decoder, and 95.4% on real-word tap typing data. In particular, our decoder supports Flexible Typing, allowing users to enter a word with taps, gestures, multi-stroke gestures, and tap-gesture combinations. User study results show that Flexible Typing is beneficial and well-received by participants, where 35.9% of words were entered using word gestures, 29.0% with taps, 6.1% with multi-stroke gestures, and the remaining 29.0% using tap-gestures. Our investigation suggests that the LLM-based decoder improves decoding accuracy over existing word gesture decoders while enabling the Flexible Typing method, which enhances the overall typing experience and accommodates diverse user preferences.

While gesture typing is widely adopted on touchscreen keyboards, its support for low vision users is limited. We have designed and implemented two keyboard prototypes, layout-magnified and key-magnified keyboards, to enable gesture typing for people with low vision. Both keyboards facilitate uninterrupted access to all keys while the screen magnifier is active, allowing people with low vision to input text with one continuous stroke. Furthermore, we have created a kinematics-based decoding algorithm to accommodate the typing behavior of people with low vision. This algorithm can decode the gesture input even if the gesture trace deviates from a pre-defined word template, and the starting position of the gesture is far from the starting letter of the target word. Our user study showed that the key-magnified keyboard achieved 5.28 words per minute, 27.5% faster than a conventional gesture typing keyboard with voice feedback.

In recent years, interest in measuring air quality has spiked due to rising environmental and health concerns in South Korea. In particular, microfine dust (microdust) is known to cause serious health issues to people. Therefore, measuring and predicting mircodust is an important problem. A typical way of measuring microdust is to use sensors from fixed location. However, this cannot capture the local dynamics of microdust and is limited to accurate measurement near fixed locations. Therefore, there is an immediate need to provide more accurate local air quality measurements in the areas where fixed local sensors are not installed. In this preliminary research, we focus on modeling the air quality pattern in a given local area by using vehicles equipped with cheap IoT sensors, where vehicles move around the area. As a pilot study, We measured the microdust level running experiments for 2 weeks with 3 different cars. Also, we developed an machine learning algorithm to better predict the local air quality using moving sensors. Further, we built an application where measured air quality is reported to the end users. We demonstrated the feasibility of using inexpensive IoT sensors in moving vehicles to provide better local air quality to end users.