You seem to have javascript disabled. Please note that many of the page functionalities won't work as expected without javascript enabled.

Search for Articles:

Title / Keyword

Author / Affiliation / Email

Journal

Article Type

Advanced Search

Section

Special Issue

Volume

Issue

Number

Page

Logical OperatorOperator

Search Text

Search Type

Deep Learning for Brain MRI Tissue and Structure Segmentation: A Comprehensive Review
Exploring the Impact of AI Tools on Cognitive Skills: A Comparative Analysis
Recent Trends in the Optimization of Logistics Systems Through Discrete-Event Simulation and Deep Learning

Journal Description

Algorithms

Algorithms is a peer-reviewed, open access journal which provides an advanced forum for studies related to algorithms and their applications, and is published monthly online by MDPI. The European Society for Fuzzy Logic and Technology (EUSFLAT) is affiliated with Algorithms and its members receive discounts on the article processing charges.

Open Access — free for readers, with article processing charges (APC) paid by authors or their institutions.
High Visibility: indexed within Scopus, ESCI (Web of Science), Ei Compendex, and other databases.
Journal Rank: JCR - Q2 (Computer Science, Theory and Methods) / CiteScore - Q1 (Numerical Analysis)
Rapid Publication: manuscripts are peer-reviewed and a first decision is provided to authors approximately 19.2 days after submission; acceptance to publication is undertaken in 3.7 days (median values for papers published in this journal in the second half of 2025).
Testimonials: See what our editors and authors say about Algorithms.
Recognition of Reviewers: reviewers who provide timely, thorough peer-review reports receive vouchers entitling them to a discount on the APC of their next publication in any MDPI journal, in appreciation of the work done.
Journal Cluster of Artificial Intelligence: AI, AI in Medicine, Algorithms, BDCC, MAKE, MTI, Stats, Virtual Worlds and Computers.

Impact Factor: 2.1 (2024); 5-Year Impact Factor: 2.0 (2024)

Imprint Information Journal Flyer Open Access ISSN: 1999-4893

Latest Articles

30 pages, 6033 KB

Open AccessArticle

Virtual Reality Interventions for Enhancing Executive Functions in Children and Adolescents with Autism Spectrum Disorder

by Angeliki Sideraki and Christos-Nikolaos Anagnostopoulos

Algorithms 2026, 19(3), 201; https://doi.org/10.3390/a19030201 (registering DOI) - 7 Mar 2026

This study investigates the impact of a Virtual Reality (VR)-based intervention on the enhancement of executive functions—cognitive flexibility, inhibitory control, and working memory—in children diagnosed with Autism Spectrum Disorder (ASD). Employing a single-case experimental design with repeated measures, the research was conducted with [...] Read more.

This study investigates the impact of a Virtual Reality (VR)-based intervention on the enhancement of executive functions—cognitive flexibility, inhibitory control, and working memory—in children diagnosed with Autism Spectrum Disorder (ASD). Employing a single-case experimental design with repeated measures, the research was conducted with two male participants, aged 9 and 10, both formally diagnosed with ASD. The intervention was structured into four phases: Baseline (no training), Intervention (targeted VR training), Generalization (skill transfer testing), and Follow-up (maintenance assessment). Each participant engaged in a total of 18 tasks (six per executive function), delivered through immersive VR environments featuring gamified elements, adaptive feedback, and increasing difficulty. Each task consisted of up to 15 sub-items, scored as correct or incorrect. Results indicate consistent improvements across executive function domains during the intervention phase, with partial maintenance at follow-up and evidence of task generalization. Given the single-case framework and limited sample size, findings should be interpreted as exploratory and hypothesis-generating rather than population-generalizable. The study provides proof-of-concept evidence supporting the feasibility and potential of immersive VR-based executive function training for ASD populations, warranting further validation through larger-scale controlled trials. Full article

(This article belongs to the Special Issue Machine Learning in Medical Signal and Image Processing (4th Edition))

20 pages, 3154 KB

Open AccessArticle

A Data-Centric Algorithmic Pipeline for Enhancing Cardiac MRI Segmentation Using ViTUNeT and Quality-Aware Filtering

by Salvador de Haro, Jesús Cámara, Pilar González-Férez, José Manuel García and Gregorio Bernabé

Algorithms 2026, 19(3), 200; https://doi.org/10.3390/a19030200 - 6 Mar 2026

The performance of deep-learning-based segmentation models is strongly dependent on the quality of the input data, which is frequently heterogeneous or degraded in real-world medical imaging scenarios. This work presents a data-centric algorithmic pipeline designed to improve cardiac MRI segmentation accuracy through systematic [...] Read more.

The performance of deep-learning-based segmentation models is strongly dependent on the quality of the input data, which is frequently heterogeneous or degraded in real-world medical imaging scenarios. This work presents a data-centric algorithmic pipeline designed to improve cardiac MRI segmentation accuracy through systematic image enhancement and automatic slice-quality filtering. The proposed method is formalized as deterministic algorithm that combines image processing and supervised learning components. The approach integrates a contrast- and structure-preserving enhancement stage, based on bilateral filtering and adaptive histogram equalization, with a quality-aware selection algorithm. Slice quality is assessed using anatomical attributes extracted via YOLOv11s-based localization and a supervised classification model trained to identify diagnostically reliable images. When applied to transformer-based segmentation architectures such as ViTUNeT, the pipeline yields consistent improvements across all evaluation metrics without increasing model complexity or training cost. These findings emphasize the importance of algorithmic data curation as an effective strategy for enhancing robustness and stability in deep-learning segmentation pipelines and demonstrate the broader applicability of the proposed approach to computer-vision tasks involving heterogeneous or low-quality image datasets. Full article

(This article belongs to the Special Issue AI-Powered Biomedical Image Analysis)

► Show Figures

Figure 1

30 pages, 1413 KB

Open AccessArticle

Enhancing Post-Editing of Kazakh Translations Using Fine-Tuned Large Language Models

by Akbayan Bekarystankyzy, Diana Rakhimova, Aliya Zhiger, Assel Sakatay, Nazym Zhumakhan, Aigerim Yerimbetova, Dina Oralbekova and Mussa Turdalyuly

Algorithms 2026, 19(3), 199; https://doi.org/10.3390/a19030199 - 6 Mar 2026

Machine translation for low-resource languages such as Kazakh remains a complex task due to the scarcity of training data, intricate morphological structures, and culturally specific linguistic characteristics. This study presents the first extensive exploration of fine-tuning large language models for automated post-editing of [...] Read more.

Machine translation for low-resource languages such as Kazakh remains a complex task due to the scarcity of training data, intricate morphological structures, and culturally specific linguistic characteristics. This study presents the first extensive exploration of fine-tuning large language models for automated post-editing of Kazakh translations. We introduce KazPE, a carefully curated and annotated dataset that includes 10,008 training sentences and 311 test sentences spanning six domains: the medical, scientific, journalistic, oral, fiction, and legal. The dataset features detailed error classifications across 9 linguistic categories. Our method fine-tunes GPT-4.1 mini using supervised learning to enhance translation quality by systematically correcting targeted errors. According to human evaluations, conducted on a continuous 0–1 scale, the fine-tuned model achieves an average quality score of 0.84, surpassing the baseline score of 0.80, corresponding to a 5% relative improvement. The greatest improvements are observed in handling morphological and lexical errors, as well as in domain-specific texts—particularly in legal (+17%) and medical (+22%) domains. In addition, the translations were evaluated using the automatic metrics: BLEU, TER and METEOR. The fine-tuned model shows improvements across all automatic metrics (BLEU, TER, METEOR), which confirms better n-gram overlap with reference texts, fewer edits needed, and enhanced lexical and semantic alignment with the reference texts. Comprehensive error analysis shows that the fine-tuning process effectively mitigates challenges related to Kazakh’s agglutinative morphology and specialized terminology, while preserving accuracy on already correct sentences. This research establishes the first structured evaluation framework for Kazakh translation post-editing and offers valuable guidance for enhancing machine translation in morphologically rich, low-resource languages. To facilitate further progress in Turkic language processing, we publicly release the KazPE dataset, trained models, and evaluation framework. Full article

(This article belongs to the Special Issue AI Applications and Modern Industry)

► Show Figures

Figure 1

25 pages, 1774 KB

Open AccessArticle

An Agentic Digital Twin Framework for Fuzzy Multi-Objective Optimization in Dynamic Humanitarian Logistics

by Zornitsa Yordanova and Hamed Nozari

Algorithms 2026, 19(3), 198; https://doi.org/10.3390/a19030198 - 6 Mar 2026

Humanitarian logistics faces challenges such as conflicting objectives, severe uncertainty, temporal dynamics, and the need for interpretable decisions. This research presents an integrated decision-making framework that simultaneously considers fuzzy uncertainty, system dynamics, and adaptive decision logic. Operational uncertainties are modeled using triangular fuzzy [...] Read more.

Humanitarian logistics faces challenges such as conflicting objectives, severe uncertainty, temporal dynamics, and the need for interpretable decisions. This research presents an integrated decision-making framework that simultaneously considers fuzzy uncertainty, system dynamics, and adaptive decision logic. Operational uncertainties are modeled using triangular fuzzy numbers and a dynamic representation of the system allows for continuous updating of decisions over time. Computational results based on simulated data show that the proposed framework is capable of generating stable, diverse, and interpretable solutions. An improvement in the average quality of the Pareto front of more than 5% and a reduction in the distance from the reference front of about 30% are observed compared to non-adaptive approaches. Also, stability and dynamic behavior analyses show that the decisions are robust to changing environmental conditions and parameters and have high adaptability. These features make the proposed framework a reliable tool for decision support in relief operations. Full article

(This article belongs to the Special Issue Optimizing Logistics Activities: Models and Applications)

► Show Figures

Figure 1

28 pages, 2304 KB

Open AccessReview

Machine Learning in Smart Mining: A Systematic Review of Applications, Algorithms, Benefits, and Challenges

by Jimmy Aurelio Rosales Huamani, Jose Antonio Ogosi Auqui, Mery Gomez Marroquin, Roberto Valentin Vite Casaverde, Jose Luis Arenas Ñiquin and Alberto Landauro Abanto

Algorithms 2026, 19(3), 197; https://doi.org/10.3390/a19030197 - 5 Mar 2026

Background: Smart mining is rapidly evolving through the integration of automation, advanced sensing technologies, and Machine Learning (ML). Methods: This Systematic Literature Review (SLR), based on 99 peer-reviewed studies published between 2021 and 2025 and synthesized following PRISMA 2020 guidelines, analyzes the current [...] Read more.

Background: Smart mining is rapidly evolving through the integration of automation, advanced sensing technologies, and Machine Learning (ML). Methods: This Systematic Literature Review (SLR), based on 99 peer-reviewed studies published between 2021 and 2025 and synthesized following PRISMA 2020 guidelines, analyzes the current role of ML algorithms in the mining sector, focusing on their applications, algorithmic prevalence, benefits, and challenges. Results: Machine Learning algorithms are primarily applied to equipment failure prediction, ore classification, grade and flotation control, transportation optimization, and environmental monitoring. The most frequently adopted algorithms include Decision Tree-based models, Artificial Neural Networks, Deep Learning architectures, Support Vector Machines, K-means clustering, and Gradient Boosting methods, reflecting different trade-offs between interpretability, computational complexity, and predictive performance. Reported benefits include improved operational efficiency, cost reduction, enhanced predictive maintenance, improved decision-making, and increased safety and environmental performance. However, widespread adoption remains constrained by limited availability of high-quality data, data heterogeneity, high implementation costs, shortages of specialized personnel, algorithm interpretability issues, and cybersecurity risks. Conclusions: Overall, ML algorithms emerge as key enablers of intelligent and sustainable mining. The review highlights the need for explainable and robust algorithms, improved multimodal data integration, and large-scale real-world validation to support the next generation of smart mining systems. Full article

(This article belongs to the Special Issue AI Applications and Modern Industry)

► Show Figures

Figure 1

20 pages, 707 KB

Open AccessArticle

The Non-Simulation Resilience Assessment for Electric–Gas Distribution Networks

by Chun Xiao, Tingjun Li and Xiaoqing Han

Algorithms 2026, 19(3), 196; https://doi.org/10.3390/a19030196 - 5 Mar 2026

Unlike traditional power systems, the heterogeneous energy support of electric–gas regional distribution networks brings new challenges to resilience assessment. On the basis of identifying N-k fault uncertainty risks, establishing a resilience assessment methodology is one of the important issues in resilience research. Existing [...] Read more.

Unlike traditional power systems, the heterogeneous energy support of electric–gas regional distribution networks brings new challenges to resilience assessment. On the basis of identifying N-k fault uncertainty risks, establishing a resilience assessment methodology is one of the important issues in resilience research. Existing reliability assessment methods cannot accurately quantify resilience under N-k extreme fault scenarios. To address this limitation, we propose a non-simulation resilience assessment method. The approach can simultaneously quantify the dynamic interactions of heterogeneous energy flows and the impact of repair process time uncertainty on system resilience under extreme fault scenarios. Specifically, the resilience indexes are established by combining the load outage and mathematical expectation during/after the extreme fault and applying probabilistic knowledge to express the N-k load outage event, so as to effectively offset the data scarcity due to the limited N-k fault data samples. The internal consistency and parametric responsiveness of the proposed non-simulation method are demonstrated through systematic case comparisons under varying failure rates, repair times, and coupling conditions. Full article

► Show Figures

Figure 1

23 pages, 3612 KB

Open AccessArticle

A Security Framework for Resilient Smart Grids Based on Self-Organizing Graph Neural Cellular Automata

by Rongxu Hou, Yiying Zhang, Siwei Li, Yeshen He and Pizhen Zhang

Algorithms 2026, 19(3), 195; https://doi.org/10.3390/a19030195 - 5 Mar 2026

As smart grids evolve into complex cyber-physical systems, conventional static defenses struggle to address time-varying topologies and Advanced Persistent Threats (APTs). We propose the Security Framework for Resilient Smart Grids based on Self-Organizing Graph Neural Cellular Automata (SG-GNC). Specifically, a Neural Homeostatic Embedding [...] Read more.

As smart grids evolve into complex cyber-physical systems, conventional static defenses struggle to address time-varying topologies and Advanced Persistent Threats (APTs). We propose the Security Framework for Resilient Smart Grids based on Self-Organizing Graph Neural Cellular Automata (SG-GNC). Specifically, a Neural Homeostatic Embedding (NHE) mechanism utilizes variational graph autoencoders to construct a continuous health manifold for unsupervised anomaly detection, while a Neural Cellular Automata (NCA) engine employs shared-weight local rules to empower nodes with decentralized self-healing capabilities. Finally, a Generative Adversarial Immunity (GAI) strategy facilitates active defense co-evolution, enhancing robustness against zero-day attacks. Experimental results on the IEEE 118 and 300-bus systems demonstrate an average detection accuracy of 98.23%, significantly outperforming benchmarks. In scenarios involving dynamic topology and zero-day attacks, the framework maintains over 96% accuracy with an inference latency of only 9.45 ms. These findings validate the capability of SG-GNC to provide resilient, endogenous defense in complex heterogeneous environments. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

13 pages, 575 KB

Open AccessArticle

Green Power Price Forecast Based on Multi-Dimensional Taylor Network and Wavelet Method

by Yaqin Qiu, Chao Zhang, Nanyun Jiang and Qiming Sun

Algorithms 2026, 19(3), 194; https://doi.org/10.3390/a19030194 - 5 Mar 2026

Time series forecasting in power systems is crucial for power supply planning and exerts a direct impact on the electricity market. Accurate forecasting can effectively mitigate decision-making risks. This paper proposes a forecasting method based on a multi-dimensional Taylor network (MTN) and applies [...] Read more.

Time series forecasting in power systems is crucial for power supply planning and exerts a direct impact on the electricity market. Accurate forecasting can effectively mitigate decision-making risks. This paper proposes a forecasting method based on a multi-dimensional Taylor network (MTN) and applies it to electricity price prediction. The time series is decomposed into one low-frequency signal and several high-frequency signals. The MTN model is constructed for each frequency sequence. The final forecast is obtained by aggregating the predictions from all frequency components. Using European electricity price data as a case study, experimental results demonstrate that the proposed method achieves high predictive accuracy. Full article

(This article belongs to the Section Algorithms and Mathematical Models for Computer-Assisted Diagnostic Systems)

► Show Figures

Figure 1

25 pages, 918 KB

Open AccessReview

Parkinson’s Disease Detection Using Machine Learning Algorithms: A Comprehensive Review

by Jelica Cincović, Miloš Cvetanović, Milica Djurić-Jovičić, Nebojsa Bacanin and Boško Nikolić

Algorithms 2026, 19(3), 193; https://doi.org/10.3390/a19030193 - 4 Mar 2026

Parkinson’s disease (PD) is a progressive neurodegenerative disorder in which early detection remains a major clinical challenge due to heterogeneous motor and non-motor manifestations and the lack of reliable biomarkers. In recent years, machine learning (ML) and deep learning (DL) methods have been [...] Read more.

Parkinson’s disease (PD) is a progressive neurodegenerative disorder in which early detection remains a major clinical challenge due to heterogeneous motor and non-motor manifestations and the lack of reliable biomarkers. In recent years, machine learning (ML) and deep learning (DL) methods have been increasingly investigated as decision-support tools for PD screening using diverse clinical and behavioral data. This review synthesizes PD detection studies published between 2017 and 2025, systematically analyzing 32 representative works across multiple modalities, including MRI, PET, EEG, REM sleep biomarkers, voice recordings, gait signals, handwriting/drawing tasks, and finger-tapping measurements. Across the reviewed literature, high classification performance is frequently reported, with CNN-based and hybrid DL architectures achieving particularly strong results in imaging and time-series settings, while classical ML approaches such as SVM and ensemble models remain competitive for engineered feature-based datasets. However, the review also reveals major barriers to reliable translation, including small datasets, inconsistent evaluation protocols, limited external validation, and the risk of performance inflation caused by non-subject-independent data splitting. Overall, this review provides a structured and modality-oriented reference of algorithms, datasets, and performance trends, while highlighting key methodological gaps and practical priorities for developing robust and clinically deployable PD detection systems. Full article

(This article belongs to the Special Issue Recent Advances in Artificial Intelligence and Metaheuristics Optimization)

► Show Figures

Figure 1

29 pages, 1306 KB

Open AccessArticle

AGRO: An Adaptive Gold Rush Optimizer with Dynamic Strategy Selection

by Costas Panagiotakis

Algorithms 2026, 19(3), 192; https://doi.org/10.3390/a19030192 - 4 Mar 2026

In this paper, we propose a metaheuristic optimization algorithm called Adaptive Gold Rush Optimizer (AGRO), a substantial evolution of the original Gold Rush Optimizer (GRO). Unlike the standard GRO, which relies on fixed probabilities in the strategy selection process, AGRO utilizes a novel [...] Read more.

In this paper, we propose a metaheuristic optimization algorithm called Adaptive Gold Rush Optimizer (AGRO), a substantial evolution of the original Gold Rush Optimizer (GRO). Unlike the standard GRO, which relies on fixed probabilities in the strategy selection process, AGRO utilizes a novel adaptive mechanism that prioritizes strategies improving solution quality. This adaptive component, which can be applied to any optimization algorithm with fixed probabilities in the strategy selection, adjusts the probabilities of the three core search strategies of GRO (Migration, Collaboration, and Panning), in real time, rewarding those that successfully improve solution quality. Furthermore, AGRO introduces fundamental modifications to the search equations, eliminating the inherent attraction towards the zero coordinates, while explicitly incorporating objective function values to guide prospectors towards promising regions. Experimental results demonstrate that AGRO is highly competitive against ten state-of-the-art algorithms on the twenty-three classical benchmark functions, the CEC2017, and the CEC2019 datasets, offering robust performance across diverse problem landscapes. Full article

(This article belongs to the Special Issue Machine Learning for Pattern Recognition (3rd Edition))

► Show Figures

Graphical abstract

21 pages, 1585 KB

Open AccessArticle

Beyond Significance: Promoting Effect Size Measures in Comparing Metaheuristic Algorithms

by Nourhan M. H. Ismail and Mahamed G. H. Omran

Algorithms 2026, 19(3), 191; https://doi.org/10.3390/a19030191 - 4 Mar 2026

This paper advocates the systematic use of effect size measures—such as Cohen’s d and Cliff’s

δ

—in the comparative evaluation of metaheuristic optimization methods. While statistical significance tests remain the dominant tool for determining whether observed performance differences are unlikely to be due [...] Read more.

This paper advocates the systematic use of effect size measures—such as Cohen’s d and Cliff’s

δ

—in the comparative evaluation of metaheuristic optimization methods. While statistical significance tests remain the dominant tool for determining whether observed performance differences are unlikely to be due to chance, they do not convey the magnitude or practical relevance of these differences. As a result, many studies report “significant” results that offer limited insight into the actual strength of one algorithm over another. Despite the clear value of effect size measures in addressing this gap, their adoption within the metaheuristics community remains limited. This paper highlights the role of effect sizes as complementary, not alternative, to traditional hypothesis testing. Through illustrative examples and discussion, we demonstrate how effect sizes provide a more informative and transparent basis for interpreting algorithmic superiority, contributing to more robust, reproducible, and meaningful empirical comparisons. The paper aims to encourage researchers to integrate effect size reporting into standard practice, thereby strengthening the methodological foundations of experimental research in metaheuristics. Full article

(This article belongs to the Section Evolutionary Algorithms and Machine Learning)

► Show Figures

Figure 1

16 pages, 440 KB

Open AccessArticle

Artificial Intelligence Promotes Rapid Detection of Humidity in Semiconductor Manufacturing Environments

by Fengting Yao, Tianshuo Li and Hongjun Wang

Algorithms 2026, 19(3), 190; https://doi.org/10.3390/a19030190 - 4 Mar 2026

Precise control of humidity levels within semiconductor manufacturing environments is paramount to ensuring product quality and yield. Unsuitable conditions can induce various wafer-related defects, including corrosion, oxidation, and poor film adhesion, thereby increasing production costs and compromising equipment reliability. This paper presents an [...] Read more.

Precise control of humidity levels within semiconductor manufacturing environments is paramount to ensuring product quality and yield. Unsuitable conditions can induce various wafer-related defects, including corrosion, oxidation, and poor film adhesion, thereby increasing production costs and compromising equipment reliability. This paper presents an innovative artificial intelligence-based framework, Lifelong Boosting Learning (

L^{2}

Boost), for rapid and accurate environmental detection within manufacturing facilities. By utilising datasets correlating sensor data with wafer defect labels, we establish links between environmental conditions and defects. Our approach employs an

L^{2}

Boost strategy to analyse heterogeneous sensor data and identify patterns indicative of environment-induced anomalies. The proposed system enables near-real-time environmental monitoring by indirectly measuring process characteristics correlated with defects, providing an early warning mechanism for environmental control systems. Experimental results demonstrate that

L^{2}

Boost accurately identifies environment-related defects from sensor data, achieving a macro-averaged Precision of 0.9912, Recall of 0.9804, F1 of 0.9858, and an ROC-AUC of 0.9945. This research contributes to the development of intelligent environmental monitoring systems for semiconductor manufacturing, offering a cost-effective solution for maintaining optimal production conditions. Ultimately, this framework provides actionable insights and automated diagnostic capabilities that are highly useful for process engineers, facility managers, and quality control teams striving to optimize yield in smart manufacturing environments. Full article

► Show Figures

Figure 1

28 pages, 2739 KB

Open AccessArticle

Sideslip Angle Estimation for Electric Vehicles Based on Adaptive Weight Fusion: Collaborative Optimization of Robust Observer and Kalman Filter

by Xi Chen, Kanghui Cheng, Te Chen, Guowei Dou, Xinlong Cheng and Xiaoyu Wang

Algorithms 2026, 19(3), 189; https://doi.org/10.3390/a19030189 - 3 Mar 2026

Accurate estimation of vehicle sideslip angle is vital for the stability and safety of four-wheel independent drive electric vehicles (4WIDEVs), but it faces challenges, including model uncertainties caused by tire yaw stiffness variations and system delays. This paper proposes a novel adaptive fusion [...] Read more.

Accurate estimation of vehicle sideslip angle is vital for the stability and safety of four-wheel independent drive electric vehicles (4WIDEVs), but it faces challenges, including model uncertainties caused by tire yaw stiffness variations and system delays. This paper proposes a novel adaptive fusion strategy that combines the dynamic robust observer (DRO) and the improved adaptive square-root unscented Kalman filter (ASUKF). The DRO is designed based on a two-degrees-of-freedom vehicle model and ensures stability through linear matrix inequalities (LMIs), effectively handling parameter uncertainties and time delays; the ASUKF utilizes a three-degrees-of-freedom model and the magic formula tire model, combined with Sage–Husa adaptive filtering, to address the nonlinear tire dynamics. The key innovation of this paper is the introduction of a fuzzy-rule-based adaptive weighting mechanism that dynamically adjusts the fusion weights of the DRO and ASUKF in real time, thereby exploiting their complementary advantages under uncertainty and nonlinear conditions. The simulation and experimental validations demonstrate that this method significantly improves estimation accuracy, reducing the estimation error of vehicle sideslip angle by an average of 9.36%, and maintains robust performance and dynamic adaptability in various conditions, providing a reliable solution for the real-time state estimation of intelligent electric vehicles. Full article

► Show Figures

Figure 1

24 pages, 2827 KB

Open AccessArticle

Balanced Index-Encoding Genetic Algorithm for Extreme Prototype Reduction in k-Nearest Neighbor Classification

by Victor Ayala-Ramirez, Jose-Gabriel Aguilera-Gonzalez, Antonio Tierrasnegras-Badillo and Uriel Calderon-Uribe

Algorithms 2026, 19(3), 188; https://doi.org/10.3390/a19030188 - 3 Mar 2026

Nearest-neighbor classifiers are accurate and easy to deploy, but their memory footprint and inference time grow with the size of the reference set. This paper studies an evolutionary prototype selection strategy for k-nearest neighbor (K-NN) classification aimed at extreme, class-balancedreduction. A compact genetic [...] Read more.

Nearest-neighbor classifiers are accurate and easy to deploy, but their memory footprint and inference time grow with the size of the reference set. This paper studies an evolutionary prototype selection strategy for k-nearest neighbor (K-NN) classification aimed at extreme, class-balancedreduction. A compact genetic algorithm (GA) evolves a fixed number of prototype indices per class drawn from a disjoint design partition; the selected prototypes are then used by a 1-NN classifier, with fitness defined as the number of correctly classified test instances. To address concerns about generality and baseline strength, we evaluate an experimental suite including synthetic 2D Gaussians (

σ = 0.5

and

σ = 1.0

) and a 3D three-moons geometry, as well as public benchmarks spanning binary and multi-class settings and higher-dimensional data (Breast Cancer Wisconsin, Wine, Reduced MNIST/Digits 8 × 8, Forest CoverType with seven classes, and a 10D five-class spiral benchmark). We compare against K-NN baselines with

k \in {1, 3, 5, 7}

using all design samples, and include GA operator ablations (GA1/GA2/GA3). Each scenario is repeated over 30 independent runs, reporting mean ± std, min/max, per-run distributions, win/tie/loss counts, and non-parametric significance tests (paired Wilcoxon with Holm correction; Friedman where applicable). Across datasets, the GA-selected prototype banks—often orders of magnitude smaller than the full design set—match or improve accuracy, with frequent statistically supported wins against strong K-NN baselines, and in the hardest cases provide substantial compression with no loss relative to the best baseline. These results establish a reproducible baseline for extreme, class-balanced prototype reduction suitable for memory- and latency-constrained deployments and for fair comparison against more elaborate prototype selection methods. Full article

(This article belongs to the Section Evolutionary Algorithms and Machine Learning)

► Show Figures

Figure 1

29 pages, 7418 KB

Open AccessArticle

EvoDropX: Evolutionary Optimization of Feature Corruption Sequences for Faithful Explanations of Transformer Models

by Dhiraj Kumar Singh and Conor Ryan

Algorithms 2026, 19(3), 187; https://doi.org/10.3390/a19030187 - 2 Mar 2026

As deep learning models become increasingly integrated into critical decision-making systems, the need for explainable Artificial Intelligence (xAI) has grown paramount to ensure transparency, accountability, and trust. Post hoc explainability methods, which analyse trained models to interpret their predictions without modifying the underlying [...] Read more.

As deep learning models become increasingly integrated into critical decision-making systems, the need for explainable Artificial Intelligence (xAI) has grown paramount to ensure transparency, accountability, and trust. Post hoc explainability methods, which analyse trained models to interpret their predictions without modifying the underlying architecture, have become increasingly important, especially in fields such as healthcare and finance. Modern xAI techniques often produce feature importance rankings that fail to capture the true causal influence of features, particularly in transformer-based models. Recent quantitative metrics, such as Symmetric Relevance Gain (SRG), which measures the area between the feature corruption performance curves of the Most Important Feature (MIF) and the Least Important Feature (LIF), provide a more rigorous basis for evaluating explanation fidelity. In this study, we first show that existing xAI methods exhibit consistently poor performance under the SRG criterion when explaining transformer-based text classifiers. To address these limitations, we introduceEvoDropX, a novel framework that formulates explanation as an optimisation problem. EvoDropX leverages Grammatical Evolution (GE) to evolve sequences of feature corruption with the explicit objective of maximising SRG, thereby identifying features that most strongly influence model predictions. EvoDropX provides interventional, input–output (behavioural) explanations and does not attempt to infer or interpret internal model mechanisms. Through comprehensive experiments across multiple datasets (IMDb movie reviews (IMDB), Stanford Sentiment Treebank (SST-2), Amazon Polarity (AP)), multiple transformer models (Bidirectional Encoder Representations from Transformers (BERT), RoBERTa, DistilBERT), and multiple metrics (SRG, MIF, LIF, Counterfactual Conciseness (CFC)), we demonstrate that EvoDropX significantly outperforms all state-of-the-art (SOTA) xAI baselines including Attention-Aware Layer- Wise Relevance Propagation for Transformers (AttnLRP), SHapley Additive exPlanations (SHAP), and Local Interpretable Model-agnostic Explanations (LIME), when evaluated using intervention-based faithfulness criteria. Notably, EvoDropX achieves

74.77 %

improvement in SRG than the best-performing baseline on the IMDB dataset with the BERT model, with consistent improvements observed across all dataset-model pairs. Finally, qualitative and linguistic analyses reveal that EvoDropX captures both sentiment-bearing terms and their structural relationships within sentences, yielding explanations that are both faithful and interpretable. Full article

(This article belongs to the Special Issue Explainable AI: Advances in Interpretability Algorithms and Applications)

► Show Figures

Figure 1

27 pages, 1391 KB

Open AccessArticle

Multi-Strategy Collaborative Improvement of an H5N1 Viral-Inspired Optimization Algorithm for Mobile Robot Path Planning

by Zehui Zhao, Changyong Li, Juntao Shi and Shunchun Zhang

Algorithms 2026, 19(3), 186; https://doi.org/10.3390/a19030186 - 2 Mar 2026

Mobile robots play an important role in promoting industrial intelligence and modernization. However, the existing obstacle avoidance path planning algorithms for mobile robots have poor stability and applicability. To this end, this paper proposes a path planning scheme for mobile robots based on [...] Read more.

Mobile robots play an important role in promoting industrial intelligence and modernization. However, the existing obstacle avoidance path planning algorithms for mobile robots have poor stability and applicability. To this end, this paper proposes a path planning scheme for mobile robots based on ISH5N1 algorithm. Firstly, aiming at the problem of low initial population quality of SH5N1 algorithm, Tent chaos initialization strategy was proposed, which increased the diversity of the population, improved the quality of initial solution, and laid a foundation for subsequent deeper search. Secondly, by fusing the multi-source direction vectors and applying them to the position update, the solution accuracy of the algorithm was improved and the convergence speed of the algorithm was accelerated. Then, the mutation step size control strategy enhanced by Logistic chaos was used to enhance the ability of the algorithm to jump out of local optimum. Finally, the attenuation coefficient of inertia weight is optimized by combining cosine annealing strategy, which strengthens the ability of the algorithm to balance global search and local development. The ISH5N1 algorithm was compared with several commonly used intelligent optimization algorithms on benchmark functions and grid maps with different complexities. The results show that ISH5N1 algorithm shows good stability, higher solution accuracy and faster convergence speed in solving most benchmark functions. In the path planning experiment, the ISH5N1 algorithm can plan a shorter and smoother path, which further proves that the algorithm has good optimization ability and robustness. Finally, ablation experiments were carried out on a 20 × 20 grid map to verify the effectiveness of each optimization strategy. Full article

► Show Figures

Figure 1

14 pages, 392 KB

Open AccessReview

Distributed Trust in the Age of Malware Blockchain Applications

by Paul A. Gagniuc, Maria-Iuliana Dascălu and Ionel-Bujorel Păvăloiu

Algorithms 2026, 19(3), 185; https://doi.org/10.3390/a19030185 - 2 Mar 2026

Blockchain technology is redefining the foundations of cybersecurity by introducing decentralized, tamper-resistant mechanisms for data integrity, trust management, and malware intelligence sharing. Traditional detection systems, which are dependent on centralized control and opaque validation, remain vulnerable to data manipulation and systemic compromise. The [...] Read more.

Blockchain technology is redefining the foundations of cybersecurity by introducing decentralized, tamper-resistant mechanisms for data integrity, trust management, and malware intelligence sharing. Traditional detection systems, which are dependent on centralized control and opaque validation, remain vulnerable to data manipulation and systemic compromise. The integration of blockchain transforms these paradigms because it provides verifiable provenance, distributed consensus, and autonomous enforcement through smart contracts. This review synthesizes fifteen years of progress (2010–2025) at the intersection of blockchain and malware detection and discusses core architectures, consensus protocols, and cryptographic properties that underpin decentralized defenses. The review follows a structured literature review methodology, which focuses on blockchain architectures, consensus protocols, and malware-detection pipelines reported in the cybersecurity literature. It also analyzes blockchain detection pipelines, performance tradeoffs, and data protection mechanisms in distributed learning systems and artificial intelligence models. Special attention is given to scalability constraints, regulatory compliance, and interoperability challenges that shape adoption. The review identifies three dominant design patterns: (i) decentralized threat-intelligence sharing with provenance guarantees, (ii) consensus-driven validation of malware artifacts, and (iii) on-chain trust and reputation mechanisms for detector accountability. Through the union of blockchain, artificial intelligence, edge computation, and federated learning, cybersecurity attains an auditable and adaptive architecture resilient to adversarial threats. The study concludes that blockchain provides a verifiable trust infrastructure for malware detection, but its practical deployment requires faster transaction validation and stronger protection of sensitive data; future research should address performance optimization and regulatory compliance. Full article

(This article belongs to the Special Issue Algorithms for Cyber Defense: From Cryptography to Behavioral Analysis)

► Show Figures

Figure 1

20 pages, 3035 KB

Open AccessArticle

Bridging Epidemiology and Limnology for Improved Prediction of Harmful Algal Blooms in Freshwater Lakes

by My Thi Nguyen, Kateryna Hushchyna, Qianbo Sheng, Kayla McLellan, Quoc Bao Vo and Tri Nguyen-Quang

Algorithms 2026, 19(3), 184; https://doi.org/10.3390/a19030184 - 1 Mar 2026

Harmful algal blooms (HABs) remain a growing threat to freshwater systems, yet predictive tools often rely on generic indices centered on chlorophyll-a (Chl-a), which is not cyanobacteria-specific. This paper introduces the Threshold Index (TRINDEX) as a new tool for predicting harmful algal blooms [...] Read more.

Harmful algal blooms (HABs) remain a growing threat to freshwater systems, yet predictive tools often rely on generic indices centered on chlorophyll-a (Chl-a), which is not cyanobacteria-specific. This paper introduces the Threshold Index (TRINDEX) as a new tool for predicting harmful algal blooms (HABs) in freshwater lakes. Unlike classical indices, TRINDEX explicitly integrates phycocyanin (PC), the pigment unique to cyanobacteria, making it the first cyanobacteria-specific threshold-based index. Using receiver operating characteristic (ROC) curve analysis, TRINDEX demonstrated excellent predictive tool, with area under the curve (AUC) values of 0.956 for TRINDEX₂ and 0.888 for TRINDEX₁ in Lake Torment, Nova Scotia. Furthermore, cohort studies, adapted from epidemiology, introduced here for the first time in HAB research, further validated TRINDEX, showing a 14.1% predicted bloom risk compared to 17.6% observed risk in Lake Torment. Validation across three independent waterbodies in New Brunswick confirmed TRINDEX’s robustness, with AUC values ranging from 0.714 to 0.979. These innovations demonstrate that TRINDEX yields robust, quantitative bloom thresholds, providing a practical foundation for future early-warning systems linked with remote sensing and real-time sensors to support effective water-quality management. Full article

(This article belongs to the Special Issue Mathematical Modelling in Engineering and Human Behaviour (4th Edition))

► Show Figures

Figure 1

34 pages, 5939 KB

Open AccessArticle

Explainable Machine Learning for Volatile Fatty Acid Soft-Sensing in Anaerobic Digestion: A Pilot Feasibility Study

by Bibars Amangeldy, Assiya Boltaboyeva, Nurdaulet Tasmurzayev, Zhanel Baigarayeva, Baglan Imanbek, Aliya Jemal Getahun, Dinara Turmakhanbet, Moldir Kuatova and Waldemar Wojcik

Algorithms 2026, 19(3), 183; https://doi.org/10.3390/a19030183 - 1 Mar 2026

Sustainable energy systems such as anaerobic digestion (AD) bioreactors exhibit complex nonlinear dynamics that complicate the monitoring of key stability indicators using conventional laboratory-based methods. As a preliminary investigation, this pilot study explores the feasibility of using machine learning-based soft sensing to estimate [...] Read more.

Sustainable energy systems such as anaerobic digestion (AD) bioreactors exhibit complex nonlinear dynamics that complicate the monitoring of key stability indicators using conventional laboratory-based methods. As a preliminary investigation, this pilot study explores the feasibility of using machine learning-based soft sensing to estimate Total Volatile Fatty Acids (TVFA(M)) from routinely measured physicochemical parameters. Using a short-term laboratory dataset obtained from controlled CO₂ biomethanisation experiments, several regression models were benchmarked, including an attention-based deep learning architecture (TabNet), multi-architecture artificial neural networks (ANNs), gradient-boosting ensembles (CatBoost, XGBoost, LightGBM), and classical kernel-based approaches. Model performance was evaluated under a cross-validated framework to assess predictive capability and consistency across folds within the limited experimental scope. Among the tested models, TabNet achieved highly competitive performance, yielding an R² of 0.8551, an RMSE of 0.0090, and an MAE of 0.0067. To support model transparency and interpretability, Explainable Artificial Intelligence (XAI) techniques based on SHapley Additive exPlanations (SHAP) were applied, identifying pCO₂ as the dominant contributor to TVFA(M) predictions within the studied operational range. The results demonstrate the potential of explainable machine learning models as soft sensors for TVFA(M) estimation under controlled laboratory conditions. Although restricted to controlled laboratory conditions and a short observation period, this pilot study demonstrates the potential of explainable machine learning models for TVFA(M) estimation and provides a methodological benchmark for future validation using larger and more diverse datasets. Full article

(This article belongs to the Special Issue Machine Learning and Artificial Intelligence in Engineering Applications: 2nd Edition)

► Show Figures

Figure 1

21 pages, 4105 KB

Open AccessEssay

MACFormer: Multi-Dimensional Attention and Composite Loss Former for Enhancing Few-Shot Image Classification

by Yuntao Shi, Wei Chen, Jie Li and Shuqin Li

Algorithms 2026, 19(3), 182; https://doi.org/10.3390/a19030182 - 1 Mar 2026

Addressing challenges in few-shot image classification, this study introduces the Multi-Dimensional Attention and Composite Loss Former, a meta-learning model built on a Residual Network-12 backbone. The model incorporates multi-dimensional attention mechanisms and is trained with a composite loss function applied across the entire [...] Read more.

Addressing challenges in few-shot image classification, this study introduces the Multi-Dimensional Attention and Composite Loss Former, a meta-learning model built on a Residual Network-12 backbone. The model incorporates multi-dimensional attention mechanisms and is trained with a composite loss function applied across the entire architecture. It enhances feature extraction by dynamically focusing on critical local and global information, while the composite loss optimizes classification accuracy, emphasizes hard samples, suppresses overfitting, and promotes intra-class feature compactness. Comprehensive experiments conducted on the miniImageNet and tieredImageNet datasets demonstrate that the proposed model achieves superior performance in both meta-training and meta-testing stages compared to existing benchmarks, effectively validating its robustness and generalization capabilities in few-shot learning tasks. Full article

(This article belongs to the Section Evolutionary Algorithms and Machine Learning)

► Show Figures

Figure 1

More Articles...

Submit to Algorithms Review for Algorithms

Journal Menu

Journal Browser

► Journal Browser

Highly Accessed Articles

View More...

Latest Books

More Books and Reprints...

E-Mail Alert

News

6 November 2025
MDPI Launches the Michele Parrinello Award for Pioneering Contributions in Computational Physical Science

11 September 2025
Meet Us at Entropy 2026: Exploring Complexity and Information in Science, 1–3 July 2026, Barcelona, Spain

28 February 2026
MDPI INSIGHTS: The CEO’s Letter #32 - MDPI China and Thailand, China Science Daily, 1,000 Partnerships, R2R

More News & Announcements...

Topics

Propose a Topic

Topic in Actuators, Algorithms, BDCC, Future Internet, JMMP, Machines, Robotics, Systems

Smart Product Design and Manufacturing on Industrial Internet Topic Editors: Pingyu Jiang, Jihong Liu, Ying Liu, Jihong Yan
Deadline: 30 June 2026

Topic in Algorithms, Data, Earth, Geosciences, Mathematics, Land, Water, IJGI

Applications of Algorithms in Risk Assessment and Evaluation Topic Editors: Yiding Bao, Qiang Wei
Deadline: 31 July 2026

Topic in Algorithms, Applied Sciences, Electronics, MAKE, AI, Software

Applications of NLP, AI, and ML in Software Engineering Topic Editors: Affan Yasin, Javed Ali Khan, Lijie Wen
Deadline: 30 August 2026

Topic in Agriculture, Energies, Vehicles, Sensors, Sustainability, Urban Science, Applied Sciences, Algorithms

Sustainable Energy Systems Topic Editors: Luis Hernández-Callejo, Carlos Meza Benavides, Jesús Armando Aguilar Jiménez
Deadline: 31 October 2026

More Topics

Conferences

Propose a Conference Collaboration

1–3 July 2026 Entropy 2026: Exploring Complexity and Information in Science

27–30 April 2026 Florence HeriTech 2026 International Conference 5th Edition

More Conferences...

Special Issues

Propose a Special Issue

Special Issue in Algorithms

Advanced Artificial Intelligence/Machine Learning Techniques for Safe Operation and Control in Power and Sustainable Energy Systems: 2nd Edition Guest Editors: Van-Hai Bui, Xuan Zhou, Wencong Su, Akhtar Hussain
Deadline: 20 March 2026

Special Issue in Algorithms

Algorithms for Dynamical Systems and Differential Equations: Theory, Computation Innovations and Applications Guest Editor: Adil Jhangeer
Deadline: 31 March 2026

Special Issue in Algorithms

Bayesian Machine Learning for Ecological and Environmental Applications Guest Editor: Nezamoddin N. Kachouie
Deadline: 31 March 2026

Special Issue in Algorithms

Multi-Objective and Multi-Level Optimization: Algorithms and Applications (2nd Edition) Guest Editor: Massimiliano Caramia
Deadline: 31 March 2026

More Special Issues

Topical Collections

Topical Collection in Algorithms

Feature Papers in Evolutionary Algorithms and Machine Learning Collection Editor: Stefano Mariani

Topical Collection in Algorithms

Feature Papers in Algorithms and Mathematical Models for Computer-Assisted Diagnostic Systems Collection Editor: Francesc Pozo

Topical Collection in Algorithms

Traditional and Machine Learning Methods to Solve Imaging Problems Collection Editors: Laura Antonelli, Lucia Maddalena

Topical Collection in Algorithms

Feature Papers on Artificial Intelligence Algorithms and Their Applications Collection Editors: Ulrich Kerzel, Mostafa Abbaszadeh, Andres Iglesias, Akemi Galvez Tomida

More Topical Collections

Back to TopTop