Advancements in bioelectronic sensors and actuators have paved the way for real-time monitoring and control of the progression of wound healing. Real-time monitoring allows for precise adjustment of treatment strategies to align them with an individual’s unique biological response. However, due to the complexities of human–drug interactions and a lack of predictive models, it is challenging to determine how one should adjust drug dosage to achieve the desired biological response. This work proposes an adaptive closed-loop control framework that integrates deep learning, optimal control, and reinforcement learning to update treatment strategies in real time, with the goal of accelerating wound closure. The proposed approach eliminates the need for mathematical modeling of complex nonlinear wound-healing dynamics. We demonstrate the convergence of the controller via an in silico experimental setup, where the proposed approach successfully accelerated the wound-healing process by 17.71%. Finally, we share the experimental setup and results of an in vivo implementation to highlight the translational potential of our work. Our data-driven model suggests that the treatment strategy, as determined by our deep reinforcement learning algorithm, results in an accelerated onset of inflammation and subsequent transition to proliferation in a porcine wound model.
Aerosol is one of the important factors that will influence the air quality, visibility, clouds, and precipitation processes in the troposphere. In this work, we investigated the variation of aerosol during daytime in Penang, Malaysia in certain days within July 2013. Vertical LIDAR scattering ratio and backscattering profiles, and columnar optical properties (optical depth, Angström exponent) of aerosols were measured using Raymetrics LIDAR and a CIMEL sunphotometer respectively. Specifically, we have determined the daytime variation of intensity and distribution level of aerosol, as well as the planetary boundary layer (PBL) and cloud classification. Subsequently, the data of columnar aerosol optical depth (AOD) and size distribution in the atmospheric were used to quantify the properties of aerosol variation during daytime over Penang, Malaysia.
23 June 2014 in IOP Conference Series: Earth and Environmental Science
Advanced imaging tools are revolutionizing the diagnosis, treatment, and monitoring of medical conditions, offering unprecedented insights into live cell behavior and biophysical markers. We introduce a modular, hand-held fluorescent microscope featuring rapid set-up and sub-millimeter resolution for real-time biological analysis. We apply our system to map pH and nitric oxide (NO), biomarkers central to wound healing, in subcutaneous wounds. Using machine learning to cluster pH reveals spatiotemporal trends, including a concentric gradient peaking at the center and stabilization at the wound edge. NO clustering shows high-concentration structures that decrease in size but intensify as healing progresses from hemostasis to proliferation, enabling prediction of the healing day and re-epithelialization. These biomarker mappings offer insights poised to inform future wound healing studies. This research lays the groundwork for integrating the modular imaging unit with bioelectronic devices in closed-loop feedback systems, using machine learning to guide optimal wound treatment and accelerate healing.