Algorithms

15 pages, 1389 KB

Open AccessArticle

Comparative Analysis of Real-Time Detection Models for Intelligent Monitoring of Cattle Condition and Behavior

by Oleg Ivashchuk, Zhanat Kenzhebayeva, Alexey Zhigalov, Moldir Allaniyazova, Gulnara Kaziyeva, Kaiyrbek Makulov, Vyacheslav Fedorov and Olga Ivashchuk

Algorithms 2025, 18(12), 763; https://doi.org/10.3390/a18120763 (registering DOI) - 2 Dec 2025

Abstract

This study benchmarks nine state-of-the-art object detection models on a specialized cattle dataset to assess accuracy and inference speed for real-time agricultural applications. Using a unified protocol without model-specific augmentations, and evaluating all detectors on identical RTX 4090 hardware, we provide a fair [...] Read more.

This study benchmarks nine state-of-the-art object detection models on a specialized cattle dataset to assess accuracy and inference speed for real-time agricultural applications. Using a unified protocol without model-specific augmentations, and evaluating all detectors on identical RTX 4090 hardware, we provide a fair architectural comparison of two-stage, one-stage, and transformer-based models. D_FINE_L and Co_DETR_R_50 achieved the highest accuracy (AP@[0.50:0.95] = 0.872 and 0.851), while RTMDet and YOLOv11_L were the fastest (15.81 and 19.14 ms/image). All models showed substantial accuracy gains on the domain dataset compared to COCO, while maintaining consistent relative speed rankings. Full article

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

► Show Figures

Figure 1

12 pages, 706 KB

Open AccessArticle

Improving Deep Learning Models by Bayesian Optimization to Predict Crude Oil Prices

by Shagun Kachwaha and Salim Lahmiri

Algorithms 2025, 18(12), 762; https://doi.org/10.3390/a18120762 (registering DOI) - 2 Dec 2025

Abstract

We implement, optimize, and compare the performance of deep learning models in forecasting prices of crude oil markets, namely West Texas Intermediate (WTI) and Brent. We focus on deep learning models as these are state-of-the-art forecasting systems for complex and nonlinear time series. [...] Read more.

We implement, optimize, and compare the performance of deep learning models in forecasting prices of crude oil markets, namely West Texas Intermediate (WTI) and Brent. We focus on deep learning models as these are state-of-the-art forecasting systems for complex and nonlinear time series. In this regard, we implement convolutional neural networks (CNNs), long short-term memory (LSTM), and gated recurrent units (GRUs). Classical recurrent neural networks (RNNs) are chosen as the baseline artificial neural networks. We contribute to the literature by examining the effect of fine-tuning of the parameters of the predictive systems by means of Bayesian optimization (BO) on their performance. Also, to check the robustness of the optimized models, they are trained and tested on daily, weekly, and monthly data. The assessment of forecasting performance is based on three different metrics including the root mean of squared errors (RMSE), mean absolute deviation (MAD), and mean absolute percentage error (MAPE). The simulation results show that the GRU-BO and RNN-BO are respectively the best systems to predict prices of BRENT and WTI. In addition, the simulation results show that BO enhances the accuracy of the predictive models. The results obtained would help oil producers, suppliers, traders, and investors to implement the appropriate prediction system for each market to improve accuracy and generate profits for each time horizon. Full article

(This article belongs to the Section Algorithms for Multidisciplinary Applications)

► Show Figures

Figure 1

23 pages, 9200 KB

Open AccessArticle

GC-HG Gaussian Splatting Single-View 3D Reconstruction Method Based on Depth Prior and Pseudo-Triplane

by Hua Gong, Peide Wang, Yuanjing Ma and Yong Zhang

Algorithms 2025, 18(12), 761; https://doi.org/10.3390/a18120761 (registering DOI) - 30 Nov 2025

Abstract

3D Gaussian Splatting (3DGS) is a multi-view 3D reconstruction method that relies solely on image loss for supervision, lacking explicit constraints on the geometric consistency of the rendering model. It uses a multi-view scene-by-scene training paradigm, which limits generalization to unknown scenes in [...] Read more.

3D Gaussian Splatting (3DGS) is a multi-view 3D reconstruction method that relies solely on image loss for supervision, lacking explicit constraints on the geometric consistency of the rendering model. It uses a multi-view scene-by-scene training paradigm, which limits generalization to unknown scenes in the case of single-view limited input. To address these issues, this paper proposes a Geometric Consistency-High Generalization (GC-HG), a single-view 3DGS reconstruction framework integrating depth prior and a pseudo-triplane. First, we utilize the VGGT 3D geometry pre-trained model to derive depth prior, back-projecting them into point clouds to construct a dual-modal input alongside the image. Second, we introduce a pseudo-triplane mechanism with a learnable Z-plane token for feature decoupling and pseudo-triplane feature fusion, thereby enhancing geometry perception and consistency. Finally, we integrate a parent–child hierarchical Gaussian renderer into the feed-forward 3DGS framework, combining depth and 3D offsets to model depth and geometry information, while mapping parent and child Gaussians into a linear structure through an MLP. Evaluations on the RealEstate10K dataset validate our approach, demonstrating improvements in geometric modeling and generalization for single-view reconstruction. Our method improves Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Learned Perceptual Image Patch Similarity (LPIPS) metrics, demonstrating its advantages in geometric consistency modeling and cross-scene generalization. Full article

(This article belongs to the Special Issue Artificial Intelligence in Modeling and Simulation (2nd Edition))

► Show Figures

Figure 1

18 pages, 5244 KB

Open AccessArticle

Computing Well-Balanced Spanning Trees of Unweighted Networks

by Lovro Šubelj

Algorithms 2025, 18(12), 760; https://doi.org/10.3390/a18120760 (registering DOI) - 29 Nov 2025

Abstract

A spanning tree of a network or graph is a subgraph that connects all nodes with the minimum number or total weight of edges. Spanning trees are among the simplest yet most effective techniques for network simplification, sampling, and uncovering a network’s backbone [...] Read more.

A spanning tree of a network or graph is a subgraph that connects all nodes with the minimum number or total weight of edges. Spanning trees are among the simplest yet most effective techniques for network simplification, sampling, and uncovering a network’s backbone or skeleton. Prim’s algorithm and Kruskal’s algorithm are well-known algorithms for computing a spanning tree of a weighted network, and are therefore also the default procedure for unweighted networks in the most popular network libraries. In this paper, we empirically evaluate the performance of these algorithms on unweighted networks and compare them with priority-first search algorithms. We show that the distances between the nodes are better preserved by a simpler algorithm based on breadth-first search. The spanning trees are also more compact and well-balanced, as measured by classical graph indices. We support our findings with experiments on synthetic graphs and over a thousand real networks, and demonstrate the practical applications of the computed spanning trees. We conclude that for preserving the structure of an unweighted network, the breadth-first search algorithm should be the preferred choice. Full article

(This article belongs to the Section Combinatorial Optimization, Graph, and Network Algorithms)

► Show Figures

Figure 1

15 pages, 332 KB

Open AccessArticle

Compact Models for Some Cluster Problems on Node-Colored Graphs

by Roberto Montemanni, Derek H. Smith, Pongchanun Luangpaiboon and Pasura Aungkulanon

Algorithms 2025, 18(12), 759; https://doi.org/10.3390/a18120759 (registering DOI) - 29 Nov 2025

Abstract

Three optimization problems based on node-colored undirected graphs are the subject of the present study. These problems model real-world applications in several domains, such as cybersecurity, bioinformatics, and social networks, although they have a similar abstract representation. In all of the problems, the [...] Read more.

Three optimization problems based on node-colored undirected graphs are the subject of the present study. These problems model real-world applications in several domains, such as cybersecurity, bioinformatics, and social networks, although they have a similar abstract representation. In all of the problems, the goal is to partition the graph into colorful connected components, which means that in each of the connected components, a color can appear in at most one node. The problems are optimized according to different objective functions, leading to different optimal partitions. We propose a compact Mixed Integer Linear Programming formulation for each of the three problems. These models are based on spanning trees, represented through multi-commodity flows. The compact nature of the new linear models is easier to handle than the approaches that previously appeared in the literature. These were based on models with an exponential number of constraints, which, therefore, required complex solving techniques based on the dynamic generation of constraints within a branch-and-cut framework. Computational experiments carried out on the standard benchmark instances for the problems show the potential of the new compact methods, which, once fed into modern state-of-the-art solvers, are able to obtain results better than the previous algorithmic approaches. As an outcome of the experimental campaign, a dozen instances of the different problems considered are closed for the first time. Full article

(This article belongs to the Section Combinatorial Optimization, Graph, and Network Algorithms)

► Show Figures

Figure 1

47 pages, 4638 KB

Open AccessArticle

Blockchain-Native Asset Direction Prediction: A Confidence-Threshold Approach to Decentralized Financial Analytics Using Multi-Scale Feature Integration

by Oleksandr Kuznetsov, Dmytro Prokopovych-Tkachenko, Maksym Bilan, Borys Khruskov and Oleksandr Cherkaskyi

Algorithms 2025, 18(12), 758; https://doi.org/10.3390/a18120758 (registering DOI) - 29 Nov 2025

Abstract

Blockchain-based financial ecosystems generate unprecedented volumes of multi-temporal data streams requiring sophisticated analytical frameworks that leverage both on-chain transaction patterns and off-chain market microstructure dynamics. This study presents an empirical evaluation of a two-class confidence-threshold framework for cryptocurrency direction prediction, systematically integrating macro [...] Read more.

Blockchain-based financial ecosystems generate unprecedented volumes of multi-temporal data streams requiring sophisticated analytical frameworks that leverage both on-chain transaction patterns and off-chain market microstructure dynamics. This study presents an empirical evaluation of a two-class confidence-threshold framework for cryptocurrency direction prediction, systematically integrating macro momentum indicators with microstructure dynamics through unified feature engineering. Building on established selective classification principles, the framework separates directional prediction from execution decisions through confidence-based thresholds, enabling explicit optimization of precision–recall trade-offs for decentralized financial applications. Unlike traditional three-class approaches that simultaneously learn direction and execution timing, our framework uses post-hoc confidence thresholds to separate these decisions. This enables systematic optimization of the accuracy-coverage trade-off for blockchain-integrated trading systems. We conduct comprehensive experiments across 11 major cryptocurrency pairs representing diverse blockchain protocols, evaluating prediction horizons from 10 to 600 min, deadband thresholds from 2 to 20 basis points, and confidence levels of 0.6 and 0.8. The experimental design employs rigorous temporal validation with symbol-wise splitting to prevent data leakage while maintaining realistic conditions for blockchain-integrated trading systems. High confidence regimes achieve peak profits of 167.64 basis points per trade with directional accuracies of 82–95% on executed trades, suggesting potential applicability for automated decentralized finance (DeFi) protocols and smart contract-based trading strategies on similar liquid cryptocurrency pairs. The systematic parameter optimization reveals fundamental trade-offs between trading frequency and signal quality in blockchain financial ecosystems, with high confidence strategies reducing median coverage while substantially improving per-trade profitability suitable for gas-optimized on-chain execution. Full article

(This article belongs to the Special Issue Blockchain and Big Data Analytics: AI-Driven Data Science)

► Show Figures

Figure 1

27 pages, 10258 KB

Open AccessArticle

Optimized Active Learning Method for High-Dimensional Industrial Regression Problems

by Clara Guilhaumon, Nicolas Hascoet, Francisco Chinesta and Marc Lavarde

Algorithms 2025, 18(12), 757; https://doi.org/10.3390/a18120757 (registering DOI) - 29 Nov 2025

Abstract

Machine learning approaches are commonly used to model physical phenomena due to their adaptability to complex systems. In general, a substantial number of samples must be collected to create a model with reliable results. However, collecting numerous data points is often costly. Moreover, [...] Read more.

Machine learning approaches are commonly used to model physical phenomena due to their adaptability to complex systems. In general, a substantial number of samples must be collected to create a model with reliable results. However, collecting numerous data points is often costly. Moreover, high-dimensional problems inherently require large amounts of data due to the curse of dimensionality. That is why new approaches based on smart sampling techniques are being investigated to optimize the acquisition of training samples, such as active learning methods. Initialization is a crucial step in active learning as it influences both performance and computational cost. Moreover, the scenarios used to select the next sample, such as classic pool-based sampling, can be highly resource- and time consuming. This study focuses on optimizing active learning methods through a comprehensive analysis of initialization strategies and scenario design, proposing and evaluating multiple approaches to determine the optimal configurations. The methods are applied to high-dimensional industrial problems with dimensions ranging from 5 to 15, where challenges associated with high dimensionality are already significant. To address this, the proposed study uses an active learning criterion that combines Sparse Proper Generalized Decomposition with Fisher information theory, specifically tailored to high-dimensional industrial settings. We illustrate the effectiveness of these techniques through examples on theoretical 5D and 15D functions, as well as a practical industrial crash simulation application. Full article

► Show Figures

Figure 1

27 pages, 2022 KB

Open AccessArticle

Review-Aware Recommendation Based on Polarity and Temporality

by Ye Yuan, Xifan Wu, Yulu Du, Yuhao Ren, Qiao Zou and Jiacheng Liu

Algorithms 2025, 18(12), 756; https://doi.org/10.3390/a18120756 (registering DOI) - 28 Nov 2025

Abstract

Review-aware recommendation systems aim to enhance recommendation performance by leveraging user reviews and their associated attributes to model user preferences. However, most existing methods fail to address two critical challenges introduced by user reviews: polarity bias and temporal dynamics. Polarity bias refers to [...] Read more.

Review-aware recommendation systems aim to enhance recommendation performance by leveraging user reviews and their associated attributes to model user preferences. However, most existing methods fail to address two critical challenges introduced by user reviews: polarity bias and temporal dynamics. Polarity bias refers to inconsistencies between a user’s numerical ratings and the sentiment expressed in their reviews—for example, a user might give a restaurant a high rating while writing a negative review. In addition, user preferences may evolve over time, as individuals can review the same item on multiple occasions. To address these issues, we propose RARPT, a review-aware recommendation framework that jointly models polarity and temporality. Specifically, we process positive and negative reviews separately and employ a sequential model to capture the temporal evolution of user preferences. We also introduce a polarity balance module, which uses a cross-attention mechanism to generate supplementary collaborative vectors from reviews of the opposite polarity, thereby mitigating both quantitative and relational imbalances. We conduct extensive experiments on two real-world datasets from Amazon and Yelp. The results show that our proposed model significantly outperforms several state-of-the-art baselines. Moreover, our model offers enhanced interpretability, helping deliver more effective personalized recommendations. Full article

► Show Figures

Figure 1

30 pages, 3017 KB

Open AccessArticle

Heterogeneous Genetic Learning and Comprehensive Learning Strategy Particle Swarm Optimizer

by Shengliang Wang, Yuqing Li and Yao Li

Algorithms 2025, 18(12), 755; https://doi.org/10.3390/a18120755 (registering DOI) - 28 Nov 2025

Abstract

In canonical PSO, maintaining an appropriate balance between exploration and exploitation is vital for optimizing particle behavior. However, this balance can be difficult to achieve in some complex scenarios. To tackle this issue, this study proposes an innovative PSO variant, named the heterogeneous [...] Read more.

In canonical PSO, maintaining an appropriate balance between exploration and exploitation is vital for optimizing particle behavior. However, this balance can be difficult to achieve in some complex scenarios. To tackle this issue, this study proposes an innovative PSO variant, named the heterogeneous genetic learning and comprehensive learning strategy PSO (HGCLPSO). The HGCLPSO incorporates the genetic learning strategy (GLS) and comprehensive learning strategy (CLS) to form heterogeneous sub-populations, effectively balancing the exploration and exploitation capabilities. Furthermore, a potentially excellent gene activation (PEGA) mechanism is designed to update the archived position of gbest (Abest) by learning some excellence gene of individual particles to further enhance the GLS sub-population exploitation ability. A repulsive mechanism is incorporated into the CLS sub-population to prevent premature convergence and preserve diversity. Additionally, a local search operator based on the BFGS Quasi-Newton method is utilized to fine-tune the best solution during the later stages of evolution. To evaluate the performance of HGCLPSO, it is benchmarked against eight renowned PSO variants and six additional evolutionary algorithms using the CEC2014 and CEC2017 test suites as well as a real-world WSN coverage engineering problem. Experimental outcomes show that HGCLPSO obtains the optimal average rank in the majority of test problems, which verifies its robustness and competitiveness as an optimization tool for addressing continuous optimization tasks. Full article

(This article belongs to the Special Issue Evolutionary and Swarm Computing for Emerging Applications)

► Show Figures

Figure 1

20 pages, 2080 KB

Open AccessArticle

A Multi-Objective Evolutionary Computation Approach for Improving Neural Network-Based Surrogate Models in Structural Engineering

by Néstor López-González, Eduardo Rodríguez and David Greiner

Algorithms 2025, 18(12), 754; https://doi.org/10.3390/a18120754 (registering DOI) - 28 Nov 2025

Abstract

Surrogate models are widely used in science and engineering to approximate other methods that are usually computationally expensive. Here, artificial neural networks (ANNs) are employed as surrogate regression models to approximate the finite element method in the problem of structural analysis of steel [...] Read more.

Surrogate models are widely used in science and engineering to approximate other methods that are usually computationally expensive. Here, artificial neural networks (ANNs) are employed as surrogate regression models to approximate the finite element method in the problem of structural analysis of steel frames. The focus is on a multi-objective neural architecture search (NAS) that minimizes the training time and maximizes the surrogate accuracy. To this end, several configurations of the non-dominated sorting genetic algorithm (NSGA-II) are tested versus random search. The robustness of the methodology is demonstrated by the statistical significance of the hypervolume indicator. Non-dominated solutions (consisting of the set of best designs in terms of accuracy for each training time or in terms of training time for each accuracy) reveal the importance of multi-objective hyperparameter tuning in the performance of ANNs as regression surrogates. Non-evident optimal values were attained for the number of hidden layers, the number of nodes per layer, the batch size, and alpha parameter of the Leaky ReLU transfer function. These results are useful for comparing with state-of-the-art ANN regression surrogates recently attained in the recent structural engineering literature. This approach facilitates the selection of models that achieve the optimal balance between training speed and predictive accuracy, according to the specific requirements of the application. Full article

(This article belongs to the Special Issue Multi-Objective and Multi-Level Optimization: Algorithms and Applications (2nd Edition))

► Show Figures

Figure 1

27 pages, 11057 KB

Open AccessArticle

A Variable-Speed and Multi-Condition Bearing Fault Diagnosis Method Based on Adaptive Signal Decomposition and Deep Feature Fusion

by Ting Li, Mingyang Yu, Tianyi Ma, Yanping Du and Shuihai Dou

Algorithms 2025, 18(12), 753; https://doi.org/10.3390/a18120753 - 28 Nov 2025

Abstract

To address the challenges in identifying effective fault features and achieving sufficient diagnostic accuracy and robustness in variable-speed printing press bearings, where complex mixed-condition vibration signals exhibit non-stationarity, strong nonlinearity, ambiguous time-frequency characteristics, and overlapping fault features across multiple operating conditions, this paper [...] Read more.

To address the challenges in identifying effective fault features and achieving sufficient diagnostic accuracy and robustness in variable-speed printing press bearings, where complex mixed-condition vibration signals exhibit non-stationarity, strong nonlinearity, ambiguous time-frequency characteristics, and overlapping fault features across multiple operating conditions, this paper proposes an adaptive optimization signal decomposition method combined with dual-modal time-series and image deep feature fusion for variable-speed multi-condition bearing fault diagnosis. First, to overcome the strong parameter dependency and significant noise interference of traditional adaptive decomposition algorithms, the Crested Porcupine Optimization Algorithm is introduced to adaptively search for the optimal noise amplitude and integration count of ICEEMDAN for effective signal decomposition. IMF components are then screened and reorganized based on correlation coefficients and variance contribution rates to enhance fault-sensitive information. Second, multidimensional time-domain features are extracted in parallel to construct time-frequency images, forming time-sequence-image bimodal inputs that enhance fault representation across different dimensions. Finally, a dual-branch deep learning model is developed: the time-sequence branch employs gated recurrent units to capture feature evolution trends, while the image branch utilizes SE-ResNet18 with embedded channel attention mechanisms to extract deep spatial features. Multimodal feature fusion enables classification recognition. Validation using a bearing self-diagnosis dataset from variable-speed hybrid operation and the publicly available Ottawa variable-speed bearing dataset demonstrates that this method achieves high-accuracy fault identification and strong generalization capabilities across diverse variable-speed hybrid operating conditions. Full article

(This article belongs to the Special Issue Machine Learning Algorithms for Signal Processing)

► Show Figures

Figure 1

16 pages, 1656 KB

Open AccessArticle

Predicting Critical Failure Zones in Dental Implants: A Comparison of MLP and Random Forest Classifiers

by María Prados-Privado

Algorithms 2025, 18(12), 752; https://doi.org/10.3390/a18120752 - 28 Nov 2025

Abstract

Dental implants have excellent clinical results, but they still face a significant engineering hurdle: mechanical failure from repeated loading. Finite element simulations are widely used to identify areas of elevated stress in implant structures, but their computational cost makes them impractical for exhaustive [...] Read more.

Dental implants have excellent clinical results, but they still face a significant engineering hurdle: mechanical failure from repeated loading. Finite element simulations are widely used to identify areas of elevated stress in implant structures, but their computational cost makes them impractical for exhaustive scenario testing. This study proposes an artificial intelligence-based solution for rapidly predicting biomechanically critical conditions in dental implants. Specifically, two machine learning classifiers—a multilayer perceptron neural network and a Random Forest—were developed and compared. A dataset of 200 simulations was generated using finite element analysis by varying implant diameter, loading angle, and force magnitude. For each case, three biomechanical features were extracted: maximum von Mises stress, equivalent deformation, and fatigue safety factor. Risk cases were labeled based on a fatigue safety factor threshold. The neural network consisted of two hidden layers, while the Random Forest model comprised 100 decision trees. Both models were trained on 80% of the data and validated on the remaining 20%. The neural network achieved 99% classification accuracy, while the Random Forest reached 100%. The neural model demonstrated better sensitivity in identifying failure-prone scenarios, whereas the Random Forest provided better interpretability through feature importance analysis. These results highlight how artificial intelligence can be effectively integrated into the engineering workflow to support failure risk assessment in implant design and planning. The proposed surrogate models significantly reduce computation time and enable scalable, biomechanically informed decision-making. Full article

(This article belongs to the Special Issue Machine Learning and Deep Learning in Medical Imaging Diagnostics)

► Show Figures

Figure 1

19 pages, 4927 KB

Open AccessArticle

Enhanced Remote Sensing Object Detection via AFDNet: Integrating Dual-Sensing Attention and Dynamic Bounding Box Optimization

by Ziyan Wang, Miao Fang and Xiaofei Zhang

Algorithms 2025, 18(12), 751; https://doi.org/10.3390/a18120751 - 28 Nov 2025

Abstract

Existing remote sensing object detection methods struggle with challenges such as complex background interference, variable object scales, and class imbalance due to a lack of coordinated internal optimization. This paper proposes AFDNet, a novel RSOD algorithm that establishes an internal collaborative evolution mechanism [...] Read more.

Existing remote sensing object detection methods struggle with challenges such as complex background interference, variable object scales, and class imbalance due to a lack of coordinated internal optimization. This paper proposes AFDNet, a novel RSOD algorithm that establishes an internal collaborative evolution mechanism to systematically enhance the model’s feature perception and localization capabilities in complex scenes. AFDNet achieves this through three tightly coupled, co-evolving components: (1) A channel–spatial dual-sensing module that adaptively focuses on crucial features and suppresses background noise. (2) A dynamic bounding box optimization module that integrates distance-aware and scale-normalization strategies, significantly boosting localization accuracy and regression robustness for multi-scale objects. (3) A Gaussian adaptive activation unit that enhances the model’s nonlinear fitting capability for better detail extraction under weak conditions. Extensive experiments on two public datasets, RSOD and NWPU VHR-10, verify the excellent performance of AFDNet. AFDNet achieved a leading 95.16% mAP@50 on the RSOD dataset and an astonishing 96.52% mAP@50 on the NWPU VHR-10 dataset, which is significantly better than the mainstream detection models. This study verifies the effectiveness of introducing internal co-evolution mechanisms and provides a novel and reliable solution for high-precision remote sensing target detection. Full article

(This article belongs to the Collection Feature Papers in Combinatorial Optimization, Graph, and Network Algorithms)

► Show Figures

Figure 1

5 pages, 163 KB

Open AccessEditorial

Algorithms for Image Processing and Machine Vision

by Arslan Munir

Algorithms 2025, 18(12), 750; https://doi.org/10.3390/a18120750 - 28 Nov 2025

Abstract

The field of image processing and machine vision has undergone a remarkable transformation in recent years [...] Full article

(This article belongs to the Special Issue Algorithms for Image Processing and Machine Vision)

19 pages, 359 KB

Open AccessArticle

A Deterministic Comparison of Classical Machine Learning and Hybrid Deep Representation Models for Intrusion Detection on NSL-KDD and CICIDS2017

by Miguel Arcos-Argudo, Rodolfo Bojorque and Andrés Torres

Algorithms 2025, 18(12), 749; https://doi.org/10.3390/a18120749 - 28 Nov 2025

Abstract

Intrusion detection systems (IDSs) must balance detection quality with operational transparency. We present a deterministic, leakage-free comparison of three classical classifiers: Naïve Bayes (NB), Logistic Regression (LR), and Linear Discriminant Analysis (LDA). We also propose a hybrid pipeline that trains LR on Autoencoder [...] Read more.

Intrusion detection systems (IDSs) must balance detection quality with operational transparency. We present a deterministic, leakage-free comparison of three classical classifiers: Naïve Bayes (NB), Logistic Regression (LR), and Linear Discriminant Analysis (LDA). We also propose a hybrid pipeline that trains LR on Autoencoder embeddings (AE). Experiments use NSL-KDD and CICIDS2017 under two regimes (with/without SMOTE (Synthetic Minority Oversampling Technique) applied only on training data). All preprocessing (one-hot encoding, scaling, and imputation) is fitted on the training split; fixed seeds and deterministic TensorFlow settings ensure exact reproducibility. We report a complete metric set—Accuracy, Precision, Recall, F1, Area Under the Curve (AUC), and False Alarm Rate (FAR)—and release a replication package (code, preprocessing artifacts, and saved prediction scores) to regenerate all reported tables and metrics. On NSL-KDD, AE+LR yields the highest AUC (≈0.904) and the strongest F1 among the evaluated models (e.g., 0.7583 with SMOTE), while LDA slightly edges LR on Accuracy/F1. NB attains very high Precision (≈0.98) but low Recall (≈0.24), resulting in the weakest F1, yet a low FAR due to conservative decisions. On CICIDS2017, LR delivers the best Accuracy/F1 (0.9878/0.9752 without SMOTE), with AE+LR close behind; both approach ceiling AUC (≈0.996). SMOTE provides modest gains on NSL-KDD and limited benefits on CICIDS2017. Overall, LR/LDA remain strong, interpretable baselines, while AE+LR improves separability (AUC) without sacrificing a simple, auditable decision layer for practical IDS deployment. Full article

► Show Figures

Figure 1

15 pages, 2714 KB

Open AccessArticle

Analyzing Global Attitudes Towards ChatGPT via Ensemble Learning on X (Twitter)

by Yassir Touhami Chahdi, Fouad Mohamed Abbou, Farid Abdi, Mohamed Bouhadda and Lamiae Bouanane

Algorithms 2025, 18(12), 748; https://doi.org/10.3390/a18120748 - 28 Nov 2025

Abstract

This research investigates global public attitudes towards ChatGPT by analyzing opinions on X (Twitter) to better understand societal perceptions of generative artificial intelligence (AI) applications. As conversational AI systems become increasingly integrated into daily life, evaluating public sentiment is crucial for informing responsible [...] Read more.

This research investigates global public attitudes towards ChatGPT by analyzing opinions on X (Twitter) to better understand societal perceptions of generative artificial intelligence (AI) applications. As conversational AI systems become increasingly integrated into daily life, evaluating public sentiment is crucial for informing responsible AI development and policymaking. Unlike many prior studies that adopt a binary (positive-negative) sentiment framework, this research presents a three-class classification scheme-positive, neutral, and negative framework, enabling more comprehensive evaluation of public attitudes using X (Twitter) data. To achieve this, tweets referencing ChatGPT were collected and categorized into positive, neutral, and negative opinions. Several algorithms, including Naïve Bayes, Support Vector Machines (SVMs), Random Forest, and an Ensemble Learning model, were employed to classify sentiments. The Ensemble model demonstrated superior performance, achieving an accuracy of 86%, followed by SVM (84%), Random Forest (79%), and Naïve Bayes (66%). Notably, the Ensemble approach improved the classification of neutral sentiments, increasing recall from 73% (SVM) to 76%, underscoring its robustness in handling ambiguous or mixed opinions. These findings highlight the advantages of Ensemble Learning techniques in social media sentiment analysis and provide valuable insights for AI developers and policymakers seeking to understand and address public perspectives on emerging AI technologies such as ChatGPT. Full article

(This article belongs to the Section Algorithms for Multidisciplinary Applications)

► Show Figures

Figure 1

11 pages, 868 KB

Open AccessTechnical Note

A Monte Carlo Simulation Algorithm to Assess Rollout Feasibility in Stepped-Wedge Trials: A Case Study of National CPR Training Kiosk Deployment

by Robert Ohle and Sarah McIsaac

Algorithms 2025, 18(12), 747; https://doi.org/10.3390/a18120747 - 28 Nov 2025

Abstract

Background: Stepped-wedge cluster randomized trials (SW-CRTs) are increasingly used to evaluate population-level interventions, but trial validity depends on timely cluster transitions. Rollout feasibility is often assumed rather than modelled. In the context of a planned national trial of CPR training kiosks, we developed [...] Read more.

Background: Stepped-wedge cluster randomized trials (SW-CRTs) are increasingly used to evaluate population-level interventions, but trial validity depends on timely cluster transitions. Rollout feasibility is often assumed rather than modelled. In the context of a planned national trial of CPR training kiosks, we developed a Monte Carlo simulation algorithm to quantify logistical feasibility under uncertainty. Methods: A stochastic Monte Carlo algorithm was implemented to simulate deploying 100 CPR kiosks across eight Canadian cities under four team structures. Inputs included productivity (0.8–1.2 kiosks/day), disruption probabilities (weather, venue access, technical failure, staff illness, transport delays), and cost parameters (salaries, per diems, travel). Each scenario was simulated across 3000 iterations. Outputs included per-city feasibility (p ≤ 60 days), total project duration, and risk–cost trade-offs. Results: Single-team strategies required 9–10 months for full rollout, with winter-exposed cities such as Halifax and Charlottetown having up to 30% probability of exceeding 60 days. Two-team strategies halved rollout time (4–5 months) and achieved >95% on-time rollout across cities. Adding a third onsite staff member reduced risk by 5–15% with modest additional cost (~CAD 1500–2000 per city). Risk–cost analysis identified two teams with three staff as the most reliable strategy. Conclusions: Monte Carlo simulation provides a practical framework for assessing rollout feasibility in SW-CRTs. Applied to CPR kiosk deployment, it highlights the importance of staffing, seasonality, and city-level context. The approach is generalizable to other national interventions requiring phased rollout under uncertainty. Full article

► Show Figures

Figure 1

22 pages, 1113 KB

Open AccessArticle

Bi-Objective Optimization with Mode-Oriented Genetic Algorithm for Multi-Mode Resource-Constrained Project Scheduling

by Mingcong Xia, Guokai Liang, Rui Tong, Jianxin Zhu, Xin Xie, Jintao Chen, Weihua Tan and Yuting Liu

Algorithms 2025, 18(12), 746; https://doi.org/10.3390/a18120746 - 27 Nov 2025

Abstract

To address the time–cost trade-off challenge in real-world practices, a bi-objective optimization model of the Multi-mode Resource-Constrained Project Scheduling Problem is proposed with simultaneously minimizing both the project makespan and the resource cost. A mode-oriented Non-dominated Sorting Genetic Algorithm II is developed to [...] Read more.

To address the time–cost trade-off challenge in real-world practices, a bi-objective optimization model of the Multi-mode Resource-Constrained Project Scheduling Problem is proposed with simultaneously minimizing both the project makespan and the resource cost. A mode-oriented Non-dominated Sorting Genetic Algorithm II is developed to solve the formulated problem. Two key improvements are introduced: a mode-repair mechanism is incorporated during the initialization phase to generate feasible execution modes, thereby improving the quality of initial solutions and accelerating search efficiency, and four neighborhood structures based on mode and task execution lists are designed for local search, enabling fine-grained solution refinement in each iteration. Extensive experimental studies are conducted to verify the effectiveness of the proposed strategies, and comparative evaluations with state-of-the-art algorithms demonstrate that MNSGA-II achieves superior performance across multiple metrics, including lower mean ideal distance, better solution quality, improved diversity, and more uniform distribution of Pareto-optimal solutions. Full article

(This article belongs to the Section Algorithms for Multidisciplinary Applications)

► Show Figures

Figure 1

25 pages, 5468 KB

Open AccessArticle

Dynamic Evolution of Energy Efficiency in the Building Sector: A Changepoint Detection and Text Processing-Based Bibliometric Analysis

by Tudor Bungau, Constantin C. Bungau, Codruta Bendea, Ioana Francesca Hanga-Farcas and Gabriel Bendea

Algorithms 2025, 18(12), 745; https://doi.org/10.3390/a18120745 - 27 Nov 2025

Abstract

Energy efficiency in buildings is a vital subject within sustainable construction and climate change mitigation, yet comprehensive bibliometric analyses mapping the complete evolution of this domain remain limited. This study provides a comprehensive four-decade analysis (1981–2025) of building energy efficiency research using data [...] Read more.

Energy efficiency in buildings is a vital subject within sustainable construction and climate change mitigation, yet comprehensive bibliometric analyses mapping the complete evolution of this domain remain limited. This study provides a comprehensive four-decade analysis (1981–2025) of building energy efficiency research using data from the Web of Science database, employing VOSviewer (1.6.20), Bibliometrix (4.3.0), and custom Python (3.12.3) scripts with automated terminology normalization through TF-IDF vectorization (n-grams 2–3) and cosine similarity algorithms (threshold = 0.75). Two critical methodological innovations distinguish this investigation: first, Pruned Exact Linear Time changepoint detection statistically validated 2011 as the field’s statistically validated transition point (Mann–Whitney U test, p < 0.000001, effect size = 2.48), replacing arbitrary decade-based periodization; second, computational keyword harmonization enabled precise thematic evolution mapping across inconsistent terminology. The analysis reveals marked increase in research post-2011, with median annual output increasing from 15 articles (1981–2011) to 840.5 articles (2012–2024), and China emerging as the preeminent research center with 2978 publications. Thematic evolution analysis demonstrates fundamental transformation from seven specialized research themes (i.e., behavior, heat-transfer, simulation, impact, performance, consumption, optimization) in the foundational period to dramatic consolidation into two dominant themes (i.e., performance and simulation) in the contemporary period, reflecting maturation from fragmented, component-focused investigations toward holistic, integrated frameworks. International collaboration network analysis identifies four distinct geographic clusters with China, United States, United Kingdom, and Italy serving as central hubs. These findings provide actionable intelligence for researchers, policymakers, and industry stakeholders, while the computationally enhanced framework offers a replicable methodology for bibliometric analysis in other rapidly evolving interdisciplinary domains. Full article

► Show Figures

Figure 1

Journal Description

Algorithms

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI