Applied AI letters最新文献_第2页

Optimized Deep Learning Framework for Diabetic Retinopathy Based on Systematic Multi-Stage Transfer Learning and Predictive Risk Stratification 基于系统多阶段迁移学习和预测风险分层的糖尿病视网膜病变深度学习优化框架

Applied AI letters Pub Date : 2026-05-27 DOI: 10.1002/ail2.70035

Mujidat Jibrin, Abdsamad Benkrid

{"title":"Optimized Deep Learning Framework for Diabetic Retinopathy Based on Systematic Multi-Stage Transfer Learning and Predictive Risk Stratification","authors":"Mujidat Jibrin, Abdsamad Benkrid","doi":"10.1002/ail2.70035","DOIUrl":"https://doi.org/10.1002/ail2.70035","url":null,"abstract":"Diabetic retinopathy (DR) is a leading cause of preventable vision loss, highlighting the need for reliable and scalable diagnostic and risk assessment methodologies. This study presents an optimized deep learning framework for predictive risk stratification in DR through a systematic tuning and evaluation of six pre-trained convolutional neural network (CNN) architectures. A combined multi-source dataset of retinal fundus images was employed to support model development and generalization. Preprocessing techniques, including CLAHE-based contrast enhancement and data augmentation, were applied to improve lesion visibility and reduce inter-dataset variability. A three-stage progressive fine-tuning strategy was developed to adapt ImageNet-initialized models to retinal pathology. This strategy enables efficient feature reuse and stable convergence across all evaluated architectures. Model performance was evaluated using Accuracy, Precision, Recall, and F1-score, with EfficientNetB7 achieving the highest validation accuracy of 96% and consequently selected for risk prediction. To move beyond categorical classification, a survival-inspired encoding of DR severity was introduced to estimate a continuous risk score aligned with disease severity, enabling stratified risk assessment rather than discrete class labels. This design extends conventional DR classification toward clinically meaningful risk-based assessment. The results demonstrate strong diagnostic performance and clear risk stratification capability, underscoring the effectiveness of multi-stage transfer learning for fundus-based DR risk prediction.","PeriodicalId":72253,"journal":{"name":"Applied AI letters","volume":"7 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ail2.70035","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148094056","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}

引用次数: 0

Applied AI letters Pub Date : 2026-05-27

引用次数: 0

Applications of Artificial Intelligence (AI) in Business Entrepreneurship and Start-Ups: A Systematic Literature Review and Bibliometric Analysis 人工智能（AI）在商业创业和初创企业中的应用：系统文献综述和文献计量分析

Applied AI letters Pub Date : 2026-05-11 DOI: 10.1002/ail2.70031

Perfecto G. Aquino Jr., Mohan Kumar, Mohit Yadav, John Amoah, Jacob Muvingi, Abdul Bashiru Jibril

{"title":"Applications of Artificial Intelligence (AI) in Business Entrepreneurship and Start-Ups: A Systematic Literature Review and Bibliometric Analysis","authors":"Perfecto G. Aquino Jr., Mohan Kumar, Mohit Yadav, John Amoah, Jacob Muvingi, Abdul Bashiru Jibril","doi":"10.1002/ail2.70031","DOIUrl":"https://doi.org/10.1002/ail2.70031","url":null,"abstract":"Artificial Intelligence (AI) is transforming entrepreneurship by enabling data-driven innovation, strategic decision-making, and operational agility; however, its adoption remains uneven and fragmented due to technological, organizational, and contextual barriers. This study examines the applications, trends, and intellectual structure of AI-driven entrepreneurship through a systematic literature review and bibliometric analysis, employing the SPAR-4-SLR protocol to analyze peer-reviewed English-language articles retrieved from the Scopus database published between 2004 and 2025. The performance analysis and science mapping of 245 relevant publications was done using Biblioshiny and VOSviewer. The results demonstrate that the research output has increased exponentially since 2018 as a result of the merging of AI technologies and entrepreneurial innovation. Major AI applications have been found in marketing and customer interaction, product development and innovation, decision-making and strategy, financing, entrepreneurship education, and operational performance. The factors that support adoption include technological readiness, data-driven culture, and capability development, whereas the hindering ones are the lack of resources, the problem with data quality, and ethical and governance concerns. Thematic and key-word co-occurrence analyses demonstrate the emergent research areas of AI-enabled entrepreneurship, digital transformation, innovation, and generative AI, which highlights the increased interdisciplinarity of the domain. This study presents organized thematic taxonomy and suggests a future research paradigm, which can be of great use to researchers, entrepreneurs and policymakers who would be running AI-based entrepreneurial ecosystems.","PeriodicalId":72253,"journal":{"name":"Applied AI letters","volume":"7 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ail2.70031","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148073101","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}

引用次数: 0

Applied AI letters Pub Date : 2026-05-11

引用次数: 0

Applied AI letters Pub Date : 2026-04-27

引用次数: 0

Applied AI letters Pub Date : 2026-04-27

引用次数: 0

Cross-Method Explanation Stability Under Prediction-Preserving Perturbations in Explainable AI 可解释人工智能中保持预测扰动下的交叉方法解释稳定性

Applied AI letters Pub Date : 2026-04-27 DOI: 10.1002/ail2.70030

Muhammad Hasnain, Tooba Gul, Muhammad Fawad Ahmed, Israr Ghani, Imran Ghani

{"title":"Cross-Method Explanation Stability Under Prediction-Preserving Perturbations in Explainable AI","authors":"Muhammad Hasnain, Tooba Gul, Muhammad Fawad Ahmed, Israr Ghani, Imran Ghani","doi":"10.1002/ail2.70030","DOIUrl":"https://doi.org/10.1002/ail2.70030","url":null,"abstract":"Post hoc explanation methods include Integrated Gradients (IG), SHAP, Vanilla Gradients, and Grad-CAM, which are used to audit model decision-making in high-stakes domains. However, it remains unclear how explanations behave under prediction-preserving perturbations. This paper aims to investigate how XAI methods can be stable across different explanation methods, provided they yield the same predictions. The outcomes were derived by carrying out experiments in a very confined perturbation regime (0.01) that had no change in predicted class despite measurable divergence in explanation maps for several XAI methods using a cosine-based measure of similarity. Findings indicate that SHAP (mean = 0.6475), Vanilla Gradients (mean = 0.4647), and IG (mean = 0.3319) recorded significant variance, whereas Grad-CAM was very stable (mean = 0.0058). The cross-method analysis showed common vulnerability patterns across gradient-based and perturbation-based explainers, whereas Grad-CAM demonstrated a specific ability to be resilient. Further discussion revealed that, before prediction changes with increasing ε, explanation divergence could already have commenced, indicating that further explanation is a more sensitive measure of model vulnerability than prediction. These results indicate that the explanation's reliability is highly method-dependent and that when a particular explainer audits the case, one may be inclined to be misled. The paper presents a new criterion for robustness of cross-method explanations as a prerequisite for reliable XAI and provides empirical evidence that supports multi-explainer auditing and future defenses to promote consistency in explanations.","PeriodicalId":72253,"journal":{"name":"Applied AI letters","volume":"7 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ail2.70030","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148094757","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}

引用次数: 0

Applied AI letters Pub Date : 2026-04-20

引用次数: 0

Applied AI letters Pub Date : 2026-04-20

引用次数: 0

DepthPark: Smart, Cost-Effective Vision-Based Indoor Parking Management System Using Single Monocular Depth Estimation 深度公园：使用单目深度估计的智能，经济高效的基于视觉的室内停车场管理系统

Applied AI letters Pub Date : 2026-04-20 DOI: 10.1002/ail2.70029

Lakshay Naresh Ramchandani, Abdsamad Benkrid

{"title":"DepthPark: Smart, Cost-Effective Vision-Based Indoor Parking Management System Using Single Monocular Depth Estimation","authors":"Lakshay Naresh Ramchandani, Abdsamad Benkrid","doi":"10.1002/ail2.70029","DOIUrl":"https://doi.org/10.1002/ail2.70029","url":null,"abstract":"Urban areas increasingly face challenges due to traffic congestion and limited parking availability. Traditionally designed for outdoor spaces, parking management systems now spearhead innovative endeavors to address the unique challenges of indoor environments. Implementing smart indoor parking solutions in enclosed lots poses significant challenges, as it requires the installation of sensors in every parking space, a costly endeavor, especially in large and older facilities. To alleviate these costs, we propose harnessing visual sensor networks to develop DepthPark: a novel, cost-effective, computer vision-based parking management system that uses single monocular depth estimation for real-time indoor parking management. This system strategically positions cameras to capture license plate data during vehicle entry and exit. Additionally, it orchestrates the movement of mobile cameras on linear guides through a customized deep neural network, to ensure precise and efficient monitoring of expansive parking lots. This setup not only lowers implementation costs but can also reduce bandwidth requirements by minimizing the unnecessary transmission of frames to the server. Mobile cameras capture and log events only when they occur in the lane, and these are then processed by the server computer. The system uses simple monocular cameras, with distance measurement handled by a depth estimation-based CNN solution to estimate vehicle positions. DepthPark currently identifies two types of parking violations: occupying an unauthorized parking slot and parking across two spaces. Physical implementation of the system on an Intel Core i7-10750H processor with 16 GB RAM demonstrated high accuracy, including license number recognition accuracy of 98.31% and parking slot classification accuracy of 96%, with a throughput of 30 fps, underscoring the system's efficiency and effectiveness.","PeriodicalId":72253,"journal":{"name":"Applied AI letters","volume":"7 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ail2.70029","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148085917","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}

引用次数: 0