Applied AI letters最新文献

{"title":"Detection of Bangla AI-Generated Texts Using a Quantum Kernel Support Vector Machine","authors":"Md. Siam Ansary","doi":"10.1002/ail2.70051","DOIUrl":"https://doi.org/10.1002/ail2.70051","url":null,"abstract":"<p>Machine-generated text is increasingly hard to distinguish from human writing, raising concerns for academic integrity, journalism and information trust, especially for low-resource languages such as Bangla, where detection tooling lags far behind English. This paper presents, to the best of our knowledge, the first application of a quantum-kernel Support Vector Machine (QSVM) to detecting AI-generated Bangla text. On a class-balanced Bangla dataset spanning six genres (newspaper articles, scientific abstracts, emails, poems, short stories and office orders) that is strongly imbalanced across genres, we extract BanglaBERT contextual embeddings, reduce them to eight principal components and map each sample onto an 8-qubit Hilbert space with an angle-embedding feature map and a ring of entangling CZ gates. The fidelity between mapped states forms a quantum kernel that is passed to a classical SVM. On a held-out test split, the QSVM attains 95.0% accuracy, 95.0% F1-score and 0.989 ROC-AUC. Under the same 5-fold stratified cross-validation protocol applied to all models, it achieves 95.2% (±2.8%) mean accuracy, compared with 95.0% (±2.0%) for Logistic Regression and 93.8% (±2.4%) for an RBF-kernel SVM on identical features and 85.8% (±4.1%) for a Variational Quantum Classifier (VQC). Replacing BanglaBERT with TF-IDF features lowers the QSVM's cross-validated accuracy to 93.7% (±2.7%). Within the specific configurations evaluated, the QSVM was more accurate and less variable than the single VQC architecture tested; the experiments do not identify the cause of this gap. Per-genre results are reported alongside the aggregate metrics. These results provide a first quantitative benchmark for quantum-enhanced Bangla AI-text detection and indicate that the QSVM is competitive with, rather than superior to, strong classical baselines.</p>","PeriodicalId":72253,"journal":{"name":"Applied AI letters","volume":"7 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ail2.70051","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149205481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI-Powered Personalization Across Digital Ecosystems: A Trust-Centric Perspective on Intelligent, Ethical, and Adaptive User-Centric Systems","authors":"Mohd Munazzer Ansari,&nbsp;Shailendra Kumar,&nbsp;Umair Tariq,&nbsp;Md Belal Bin Heyat","doi":"10.1002/ail2.70044","DOIUrl":"https://doi.org/10.1002/ail2.70044","url":null,"abstract":"<p>Personalization based on Artificial Intelligence (AI) has become a paradigm shift in user-focused experiences in various digital ecosystems. We comprehensively and systematically discuss personalization methods through AI in the main domains including e-commerce, healthcare, education, entertainment, and finance. The current paper critically examines the basic techniques such as collaborative filtering, content-based filtering, hybrid recommendation methods, deep learning architectures, natural language processing (NLP), and reinforcement learning for their use in modeling complex user behavior and delivering personalized, context-aware recommendations. We propose a clear conceptual framework that visualizes the end-to-end personalization pipeline, from data collection to user profiling, training, real-time inference and feedback for optimization. Furthermore, the research uses mathematical concepts like a factorization of matrices and optimization methods to show how today's recommendation systems can be scaled and predicted. A real-world analysis is also explored, providing real-world benefits in user engagement, conversion rates and decision support systems. Besides technical improvements, this work also covers the key issues related to AI-based personalization, such as data privacy, security, bias in algorithms, and fairness. This study highlights the importance of the inclusion of ethical AI principles such as transparency, explainability, and user control in order to deploy AI responsibly. New trends such as explainable AI, cross-domain personalization and generative AI-based adaptive systems have also been explained, outlining the future of research. Overall, this research offers a holistic perspective, by bridging the technical meaning and ethical concerns, and offers valuable insights to the researchers, developers and industry practitioners aiming at designing scalable, intelligent and reliable personalization systems in future digital environments.</p>","PeriodicalId":72253,"journal":{"name":"Applied AI letters","volume":"7 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ail2.70044","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149146263","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intergenerational Green Artificial Intelligence Governance: Operationalising Environmental Accountability in Sustainable Artificial Intelligence Systems","authors":"Parul Shukla,&nbsp;Jackson Simango Magoge,&nbsp;Ishita Chatterjee,&nbsp;Praygod J. Mbilinyi,&nbsp;Malavika Nandivelugu","doi":"10.1002/ail2.70038","DOIUrl":"https://doi.org/10.1002/ail2.70038","url":null,"abstract":"<p>Artificial intelligence is increasingly promoted as a tool for sustainable development, climate governance and resource optimisation. Nevertheless, the environmental footprint of AI systems, including energy consumption, carbon emissions, water use, hardware production and electronic waste, remains insufficiently integrated into legal and regulatory frameworks. This article doctrinally examines Green AI through Edith Brown Weiss's tripartite framework of intergenerational equity comprising conservation of options, conservation of quality and conservation of access. It argues that current AI governance frameworks remain incomplete because they focus primarily on safety, bias, transparency and human oversight while treating environmental sustainability as a secondary or voluntary concern. The article develops an Intergenerational Green AI Accountability Framework that translates intergenerational equity into practical governance indicators, including FLOPs per task, CO₂e per training run, CO₂e per inference, kWh per inference, water usage effectiveness, renewable-energy share, embodied hardware carbon, e-waste destination and equitable access to green compute. It further proposes a polycentric governance architecture, such as model-level environmental disclosure, lifecycle assessment, environmental model cards, independent audits, sustainable public procurement and equity-sensitive international cooperation. The article concludes that AI should not be regarded as sustainable merely because it is deployed for climate or development objectives. It should be considered sustainable only where its own environmental costs are measured, disclosed, reduced and fairly governed.</p>","PeriodicalId":72253,"journal":{"name":"Applied AI letters","volume":"7 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ail2.70038","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149145622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mesh Multi-Context Protocol: An Adaptive Agentic AI With Mesh Concept for A Complex Ecosystem","authors":"Achmad Ginanjar,&nbsp;Xue Li","doi":"10.1002/ail2.70041","DOIUrl":"https://doi.org/10.1002/ail2.70041","url":null,"abstract":"<p>The deployment of Agentic AI systems-autonomous agents powered by large language models (LLMs) - has exposed critical vulnerabilities in multi-domain enterprise environments, with recent incidents including autonomous production database deletions highlighting fundamental architectural limitations. While frameworks such as the Multi-Context Protocol (MCP) enable LLMs to access multiple data sources, they lack domain specialization, fault isolation, and federated governance mechanisms necessary for safe enterprise-scale deployment across heterogeneous legacy systems. This paper introduces the Mesh Multi-Context Protocol (MMP), a novel framework synthesizing Agentic AI capabilities with mesh topology principles to address these limitations. MMP contributes five key innovations: dynamic node management, domain-specialized nodes, legacy system integration, lightweight operation and federated multi-node topology. By treating each domain as an autonomous node, MMP enables safe cross-organizational coordination while maintaining data sovereignty and preventing systemic failures. Unlike existing approaches requiring large foundation models and centralized orchestration, MMP supports lightweight domain-specific language models with incremental adoption pathways suitable for air-gapped, highly regulated environments including healthcare, government, and financial services. Through comprehensive architectural analysis, we demonstrate how MMP addresses fundamental challenges of deploying autonomous AI agents in complex ecosystems where privacy preservation, regulatory compliance, and operational resilience are paramount, establishing the theoretical foundation for empirical validation in real-world system-of-systems scenarios.</p>","PeriodicalId":72253,"journal":{"name":"Applied AI letters","volume":"7 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ail2.70041","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sentiment Analysis of Imbalanced Dataset Through Data Augmentation and Generative Annotation Using DistilBERT and Low-Rank Fine-Tuning","authors":"Hossein Nekkouei Nasrabadi,&nbsp;Mohammad Hossein Moattar","doi":"10.1002/ail2.70043","DOIUrl":"https://doi.org/10.1002/ail2.70043","url":null,"abstract":"<p>Sentiment analysis on social media data often suffers from severe class imbalance, which can negatively affect the performance of machine learning models. In this paper, we propose a framework that leverages large language models and lightweight transformer fine tuning to improve sentiment classification on imbalanced datasets. First, GPT-4, a multimodal large language model, is used to generate synthetic tweets through paraphrasing and back translation, with Italian serving as an intermediate language, to increase data diversity. In addition, GPT-4 is employed to annotate tweets with positive reasons by generating semantic counterparts to the 10 predefined negative categories in the Twitter US Airline Sentiment dataset. This process enables the creation of meaningful positive annotations derived from existing category structures, thereby improving dataset balance and interpretability. The augmented data are then encoded using DistilBERT to obtain sentence embeddings, while low rank adaptation (LoRA) is applied for efficient fine tuning with reduced computational cost. Finally, a SoftMax classifier is used to predict sentiment labels (positive, neutral, and negative). Experimental results on the Twitter US Airline Sentiment dataset—evaluated rigorously using a held-out test set and 10-fold cross-validation—demonstrate that the proposed framework achieves strong classification performance while maintaining low training complexity, highlighting the effectiveness of combining Large Language Model (LLM) based data augmentation with parameter-efficient transformer adaptation.</p>","PeriodicalId":72253,"journal":{"name":"Applied AI letters","volume":"7 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ail2.70043","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148943721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Multimodal Deep Learning Based Framework for Early and Accurate Diagnosis of Depression Using Electroencephalography and Event-Related Potential Signals","authors":"Atefeh Abedzadeh Attar,&nbsp;Mohammad Hossein Moattar,&nbsp;Yahya Forghani","doi":"10.1002/ail2.70042","DOIUrl":"https://doi.org/10.1002/ail2.70042","url":null,"abstract":"<p>Major depressive disorder significantly impacts both physical and mental health, leading to decreased emotional and cognitive functioning. The limitations of traditional methods for diagnosing depression—such as reliance on patient cooperation, subjective bias, and low accuracy—have prompted researchers to explore alternative diagnostic tools. This study presents a multimodal approach aimed at enhancing the accuracy of depression diagnosis by utilizing Electroencephalography (EEG) and Event-Related Potential (ERP) Signals. The multimodal approach which incorporates different knowledge from different data modalities can lead to more accurate and stable diagnosis while providing a tool for early detection. For the analysis of the mentioned modalities, three key feature sets including, spatial, time-frequency, and spectral features are extracted. Node2vec algorithm is used to extract spatial information from a graph representation of the EEG signals from different electrodes. Cross wavelet transformation (XWT) combined with a pre-trained AlexNet was employed to extract time-frequency features, while power spectral density (PSD) features were processed by a temporal-separable convolutional network (TSCN) to extract spectral features. These features were then classified separately using Gated Recurrent Unit (GRU) and Transformer models to compare their effectiveness in depression diagnosis. The data which is experimented in this article is extracted from the Multi-modal Open Dataset for Mental-Disorder Analysis (MODMA) public database and includes signals from 3 and 128 electrodes. The results show that the GRU model outperforms Transformer and achieves k-fold cross-validation accuracies of 70.91%, 81.33%, 75.33% and 91% in different datasets. To the best of our knowledge, this is the first study to integrate EEG and ERP data in a multimodal fashion using three feature sets, achieving a high accuracy of 91% with GRU-based classification. These results indicate that the combination of multimodal features and deep learning can help improve the accuracy of depression diagnosis and develop effective assistive tools in this field.</p>","PeriodicalId":72253,"journal":{"name":"Applied AI letters","volume":"7 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ail2.70042","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148943525","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multimodal Video Summarization Using Vision-Language Embeddings and Hierarchical Temporal Modeling","authors":"Saadman Sakib,&nbsp;Kaushik Deb","doi":"10.1002/ail2.70039","DOIUrl":"https://doi.org/10.1002/ail2.70039","url":null,"abstract":"<p>Video summarization aims to produce concise representations of videos by selecting the most informative frames or shots. Existing methods predominantly rely on unimodal visual features extracted from convolutional neural networks, overlooking the rich semantic information that natural language can provide. In this paper, we present an integrated multimodal video summarization framework that makes two tightly coupled contributions. Initially, we construct a semantically enriched multimodal dataset by augmenting standard video summarization benchmarks (SumMe, TVSum, OVP, and YouTube) with BLIP-2-generated frame-level captions and CLIP-based aligned visual–textual embeddings, producing four feature variants—Image-only, Text-only, Averaged fusion, and concatenated fusion—for systematic analysis of modality contributions. We validate the dataset through cross-modal retrieval, similarity gap analysis, Spearman complementarity correlation, and caption quality diagnostics, confirming that the generated captions are semantically meaningful and that the two modalities provide complementary information (average Spearman <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>ρ</mi>\u0000 <mo>=</mo>\u0000 <mn>0.53</mn>\u0000 </mrow>\u0000 <annotation>$$ rho =0.53 $$</annotation>\u0000 </semantics></math>). Finally, we develop a multi-scale temporal summarization architecture comprising a U-Net-based temporal backbone and a hierarchical transformer-style scoring head. Our best configuration achieves <i>F</i>1-scores of 59.27% on SumMe, competitive with recent state-of-the-art methods while maintaining only 28.27M parameters with linear computational scaling.</p>","PeriodicalId":72253,"journal":{"name":"Applied AI letters","volume":"7 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ail2.70039","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148785034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hybrid Graph Neural Network–Reinforcement Learning Framework for Intelligent Programmable Network Automation","authors":"Muhammad Hasnain,&nbsp;Faisal Naeem,&nbsp;Imran Ghani","doi":"10.1002/ail2.70040","DOIUrl":"https://doi.org/10.1002/ail2.70040","url":null,"abstract":"<p>Software-Defined Networking (SDN) and Network Function Virtualisation (NFV) offer the benefit of dynamic control and flexible resources that can be managed with ease. However, the growing complexity of network topologies and heterogeneous traffic patterns, combined with high-quality-of-service (QoS) demands, requires innovative routing schemes and existing AI-based optimisation procedures. Most existing methods model network structures using Graph Neural Networks (GNNs) or implement Reinforcement Learning (RL) to route traffic adaptively, but rarely combine the two in a single, more representative framework. This paper proposes a hybrid GNN-RL system coupled with a cloud-based automated experimentation system to optimise topology-aware, multi-objective, and scalable programs in the network. Graph representations were created based on network flows of two heterogeneous datasets, namely NetBench and SDNFLow and a synchronised hybrid model. A normalised, multi-objective reward function that includes throughput, latency, packet loss, and a congestion penalty was proposed to address the reward imbalance, a frequent issue in RL routing. The RL component is trained and evaluated within the abstracted simulated environment and policy-derived QoS metrics are generated by routing actions. The controlled environment enables reproducible evaluation of the hybrid-GNN framework. Experimental analysis indicates that the optimised framework is more effective at QoS than standalone RL and GNN baselines. Latency was reduced by more than 70.7 ms in the original experiments to 17.7 ms and further to 9.6 ms with reward optimisation. Packet loss dropped by 6.3% to 1.49%, and throughput remained steady at 151–231 Mbps, improving over the baseline (85–88 Mbps). The coordinated training scheme enhanced convergence rate and routing stability in dynamic traffic environments. These results affirm that the combination of structural learning, adaptive decision-making, and automated evaluation on a cloud platform offers a realisable, scalable route to intelligent, autonomous, programmable network management that can be used in next-generation communication infrastructures.</p>","PeriodicalId":72253,"journal":{"name":"Applied AI letters","volume":"7 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ail2.70040","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148784809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From Idea to Implementation: Evaluating the Influence of Large Language Models in Software Development—An Opinion Paper","authors":"Sargam Yadav,&nbsp;Asifa Mehmood Qureshi,&nbsp;Abhishek Kaushik,&nbsp;Shubham Sharma,&nbsp;Roisin Loughran,&nbsp;Subramaniam Kazhuparambil,&nbsp;Andrew Shaw,&nbsp;Mohammed Sabry,&nbsp;Niamh St John Lynch,&nbsp;Nikhil Singh,&nbsp;Padraic O'Hara,&nbsp;Pranay Jaiswal,&nbsp;Roshan Chandru,&nbsp;David Lillis","doi":"10.1002/ail2.70037","DOIUrl":"https://doi.org/10.1002/ail2.70037","url":null,"abstract":"<p>The introduction of transformer architecture was a turning point in natural language processing (NLP). Models based on the transformer architecture, such as bidirectional encoder representations from transformers (BERT) and generative pretrained transformer (GPT), have gained widespread popularity in various applications such as software development and education. The availability of large language models (LLMs) such as ChatGPT and Bard to the general public has showcased the tremendous potential of these models and encouraged their integration into various domains such as software development, for tasks such as code generation, debugging, and documentation generation. In this study, opinions from 11 experts regarding their experience with LLMs for software development have been gathered and analyzed to draw insights that can guide successful and responsible integration. The overall opinion of the experts is positive, with the experts identifying advantages such as an increase in productivity and reduced coding time. Potential concerns and challenges such as risk of overdependence and ethical considerations have also been highlighted.</p>","PeriodicalId":72253,"journal":{"name":"Applied AI letters","volume":"7 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ail2.70037","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148466932","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Transformer-Based Contextual Modeling for Predicting Calories From Recipes","authors":"Md. Siam Ansary,&nbsp;Amina Brinto","doi":"10.1002/ail2.70036","DOIUrl":"https://doi.org/10.1002/ail2.70036","url":null,"abstract":"<p>Accurate estimation of calorie content from text-based recipes is a challenging and non-trivial problem in automated dietary analysis and nutrition-aware computing. Existing methodstypically rely on shallow lexical features, sentence-level embeddings, or modular regression pipelines that struggle to capture fine-grained contextual and compositional information present in culinary text. In this paper, we propose an enhanced transformer-based regression framework that leverages contextual token representations and token-level attention pooling to directly predict calorie values from unstructured recipe descriptions. Unlike stacking-based or embedding-only approaches, the proposed model is fine-tuned end-to-end, enabling task-specific adaptation of representations and explicit weighting of calorie-relevant tokens. Extensive experiments conducted using five-fold cross-validation demonstrate that the proposed model significantly outperforms traditional lexical baselines, pretrained sentence embedding methods, and the previously introduced stacking-based transformer regression framework across all evaluation metrics. The proposed model achieves lower prediction error and higher explained variance, indicating superior calibration and generalization. These findings highlight the importance of token-level modeling and attention-based aggregation for text-based nutritional prediction. The proposed framework establishes a new state of the art in text-based caloric estimation and provides a strong foundation for future research in automated nutritional analysis and intelligent dietary support systems.</p>","PeriodicalId":72253,"journal":{"name":"Applied AI letters","volume":"7 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ail2.70036","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148357958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}