GJGaoyuan Ji

Gaoyuan Ji

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Gaoyuan Ji has a total of 34 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Continuous glucose monitoring earbuds for periodic metabolic sensing

    by Joseph Wang, Barak Sabbagh, Christian Gosti, Ellen V Stadler, Madeleine McSwain, Lauren Chiu, Muhammad Inam Khan, Qinyu Yu, Victor Perez, Tamoghna Saha, et al.

    The applications of continuous glucose monitoring (CGM) are expanding into wellness, sports and preventive health, where metabolic information is particularly valuable around specific physiological events. However, conventional CGMs remain tailored to diabetes management, requiring around-the-clock, fixed wear even when periodic monitoring is sufficient. Here, we introduce the continuous glucose in-ear monitor (cGEM), an earbud-integrated platform for periodic, on-demand glucose monitoring from in-ear sweat. The cGEM establishes a skin–sensor interface through simple insertion and removal, enabling repeated monitoring without adhesive fixation. The platform integrates osmotic sweat extraction, microfluidic sampling and electrochemical glucose sensing while retaining audio playback. Computational modelling and in vitro characterization demonstrated controlled fluid transport and reliable glucose sensing. Dual-channel adaptive noise cancellation and personalized calibration reduce on-body signal artifacts and account for individual differences in blood–sweat glucose relationships. Despite periodic use, the cGEM showed close agreement with a continuously worn commercial CGM, achieving a mean absolute relative difference (MARD) of 8.79% across more than 50 h of monitoring. Repeated 1.5–5 h sessions captured event-specific glucose responses with a Pearson correlation coefficient of r = 0.88 relative to the commercial CGM. By integrating molecular sensing into widely used wireless earbuds, cGEM opens new possibilities for widespread adoption of metabolic monitoring, making it as accessible and routine as listening to music.

  • Open Access

    A fully integrated smart ring for daily biochemical monitoring

    by Tamoghna Saha, Shichao Ding, Siyu Qin, Hannah Fishman, Rosie Pham, Te Gu, Muyang Lin, Yushan Xian, Barak Sabbagh, Abdulhameed Abdal, et al.

    Biochemical analysis complements biophysical measurements by capturing the underlying molecular and metabolic changes that drive physiological health. Here, we introduce a compact, fully integrated smart ring capable of simultaneously monitoring multiple chemical biomarkers in real-time — marking a true biochemical counterpart to existing smart rings. Our ring can continuously measure glucose, ketone, ascorbic acid, uric acid, lactate, and alcohol from passive osmotically extracted sweat, is powered by custom-built high-capacity flexible Zn-AgO batteries, and comprises ultra-compact, energy-efficient electronics for data processing and wireless transmission. It can support ~12 hours of continuous monitoring and preserves personalized calibration stability for ~2 months. The simultaneous biomarker monitoring was validated under diverse daily settings. Reliable, continuous monitoring of glucose and ketone levels showed strong agreement with commercial blood meters and continuous glucose monitors in both healthy and type 1 diabetic individuals, confirming the ring’s accuracy even for at-risk population. Overall, our ring extends beyond commercial smart rings focusing on only biophysical signals, by enabling continuous assessment of biochemical changes and advancing the development of next generation personalized and miniaturized healthcare technologies.


  • Open Access

    RWKV-IF: Efficient and Controllable RNA Inverse Folding via Attention-Free Language Modeling

    by Gaoyuan Ji, Kefan Xu, Chuhong Zheng

    We present RWKV-IF , an efficient and controllable framework for RNA inverse folding based on the attention-free RWKV language model. By treating structure-to-sequence generation as a conditional language modeling task, RWKV-IF captures long-range dependencies with linear complexity. We introduce a decoding strategy that integrates Top- k sampling, temperature control, and G-C content biasing to generate sequences that are both structurally accurate and biophysically meaningful. To overcome limitations of existing datasets, we construct a large-scale synthetic training set from randomly generated sequences and demonstrate strong generalization to real-world RNA structures. Experimental results show that RWKV-IF significantly outperforms traditional search-based baselines, achieving higher accuracy and full match rate while greatly reducing edit distance. Our approach highlights the potential of lightweight generative models in RNA design under structural and biochemical constraints. The code is available at https://github.com/Lyttr/RWKVInverseFolding.git