Kwangwoon University

The accurate identification of acupoints is an essential task in acupuncture therapy. Recent advancements in artificial intelligence (AI) have led to the exploration of automated landmark detection systems, which may provide more accurate and reliable acupoint detection. This study investigated the efficiency of an AI model in predicting the shenmen, lung, and mouth auricular acupoints and compared its performance to placements made by a practitioner of traditional Korean medicine.

Ear images from 39 individuals were captured from three different angles. The mask region-based convolutional neural network (Mask R-CNN) model was utilized to isolate the ear region, followed by landmark detection using a CNN model trained on resized images to predict three auricular acupoints. Model reliability was enhanced by treating each acupoint as a separate prediction coordinate. Acupoint distribution was also estimated using a kernel density estimation method.

Centroids of auricular acupoints predicted by the CNN model showed deviations of < 3 pixels from traditional placements by the practitioner. Kernel density estimation showed that CNN predictions led to narrower acupoint distributions compared with those placed by the practitioner, suggesting higher consistency in CNN model predictions across different images.

The AI-driven approach showed significant potential in improving both the accuracy and consistency of auricular acupoint identification. These findings support the integration of AI into acupuncture practice as a reliable tool for enhancing clinical accuracy and precision of acupoint location.

CaCu₃Ti₄O₁₂ (CCTO) is a promising material for humidity sensing applications owing to its advantageous characteristics such as high dielectric constant. However, the low surface porosity induced during the preparation of pellet-based CCTO sensors results in poor sensitivity and minimal variation in capacitance in low-humidity environments. Notably, combining NaCl with CCTO is expected to enhance its sensing performance, surface hydrophilicity, and internal porosity, thereby solving the low sensitivity and poor linearity issues associated with low-humidity environments. Therefore, a high-performance humidity sensor, based on a CCTO/NaCl composite, was developed for environmental monitoring, with potential applications in healthcare, industry, agriculture, and daily-life humidity tracking. The sensor utilized CCTO/NaCl composite films prepared via aerosol deposition. The film performance was optimized by varying the carrier gases and pretreatment protocols. Air, as the carrier gas, enhanced the surface roughness, facilitating efficient water molecule adsorption. Post-annealing at 400 °C further improved the dielectric and sensing properties of the film. The incorporation of NaCl enhanced charge transport in low-humidity environments, thereby improving the sensitivity of the sensor. The NaCl milling time and particle size were controlled to precisely tune the film microstructure and porosity, and consequently, high sensitivity (2561 pF/%RH) and fast response times (1 s/2 s) were achieved. The proposed sensor has great potential for high-performance humidity detection and respiratory monitoring.

This study aims to introduce a novel augmented display technology that enhances visibility of forward vehicles by projecting critical highlighting information onto the windshield, and to validate its effectiveness in improving occupants’ reaction, acceptance, and workload.

The rapid advancements in autonomous driving technology have brought significant changes to the automotive landscape; however, trust and safety concerns remain major barriers to widespread acceptance. To address these issues, enhancing occupants’ reaction efficiency with workload and acceptance in autonomous vehicle operations is critical.

Utilizing two distinct highlighting display methods—surface and outline—within a virtual reality simulation, the research examines their effects on occupants’ acceptance including perception of safety through AVAM (Autonomous vehicle acceptance model), and workload through NASA-TLX to dynamic road scenarios during autonomous driving.

The findings reveal that highlighting display significantly enhances acceptance and workload with reaction time, but their effectiveness varies. Surface highlighting was found to better reduce anxiety and increase perceived safety, while outline highlighting more effectively reduced mental demand.

These results offer valuable insights into the dynamic interaction between advanced display technologies and autonomous vehicle operations, highlighting the potential benefits and challenges in their implementation to foster broader acceptance of autonomous vehicles.

By intuitively projecting critical information during takeover scenarios, this technology addresses trust and safety barriers in autonomous driving, potentially enhancing prompt responses, accelerating autonomous vehicle integration, and improving the overall driving experience.