Background: The issue of population aging has emerged as a critical global challenge, driving the imperative for effective self-care and scalable health management solutions for older adults. Against the backdrop of the accelerating application of generative artificial intelligence (GenAI) in health care, a systematic evaluation is necessary to investigate how multimodal GenAI can support older adults in maintaining health and managing well-being. Objective: This study aimed to systematically evaluate the role, application contexts, empirical impacts, and developmental potential of diverse GenAI tools across critical geriatric health domains. Methods: A comprehensive search was executed across 11 major databases, including Web of Science, Scopus, PubMed, Medline, CINAHL, Cochrane, ACM Digital Library, IEEE Xplore, ScienceDirect, APA PsycInfo, and Google Scholar, with search transparency adhering to the PRISMA-S (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) extension. Results: A total of 28 studies met the inclusion criteria. Of the total, 82% (n=23) of the included publications were released within the last 2 years (2024‐2025). Analysis of technology revealed that over half (n=14) of the applications were based on text-driven conversational agents, while multimodal systems, leveraging generated audio, images, and sensor data, are rapidly emerging. GenAI applications were validated to support cognitive function maintenance, mental health, and chronic condition management through personalized content generation and multimodal interaction. However, current validation is primarily limited to cognitively normal, low-risk older adult populations. Persistent technical challenges include overreliance on text-based interaction, barriers in voice recognition accuracy, and suboptimal user interface adaptability. Conclusions: Preliminary evidence suggests a promising role for GenAI in enhancing older adults’ health self-management through highly personalized and multimodal interventions, particularly in cognitive and mental health support. To realize this potential and ensure equitable access, future efforts must prioritize strengthening interdisciplinary collaboration to integrate wearable technologies and edge computing, alongside establishing robust ethical frameworks to address data privacy, algorithmic bias, and the digital divide, which will be critical to building a safe, equitable, and effective environment for active aging.

The rapid development of computer vision technology has created new opportunities for industrial automation inspection systems, with online label inspection systems playing a crucial role in intelligent manufacturing. This paper focuses on the core principles of computer vision technology and analyzes its practical applications and technical implementation in label inspection. Through research on key technologies such as image preprocessing, object detection algorithms, and optical character recognition (OCR), the study proposes a high-precision, real-time system architecture for online label inspection. Performance and reliability were validated through applications in typical industrial scenarios. Results show that computer vision-based label inspection systems significantly enhance detection efficiency and accuracy while reducing the need for manual intervention, providing strong technical support for industrial intelligence. Finally, this paper discusses current technical challenges and future development directions, aiming to further advance the application of computer vision technology in industrial inspection.

BACKGROUND The issue of population aging has emerged as a critical global challenge, with effective self-care and health management for older adults representing a pivotal solution to addressing geriatric health concerns. Against the backdrop of the widespread application of generative artificial intelligence (GenAI) in healthcare and management, it is imperative to investigate how Multi-modal GenAI can support older adults in maintaining health and managing well-being. OBJECTIVE This study aims to systematically evaluate the role of GenAI in assisting older adults with health maintenance and management, comprehensively analyzing the application contexts, impacts, and developmental potential of diverse GAI tools across various health domains. METHODS This study followed the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. A comprehensive search was conducted across eleven databases (Web of Science, Scopus, PubMed, Medline, CINAHL, Cochrane, ACM Digital Library, IEEE Xplore, ScienceDirect, APA PsycInfo, and Google Scholar). A total of 26 articles were ultimately included in the study. RESULTS GenAI tools effectively contribute to cognitive function maintenance, mental health support, and health condition management through personalized content generation and multimodal interaction. However, current applications are predominantly limited to cognitively normal, low-risk elderly populations, with insufficient coverage of high-risk groups and marginalized populations. Technical challenges persist, including over-reliance on text-based interaction, barriers in voice recognition, and suboptimal interface adaptability for elderly users. Ethical concerns such as data privacy risks and algorithmic bias remain under-addressed. CONCLUSIONS GenAI’s promising role in enhancing older adults’ health self-management through personalized and multimodal interventions, particularly in cognitive and mental health support. Strengthening interdisciplinary collaboration to integrate wearable technologies and edge computing, while establishing robust ethical frameworks for data privacy and fairness, will be critical to building a safe, equitable, and effective environment for active aging.

With the rapid development of video streaming platforms and the diversification of user content consumption habits, personalized recommendation systems have gradually become a critical technology for enhancing user experience, increasing user engagement, and optimizing platform profitability. This paper systematically studies the technical architecture and application scenarios of recommendation systems in video streaming platforms, focusing on the unique challenges in handling large volumes of video data, analyzing user behavior, and delivering personalized content recommendations. By examining the overall architecture of recommendation systems, data processing, feature engineering, model design, and optimization strategies, this paper summarizes the application effects of various commonly used recommendation algorithms on video streaming platforms and explores the value of recommendation systems in these platforms through practical case studies. Additionally, this paper discusses the future challenges and potential technological breakthroughs in recommendation systems, such as deep learning and multi-modal feature fusion, reinforcement learning and real-time recommendations, as well as privacy protection and fairness research. The research findings indicate that a well-designed and optimized recommendation system can effectively enhance the depth of user content exploration and the overall activity level of the platform, providing strong support for the sustainable development of video streaming platforms.

Multimodal image analysis is a significant research direction in the field of computer vision, playing a crucial role in tasks such as image captioning and visual question answering (VQA). However, existing visual-language fusion methods often struggle to capture the fine-grained interactions between visual and language modalities, leading to suboptimal fusion results. To address this issue, this paper proposes a visual-language fusion model based on the Cross-Attention Transformer, which constructs deep interactive relationships between visual and language modalities through cross-attention mechanisms, thereby achieving effective multimodal feature fusion. The proposed model first utilizes convolutional neural networks (CNN) and pre-trained language models (e.g., BERT) to extract visual and language features separately, and then applies cross-attention modules to capture mutual dependencies in feature sequences, resulting in a unified multimodal representation vector. Experimental results demonstrate that the proposed model significantly outperforms traditional methods in tasks such as image captioning and VQA, validating its superiority in multimodal image analysis. Additionally, visualization analysis and ablation experiments further explore the contribution of the cross-attention mechanism to model performance, while discussing the model's limitations and potential future improvements.

With the rapid advancement of artificial intelligence technology, AI-enabled image recognition has emerged as a potent tool for addressing challenges in traditional environmental monitoring. This study focuses on the detection of floating objects in river and lake environments, exploring an innovative approach based on deep learning. By intricately analyzing the technical pathways for detecting static and dynamic features and considering the characteristics of river and lake debris, a comprehensive image acquisition and processing workflow has been developed. The study highlights the application and performance comparison of three mainstream deep learning models -SSD, Faster-RCNN, and YOLOv5- in debris identification. Additionally, a detection system for floating objects has been designed and implemented, encompassing both hardware platform construction and software framework development. Through rigorous experimental validation, the proposed system has demonstrated its ability to significantly enhance the accuracy and efficiency of debris detection, thus offering a new technological avenue for water quality monitoring in rivers and lakes