International Journal of Intelligent Systems最新文献

{"title":"Explainability-Aligned Reliability-Weighted Fuzzy Ensemble for Automated Cervical Cancer Classification","authors":"Süheyla Demirtaş Alpsalaz,&nbsp;Emrah Aslan,&nbsp;Yıldırım Özüpak,&nbsp;Feyyaz Alpsalaz,&nbsp;Hasan Uzel,&nbsp;Ievgen Zaitsev","doi":"10.1155/int/2931556","DOIUrl":"https://doi.org/10.1155/int/2931556","url":null,"abstract":"<div>\u0000 \u0000 <section>\u0000 \u0000 \u0000 <p>Cervical cancer remains a major global health concern, highlighting the need for computer-aided diagnostic systems that are both reliable and interpretable. Despite advances in deep learning–based cytology image classification, a gap persists in aligning model predictions with biologically meaningful explanations. This study aims to develop an explainability-aligned, sample-wise reliability-weighted fuzzy ensemble framework for cervical cytology image classification to enhance both performance and interpretability.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>The proposed framework integrates three pretrained convolutional neural network backbones—InceptionV3, MobileNetV2, and Inception-ResNetV2—within a fuzzy ensemble structure. A novel explainability metric, termed Explainable Artificial Intelligence Alignment (XAIHit), is introduced to quantitatively assess the spatial correspondence between Grad-CAM activation maps and annotated cytoplasmic and nuclear regions. The model combines calibrated confidence estimates with XAIHit to produce a per-sample reliability score that guides fuzzy aggregation, ensuring anatomically informed and statistically robust decision-making. Experiments were conducted on the SIPaKMeD dataset.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>The proposed ensemble achieved strong predictive performance, with accuracy ≈ 0.94, F1-score ≈ 0.94, and area under the curve (AUC) ≈ 0.99. Calibration metrics further confirmed model reliability, with an expected calibration error (ECE) of 0.030, a Brier score of 0.078, and a negative log-likelihood (NLL) of 0.198. The approach consistently outperformed conventional deep learning and fuzzy ensemble baselines.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>This study presents an interpretable and reliability-aware fuzzy ensemble framework that advances AI-assisted cervical cancer screening. By integrating explainability alignment and calibrated confidence into a unified reliability measure, the method fosters both diagnostic accuracy and clinical trust, marking a significant step toward safe, transparent medical AI systems. Comparable performance was also observed on an independent external validation dataset, confirming the cross-dataset generalization capability of the proposed framework.</p>\u0000 </section>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2026 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2026-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/2931556","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147566866","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fraud Detection Framework for Blockchain Finance: Tackling Arbitrage, Liquidity Exploits, and Money Laundering","authors":"Aleaddin Ozer,&nbsp;Murat Aydos","doi":"10.1155/int/3803992","DOIUrl":"https://doi.org/10.1155/int/3803992","url":null,"abstract":"<p>Blockchain technology has revolutionized numerous industries by providing decentralized, transparent, and immutable ledgers. However, its adoption is hindered by persistent security challenges, including arbitrage attacks, liquidity exploits, and noncompliance with antimoney laundering (AML) regulations. This paper proposes an enhanced framework to address these issues, combining dynamic pricing mechanisms, AI-based anomaly detection, and regulatory compliance checks within a multilayered architecture. The framework is composed of five interconnected layers: the input layer for data collection and validation, the data warehouse layer for structured data classification, the processing layer for anomaly detection and pricing adjustments, and the decision layer for transaction validation, execution, and reporting. The integration of these layers ensures robust security and compliance mechanisms, reducing system vulnerabilities while optimizing efficiency. To validate the proposed framework, we conducted simulations using real-world blockchain scenarios, including decentralized finance (DeFi) platforms and cryptocurrency exchanges. Results demonstrate significant reductions in arbitrage opportunities and liquidity risks, with improved accuracy in anomaly detection and compliance adherence. For instance, the dynamic pricing mechanism mitigated 87% of arbitrage attack attempts, while the AI-based anomaly detection achieved an 89% accuracy rate in identifying high-risk transactions. This study provides actionable insights and a scalable solution for enhancing blockchain security and trust. Future work will focus on integrating cross-chain interoperability, real-time threat intelligence, and privacy-preserving techniques to further expand the framework’s applicability. By addressing critical vulnerabilities, this research contributes to the development of secure, transparent, and compliant blockchain ecosystems, paving the way for wider adoption across industries. Unlike previous blockchain security models, our framework introduces a real-time, AI-enhanced risk assessment mechanism that dynamically updates transaction risk scores, mitigating financial threats in decentralized environments. This holistic approach provides a scalable, explainable, and adaptive security system that not only protects decentralized financial infrastructures but also aligns with emerging regulatory requirements, ensuring long-term applicability.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2026 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2026-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/3803992","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147566448","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Research on the Information Security and System Security of the Zero-Trust Framework—Taking an Intelligent Connected Vehicle Platoon as an Example","authors":"Yuhong Na,&nbsp;Yanning Wang,&nbsp;Xingxing Hua,&nbsp;Yaxing Zhang,&nbsp;Yunhu Zhou,&nbsp;Darong Huang","doi":"10.1155/int/5583362","DOIUrl":"https://doi.org/10.1155/int/5583362","url":null,"abstract":"<p>With the rapid development of artificial intelligence, in the open communication environment, interference and network attacks on intelligent terminals are more frequent. Therefore, communication security and system security issues in the intelligent platoons become hot topics. Motivated by these, the concept of zero trust was proposed. Under this communication framework, all clients are not trusted by default, and the principle of “never trust, always verify” is followed. In order to maintain communication, they need to be authenticated and authorized. This work discusses the zero-trust framework and mechanism aiming at communication security and gives the structure and module function in detail. Moreover, the impact of malicious cyber-attacks on the network is parameterized, and the safety coefficients of the full-trust and zero-trust frameworks are compared to show the effect of the zero-trust framework on information security. After that, the research studies range from information security to system security, where the effects of the zero-trust framework on terminal distribution, controller design, and system stability are studied, taking an intelligent connected vehicle platoon as an example. Finally, three examples verify the positive impact of the zero-trust framework on network information security.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2026 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2026-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/5583362","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147565012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predictive Analysis of Early Thyroid Disorders Using Integration of Data Mining and Ensemble Intelligence Approaches","authors":"Sa’ed Abed,&nbsp;Sherlin Saji,&nbsp;Mohammad H. Alshayeji","doi":"10.1155/int/6746134","DOIUrl":"https://doi.org/10.1155/int/6746134","url":null,"abstract":"<p>This study proposes a novel machine learning (ML) approach for early detection of thyroid disorders using data mining and ensemble learning techniques. By leveraging a diverse dataset—including demographic details, medical history, symptoms, and diagnostic test results—a high-precision model is developed to predict the risk of thyroid dysfunction. The methodology integrates self-adaptive stacking, weighted metafeatures, and Bayesian optimization to enhance model performance. After preprocessing, feature selection, and correlation analysis, various ensemble classifiers are trained and evaluated. Ensemble methods improve prediction accuracy by combining multiple base models, making them well suited for complex medical classification tasks. The proposed model achieved outstanding performance, with an accuracy of 99.46%, sensitivity (recall for class 1) of 99.85%, specificity (recall for class 0) of 94.83%, and an overall F1-score of 99.71%. The slight variation in class-wise F1-scores reflects the impact of class imbalance, where metrics tend to favor the majority class. Nevertheless, these metrics collectively underscore the model’s robustness in effectively identifying at-risk individuals while minimizing false positives and false negatives. Heat maps and other visualization tools were used to interpret patterns and improve model transparency. The findings support the potential of data-driven approaches to enhance early diagnosis, inform personalized treatment plans, and improve clinical decision-making. This work not only contributes to better thyroid disease detection but also advances the development of robust, interpretable, and scalable ML models for healthcare applications.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2026 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2026-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/6746134","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147564428","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Novel Intelligent Sedimentary Microfacies Identification Model Based on Limited Well-Logging Data","authors":"Tianru Song,&nbsp;Weiyao Zhu,&nbsp;Hongqing Song,&nbsp;Ming Yue","doi":"10.1155/int/6562891","DOIUrl":"https://doi.org/10.1155/int/6562891","url":null,"abstract":"<p>Sedimentary microfacies identification is fundamental for reservoir characterization, directly influencing hydrocarbon exploration and production strategies. However, traditional methods relying on core analysis, seismic interpretation, and manual well-log analysis face significant challenges: (1) high costs and limited coverage of coring data, (2) subjectivity in seismic facies interpretation, and (3) poor generalization of conventional machine learning models when trained on small datasets. To overcome these limitations, this study proposes Hopular—a novel deep learning architecture leveraging modern Hopfield networks. We validated the framework using 4000 normalized data points from 10 wells, covering eight logging parameters and five microfacies types. Evaluations across small (≤ 500 samples), medium (≤ 2000), and large (≥ 3000) datasets demonstrated robust performance, with <i>R</i>² scores of 0.704 (±0.021), 0.809 (±0.059), and 0.925, respectively. The model excels in capturing data relationships, particularly in small data regimes (11.6% <i>R</i>² improvement over ensemble methods). In summary, Hopular provides an accurate, data-efficient solution for microfacies identification and supports exploration in data-scarce settings. This work advances reservoir characterization by combining Hopfield networks’ associative memory with deep learning, offering reliable technical support for subsurface interpretation.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2026 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2026-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/6562891","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147563255","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"GCKT: Context-Aware Gating of Heterogeneous Learning Features With Transformer for Cognitive Knowledge Tracing in Intelligent Tutoring Systems","authors":"Zhifeng Wang,&nbsp;Jinyu Liu,&nbsp;Chunyan Zeng","doi":"10.1155/int/3037960","DOIUrl":"https://doi.org/10.1155/int/3037960","url":null,"abstract":"<p>With the rapid growth of online education, Knowledge Tracing (KT) has become central to adaptive learning systems. Yet existing models struggle to integrate the multidimensional and heterogeneous signals generated during learning—such as exercise attributes, response behaviors, temporal factors, and hierarchical knowledge structure. Many methods rely on naive feature concatenation or fixed weighting, limiting their ability to capture synergistic interactions among features. We propose Gated full-features Transformer Cognitive Knowledge Tracing (GCKT), a Transformer-based model with a gated fusion mechanism that dynamically integrates multiple inputs. The model first embeds exercise, response correctness, response time, and hierarchical knowledge features (topics and concepts). Topic and concept embeddings are linearly projected into a unified knowledge representation. The exercise, time, correctness, and unified knowledge embeddings are then concatenated and passed through a learnable gating network (linear layer with sigmoid) to produce context-aware importance weights. These weights are applied element-wise to adaptively scale each feature before projection into a fused representation for the sequence encoder, enabling the Transformer to more accurately model the evolution of students’ cognitive states. Extensive experiments on public datasets, including MOOCRadar and Math, show that GCKT consistently outperforms strong baselines—such as DKT, AKT, and SAINT+—on key metrics (AUC and F1), delivering robust gains across settings. The results demonstrate that dynamic, fine-grained feature fusion substantially improves KT performance and that GCKT offers a general, effective approach for modeling complex learning scenarios.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2026 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2026-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/3037960","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147562709","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Dual-Encoding Dynamic Patent Quality Assessment Network With an Application to Green Technology Patents","authors":"Xuan Wei,&nbsp;Ranran Liu","doi":"10.1155/int/1635916","DOIUrl":"10.1155/int/1635916","url":null,"abstract":"<p>Patent quality serves as a critical indicator of technological innovation and intellectual value. While existing studies predominantly frame patent quality assessment as a static classification task, this work reconceptualizes it as a dynamic multidimensional process evolving under technological and market uncertainties. We propose the Dual-channel Dynamic Patent Quality Assessment Network (DPQAN), which synergistically models intrinsic patent attributes and extrinsic influence trajectories through two novel encoders: (1) cross-sectional time-series encoding capturing annual multidimensional quality state and (2) dimensionwise evolutionary sequence encoding tracking longitudinal indicator patterns. Additionally, we investigate a dual-stage attention mechanism for performance analysis. Experiments on green technology patents demonstrate DPQAN’s superiority over baseline methods in multiyear forecasting while maintaining computational efficiency. This work bridges the gap between dynamic IP valuation and AI-driven innovation policy, offering tangible tools for sustainable R&amp;D allocation.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2026 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2026-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/1635916","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147563016","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dataset Construction and Real-Time Monitoring for Developing an Intelligent Drowning Warning Algorithm by the CamTra System","authors":"Bing Bai,&nbsp;Chen Chuan Yu,&nbsp;Yan Wu,&nbsp;Sinuo Hou,&nbsp;Wang Qin,&nbsp;Litao Zhou,&nbsp;Xiaozheng Li","doi":"10.1155/int/6348286","DOIUrl":"10.1155/int/6348286","url":null,"abstract":"<p>To solve the problem of sparse images in real-world drowning datasets, this study aims to create an intelligent system that can generate a large number of drowning datasets by optimizing AI image generation algorithms. The system will gradually be used to make up for the shortage of rare real-world drowning datasets based on the CamTra (camera tracking) System. This method is not only based on traditional AI image generation steps but also optimizes the engine framework to create more drowning datasets. For the key elements of drowning, on the one hand, different filters, especially blue and green filters, will be added to distinguish color differences between underwater and above water. On the other hand, the framework structure of the generative adversarial network (GAN), variational autoencoder (VAE), and diffusion model will be optimized to further reduce system computation. Meanwhile, the detection of drowning swimmers in the system will become clearer. It can greatly improve the performance and efficiency of drowning monitoring algorithms. The artificially generated drowning dataset generated by AI can describe different real-world drowning processes and perfectly adapt to different emergencies. This method is also applicable to dangerous behaviors that are difficult to record.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2026 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/6348286","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147562485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Feature Fusion Attention-Based Deep Reinforcement Learning for Multidepot O2O Food Delivery Route Optimization","authors":"Guangyu Zou,&nbsp;Levent Yilmaz","doi":"10.1155/int/3716055","DOIUrl":"10.1155/int/3716055","url":null,"abstract":"<p>The online-to-offline (O2O) business model has facilitated millions of daily transactions on popular online food ordering platforms. Online food delivery route planning presents a complex multidepot vehicle routing problem (VRP) with capacity limits, pickup–delivery, and time-window constraints. However, the vast volume of transactions and computational complexities of delivery routes pose significant challenges. This paper proposes a novel feature fusion attention-based deep reinforcement learning model to address such constrained routing problems. The innovative encoding and masking scheme with a self-attention-guided order relocation operator efficiently handles multidepot and multiconstraint scenarios. Additionally, incorporating self-attention with a graph neural network (GNN) framework extends existing research from static unit square environments to dynamic real road networks. Computational experiments demonstrate that our proposed route solver outperforms state-of-the-art heuristics and reinforcement learning methods regarding solution quality and computation time across unit square environments and real road networks. Exploratory analysis using real-world delivery data^a illustrates the applicability of our approach to practical online ordering platforms.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2026 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2026-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/3716055","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147569855","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Physics-Informed Deep Learning Method for Quantitative Evaluation of Artificial Precipitation Enhancement Effects","authors":"Renfeng Liu,&nbsp;Ziheng Yang,&nbsp;Jie Ouyang,&nbsp;Zhengteng Yuan,&nbsp;Chi Cheng,&nbsp;Dingdong Wang","doi":"10.1155/int/4159977","DOIUrl":"10.1155/int/4159977","url":null,"abstract":"<p>Quantitative evaluation of artificial precipitation enhancement effects remains a critical challenge in meteorological science. Traditional methods rely on idealized assumptions and control area selection, with limited applicability under complex terrain conditions. To address this problem, this paper proposes physics-informed simple video prediction (SimVP) (PiSim), a hybrid physics-informed disentangled framework designed to disentangle precipitation evolution. By employing the advection–diffusion equation (ADE) as an inductive bias within the latent space, we transform spatial comparative evaluation into a precise spatiotemporal sequence prediction task. The method adopts a dual-branch architecture: The physics branch explicitly models deterministic macroscopic motion (advection and diffusion), whereas the data-driven branch learns complex nonlinear residuals, effectively compensating for microphysical processes and local variations. Experimental results on the Hubei Province Swan radar dataset demonstrate that PiSim achieves a 5.5% improvement in MSE compared to the SimVP baseline, with pronounced advantages in heavy precipitation forecasting. Evaluation of 10 typical artificial precipitation enhancement operations shows hourly net rainfall increments ranging from 0.16 to 4.60 mm, which are highly consistent with historical records, validating the method’s effectiveness.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2026 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2026-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/4159977","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147569856","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}