090570 - 10 Sep 2025
Viewed by 291
Abstract
This study investigates how Iyengar yoga postures influence autonomic nervous system (ANS) activity by analyzing multimodal physiological signals collected via wearable sensors. The goal was to explore whether subtle postural variations elicit measurable autonomic responses and to identify which sensor features most effectively [...] Read more.
This study investigates how Iyengar yoga postures influence autonomic nervous system (ANS) activity by analyzing multimodal physiological signals collected via wearable sensors. The goal was to explore whether subtle postural variations elicit measurable autonomic responses and to identify which sensor features most effectively capture these changes. Participants performed a sequence of yoga poses while wearing synchronized sensors measuring electrodermal activity (EDA), heart rate variability, skin temperature, and motion. Interpretable machine learning models, including linear classifiers, were trained to distinguish physiological states and rank feature relevance. The results revealed that even minor postural adjustments led to significant shifts in ANS markers, with phasic EDA and RR interval features showing heightened sensitivity. Surprisingly, micro-movements captured via accelerometry and transient electrodermal reactivity, specifically EDA peak-to-RMS ratios, emerged as dominant contributors to classification performance. These findings suggest that small-scale kinematic and autonomic shifts, which are often overlooked, play a central role in the physiological effects of yoga. The study demonstrates that wearable sensor analytics can decode a more nuanced and granular physiological profile of mind–body practices than traditionally appreciated, offering a foundation for precision-tailored biofeedback systems and advancing objective approaches to yoga-based interventions. Full article
(This article belongs to the Special Issue Algorithms and Applications of Machine Learning Techniques for Healthcare)
►▼ Show Figures

Figure 1

18 pages, 3213 KB  
Article
Research on CNC Machine Tool Spindle Fault Diagnosis Method Based on Deep Residual Shrinkage Network with Dynamic Convolution and Selective Kernel Attention Model
by Xiaoxu Li, Jixuan Wang, Jianqiang Wang, Jiahao Wang, Jiamin Liu, Jiaming Chen and Xuelian Yu
Algorithms 2025, 18(9), 569; https://doi.org/10.3390/a18090569 - 9 Sep 2025
Viewed by 347
Abstract
Rolling bearing vibration signals are often severely affected by strong external noise, which can obscure fault-related features and hinder accurate diagnosis. To address this challenge, this paper proposes an enhanced Deep Residual Shrinkage Network with Dynamic Convolution and Selective Kernel Attention (DDRSN-SKA). First, [...] Read more.
Rolling bearing vibration signals are often severely affected by strong external noise, which can obscure fault-related features and hinder accurate diagnosis. To address this challenge, this paper proposes an enhanced Deep Residual Shrinkage Network with Dynamic Convolution and Selective Kernel Attention (DDRSN-SKA). First, one-dimensional vibration signals are converted into two-dimensional time frequency images using the Continuous Wavelet Transform (CWT), providing richer input representations. Then, a dynamic convolution module is introduced to adaptively adjust kernel weights based on the input, enabling the network to better extract salient features. To improve feature discrimination, an Selective Kernel Attention (SKAttention) module is incorporated into the intermediate layers of the network. By applying a multi-receptive field channel attention mechanism, the network can emphasize critical information and suppress irrelevant features. The final classification layer determines the fault types. Experiments conducted on both the Case Western Reserve University (CWRU) dataset and a laboratory-collected bearing dataset demonstrate that DDRSN-SKA achieves diagnostic accuracies of 98.44% and 94.44% under −8 dB Gaussian and Laplace noise, respectively. These results confirm the model’s strong noise robustness and its suitability for fault diagnosis in noisy industrial environments. Full article
(This article belongs to the Special Issue AI-Powered Predictive Maintenance: Transforming Industrial Operations Through Intelligent Fault Diagnosis)
►▼ Show Figures

Figure 1

11 pages, 474 KB  
Article
Secant-Type Iterative Classes for Nonlinear Equations with Multiple Roots
by Francisco I. Chicharro, Neus Garrido-Saez and Julissa H. Jerezano
Algorithms 2025, 18(9), 568; https://doi.org/10.3390/a18090568 - 9 Sep 2025
Viewed by 262
Abstract
General-purpose iterative methods for solving nonlinear equations provide approximations to solving problems without closed-form solutions. However, these methods lose some properties when the problems have multiple roots or are not differentiable, in which case specific methods are used. However, in most problems the [...] Read more.
General-purpose iterative methods for solving nonlinear equations provide approximations to solving problems without closed-form solutions. However, these methods lose some properties when the problems have multiple roots or are not differentiable, in which case specific methods are used. However, in most problems the multiplicity of the root is unknown, which reduces the range of methods available to us. In this work we propose two iterative classes with memory for solving multiple-root nonlinear equations without knowing the multiplicity. One of the proposals includes derivatives, but the other is derivative-free, obtained from the previous one using divided differences and a parameter in its iterative expression. The order of convergence of the proposed schemes is analyzed. The stability of the methods is studied using real dynamics, showing the good behavior of the methods. A numerical benchmark confirms the theoretical study. Full article
(This article belongs to the Special Issue Mathematical Modelling in Engineering and Human Behaviour (3rd Edition))
►▼ Show Figures

Figure 1

27 pages, 1902 KB  
Article
Few-Shot Breast Cancer Diagnosis Using a Siamese Neural Network Framework and Triplet-Based Loss
by Tea Marasović and Vladan Papić
Algorithms 2025, 18(9), 567; https://doi.org/10.3390/a18090567 - 8 Sep 2025
Viewed by 411
Abstract
Breast cancer is one of the leading causes of death among women of all ages and backgrounds globally. In recent years, the growing deficit of expert radiologists—particularly in underdeveloped countries—alongside a surge in the number of images for analysis, has negatively affected the [...] Read more.
Breast cancer is one of the leading causes of death among women of all ages and backgrounds globally. In recent years, the growing deficit of expert radiologists—particularly in underdeveloped countries—alongside a surge in the number of images for analysis, has negatively affected the ability to secure timely and precise diagnostic results in breast cancer screening. AI technologies offer powerful tools that allow for the effective diagnosis and survival forecasting, reducing the dependency on human cognitive input. Towards this aim, this research introduces a deep meta-learning framework for swift analysis of mammography images—combining a Siamese network model with a triplet-based loss function—to facilitate automatic screening (recognition) of potentially suspicious breast cancer cases. Three pre-trained deep CNN architectures, namely GoogLeNet, ResNet50, and MobileNetV3, are fine-tuned and scrutinized for their effectiveness in transforming input mammograms to a suitable embedding space. The proposed framework undergoes a comprehensive evaluation through a rigorous series of experiments, utilizing two different, publicly accessible, and widely used datasets of digital X-ray mammograms: INbreast and CBIS-DDSM. The experimental results demonstrate the framework’s strong performance in differentiating between tumorous and normal images, even with a very limited number of training samples, on both datasets. Full article
(This article belongs to the Special Issue Machine Learning for Pattern Recognition (3rd Edition))
►▼ Show Figures

Figure 1

17 pages, 2625 KB  
Article
Improved Active Disturbance Rejection Speed Tracking Control for High-Speed Trains Based on SBWO Algorithm
by Chuanfang Xu, Chengyu Zhang, Mingxia Xu, Jiaqing Chen, Longda Wang and Zhaoyu Han
Algorithms 2025, 18(9), 566; https://doi.org/10.3390/a18090566 - 8 Sep 2025
Viewed by 319
Abstract
To address the problems of random noise interference, inadequate disturbance estimation and compensation, and the difficulty in controller parameter tuning in speed tracking control of high-speed trains, an improved Active Disturbance Rejection Control (ADRC) strategy combined with a Sobol-based Black Widow Optimization (SBWO) [...] Read more.
To address the problems of random noise interference, inadequate disturbance estimation and compensation, and the difficulty in controller parameter tuning in speed tracking control of high-speed trains, an improved Active Disturbance Rejection Control (ADRC) strategy combined with a Sobol-based Black Widow Optimization (SBWO) algorithm is proposed. An improved Tracking Differentiator (TD) is adopted by integrating a novel optimal control synthesis function with a phase compensator to suppress input noise and ensure a smooth transition process. A novel Extended State Observer (ESO) using a nonlinear saturation function is designed to improve the observation accuracy and decrease chattering. An enhanced Nonlinear State Error Feedback (NLSEF) law that incorporates an error integral and adaptive parameter update laws is developed to reduce steady-state error and achieve self-tuned proportional and derivative gains. A feedforward compensation term is added to provide real-time dynamic compensation for ESO estimation errors. Finally, an enhanced Black Widow Optimization (BWO) algorithm, which initializes its population with Sobol sequences to improve its global search capability, is employed for parameter optimization. The simulation results demonstrate that compared with the control methods based on Proportional–Integral–Derivative (PID) control and conventional ADRC, the proposed strategy achieves higher steady-state tracking accuracy, better adaptability to dynamic operating conditions, stronger anti-disturbance ability, and more precise stopping precision. Full article
(This article belongs to the Topic Optimization Control and Fault Diagnosis of Intelligent Transportation Systems)
►▼ Show Figures

Figure 1

15 pages, 843 KB  
Article
Extended von Bertalanffy Equation in Solow Growth Modelling
by Antonio E. Bargellini, Daniele Ritelli and Giulia Spaletta
Algorithms 2025, 18(9), 565; https://doi.org/10.3390/a18090565 - 7 Sep 2025
Viewed by 341
Abstract
The aim of this work is to model the growth of an economic system and, in particular, the evolution of capital accumulation over time, analysing the feasibility of a closed-form solution to the initial value problem that governs the capital-per-capita dynamics. The latter [...] Read more.
The aim of this work is to model the growth of an economic system and, in particular, the evolution of capital accumulation over time, analysing the feasibility of a closed-form solution to the initial value problem that governs the capital-per-capita dynamics. The latter are related to the labour-force dynamics, which are assumed to follow a von Bertalanffy model, studied in the literature in its simplest form and for which the existence of an exact solution, in terms of hypergeometric functions, is known. Here, we consider an extended form of the von Bertalanffy equation, which we make dependent on two parameters, rather than the single-parameter model known in the literature, to better capture the features that a reliable economic growth model should possess. Furthermore, we allow one of the two parameters to vary over time, making it dependent on a periodic function to account for seasonality. We prove that the two-parameter model admits an exact solution, in terms of hypergeometric functions, when both parameters are constant. In the time-varying case, although it is not possible to obtain a closed-form solution, we are able to find two exact solutions that closely bound, from below and from above, the desired one, as well as its numerical approximation. The presented models are implemented in the Mathematica environment, where simulations, parameter sensitivity analyses and comparisons with the known single-parameter model are also performed, validating our findings. Full article
(This article belongs to the Section Analysis of Algorithms and Complexity Theory)
►▼ Show Figures

Figure 1

30 pages, 6483 KB  
Article
The Generative Adversarial Approach: A Cautionary Tale of Finite Samples
by Marcos Escobar-Anel and Yiyao Jiao
Algorithms 2025, 18(9), 564; https://doi.org/10.3390/a18090564 - 5 Sep 2025
Viewed by 352
Abstract
Given the relevance and wide use of the Generative Adversarial (GA) methodology, this paper focuses on finite samples to better understand its benefits and pitfalls. We focus on its finite-sample properties from both statistical and numerical perspectives. We set up a simple and [...] Read more.
Given the relevance and wide use of the Generative Adversarial (GA) methodology, this paper focuses on finite samples to better understand its benefits and pitfalls. We focus on its finite-sample properties from both statistical and numerical perspectives. We set up a simple and ideal “controlled experiment” where the input data are an i.i.d. Gaussian series where the mean is to be learned, and the discriminant and generator are in the same distributional family, not a neural network (NN), as in the popular GAN. We show that, even with the ideal discriminant, the classical GA methodology delivers a biased estimator while producing multiple local optima, confusing numerical methods. The situation worsens when the discriminator is in the correct parametric family but is not the oracle, leading to the absence of a saddle point. To improve the quality of the estimators within the GA method, we propose an alternative loss function, the alternative GA method, that leads to a unique saddle point with better statistical properties. Our findings are intended to start a conversation on the potential pitfalls of GA and GAN methods. In this spirit, the ideas presented here should be explored in other distributional cases and will be extended to the actual use of an NN for discriminators and generators. Full article
(This article belongs to the Section Evolutionary Algorithms and Machine Learning)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-59
Previous Issue
Next Issue
Back to TopTop