AI for herbal medicine

Wed, 27 Apr 2016 00:00:00 +0000

The “AI for Traditional Chinese Herbal Medicine” project is an innovative intersection of artificial intelligence (AI) and traditional Chinese medicine (TCM), aiming to revolutionize the way herbal remedies are studied, developed, and utilized. This project’s motivation stems from the complex nature of TCM, where the efficacy of herbal treatments depends on a multitude of factors, including plant species, harvest time, and preparation methods. AI, with its robust data processing and pattern recognition capabilities, offers a powerful tool to unravel these complexities.

The core of this project involves using machine learning algorithms and data analytics to analyze vast amounts of historical and contemporary data on herbal medicines. This includes patient outcomes, herbal compositions, and their pharmacological effects. By doing so, the project seeks to identify effective herbal combinations, predict therapeutic effects, and personalize treatments for individual patients.

Significantly, this project also focuses on digitizing and translating ancient TCM texts and pharmacopoeias, converting centuries-old knowledge into accessible data for AI analysis. This fusion of traditional knowledge and modern technology not only preserves ancient wisdom but also enhances it with new insights and applications.

The work completed so far in this project has shown promising results in areas like identifying potential herbal treatments for modern diseases, optimizing herbal formulations, and even aiding in new drug discovery. The next steps involve further refining the AI models, expanding the herbal database, and integrating these findings into clinical practice to provide more effective and personalized healthcare solutions..

My recent publications in this field:

Y. Yao et al., “An ontology-based artificial intelligence model for medicine side-effect prediction: taking traditional chinese medicine as an example,” Computational and Mathematical Methods in Medicine, vol. 2019, pp. 1–7, Oct. 2019, doi: 10.1155/2019/8617503.
Z. Wang, L. Li, J. Yan, and Y. Yao, “Approaching high-accuracy side effect prediction of traditional chinese medicine compound prescription using network embedding and deep learning,” IEEE Access, vol. 8, pp. 82493–82499, 2020, doi: 10.1109/ACCESS.2020.2991750.
Z. Wang, L. Li, M. Song, J. Yan, J. Shi, and Y. Yao, “Evaluating the traditional chinese medicine (TCM) officially recommended in china for COVID-19 using ontology-based side-effect prediction framework (OSPF) and deep learning,” Journal of Ethnopharmacology, vol. 272, p. 113957, Feb. 2021, doi: 10.1016/j.jep.2021.113957.

AI for semiconductor device modeling

Wed, 27 Apr 2016 00:00:00 +0000

The “AI for Semiconductor Device Modeling” project is an ambitious endeavor that harnesses the power of artificial intelligence to revolutionize the field of semiconductor device design and analysis. The primary motivation behind this initiative is to overcome the increasing complexity and scalability challenges in semiconductor device modeling, which traditional computational methods struggle to address efficiently.

At the heart of this project is the application of advanced machine learning algorithms and data-driven approaches to model the behavior of semiconductor devices. These AI models are capable of analyzing vast datasets, derived from both experimental measurements and theoretical simulations, to predict device performance, optimize design parameters, and identify novel materials and structures for semiconductor fabrication.

One of the key achievements of this project has been the development of predictive models that significantly reduce the time and resources needed for device characterization and simulation. By leveraging AI, the project has enabled more accurate and rapid prototyping, leading to faster innovation cycles in semiconductor technology.

Looking forward, the project aims to integrate AI more deeply into the semiconductor manufacturing process, enhancing automation and precision in fabrication techniques. The ultimate goal is to establish a new paradigm in semiconductor design where AI-driven insights guide the development of more powerful, energy-efficient, and miniaturized electronic devices.

My recent publications in this field:

Z. Wang et al., “Improving Semiconductor Device Modeling for Electronic Design Automation by Machine Learning Techniques,” IEEE Trans. Electron Devices, pp. 1–9, 2023, doi: 10.1109/TED.2023.3307051.
Z. Wang, L. Li, and Y. Yao, “A machine learning-assisted model for GaN ohmic contacts regarding the fabrication processes,” IEEE Trans. Electron Devices, vol. 68, no. 5, pp. 2212–2219, May 2021, doi: 10.1109/TED.2021.3063213.

cml | Zeheng Wang's page

AI for herbal medicine

AI for semiconductor device modeling