International Journal of Intelligent Systems最新文献

{"title":"Modelling of Switching Operation Process and Real-Time Violation Detection Method Based on Dynamic Graph Transformer","authors":"Zhi-Qiang Lin,&nbsp;Jing Yan,&nbsp;Jing-He Wen,&nbsp;Haowei Chen,&nbsp;Yong-Liang Feng,&nbsp;Haozhao Lin","doi":"10.1155/int/3348323","DOIUrl":"https://doi.org/10.1155/int/3348323","url":null,"abstract":"<p>Substation switching operation is a high-risk manual procedure where any misordering or omission may cause serious safety accidents. Existing rule engines cannot cover the diverse violation patterns induced by topology switching, and sequence-based deep models ignore electrical topology constraints and the ticket-level operation task. This paper proposes a real-time detection method that models the switching-operation process as a dynamic heterogeneous graph and encodes it with a spatiotemporal dual-channel dynamic graph Transformer. Each step triggers an incremental hard-update of graph topology, producing snapshots enriched with device state, electrical polarity, voltage level and topological position; the spatial graph-attention channel and the temporal causal Transformer channel are jointly conditioned on the operation-task label. A contrastive strategy mixing controlled violation injection with real held-out violations alleviates label scarcity; a task-conditioned multiprototype scorer captures the multimodal distribution of normal operations; a three-level risk-graded thresholding scheme aligns alarms with safety-consequence severity; and a ticket-level task-consistency check catches violations where all steps are locally correct but the ticket does not match the declared task. Experiments on 6842 tickets from 12 real substations achieve <i>F</i>1 = 87.4% (+2.0% over the best 2025 SOTA baseline), 0.6-step detection latency, 18.3-ms single-step inference, 91.2% top-3 step localisation and only 3.6% F1 drop on three unseen substations.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2026 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2026-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/3348323","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149205533","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":"Toward Intelligent and Affordable Humanoid Manipulation: A Lightweight 6-DOF Robotic Arm With Neural Inverse Kinematics and Optimized Control","authors":"Mustafa Mahmoud Elsayed,&nbsp;Mostafa Orban,&nbsp;Basem Akl,&nbsp;Kai Guo,&nbsp;Hongbo Yang,&nbsp;Mohamed Selmy,&nbsp;Mahmoud Elsamanty","doi":"10.1155/int/6164485","DOIUrl":"https://doi.org/10.1155/int/6164485","url":null,"abstract":"<p>This study presents the design and intelligent control of a lightweight and low-cost 6-DOF humanoid robotic arm developed for assistive robotic applications. The manipulator is fabricated using 3D printing technology, achieving more than 60% weight reduction with structural performance evaluated using static finite-element analysis. A comprehensive modeling framework is established, including forward and inverse kinematics (IK), 3D workspace volume analysis, and trajectory planning within the MATLAB Simscape environment. System identification is performed for each joint, achieving model fit accuracies ranging from 90.34% to 97.07%. To address the highly nonlinear IK problem, a ResNet-style neural network (IKNet) employing unit-normalized trigonometric (sin<i>q</i>_<i>i</i>, cos<i>q</i>_<i>i</i>) output encoding and forward-kinematic position loss is trained for 100 epochs on a 2,000,000-sample dataset generated via uniform joint-space sampling, adhering to a 70/15/15 train/validation/test split. On a fixed random subset of 10,000 poses drawn from the 300,000-pose held-out test set, IKNet achieves a mean position error of 0.2954 mm and a P95 error of 0.7108 mm; the near-singular subset has a mean error of 0.4896 mm according to Yoshikawa’s manipulability index. On an unseen 100 × 100 mm square trajectory, IKNet yields a mean tracking error of 1.6464 mm and an inference time of 0.0308 ms per pose (32,499 Hz). For motion control, PID controllers are optimized using three metaheuristic algorithms: genetic algorithm (GA), particle swarm optimization (PSO), and Honey Badger algorithm (HBA). Simulation and hardware evaluations demonstrate the tracking and transient performance of the proposed control framework.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2026 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2026-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/6164485","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149205445","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":"DSIQ-GEN: Automatic Generation and Classification of Data Science Interview Questions","authors":"Md. Easin Arafat,&nbsp;Fanni Barbara Császár,&nbsp;Zakarya Farou,&nbsp;Tamás Orosz","doi":"10.1155/int/1523398","DOIUrl":"https://doi.org/10.1155/int/1523398","url":null,"abstract":"<p>Domain-specific question generation and classification systems are increasingly needed in technical fields like data science for education, recruitment, and adaptive learning. However, existing large language models lack domain-specific knowledge and provide limited control over question attributes. This study develops a comprehensive framework for automatic generation and classification of data science interview questions using parameter-efficient fine-tuning (PEFT) methods. We evaluate three PEFT approaches, Low-Rank Adaptation (LoRA), P-tuning, and Prefix tuning, across 105 checkpoints on Llama-3.2-1B. LoRA achieves optimal performance with 85% diversity, 87.1% domain relevance, and only 0.9% trainable parameters. Conditional generation expands the 167-question corpus to 1011 questions (505.4% increase), achieving balanced difficulty distribution and reducing topic standard deviation from 6.9% to 2.5% in the fully merged dataset. Classification experiments show Transformers achieve 87.7% difficulty and 96.7% topic accuracy on extended data, with keyword tokenization (198 tokens) matching full vocabulary (357 tokens) while reducing training time by approximately 15%. Unsupervised clustering validates quality with 77.3% purity (+8.1 points). An independent human evaluation (<i>n</i> = 104 generated questions, 3 raters) corroborates these automatic metrics, yielding substantial inter-rater agreement (weighted <i>κ</i> = 0.602) and directly addressing the risk of circular validation inherent in classifier-only evaluation pipelines. Critical findings reveal conditioning fails below 8%–10% class representation, and topic semantic overlap reduces effectiveness. This research demonstrates PEFT as a practical solution for synthetic data generation in specialized domains under data scarcity constraints.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2026 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/1523398","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149146302","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":"BARD10: A Bangla Authorship Attribution Dataset for Analyzing the Stylistic Role of Stop-Words","authors":"Abdullah Muhammad Moosa,&nbsp;Nusrat Sultana,&nbsp;Mahdi Muhammad Moosa,&nbsp;Md Miraiz Hossain","doi":"10.1155/int/2588181","DOIUrl":"https://doi.org/10.1155/int/2588181","url":null,"abstract":"<p>Stop-word removal is a common preprocessing step in natural language processing, but in authorship attribution, frequent function words may preserve important stylistic information. For Bangla, the effect of stop-word removal remains insufficiently examined, particularly beyond literary corpora and under consistent comparisons between classical and neural models. This study introduces the Bangla Authorship Recognition Dataset of 10 Authors (BARD10), a curated dataset of 2337 postlevel texts from 10 contemporary Bangla authors, and evaluates it alongside the literary benchmark Bangla Authorship Attribution Dataset (BAAD16). We compare four model families: support vector machine (SVM), eXtreme Gradient Boosting (XGBoost), an embedding-based multilayer perceptron (MLP), and BanglaBERT, a Bangla-adapted bidirectional encoder representations from transformers (BERT) model, under stop-word–retained and stop-word–removed conditions. For the classical models, we further examine word-level, character-level, and subword-level term frequency–inverse document frequency (TF–IDF) representations. Across both datasets, sparse TF–IDF features combined with linear SVM achieve the strongest overall performance, reaching a macro-F1 of 0.9956 on BAAD16 and 0.9232 ± 0.0086 on BARD10. BanglaBERT remains competitive but does not surpass the best sparse-feature configurations. The results show that the effect of stop-word removal is not uniform across models, tokenization settings, or datasets. In particular, stop-words often preserve useful authorial information in BARD10, indicating their importance in contemporary online Bangla writing. A word-level Δ-recall analysis further shows that individual stop-word effects are heterogeneous and author-dependent. These findings suggest that Bangla stop-words should not be treated as uniformly disposable preprocessing noise and that interpretable sparse-feature baselines remain essential reference points for Bangla authorship attribution.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2026 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2026-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/2588181","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149145684","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":"Risk-Aware Route Optimization Using Minimum Spanning Tree Initialization and a Transferable Reinforcement Learning Policy","authors":"İhsan Ömür Bucak","doi":"10.1155/int/6250567","DOIUrl":"https://doi.org/10.1155/int/6250567","url":null,"abstract":"<p>Efficient route planning is a central challenge in applications such as autonomous area monitoring, infrastructure inspection, and logistics, where an agent must visit a set of locations while accounting not only for travel distance but also for spatially varying traversal risk. Classical distance-only optimizers minimize path length but are blind to such nongeometric costs. We propose a hybrid framework that integrates minimum spanning tree (MST)–based initialization with a transferable reinforcement-learning (RL) refinement policy for risk-aware routing. The MST provides a structured, low-cost initial tour; the RL agent then refines it under a multicriteria cost that combines distance and risk exposure. The key design choice is that the policy’s action-value function is linear in instance-independent, size-normalized features of a candidate edge exchange. As a result, a single 10-parameter weight vector is trained once and deployed on unseen instances and unseen problem sizes without any per-instance retraining. Across instances of 15–100 nodes (30 independent instances per size; 12 at <i>n</i> = 100), the proposed MST–RL method reduces multicriteria cost by 16%–27% over the MST baseline (<i>p</i> &lt; 10⁻³ at every size) and decisively outperforms a randomly initialized RL policy (up to 44% at <i>n</i> = 100, <i>p</i> &lt; 10⁻³), confirming the value of MST initialization. It attains cost competitive with, though not superior to, exhaustive local search and ant colony optimization while running 24–126 × faster per instance at <i>n</i> = 100, with inference time that does not grow with problem size. A reward-weight sweep demonstrates controllable distance–risk trade-offs. These properties make the method attractive for on-board, real-time deployment on resource-constrained hardware.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2026 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2026-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/6250567","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149146807","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":"MaskFused-DynamicPerception Generative Adversarial Network (MF-DPGAN): High-Quality Fabric Defect Samples Synthesis Algorithm for Improving Visual-Based Detection Performance","authors":"Shun Xu,&nbsp;Xin Wang,&nbsp;Shuyang Jin,&nbsp;Zhehao Lu","doi":"10.1155/int/6726004","DOIUrl":"https://doi.org/10.1155/int/6726004","url":null,"abstract":"<p>Deep learning–based fabric defect detection has emerged as a pivotal approach to improving textile quality consistency. However, the scarcity of high-quality defect samples remains a widespread bottleneck that limits the performance of defect detection networks. To address this issue, an innovative hierarchical-synthesis structure-based fabric defect samples generation model: the MaskFused-DynamicPerception Generative Adversarial Network (MF-DPGAN) was proposed. The dual Defect-Mask Generator (DM-G) with hierarchical attention, which decouples defect foregrounds from complex textile backgrounds, focuses on generating defect detail features and enhances the generation quality while suppressing interference from intricate background textures, endowing MF-DPGAN with flexible and controllable defect migration capability. A multilayer perception module incorporating multibranch mixed dynamic selective kernel mechanism, DSK-MixMLP block, strengthens the adaptability of MF-DPGAN to multiscale defect features and morphological variations with complex backgrounds. A composite loss function, <i>L</i>_MF-DPG, additionally integrating identity loss and mask loss, holistically regulates the balance between generated defects and background textures. Combined with DM-G and DSK-MixMLP, it achieves defect-background decoupling and high-fidelity defect synthesis. Extensive experiments demonstrate that MF-DPGAN can flexibly generate various multiscale defect samples with physical plausibility and distribution diversity, achieving a 20.87% improvement in Fréchet Inception Distance (FID). Furthermore, the dataset augmented by MF-DPGAN is energetically able to train more accuracy models and then significantly enhances the performance of defect detection networks, yielding a state-of-the-art mAP of 98.83%. The designed MF-DPGAN provides an exceedingly effective solution for roundly facilitating the promotion of defect detection performance with the conditions of scarce defect samples. Furthermore, human-centered visual perception experiments have confirmed the exceptional subjective authenticity and visual naturalness of the defect images generated by MF-DPGAN. Additional validation using a dataset constructed from real-world defect samples demonstrates that MF-DPGAN maintains competent generalization capability for fabric defect generation even in complex industrial environments.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2026 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2026-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/6726004","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149146836","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":"Enhancing Resilience in Aerospace and Defense MRO: A FIT2 Gaussian Fuzzy MCDM Framework for Enterprise Blockchain Selection","authors":"A. Çağrı Tolga,&nbsp;Biset Toprak,&nbsp;Metin Emin Aslan","doi":"10.1155/int/7461384","DOIUrl":"https://doi.org/10.1155/int/7461384","url":null,"abstract":"<p>Blockchain technology offers transformative potential for enhancing transparency, traceability, and operational resilience in aviation maintenance, repair, and overhaul (MRO). However, a critical research gap exists in evaluating enterprise-level blockchain adoption within highly regulated, security-sensitive aerospace and defense (A&amp;D) MRO ecosystems, where the strategic make-or-buy technological dilemma remains fundamentally unresolved. This study addresses this gap by proposing a novel decision making framework that integrates the Analytic Network Process (ANP) with the Finite Interval Type-2 (FIT2) Gaussian fuzzy Equivalent Uniform Annual Cost (EUAC) and Weighted Euclidean Distance-Based Approach (WEDBA). A comprehensive model comprising five main criteria, 31 subcriteria, and nine blockchain alternatives was evaluated, successfully isolating objective financial parameters through the EUAC method. Applied to a Turkish state-owned MRO enterprise operating in the A&amp;D sector, the ANP identified <i>Records Management Process</i>, <i>Flight Safety</i>, and <i>Corporate Security</i> as the most critical adoption drivers. However, to resolve the strategic conflict between cost-efficiency and data sovereignty, the integrated FIT2 Gaussian fuzzy EUAC-WEDBA methodology prioritized an internally developed enterprise blockchain alternative in the logistics and supply chain domain (A9) as the optimal solution. The findings mathematically demonstrate that bespoke in-house ledgers effectively mitigate third-party vulnerabilities and external counterfeit risks, fostering unparalleled supply chain resilience that strategically outweighs the short-term financial savings of commercial off-the-shelf solutions. This is the first study to combine these advanced uncertainty-modeling methods within a domain-specific framework, offering a highly replicable roadmap for secure and resilient digital transformation.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2026 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2026-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/7461384","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149048405","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":"Physics-Inspired Machine Learning for Nanomaterial-Based Voltammetric Biosensors: A Data-Efficient Feature Engineering Approach","authors":"Emine Sezer,&nbsp;Sinan Akgöl","doi":"10.1155/int/2157466","DOIUrl":"https://doi.org/10.1155/int/2157466","url":null,"abstract":"<p>This study introduces a physics-inspired machine learning (ML) framework for the calibration of voltammetric nanosensing platforms. By explicitly embedding electrochemical domain knowledge, specifically dynamic resistance (<i>R</i> = <i>V</i>/<i>I</i>), instantaneous power (<i>P </i>=<i> V </i>×<i> I</i>), and logarithmic kinetic descriptors, into the ML pipeline, we enable a peak-agnostic sensing paradigm that avoids manual peak selection and baseline correction. The framework is validated across three distinct nanopolymeric biosensing systems: reduced graphene oxide–incorporated molecularly imprinted polymer (rGO-MIP) nanostructures for C-reactive protein (CRP), histidine-functionalized poly(2-hydroxyethyl methacrylate-co-ethylene glycol dimethacrylate) (HEMA-co-EGDMA) nanoparticles for vitamin C, and vitamin E acetate (VEA)-imprinted poly(2-hydroxyethyl methacrylate-co-methacryloylamido phenylalanine) (HMA-co-PA) nanoparticles for vitamin E analysis. Across 13 evaluated ML algorithms, physics-inspired features yielded a real but model-dependent improvement in predictive performance, averaging an 8.7% reduction in Test root mean square error (RMSE); the benefit was most pronounced for linear and kernel-based regressors and more limited for the strongest tree-based ensembles, which already captured substantial nonlinear structure directly from raw voltage–current signals. Permutation feature importance indicated a shift in predictive attribution toward electrochemically interpretable descriptors, though collinearity among the engineered features warrants caution in attributing this shift to any single descriptor. Grouped cross-validation and prospective external validation on independently collected replicate measurements further supported the reliability of the proposed models for new, previously uncharacterized measurements within their calibrated concentration range. A comparison with classical peak-current calibration indicated that the proposed framework performs competitively with this established approach, with its principal practical advantage lying in avoiding manual peak selection and baseline correction rather than in superior raw predictive accuracy.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2026 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2026-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/2157466","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149048437","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":"Multiclass Fruit Disease and Maturity Classification Using Hybrid Deep Neural and Transformer Models With Explainable AI Techniques","authors":"Ranjith Kumar Anandan,&nbsp;Saravanan Srinivasan,&nbsp;A. Prathik,&nbsp;Jitender Tanwar,&nbsp;Sandeep Kumar Mathivanan,&nbsp;Usha Moorthy","doi":"10.1155/int/3509930","DOIUrl":"https://doi.org/10.1155/int/3509930","url":null,"abstract":"<p>The principal aim of this research work is to develop an efficient and explainable deep learning (DL) framework for the classification of fruit diseases. Timely and accurate detection of diseases in plants is essential in order to reduce the loss of crops and high-quality yields. Existing traditional methods of inspecting the crops manually are laborious and prone to errors. Most existing DL solutions are limited in the sense that they are trained on a single fruit type, depend on heavy models that are hard to use in real farm conditions, and do not explain their predictions. The proposed FruitViTNet is used to overcome these limitations by handling five fruits and sixteen disease classes in one model and by using a lightweight architecture that can be deployed on mobile and edge devices. Hence, this study aims for high classification accuracy with interpretable means obtained from explainable AI techniques so that they can be reliably used for applications in precision agriculture. The experiments were performed using public, labeled datasets of fruit diseases, namely, Apple (4 classes), Orange (3 classes), Pomegranate (2 classes), Banana (4 classes), and Papaya (3 classes), obtained from the online data sources. The dataset was divided into training (65%), validation (15%), and testing (20%) so as to ensure a balanced evaluation of the models. In this study, two pretrained convolutional neural network (CNN) models, two pretrained Transformer models, and the proposed hybrid deep transformer model were presented for plant disease classification. The evaluation framework was generated in such a way that it contained model training, 6-fold cross-validation in order to develop a robust model, and final testing. To improve explainability and trust in the results from the classification model, some Explainable AI techniques, such as Gradient-weighted Class Activation Mapping (Grad-CAM) and Local Interpretable Model-agnostic Explanations (LIME), were employed so that visual explanations of the model predictions could be made. The proposed hybrid deep transformer model showed better performance over existing CNN and Transformer background models, achieving a testing accuracy of 99.31%. The results from cross-validation also indicate that the model is stable and robust across various folds in the dataset. In conclusion, the results show that the proposed hybrid model leads to significant enhancement in the classification of fruit diseases, possibly due to the combination of local feature extraction from CNNs with global attention mechanism from Transformer models. The integration of explainable AI techniques leads to transparency in the model predictions, thereby enabling its use in real-time agriculture for applications in precision farming.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2026 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2026-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/3509930","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149048434","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":"Automated Swarm-Intelligence Approach for Auditable Disinfection in Smart IoT Environments","authors":"Dharmendra Kumar,&nbsp;Alok Kumar Shukla,&nbsp;Shubhra Dwivedi,&nbsp;Sushma Kumari,&nbsp;Sanket Mishra","doi":"10.1155/int/3491329","DOIUrl":"https://doi.org/10.1155/int/3491329","url":null,"abstract":"<p>Monitoring liquid disinfectants is essential in healthcare, food processing and water treatment, where it ensures effective pathogen elimination while maintaining compliance with safety regulations. However, classifying disinfectant-related gases and odours remains challenging because of the high dimensionality and correlated nature of gas-sensor data. Existing swarm-based feature-selection methods often suffer from limited exploration or premature convergence to local optima, particularly in such complex scenarios. At the same time, the growth of the Internet of Things (IoT) has created new opportunities to automate hygiene monitoring in pathogenic environments. To address these issues, this study proposes a binary hybrid of the grey wolf optimizer (GWO) and the genetic algorithm (GA), termed BGWOA, which selects the most informative subset of features from an array of MQ-series gas sensors while simultaneously minimizing the number of selected features. Although GWO converges rapidly, its restricted search behaviour can limit exploration and lead to premature convergence; the proposed hybrid therefore uses GWO to drive fast convergence in the early stages and GA-based mutation and selection to sustain population diversity and refine the global search in later stages. Because the precision of disinfectant identification is critical, the <i>k</i>-nearest neighbour (<i>k</i> NN) classifier is used as the wrapper fitness function to evaluate the candidate feature subsets generated by BGWOA and to identify optimal solutions. Five classical machine-learning classifiers (<i>k</i> NN, decision tree, Naïve Bayes, multilayer perceptron and support vector machine) are compared on a purpose-built disinfectant dataset, and the BGWOA-<i>k</i> NN framework consistently outperforms the individual classifiers and competing wrapper methods (GWO, PSO, BBA and GA). Across all five classifiers and five folds, BGWOA achieves a mean accuracy of 0.996 (with the BGWOA-<i>k</i> NN framework attaining an AUC and average precision of 1.00) against approximately 0.88 for the baselines. It is also the most efficient wrapper, requiring only 173.8 s versus 432.6 s for plain GWO. A nonparametric Friedman test confirms that these improvements are significant (<span></span><math></math>, 4 degrees of freedom, <i>p</i> = 0.0159), with BGWO obtaining the best average rank (1.00) among the five algorithms. Beyond accuracy, the proposed system supports auditable disinfection by promoting the consistent and correct use of disinfectants by facility personnel, thereby reducing potential health risks.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2026 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2026-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/3491329","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149048435","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}