Search for: All records

Efficient performance and acquisition of physical skills, from sports techniques to surgical procedures, require instruction and feedback. In the absence of a human expert, Mixed Reality Intelligent Task Support (MixITS) can offer a promising alternative. These systems integrate Artificial Intelligence (AI) and Mixed Reality (MR) to provide realtime feedback and instruction as users practice and learn skills using physical tools and objects. However, designing MixITS systems presents challenges beyond engineering complexities. The complex interactions between users, AI, MR interfaces, and the physical environment create unique design obstacles. To address these challenges, we present MixITS-Kit—an interaction design toolkit derived from our analysis of MixITS prototypes developed by eight student teams during a 10-week-long graduate course. Our toolkit comprises design considerations, design patterns, and an interaction canvas. Our evaluation suggests that the toolkit can serve as a valuable resource for novice practitioners designing MixITS systems and researchers developing new tools for human-AI interaction design. 

Electroencephalogram (EEG) signals are often used as an input modality for Brain Computer Interfaces (BCIs). While EEG signals can be beneficial for numerous types of interaction scenarios in the real world, high levels of noise limits their usage to strictly noise-controlled environments such as a research laboratory. Even in a controlled environment, EEG is susceptible to noise, particularly from user motion, making it highly challenging to use EEG, and consequently BCI, as a ubiquitous user interaction modality. In this work, we address the EEG noise/artifact correction problem. Our goal is to detect physiological artifacts in EEG signal and automatically replace the detected artifacts with imputed values to enable robust EEG sensing overall requiring significantly reduced manual effort than is usual. We present a novel EEG state-based imputation model built upon a recurrent neural network, which we call SRI-EEG, and evaluate the proposed method on three publicly available EEG datasets. From quantitative and qualitative comparisons with six conventional and neural network based approaches, we demonstrate that our method achieves comparable performance to the state-of-the-art methods on the EEG artifact correction task. 

Expert-layman text style transfer technologies have the potential to improve communication between members of scientific communities and the general public. High-quality information produced by experts is often filled with difficult jargon laypeople struggle to understand. This is a particularly notable issue in the medical domain, where layman are often confused by medical text online. At present, two bottlenecks interfere with the goal of building high-quality medical expert-layman style transfer systems: a dearth of pretrained medical-domain language models spanning both expert and layman terminologies and a lack of parallel corpora for training the transfer task itself. To mitigate the first issue, we propose a novel language model (LM) pretraining task, Knowledge Base Assimilation, to synthesize pretraining data from the edges of a graph of expert- and layman-style medical terminology terms into an LM during self-supervised learning. To mitigate the second issue, we build a large-scale parallel corpus in the medical expert-layman domain using a margin-based criterion. Our experiments show that transformer-based models pretrained on knowledge base assimilation and other well-established pretraining tasks fine-tuning on our new parallel corpus leads to considerable improvement against expert-layman transfer benchmarks, gaining an average relative improvement of our human evaluation, the Overall Success Rate (OSR), by 106%. 

Location-based or Out-of-Home Entertainment refers to experiences such as theme and amusement parks, laser tag and paintball arenas, roller and ice skating rinks, zoos and aquariums, or science centers and museums among many other family entertainment and cultural venues. More recently, location-based VR has emerged as a new category of out-of-home entertainment. These VR experiences can be likened to social entertainment options such as laser tag, where physical movement is an inherent part of the experience versus at-home VR experiences where physical movement often needs to be replaced by artificial locomotion techniques due to tracking space constraints. In this work, we present the first VR study to understand the impact of natural walking in a large physical space on presence and user preference. We compare it with teleportation in the same large space, since teleportation is the most commonly used locomotion technique for consumer, at-home VR. Our results show that walking was overwhelmingly preferred by the participants and teleportation leads to significantly higher self-reported simulator sickness. The data also shows a trend towards higher self-reported presence for natural walking.