Transactions on Machine Intelligence2821-16939120260301MultiCNKG: Integrating Cognitive Neuroscience, Gene, and Disease Knowledge Graphs Using Large Language Models11524494310.22034/TMI.2026.244943ENA.SarabadaniPh.D. in IT Engineering , Department of Computer Engineering and Information Technology, University of Qom, Qom, Iran.0000-0002-3521-1401Kh.Rahsepar FardKheirolah Rahsepar Fard
Department of Computer Engineering and Information Technology, University of Qom, Qom, Iran.0000-0001-5452-4596H.HaririDepartment of Computer Engineering, Malek Ashtar University of Technology, TehranJournal Article20251126The advent of large language models (LLMs) has revolutionized the integration of knowledge graphs (KGs) in the biomedical and cognitive sciences, effectively overcoming the limitations of traditional machine learning methods in capturing intricate semantic links among genes, diseases, and cognitive processes. This paper introduces MultiCNKG, an innovative framework that merges three distinct knowledge sources: the Cognitive Neuroscience Knowledge Graph (CNKG), containing 2.9K nodes and 4.3K edges across 9 node types and 20 edge types; the Gene Ontology (GO), featuring 43K nodes and 75K edges across 3 node types and 4 edge types; and the Disease Ontology (DO), comprising 11.2K nodes and 8.8K edges with 1 node type and 2 edge types. Utilizing advanced LLMs such as GPT-4, we perform automated entity alignment, semantic similarity computation, and graph augmentation to construct a unified, cohesive KG that interconnects genetic mechanisms, neurological disorders, and cognitive functions. The resulting MultiCNKG unified graph encompasses 6.9K nodes across 5 distinct types and 11.3K edges spanning 7 relational types, establishing a multi-layered analytical pipeline from molecular to behavioral domains. Empirical evaluations demonstrate robust framework performance, achieving an 85.20% precision rate, 87.30% recall, 92.18% coverage, 82.50% graph consistency, a 40.28% novelty detection rate, and an 89.50% expert validation score. Furthermore, link prediction benchmarks utilizing TransE (MR: 391, MRR: 0.411) and RotatE (MR: 263, MRR: 0.395) yield highly competitive performance against standard benchmarks like FB15k-237 and WN18RR. Ultimately, this integrated KG advances clinical and research applications in personalized medicine, cognitive disorder diagnostics, and data-driven hypothesis formulation within cognitive neuroscience.https://www.tmachineintelligence.ir/article_244943_aa16be04cc910a98bfc703806c161d56.pdfTransactions on Machine Intelligence2821-16939120260302A Systematic Review of Fairness-Aware and Optimization-Driven Virtual Machine Allocation Models in Cloud Computing163124494210.22034/TMI.2026.244942ENJ. TopeOlujayetanMSc ,Computer Science, Achievers University, Owo , Nigeria0009-0002-7490-5657Journal Article20251009Virtual machine (VM) allocation remains a foundational challenge in Infrastructure-as-a-Service (IaaS) cloud computing, particularly as multi-tenant environments grow in scale, heterogeneity, and complexity. Recent advancements increasingly emphasize the dual objectives of fairness and optimization, reflecting the need for equitable resource distribution without compromising system performance. This systematic review synthesizes peer-reviewed research published between 2020 and 2025, evaluating fairness-driven, optimization-driven, and hybrid VM allocation models. Following a PRISMA-aligned search strategy across IEEE Xplore, ACM Digital Library, ScienceDirect, SpringerLink, and Google Scholar, 15 high-quality studies meeting strict inclusion criteria were selected. Findings reveal that while fairness-driven models successfully reduce resource starvation and improve equity, they often incur higher makespan and computational overhead. Conversely, optimization-driven models demonstrate substantial gains in throughput, energy efficiency, and load balancing, yet frequently deprioritize fairness, leading to disproportionate resource allocation for low-priority tasks. Hybrid models have subsequently emerged as a dominant research direction, leveraging multi-objective and machine learning-based approaches to balance efficiency and equity effectively. Despite this progress, key research gaps persist, including a lack of standardized fairness metrics, limited validation using real-world workload traces, and inconsistent reporting of scalability and convergence properties. This review situates the Optimized Proportional Equity Model (OPEM) within this evolving landscape, highlighting its deterministic, fairness-centered design and potential to contribute to transparent resource allocation frameworks. The study concludes with actionable recommendations for developing next-generation allocation mechanisms grounded in rigorous evaluation, hybrid optimization, and standardized assessment.https://www.tmachineintelligence.ir/article_244942_daa2d9ff04bff2f318f06ad3a14ab27b.pdfTransactions on Machine Intelligence2821-16939120260304HGNN-SF: Heterogeneous Graph Neural Network with Gated Semantic Fusion for Robust Link Prediction324724494410.22034/TMI.2026.244944ENM. A.JavadzadeFaculty of artificial intelligence and cognitive sciences, Imam Hossein Comprehensive University, Tehran, IranM. J.Khedmati YavandFaculty of artificial intelligence and cognitive sciences, Imam Hossein Comprehensive University, Tehran, Iran0009-0000-7304-5654H.HosseiniFaculty of artificial intelligence and cognitive sciences, Imam Hossein Comprehensive University, Tehran, IranJournal Article20251215Effectively fusing heterogeneous semantic information while ensuring training stability remains a critical challenge in graph learning. This paper proposes HGNN-SF, a robust architecture designed for link prediction in dense and complex heterogeneous graphs. The core of the proposed model is a novel Semantic Fusion Layer (SF-Layer) that integrates a two-level attention mechanism. First, Intra-Type Spectral Attention incorporates spectral normalization into relation-specific attention modules to stabilize message propagation and prevent gradient explosion in high-degree, dense graph structures. Second, a Hierarchical Semantic Fusion mechanism dynamically assigns importance weights to aggregated messages from distinct relation types, enabling effective semantic integration without relying on predefined meta-paths. To regulate information flow and mitigate over-smoothing in deep heterogeneous message passing, node representations are updated using a Gated Recurrent Unit (GRU). An ablation study demonstrates that this gated update significantly outperforms conventional residual connections in preserving feature discriminability. Additionally, Hard Negative Sampling is employed during training to enhance model robustness against structurally challenging negative instances. Extensive experiments conducted on four large-scale, real-world datasets (DBLP, ACM, Amazon, and LiveJournal) demonstrate that HGNN-SF consistently outperforms strong graph neural network (GNN) and heterogeneous GNN (HGNN) baselines in link prediction tasks. Notably, on the highly challenging LiveJournal dataset, HGNN-SF achieves a Test AUC of 0.9044, confirming the efficacy of combining spectral attention and gated semantic fusion for stable, accurate representation learning in heterogeneous networks.https://www.tmachineintelligence.ir/article_244944_0fc1384eb8ee80d8988f7a1f9f91b159.pdfTransactions on Machine Intelligence2821-16939120260309Earthquake Prediction and Early Warning System Using Hybrid Random Forest and Time-Series Transformer Deep Learning Algorithms486424494610.22034/TMI.2026.244946ENS.GhanerezghMaster of Information Technology, Computer, Faculty of Electrical, Computer and Mechanical Engineering, University of Eyvanakey, Semnan, Iran0009-0000-2186-7613M.RabieiAssistant Professor, Computer, Faculty of Electrical, Computer and Mechanical Engineering, University of Eyvanakey, Semnan, Iran,0000-0001-8728-8825Journal Article20251227Earthquakes pose a catastrophic threat to human life and critical infrastructure, necessitating the development of highly accurate early warning systems. The primary objective of this research is to design an earthquake early warning framework capable of predicting both seismic magnitude and occurrence timing by integrating machine learning and deep learning architectures. In this study, a Random Forest Regression model is employed to estimate earthquake magnitudes, while a time-series Transformer algorithm is utilized to forecast occurrence times. The underlying dataset, sourced from seismic networks in Japan, underwent comprehensive preprocessing, normalization, and train-test partitioning. To predict timing, data was converted into a sequential time-series format before feeding it into the Transformer network. The designed Transformer model incorporates multi-head self-attention mechanisms, layer normalization, and aggregation modules, significantly enhancing its temporal forecasting capacity. Operationally, the Random Forest algorithm first identifies seismic events exceeding a magnitude of 5.0, after which the time-series Transformer predicts the exact occurrence window down to the minute. By combining these predictive outputs, the system dynamically generates visual warning alerts based on the forecasted severity and timeline. Empirical evaluations demonstrate strong predictive proficiency. The magnitude estimation model achieved a Mean Squared Error (MSE) of 0.0261, a Mean Absolute Error (MAE) of 0.0883, a Root Mean Squared Error (RMSE) of 0.1615, and a Coefficient of Determination (R^2) of 0.7737. For earthquake timing forecasting, the system yielded an MSE of 0.0007, an MAE of 0.0265, and an RMSE of 0.0264. Implementing this hybrid early warning system offers a vital tool for effective disaster risk management and mitigation strategies in seismically active regions.https://www.tmachineintelligence.ir/article_244946_bcdd1190d9b358891f7083975a7e73e8.pdfTransactions on Machine Intelligence2821-16939120260301Designing a Foresight Framework for Proactive Contractual Claims Management in EPC Projects in Iran’s Oil and Gas Industry: A Hybrid Approach Based on Scenario Planning, Delphi, and Causal Layered Analysis657325098310.22034/tmi.2026.250983ENR.AlmasianM.Sc. in Project and Construction Management from Noor e Touba University, Tehran, Iran and contract management specialist at Petrosaze Mobin Engineering and Development Company0009-0006-4649-8598P.NejatiB.Sc. in Civil Engineering from Barajin Azad University, Qazvin, Iran and Project Manager for Maroon 1 and 4 of the Development and Maintenance Plan for 28 Reservoirs in the Southern Oil-Prone Areas of North Drilling CompanyJournal Article20251225Contractual claims management in engineering, procurement, and construction (EPC) projects in Iran’s oil and gas industry has traditionally followed a reactive and post-event approach, whereby contract specialists primarily identify, document, and quantify claims after a dispute has occurred. This approach imposes substantial financial, time-related, and legal costs on the parties in an environment characterized by geopolitical uncertainties, exchange-rate volatility, sanctions-related constraints, and the rapid evolution of digital contract management technologies. This study aims to develop a proactive framework for claims management by drawing on the literature and tools of futures studies. To this end, a hybrid approach integrating Global Business Network (GBN) scenario planning, a three-round Delphi method, and Causal Layered Analysis (CLA) was employed. The findings indicate that the two driving forces of sanctions intensity and stability and digital maturity of contract management have the greatest influence and uncertainty regarding the future of contractual claims. Based on these drivers, four future scenarios were developed, along with a set of robust strategies, including the implementation of an integrated digital documentation system, the development of flexible contractual clauses, and the establishment of an early-warning claims monitoring team. The proposed framework can provide a practical foundation for owner and contractor companies in Iran’s oil and gas industry to transition from reactive claims management toward a proactive and foresight-oriented approach.https://www.tmachineintelligence.ir/article_250983_abded93396dcfdcbec914da17ed5295c.pdfTransactions on Machine Intelligence2821-16939120260301Comparative Evaluation of Support Vector Machine and Multiple Linear Regression for Predicting the Compressive Strength of Fly Ash-Containing Concrete748325098410.22034/tmi.2026.250984ENS. R.SalimBahramiAssistant Professor, Department of Civil Engineering, Faculty of Civil Engineering and Architecture, Technical and Vocational University (TVU), Tehran, Iran0000-0002-8208-6287M.ImaniB.Sc. Student, Department of Civil Engineering, Faculty of Civil Engineering and Architecture, Technical and Vocational University (TVU), Tehran, IranJournal Article20260114Fly ash-containing concrete has attracted considerable attention as an effective approach to sustainable concrete development due to its potential to reduce cement consumption, reuse an industrial by-product, and mitigate the environmental impacts associated with cement production. However, the complex and nonlinear relationships among mix-design constituents, concrete age, and compressive strength make accurate strength prediction challenging. This study investigates and compares the performance of a Support Vector Machine (SVM) with a Radial Basis Function (RBF) kernel and Multiple Linear Regression (MLR) for predicting the compressive strength of fly ash-containing concrete. For this purpose, a dataset comprising 471 laboratory observations with seven input variables representing mix-design parameters and concrete age was employed. The data were divided into training and testing sets, and five-fold cross-validation was performed to assess the stability and generalizability of the models. The SVM hyperparameters were optimized using grid search. The results demonstrated that SVM outperformed MLR in modeling the complex relationships governing compressive strength. Specifically, during the training phase, SVM achieved a correlation coefficient of 0.988, compared with 0.814 for MLR. The cross-validation results further confirmed the superior performance and greater stability of the SVM model. These findings highlight the potential of nonlinear machine-learning models for estimating compressive strength and supporting the design of sustainable fly ash-containing concrete.https://www.tmachineintelligence.ir/article_250984_8275abc5e60b44006f23e20d911a5f32.pdf