A comprehensive large-scale biomedical knowledge graph for AI-powered data-driven biomedical research
Related Articles
Electro-spun nanofibers-based triboelectric nanogenerators in wearable electronics: status and perspectives
Electro-Spun nanofibers (ESNs), with their design flexibility, tailorable morphologies, and high surface area, are well-favored as triboelectric nanogenerator (TENG) materials for wearable electronics. Here, various aspects of ESNs-based wearable TENGs were examined. After introducing the most common TENG operating modes, an insightful overview of wearable TENG applications based on ESNs was presented. In this survey, a special attention is paid to wearable sensing, human-machine interaction, self-powered devices, and amplified energy harvesting. Efforts towards improving energy conversion efficiency, material durability, and compatibility with diverse wearable platforms were visited. Finally, a perspective based on particularly material aspect of ESNs is given, which could be insightful in tackling prevailing challenges and giving birth to new directions.
Evolutionary modeling reveals that value-oriented knowledge creation behaviors reinvent jobs
Recently, the strong artificial intelligence-based augmented capability enables the autonomous completion of traditional jobs devoid of human intervention, impacting labor markets. However, the underlying mechanisms have not been explored enough in prior research. In this research, we propose a computational model, focusing on the interplay between world knowledge networks and organizational knowledge sets, along with external labor market conditions. This model incorporates dynamic knowledge creation behaviors and is validated using a substantial dataset from a leading online recruitment platform in China, featuring over 20 million job postings and 1 million skill-related keywords. The results demonstrate that swift knowledge search and emulating knowledge within existing jobs are the main methods in the early developmental stage of organizations, accounting for about 75% of all simulation samples and forming the initial job evolution. As organizations progress, although fine-tuning the knowledge within existing jobs still remains significant, the intensity of knowledge search declines significantly, and the intensity of knowledge reuse surpasses that of knowledge search, reaching ~1.5 times its intensity during the stable phase. We also perform several parameter experiments and a case study to illustrate how jobs evolve in the labor market with different characteristics. The robustness tests demonstrate the model’s resilience across different simulation environments and organization strategies. Our study underlies the mechanisms of job evolution from the organizational level and provides empirical evidence and insights into the job evolution dynamics within knowledge networks.
Improving EFL speaking performance among undergraduate students with an AI-powered mobile app in after-class assignments: an empirical investigation
English speaking represents one of the most challenging competencies for EFL learners, mainly due to the limited opportunities for authentic practice, especially within monolingual contexts like China. However, the ubiquitous personal mobile devices (smartphones) and the advent of AI-powered mobile apps equipped with automatic speech recognition, natural language processing, and text-to-speech present novel solutions to overcome these hurdles. This study investigates the effects of an AI-powered mobile application (Liulishuo) on Chinese undergraduate EFL students’ speaking performance, using features such as automatic feedback, process-oriented monitoring, and tailored instructions. Employing a quasi-experimental design, this 10-week study was conducted at a Chinese university with two groups of participants. The control group (n = 31) engaged with WeChat for after-class assignments, whereas the experimental group (n = 32) supplemented WeChat use with Liulishuo, diversifying their educational tools. Results indicated that participants in the experimental group significantly outperformed those in the control group regarding overall speaking performance. More specifically, notable improvements were observed in pronunciation and fluency, while vocabulary and grammar enhancements were not statistically significant. These findings underscore the capacity of AI-powered mobile apps to enhance EFL speaking performance, signaling novel pathways for the evolution of language education.
Construction of a knowledge graph for framework material enabled by large language models and its application
Framework materials (FMs) have been extensively investigated with a plethora of literature documenting their unique properties and potential applications. Despite this, a comprehensive knowledge graph for this emerging field has not yet been constructed. In this study, by utilizing the natural language processing capabilities of large language models (LLMs), we have established a comprehensive knowledge graph (KG-FM). It covers synthesis, properties, applications, and other aspects of FMs including metal-organic frameworks (MOFs), covalent-organic frameworks (COFs), and hydrogen-bonded organic frameworks (HOFs). The knowledge graph was constructed through the analysis of over 100,000 articles, resulting in 2.53 million nodes and 4.01 million relationships. Subsequently, its application has been explored for enhancing data retrieval, mining, and the development of sophisticated question-answering systems. Especially when integrating the KGs with LLMs, resulted Qwen2-KG not only achieves a higher accuracy rate of 91.67% in question-answering than existing models but also provides precise information sources.
Empowering Alzheimer’s caregivers with conversational AI: a novel approach for enhanced communication and personalized support
Alzheimer’s disease and related dementias (ADRD) place a significant burden on caregivers. To address this, we developed ADQueryAid, a conversational AI system designed to empower ADRD caregivers. Built on a Large Language Model and enriched with ADRD knowledge, ADQueryAid uses Retrieval-Augmented Generation to provide personalized and informative support. A user study comparing ADQueryAid to a baseline model (ChatGPT 3.5) demonstrated its superior usability, offering contextually relevant information and emotional support. This study highlights the potential of tailored AI systems to enhance the caregiving experience, paving the way for future research on their long-term impact.
Responses