Revista Internacional de Métodos Numéricos para Cálculo y Diseño en Ingeniería / International Journal of Numerical Methods for Calculation and Design in Engineering

RIMNI - An International Journal of Numerical Methods for Calculation and Design in Engineering (Revista Internacional de Métodos Numéricos para Cálculo y Diseño en Ingeniería) is a peer-reviewed Open Access journal, founded in 1985. RIMNI publishes articles written in Spanish and English. The journal's scope includes Computational and Numerical Models of Engineering Problems, Development and Application of Numerical Methods, Advances in Software, Computer Design Innovations, Soft Computing, Machine Learning, Artificial Intelligence, etc. RIMNI is an essential ... show more

DOCUMENTS1401
VIEWS189200
SCORE5

SCORE PERCENTILE100

Online First

Hierarchical Convolutional Neural Network for Emotion Recognition Using EEG and Facial Expressions
M. Shafiq, S. Awan, T. Kamal

Rev. int. métodos numér. cálc. diseño ing. (2026). Vol. Online First, 112

Abstract
Emotion recognition is crucial for advancing human–computer interaction (HCI) by enabling systems to interpret complex affective states. While Electroencephalogram (EEG) signals provide direct insights into neural activity, facial expressions offer external emotional cues. However, unimodal systems often struggle with robustness and generalization across diverse subjects. This study presents a Hierarchical Convolutional Neural Network (HCNN) framework that integrates EEG and facial expressions through multi-level convolutional feature extraction and featurelevel fusion. The proposed model combines deep hierarchical representations with handcrafted temporal–frequency and texture-based descriptors to form a unified feature vector. Experiments on the MAHNOB-HCI and DEAP datasets show that the HCNN achieves accuracies of 91.40% and 88.09%, outperforming CNN-, LSTM-, and SVM-based methods. The results demonstrate the model’s ability to effectively capture complementary cross-modal correlations while reducing feature redundancy and computational complexity. The HCNN framework shows great promise for real-time emotion recognition applications, offering a scalable, interpretable, and data-efficient solution for multimodal emotion recognition in next-generation HCI systems.
Abstract
Emotion recognition is crucial for advancing human–computer interaction (HCI) by enabling systems to interpret complex affective states. While Electroencephalogram (EEG) [...]
- 87
- read
Dynamic Variational Autoencoder Regressor for Soft Sensor Modeling
H. Wu, P. Zhang, S. Tian, Z. Chen

Rev. int. métodos numér. cálc. diseño ing. (2026). Vol. Online First, 114

Abstract
Due to the dynamics of industrial production, it is a great challenge to learn robust feature representations from industrial process data for building an accurate soft sensor model. The traditional variational autoencoder (VAE) can learn robust features that can adapt to the dynamic process better, but cannot be directly applied in soft sensor modeling. Therefore, a novel regression-based dynamic VAE (REGDVAE) is introduced in this paper. Firstly, the encoder of the DVAE, which is constructed by the graph attention and the convolutional neural networks, is utilized to obtain the robust spatio-temporal features. The decoder of the DVAE is responsible for reconstructing the input data via transposed convolution. Secondly, the Transformer is employed to capture the dynamic associations between the robust spatio-temporal features and corresponding outputs. Moreover, with the purpose of guaranteeing the confidence of the proposed method, the Gaussian loss function is used as the optimization target of the REG-DVAE to enhance the confidence of each predicted value. The proposed REG-DVAE is implemented in a real-world melt index modeling of the polypropylene production process. The results show that compared with other baseline methods, the REG-DVAE not only can achieve the best performance, but also can provide a confidence interval, which greatly enhances the credibility of the prediction results.
Abstract
Due to the dynamics of industrial production, it is a great challenge to learn robust feature representations from industrial process data for building an accurate soft sensor [...]
- 24
- read
IMA: An Interpretable Machine Learning Framework Based on Large-Scale Anonymous Evaluations to Decode the Black Box of Student-Supervisor Mentorships
Y. Gao, W. Jin, Y. Nan, Y. Ma, B. Zhao, Z. Zhang

Rev. int. métodos numér. cálc. diseño ing. (2026). Vol. Online First, 115

Abstract
Student-supervisor relationships (SSR) play a central role in postgraduate training, academic development, and research well-being. In the context of the rapid expansion of Chinese graduate education, understanding mentorship quality has become increasingly important for both educational governance and student development. However, prior SSR studies have often relied on small-scale surveys, context-specific qualitative evidence, or linear analytical approaches, which limits their ability to capture heterogeneous, non-linear, and system-level patterns across institutions and disciplines. To address this gap, we propose Interpretable Mentorship Analytics (IMA), a scalable analytical framework built on large-scale anonymous student evaluations. First, we construct a multi-platform dataset of anonymous supervisor evaluations and transform unstructured review text into structured mentorship indicators through a preprocessing and LLM-assisted feature engineering pipeline. Second, we employ gradient-boosting models, including XGBoost, LightGBM, and Gradient Boosting, to model the relationship between mentorship-related features and overall evaluation outcomes. Third, we apply explainable machine learning methods, particularly SHAP and LIME, to identify global feature importance, local decision patterns, and non-linear interactions among mentorship dimensions. The results show that IMA can effectively uncover the key drivers of mentorship satisfaction, especially the central role of teacher-student relationship quality, while also revealing substantial heterogeneity across regions, institution types, and disciplines. By combining large-scale anonymous evaluations with interpretable predictive modeling, this study provides a transparent and data-driven framework for evaluations with interpretable predictive modeling, this study provides a transparent and data-driven framework for understanding SSR and offers empirical evidence for improving postgraduate supervision and educational policy.
Abstract
Student-supervisor relationships (SSR) play a central role in postgraduate training, academic development, and research well-being. In the context of the rapid expansion of [...]
- 16
- read
CARE-FSP: A Cost-Aware and Resource-Efficient Hybrid RSO–SFO Framework for Fog-Based IoT Service Placement
H. Merouani, S. Bendib, H. Moumen, L. Guezouli

Rev. int. métodos numér. cálc. diseño ing. (2026). Vol. Online First, 116

Abstract
sup>Efficient service placement is a critical challenge in large-scale Internet of Things (IoT) environments, where fog computing must balance deployment cost and resource utilization under heterogeneous and dynamic conditions. To address this challenge, this paper proposes a hybrid metaheuristic approach that combines Rat Swarm Optimization (RSO) and Sunflower Optimization (SFO), leveraging the strong global exploration capability of RSO and the efficient local exploitation behavior of SFO. The proposed RSO–SFO framework integrates both strategies within a unified fitness function designed to minimize deployment cost while ensuring efficient allocation of fog resources. Extensive simulation results demonstrate that the proposed hybrid algorithm consistently outperforms state-of-the-art optimization techniques, including Grey Wolf Optimization (GWO), Particle Swarm Optimization (PSO), and the standalone RSO and SFO methods. Specifically, the RSO–SFO approach achieves a fitness improvement of 45.38%, reduces deployment costs by 43.71%, and maintains a high average resource utilization of 78.83%. These results confirm the effectiveness and robustness of the proposed hybrid strategy for optimal service placement in fog-based IoT environments.
Abstract
sup>Efficient service placement is a critical challenge in large-scale Internet of Things (IoT) environments, where fog computing must balance deployment cost and resource [...]
- 58
- read
Hybrid Fractional Coupled Systems with Generalized Caputo Derivatives
D. Alhwikem, M. Awadalla

Rev. int. métodos numér. cálc. diseño ing. (2026). Vol. Online First, 117

Abstract
This paper establishes a comprehensive theoretical framework for a novel coupled system of nonlinear hybrid fractional differential equations involving generalized Caputo derivatives. The system’s hybrid nature, coupled with the generality of the fractional operators, allows for modeling complex interdependent processes with memory effects that cannot be adequately captured by existing models. Using Krasnoselskii’s fixed point theorem, we prove the existence of at least one solution under explicit coupling conditions. Under appropriate Lipschitz conditions, we establish uniqueness via Banach’s contraction principle, deriving a quantitative condition involving the fractional orders, generalization parameters, and Lipschitz constants. We also conduct a rigorous analysis of Ulam-Hyers and Ulam-Hyers-Rassias stability, obtaining explicit stability constants that provide quantitative bounds on how perturbations in the input affect the solution. The theoretical results are validated through three carefully constructed numerical examples with explicit parameter values demonstrating existence, uniqueness, and Ulam-Hyers stability. A parameter sensitivity analysis confirms the robustness of the uniqueness condition across variations in fractional orders, generalization parameters, and interval lengths. The paper concludes with a discussion of limitations and directions for future research, including extensions to higher fractional orders, delay and impulsive effects, and numerical methods.
Abstract
This paper establishes a comprehensive theoretical framework for a novel coupled system of nonlinear hybrid fractional differential equations involving generalized Caputo [...]
- 84
- read
A Deep Learning-Based Time-Depth Conversion Method for Continuous Wellbore Temperature Profile Construction Using a Micro-Measurer
M. Li, Y. Wang, X. Song, S. Duan, H. Wang, W. Hao, J. Wang

Rev. int. métodos numér. cálc. diseño ing. (2026). Vol. Online First, 120

Abstract
Real-time monitoring of oil-gas wellbore temperature profiles provides important support for drilling strategy adjustment and model parameter calibration. MEMS-based micro-measurers can collect fullwellbore temperature data by flowing with drilling fluid circulation, but converting their time-series records to well depth relies on idealized steady-motion assumptions that neglect wall collisions, sticking, and local flow disturbances, introducing systematic positioning errors. In this study, a deep learning-based time-depth conversion method is proposed. A gated recurrent unit (GRU)-based temporal neural network is developed to extract motion-state features from six-axis dynamic signals, and a bounded velocity correction mechanism is introduced to compensate deviations from the idealized terminal velocity. The results show that: (1) The proposed model effectively learns motion-state deviations from dynamic response data and provides stable velocity correction under complex downhole conditions. (2) The corrected time-velocity curve exhibits transient fluctuations relative to the idealized terminal velocity, accurately capturing non-ideal behaviors while preserving directional stability. (3) During model training, the loss function decreases progressively and stabilizes, indicating good convergence and training stability. (4) Comparative analysis shows that the proposed GRU-Full method achieves a mean absolute anchor-point error of 1.23 m (0.24% of the well depth), outperforming the MLP and LSTM alternatives. Ablation experiments confirm that both the physical constraints and regularization terms contribute substantially to the model accuracy. This study enhances the spatial mapping accuracy of temperature data acquired by micro-measurers under complex downhole dynamic conditions. The established physically constrained deep learning framework provides a new technical pathway for refined wellbore thermal-field characterization and intelligent drilling decision-making.
Abstract
Real-time monitoring of oil-gas wellbore temperature profiles provides important support for drilling strategy adjustment and model parameter calibration. MEMS-based micro-measurers [...]
- 2
- read
Optimal FOPID Controller Design for DC Motor Speed Control Using Ant Lion Optimization Algorithm
S. Waseem, M. Irfan, A. Amin, S. Rahman, H. Alwadie, S. dawsari

Rev. int. métodos numér. cálc. diseño ing. (2026). Vol. Online First, 118

Abstract
DC motors are frequently utilized in industrial and automation applications where accurate speed control is crucial. Although conventional Proportional-Integral-and Derivative (PID) controllers are widely utilized, their constant gain values make them less effective in managing dynamic loads and disturbances. It’s difficult to get optimal transient and steady-state performance with traditional PID tuning methods. To overcome these limitations, more adaptable and dependable control systems are needed. This study introduces a novel control strategy by optimizing a Fractional-Order PID (FOPID) controller using the Ant Lion Optimization (ALO) method. Mathematical modeling is used to determine the DC motor’s transfer function. An ALO, a metaheuristic algorithm, is then implemented to improve five FOPID parameters using Integral Timeweighted Absolute Error (ITAE). The simulation is done in MATLAB-Simulink software. According to the findings, the enhanced ALO-FOPID controller decreased settling time (0.0728 s) and rising time (0.0455 s) when compared to the PID controller, which is taken as a reference. It is noted that the proposed ALO-tuned FOPID demonstrated enhanced response over the conventional methods, demonstrating the usefulness of bioinspired algorithms for precision control applications. The comparison of the proposed methodology is also done with other studies during different operating conditions. The results show that intelligent optimizationbased control in industrial systems is feasible, which aids in the creation of reliable and flexible automation solutions.
Abstract
DC motors are frequently utilized in industrial and automation applications where accurate speed control is crucial. Although conventional Proportional-Integral-and Derivative [...]
- 15
- read
Efficient Mean Estimation Using Repeated Measurements in PPS Sampling with Scientific Applications
M. Azeem, S. Hussain, N. Salahuddin, F. Idrees

Rev. int. métodos numér. cálc. diseño ing. (2026). Vol. Online First, 128

Abstract
Research studies in many scientific disciplines need efficient estimation methods for estimating the parameters of quantitative variables, including, but not limited to, tensile strength, wind speeds, air quality, and temperature, etc. Statisticians employ a sampling design to get a random sample and estimate the population means based on the observed sample. If the units of a finite population have different selection probabilities, unequal probability methods of sample selection are used. The existing unequal probability sampling methods allocate probabilities proportional to size (PPS) to the population units by using a one-time measurement approach. Memory– type estimation methods, on the other hand, use multiple measurements and provide more precise estimates than the traditional estimators. This research study introduces a novel memory-type estimator using a PPS sampling design. Various properties of the suggested mean estimator are analyzed, and the efficiency conditions are derived. A few real-world data sets have been used from previous studies to evaluate the performance of the suggested and competing mean estimators. Our comparative study suggests that the suggested memory-based estimator performs much better than the competing estimators, which means that the suggested memory-type estimator is an appropriate estimator for application in real-life sample surveys.
Abstract
Research studies in many scientific disciplines need efficient estimation methods for estimating the parameters of quantitative variables, including, but not limited to, tensile [...]
- 5
- read
Enhancing Few-Shot Text Classification with Parameter-Efficient Tuning of Large Language Models
M. Zhao, Y. Sun, X. Fan, Y. Tian

Rev. int. métodos numér. cálc. diseño ing. (2026). Vol. Online First, 129

Abstract
Traditional few-shot text classification models focus only on label prediction and cannot extract structured information such as entities or events, limiting their usefulness in real-world, semantics-driven tasks. They also rarely use external knowledge or parameter-efficient tuning, leading to shallow representations and weaker performance. To address this, this paper proposes a knowledge-aware multi-task framework that integrates few-shot classification with entity and event extraction. A single BERT encoder with IA3 adapters enables efficient tuning, while semantic triples extracted via spaCy and aligned with WordNet and ConceptNet are encoded using TransE. A BiLSTM captures sequential context and a softmax decoder performs token-level prediction. Experiments show strong results—97.97% accuracy, 98.00% precision, 97.95% recall, and 97.96% F1—surpassing state-of-the-art baselines. Ablation studies confirm the value of the knowledge-enhanced, multi-step design, demonstrating suitability for lowresource, knowledge-centric applications.
Abstract
Traditional few-shot text classification models focus only on label prediction and cannot extract structured information such as entities or events, limiting their usefulness [...]
- 2
- read
AI-IoMT Synergy: A Real-Time Framework for Automated Urinary Tract Infections (UTI) Detection Based on Urine Sediments
A. Ibrahim, M. Ahmed, I. Ame, C. Nwekwo, F. Hassan, S. Asir, S. Tackie, F. Al-Turjman, J. Idoko

Rev. int. métodos numér. cálc. diseño ing. (2026). Vol. Online First, 130

Abstract
A Urinary Tract Infection (UTI) is characterized by an infection affecting the urinary system, including the kidneys, bladder, urethra, and ureters, with clinical presentations including pyelonephritis, cystitis, and urethritis. While conventional diagnostic methods such as urinalysis and urine culture and sensitivity (C&S) remain widely used, they are limited by subjectivity, time-intensive processing, susceptibility to contamination and risks of false-positive or false-negative results. This study proposes a comprehensive deep learning (DL) and Internet of Things (IoMT) framework to automate the real-time detection and classification of UTIs using microscopic urine sediment images. The study employed 2 datasets (A and B). Dataset A, a clinically acquired dataset, comprises of 3345 images (normal, erythrocytes, fungi and pus) and Dataset B, a publicly accessible data comprises of 5377 images and 26,419 cropped microscopic images corresponding to 7 classes (casts, crystals, erythrocytes leukocytes, epithelial cells, epithelial nuclei, mycetes). A two-stage classification approach was implemented: a binary task to distinguish urine sediments from normal cases, followed by a multiclass task (clinical data and online data) to identify the specific infection type. All images underwent pre-processing, including normalization, resizing, noise removal, and augmentation to enhance feature visibility and model generalizability. The data were partitioned into training (65%), validation (25%), and test (10%) sets. Six state-of-the-art DL architectures, including ResNet50-V2, ResNet101-V2, Inception-V3, XceptionV2, Inception-ResNet-V2, and VGG19 were fine-tuned using transfer learning and evaluated using accuracy, precision, recall, F1-score, and confusion matrices. The proposed models were uploaded to a website to enable realtime detection (accessible via this link: https://uticlassification.app/). The proposed pipeline demonstrated strong performance in both classification tasks, underscoring the potential of deep learning as a reliable, rapid, and reproducible tool for automated urine sediment identification in clinical practice.
Abstract
A Urinary Tract Infection (UTI) is characterized by an infection affecting the urinary system, including the kidneys, bladder, urethra, and ureters, with clinical presentations [...]
- 2
- read
A New Green ETL Optimization Technique for Sustainable Data Warehousing Environment: A Scalable Energy Efficient Solution
E. Gueddoudj, A. Attia, A. Almaktoom, K. Othman, A. Noorwali, E. Zafar, A. Mohamed

Rev. int. métodos numér. cálc. diseño ing. (2026). Vol. Online First, 131

Abstract
Energy consumption is an emerging concern in many fields, including information technology, particularly in data warehousing environments where Extract, Transform, Load (ETL) processes account for a significant portion of operational costs and resource utilization. Despite advances in hardware-level optimization, limited attention has been given to software-level energy optimization within ETL workflows. In reality, software is as important as hardware, and it is equally responsible for a decrease or increase in energy consumption. We argue that for modern applications in which energy efficiency is a priority, ETL processes should be optimally designed. This paper addresses this gap by proposing a Green ETL (GETL) approach designed to reduce energy consumption while maintaining high performance. The proposed method integrates transformation-level reuse through a shared transformation cache and adaptive parallel execution using Apache Spark, enabling efficient resource utilization and elimination of redundant computations. The proposed GETL removes unnecessary calculations and reduces both execution time and energy consumption, without requiring any modifications to the underlying data processing engines. To evaluate the effectiveness of the proposed GETL, experiments were conducted using the Transaction Processing Council Data Integration (TPC-DI) benchmark across multiple scale factors. The results demonstrate that the proposed approach achieves an average energy reduction of approximately 30%, with higher savings observed under large-scale workloads. In addition, GETL improves execution efficiency and reduces resource utilization compared to a traditional Spark-based ETL implementation.
Abstract
Energy consumption is an emerging concern in many fields, including information technology, particularly in data warehousing environments where Extract, Transform, Load (ETL) [...]
- 18
- read
Computational Framework for AI-IoT Integration in Brain Tumor Detection: Numerical Modeling, Algorithmic Optimization and Real-Time Deployment
F. Ndah Tah, M. Lawal, A. Ibrahim, S. Asir, P. Pwavodi, C. Nwekwo, S. Kaba, B. Duwa

Rev. int. métodos numér. cálc. diseño ing. (2026). Vol. Online First, 132

Abstract
The integration of Artificial Intelligence (AI) and the Internet of Medical Things (IoMT) presents significant computational and engineering challenges, especially in the deployment of real-time diagnostic systems. Therefore, this study proposed a numerically optimized and computationally efficient framework that combines deep learning (DL) architectures with IoMT-enabled deployment for the automated detection and classification of brain tumors using Magnetic Resonance Imaging (MRI). The methodology revolves around rigorous numerical preprocessing techniques, including normalized resizing, advanced data augmentation, and computationally efficient feature extraction via both custom and pre-trained Convolutional Neural Networks (CNNs). The key contributions of this study are tailored toward the evaluation of algorithmic performance beyond diagnostic accuracy, incorporating metrics such as model convergence, inference latency, memory footprint, and numerical stability under varied input conditions. The proposed AI-IoMT framework, known as I-BRAINDETECT, implemented as a web-based IoMT platform, demonstrates how algorithmic design and computational modeling can address the limitations of real-time medical image analysis. Performance evaluation and comparative analysis have shown that EfficientNetB0 and DenseNet121 achieved optimal performance in binary classification with 98.5 ± 0.202% accuracy, while ResNet50 excelled in multiclass classification with 95.4 ± 1.01% accuracy, both within a computationally constrained IoT environment. Validation of the trained models on an external dataset (Figshare) has shown that DenseNet121 achieved the best result with 93.99% accuracy. This work underscores the necessity of numerical robustness and algorithmic efficiency in bridging AI and IoT for scalable biomedical engineering solutions.
Abstract
The integration of Artificial Intelligence (AI) and the Internet of Medical Things (IoMT) presents significant computational and engineering challenges, especially in the [...]
- 2
- read
AdaptiveTrack: An Environment-Aware and Confidence-Refined Framework for Online Multi-Object Tracking
S. Khan, P. Zhang, M. KAMAL, H. Samkari, M. Allehyani, H. Mostafa

Rev. int. métodos numér. cálc. diseño ing. (2026). Vol. Online First, 133

Abstract
sup>Multi-object tracking (MOT) remains challenging in conditions involving occlusion, small objects, rapid motion, and crowding, wherein the accuracy of detection and the quality of association degrade simultaneously. We propose AdaptiveTrack, an online MOT framework featuring a closed-loop, confidence-aware association and recovery design: CSI-IoU adapts spatial overlap based on confidence and scale, EAMO refines similarity through density, velocity, and scale cues, and DCR updates detection confidence utilizing association context before NMS and assignment. A lightweight continuity module additionally preserves identities during missed detections. On MOT17/MOT20, AdaptiveTrack achieves HOTA 67.33 and 66.73, MOTA 82.55 and 78.30, and IDF1 83.20 and 82.57, operating at 23.5 FPS.
Abstract
sup>Multi-object tracking (MOT) remains challenging in conditions involving occlusion, small objects, rapid motion, and crowding, wherein the accuracy of detection and [...]
- 58
- read
Carbon-Aware Last-Mile Delivery Optimization using Sparrow search algorithm and graph neural network risk assessment
J. Xu, L. Yuan, X. Du

Rev. int. métodos numér. cálc. diseño ing. (2026). Vol. Online First, 134

Abstract
With the advancement of global carbon neutrality strategies and explosive growth in e-commerce, urban last-mile delivery faces multiple challenges in balancing economic benefits, environmental impact, and risk management. Traditional optimization methods struggle to simultaneously address multi-objective trade-offs, network topological dependencies, and small-sample risk prediction problems. This study proposes a hybrid intelligent framework integrating an Improved Sparrow Search Algorithm (ISSA) with a Meta-Learning Graph Convolutional Network on Prototype Space (ML-GCNPS) for carbon-aware delivery optimization and risk assessment. ISSA-NSGA-III generates high-quality initial populations through Tent chaotic mapping, designs an adaptive periodic convergence factor to dynamically balance exploration and exploitation, and enhances global search capability by integrating Lévy flight with Elite Opposition-Based Learning (EOBL), achieving multi-objective collaborative optimization through embedding in the NSGA-III framework. ML-GCNPS designs a feature extraction network to extract discriminative features from multi-modal node data, explicitly models class centers through prototype space embedding to enhance small-sample generalization, constructs an adaptive Vertex-to-Edge (V2E) network to dynamically infer edge weights and capture risk propagation paths, and employs a two-layer graph convolutional architecture for sufficient information propagation. Experiments on the Kaggle Supply Chain Management dataset and Carbon Monitor risk dataset demonstrate that compared to standard SSA, ISSA-NSGA-III improves total cost, carbon emissions, and resource utilization by 14.0%, 14.2%, and 15.4%, respectively, with Pareto front quality improved by 28.5%. ML-GCNPS achieves an AUPRC of 0.850 (standard deviation 0.005) and a Macro Fl-Score of 0.850 (standard deviation 0.005) in 5-way 1-shot scenarios, reduces the False Negative Rate (FNR) to 0.080 (standard deviation 0.003), and achieves a Weighted Average Cost (WAC) of 45, significantly outperforming baseline methods such as ProtoNG and MAML-GNN (paired t-test, p less than 0.01 for AUPRC and FNR versus the second-best baseline GAT-FSL). Ablation experiments validate the necessity of the meta-learning framework, graph convolutional structure, V2E network, and prototype space embedding, while alternative design comparisons demonstrate the superiority of the technical choices. While the individual algorithmic components (Tent chaotic mapping, Lévy flight, EOBL, prototypical networks, and GCN) are established techniques, the principal contribution of this study líes in their systematic integration into a closed-loop optimization-assessment-feedback decision framework, where graph structure serves as an information bridge connecting delivery optimization with risk prediction. This study provides a teclmical solution for smart city logistics and offers theoretical basis and practica! guidance for sustainable delivery under carbon neutrality goals. All reported improvements over baseline methods are statistically significant across all evaluation metrics (paired t-test or Wilcoxon rank-sum test, p < 0.001
Abstract
With the advancement of global carbon neutrality strategies and explosive growth in e-commerce, urban last-mile delivery faces multiple challenges in balancing economic benefits, [...]
- 1
- read
Modulating Early-life Risk without Breaking Weibull Structure: An Odds-Based Weibull Model for Engineering Failure-Time Data
A. Ahmadini, M. Elwahab, M. Elgarhy, H. Aljohani, G. A. Marei

Rev. int. métodos numér. cálc. diseño ing. (2026). Vol. Online First, 135

Abstract
The classical Weibull distribution lacks flexibility for nonlinear or early- life failure behaviors. We present a new three- parameter generalized Weibull (NGW) distribution using a probability- based generator. The NGW preserves the monotonic Weibull hazard structure by adding a parameter that controls for early- life hazard and cumulative curvature. We derive its key properties (density, survival, hazard, quantiles, moments), estímate the parameters using maximum likelihood and Bayesian methods, and perform simulations. Application to engineering failure data shows that the NGW offers a competitive fit compared to several Weibull- type extensions, with a parsimonious and analytically tractable structure.
Abstract
The classical Weibull distribution lacks flexibility for nonlinear or early- life failure behaviors. We present a new three- parameter generalized Weibull (NGW) distribution [...]
- 1
- read
Optimization of Artificial IntelligenceDriven Evolutionary Algorithms for Complex Engineering Problems
P. Jia, F. Zhang

Rev. int. métodos numér. cálc. diseño ing. (2026). Vol. Online First, 136

Abstract
Currently, technologies such as convolutional neural network (CNNs) and deep Q network (DQNs) are undergoing intensive research and rapid development, driving vigorous advancement in the field of artificial intelligence. Nevertheless, there is still room for improvement in addressing practical industrial problems and enhancing learning efficiency and accuracy. To address the core challenges of traditional evolutionary algorithms (EAs) in complex optimization problems, such as insufficient scalability, limited environmental adaptability, and low computational efficiency, this paper proposes an evolutionary algorithm optimization framework (DLRL-EAF) that fuses deep learning and reinforcement learning. To verify the effectiveness of the proposed method, six standard test functions (Sphere, Rastrigin, Griewank, etc.) and three practical engineering optimization problems (mechanical parts design, logistics path planning, photovoltaic array layout) are selected for comparison experiments. The performance of DLRL-EAF is evaluated using the standard genetic algorithm (SGA), the particle swarm optimization algorithm (PSO), and the adaptive genetic algorithm (AGA). Experimental results show that DLRLEAF improves the accuracy of optimal solutions by an average of 23.6%, accelerates iterative convergence by 31.2%, demonstrates greater stability in high-dimensional, complex problems, and improves scalability by more than 40%. At the same time, the proposed method significantly reduces the time and resource costs of problem-solving in practical engineering applications and demonstrates its practical value in industrial settings.OPEN ACCESS Received: 27/12/2025 Accepted: 26/03/2026
Abstract
Currently, technologies such as convolutional neural network (CNNs) and deep Q network (DQNs) are undergoing intensive research and rapid development, driving vigorous advancement [...]
- 0
- read
MIMTP: Mamba-Driven Interaction-Aware Multi-Modal Trajectory Prediction for Autonomous Driving
J. Li, L. Wang, J. Pei

Rev. int. métodos numér. cálc. diseño ing. (2026). Vol. Online First, 137

Abstract
Accurate prediction of future vehicle trajectories is essential for ensuring safety and reliable decision-making in autonomous driving systems. However, existing deep learning-based approaches exhibit several limitations. Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) struggle to effectively model long-term temporal dependencies and complex agent interactions, while Transformer-based architectures often suffer from high computational complexity and limited efficiency. To overcome these challenges, this paper proposes an efficient Mamba-based feature extraction framework for jointly encoding vehicle trajectories and map information. By leveraging state-space modeling and a selective scanning mechanism, the proposed approach effectively captures longrange dependencies and enhances the representation of complex traffic behaviors. Specifically, raw scene data are first normalized and embedded into a unified feature space. A Mamba Encoder is then employed to extract high-level features from historical vehicle trajectories and map elements. Subsequently, Vehicle-Vehicle and Vehicle-Map interaction modules are introduced to explicitly model dynamic interactions among traffic participants and between vehicles and the surrounding map. The resulting high-dimensional features are further fused using an additional Mamba Encoder, while a Global Interaction Module is designed to capture scenelevel dependencies. Finally, a Gated Recurrent Unit (GRU) decoder generates multi-modal future trajectory predictions. Experimental results on the Argoverse 1 dataset demonstrate that the proposed method achieves superior performance in terms of minADE, minFDE, and minMR, while maintaining high computational efficiency.OPEN ACCESS Received: 28/01/2026 Accepted: 16/04/2026
Abstract
Accurate prediction of future vehicle trajectories is essential for ensuring safety and reliable decision-making in autonomous driving systems. However, existing deep learning-based [...]
- 0
- read
Arctan Power Half-Logistic Model: A Bayesian Approach to Progressively Censored Engineering Data
A. Hassan, M. Elwahab, M. Elgarhy, H. Alqahtani, R. Mohamed

Rev. int. métodos numér. cálc. diseño ing. (2026). Vol. Online First, 138

Abstract
The motivation behind the creation of new statistical models is primarily driven by the need to accurately describe complex data and related phenomena. This article introduces the arctan power half logistic distribution, a new and more flexible extension of the power half logistic distribution. The proposed model’s hazard rate function is highly versatile, capable of displaying decreasing, J-shaped, or reversed J-shaped patterns. We derive its key statistical properties and investigate its application to progressively Type-II censored data. Parameter estimation is conducted using both maximum likelihood and Bayesian frameworks, the latter incorporating informative and non-informative priors across multiple loss functions. Given the analytical intractability of the posterior distributions, we employ Markov Chain Monte Carlo techniques for numerical approximation. Monte Carlo simulations demonstrate that Bayesian point and interval estimates generally outperform frequentist approaches, maintaining coverage probabilities near 95%. Finally, the model’s superiority is validated using a real-world engineering dataset, where it consistently outperforms several established competing distributions.OPEN ACCESS Received: 21/02/2026 Accepted: 20/04/2026
Abstract
The motivation behind the creation of new statistical models is primarily driven by the need to accurately describe complex data and related phenomena. This article introduces [...]
- 10
- read
Dynamic Multi-Objective Collaborative Optimization of Cement Combined Grinding Based on Cooperative Game and Temporal Awareness
D. Ju, X. Ma, R. Zhang, Q. Zhang, X. Wang, Z. Liu

Rev. int. métodos numér. cálc. diseño ing. (2026). Vol. Online First, 139

Abstract
To address the multi-objective collaborative optimization of quality, energy consumption, and yield under dynamic conditions in the Portland cement combined grinding process, this paper proposes a novel algorithm, CGDS-LTL, based on cooperative game theory and temporal perception. First, a hybrid temporal model combining Linformer, TCN, and LSTM was developed to dynamically track process conditions in the Portland cement combined grinding process. Second, an optimization objective function was established, and a cooperative game theory framework was introduced to address the challenge of achieving multi-objective optimization, which could not be effectively solved with a single paretooptimal solution. Meanwhile, volatility metrics were used to quantify the adjustment range of operational variables, allowing for the dynamic optimization of decision constraints. This approach mitigated the deviation of the pareto front from current decision settings caused by high population randomness, ultimately identifying the optimal solution for the multiobjective collaborative optimization problem. Finally, experiments using real production data from a Portland cement plant demonstrated that, compared with NSGA-II and C-TAEA, the proposed method improved the hypervolume indicator by 95% and 33.3%, respectively, indicating a more uniform solution distribution and better convergence. This demonstrated the interpretability and effectiveness of the proposed framework for dynamic multi-objective optimization in Portland cement combined grinding.OPEN ACCESS Received: 14/04/2026 Accepted: 21/05/2026
Abstract
To address the multi-objective collaborative optimization of quality, energy consumption, and yield under dynamic conditions in the Portland cement combined grinding process, [...]
- 3
- read

Volume 42

Volume 41

Volume 40

Volume 39

Volume 38

Volume 37

Volume 36

Volume 35

Volume 34

Volume 33

Volume 32

Volume 31

Volume 30

Volume 29

Volume 28

Volume 27

Volume 26

Volume 25

Volume 24

Volume 23

Volume 22

Volume 21

Volume 20

Volume 19

Volume 18

Volume 17

Volume 16

Volume 15

Volume 14

Volume 13

Volume 12

Volume 11

Volume 10

Volume 9

Volume 8

Volume 7

Volume 6

Volume 5

Volume 4

Volume 3

Volume 2

Volume 1

Submit a paper

editors

Editorial board

information

About this publication

Instructions for authors

Publication Ethics

Open access

Contact

special issues

View special issues