درخت حوزه‌های تخصصی

Purpose : This study presents a user interface model for library websites tailored to visually impaired (VI) users, leveraging the potential of artificial intelligence (AI). Method : Through exploratory observation of 33 visually impaired users performing three real tasks on library websites, key factors affecting usability were identified. Data collection involved formal usability testing combined with the think-aloud protocol. The interfaces of four prominent Iranian library websites were analyzed. Content analysis supported by MAXQDA software was used to interpret the data, and Cohen’s kappa coefficient was employed to measure inter-coder reliability. Findings : The main findings of this study revealed that a logical webpage structure and clear descriptive headings have the most significant impact on usability. Additionally, inconsistent labeling, search and results presentation complexity, lack of interface customization options, and technical challenges were identified as major accessibility barriers for visually impaired users. AI-based solutions such as automatic error correction, intelligent voice assistants, AI-powered question answering, result clustering, smart filtering, text and image processing, summarization, and interface personalization were proposed to enhance the user experience. Overall, by integrating user feedback and cutting-edge AI technologies, libraries can create more inclusive digital environments that cater effectively to the needs of visually impaired patrons, setting a precedent for future developments in accessible information retrieval systems. Conclusion : Improving library website usability for visually impaired users requires a nuanced understanding of their specific needs. This research contributes by identifying underexplored AI-based strategies that can significantly enhance accessibility and user satisfaction. Future studies should assess the long-term effectiveness of these approaches and explore additional enhancements.

This study aims to present a novel generative AI-driven system for hyper-personalized health monitoring. Dynamic data processing, predictive modeling, and flexible learning improve real-time health evaluations. By combining weighted feature aggregation, iterative least squares estimation, and selective feature extraction, the suggested strategy makes predictions that are more accurate while using less computer power. Abnormality detection methods like adaptive thresholding and Kalman filtering provide accurate health monitoring. Attention, gradient-based optimization, and sequence learning improve health trend forecasts as the model improves. Generative AI-driven wearables outperform conventional and AI-based alternatives in many key performance tests. These evaluations include prediction accuracy (94%), real-time monitoring efficiency (93%), adaptability (92%), data integration quality (95%), and system reaction time (90 ms). These devices are safer (96%), have longer battery life (32 hours), and are simpler, more comfortable, and scalable. The results suggest that creative AI can transform personal healthcare into something more adaptable, safe, and affordable. Generative AI-powered smart gadgets are the most sophisticated means to monitor health in real time and deliver individualized, data-driven medical treatment. Future research will concentrate on improving prediction models and developing AI-driven modification approaches to make them more effective in additional healthcare scenarios.