Filtering by
- Creators: Computer Science and Engineering Program
- Creators: Turaga, Pavan
Design and development of an immersive virtual reality team trainer for advance cardiac life support
is challenging due to cognitive biases, varying
worker expertise, and varying subjective scales. This
work investigates new ways to determine collective decisions
by prompting users to provide input in multiple
formats. A crowdsourced task is created that aims
to determine ground-truth by collecting information in
two different ways: rankings and numerical estimates.
Results indicate that accurate collective decisions can
be achieved with less people when ordinal and cardinal
information is collected and aggregated together
using consensus-based, multimodal models. We also
show that presenting users with larger problems produces
more valuable ordinal information, and is a more
efficient way to collect an aggregate ranking. As a result,
we suggest input-elicitation to be more widely considered
for future work in crowdsourcing and incorporated
into future platforms to improve accuracy and efficiency.
Engaging users is essential for designers of any exhibit, such as the human-computer interface, the visual effects, or the informational content. The need to understand users’ experiences and learning gains has motivated a focus on user engagement across computer science. However, there has been limited review of how human-computer interaction research interprets and employs the concepts in museum and exhibit settings, specifically their joint effects. The purpose of this study is to assess users’ experience and learning outcome, while interacting with a web application part of an exhibit that showcases the NASA Psyche spacecraft model. This web application provides an interactive menu that allows the user to navigate on the touch panel installed within the Psyche Spacecraft Exhibit. The user can press the button on the menu which will light up the corresponding parts of the model with a detailed description displayed on the panel. For this study, participants were required to take a questionnaire, a pretest, and a posttest. They were also required to interact with the web application while wearing an Emotiv EPOC+ EEG headset that measures their emotions while they were visiting the exhibit. During the study, data such as questionnaire results, sensed emotions from the EEG headset, and pretest and posttest scores were collected. Using the information gathered, the study explores user experience and learning gains through both biometrics and traditional tools. The findings show that users felt engaged and frustrated the most and that users gained more knowledge but at varying degrees from the interaction. Future work can be done to lower the levels of frustration and keep learning gains at a more consistent rate by improving the exhibit design to better meet various learning needs and visitor profiles.
The expression and perception of emotions varies across speakers and cultures, thus, determining features and classification methods that generalize well to different conditions is strongly desired. A latent topic models-based method is proposed to learn supra-segmental features from low-level acoustic descriptors. The derived features outperform state-of-the-art approaches over multiple databases. Cross-corpus studies are conducted to determine the ability of these features to generalize well across different databases. The proposed method is also applied to derive features from facial expressions; a multi-modal fusion overcomes the deficiencies of a speech only approach and further improves the recognition performance.
Besides affecting the acoustic properties of speech, emotions have a strong influence over speech articulation kinematics. A learning approach, which constrains a classifier trained over acoustic descriptors, to also model articulatory data is proposed here. This method requires articulatory information only during the training stage, thus overcoming the challenges inherent to large-scale data collection, while simultaneously exploiting the correlations between articulation kinematics and acoustic descriptors to improve the accuracy of emotion recognition systems.
Identifying context from ambient sounds in a lifelogging scenario requires feature extraction, segmentation and annotation techniques capable of efficiently handling long duration audio recordings; a complete framework for such applications is presented. The performance is evaluated on real world data and accompanied by a prototypical Android-based user interface.
The proposed methods are also assessed in terms of computation and implementation complexity. Software and field programmable gate array based implementations are considered for emotion recognition, while virtual platforms are used to model the complexities of lifelogging. The derived metrics are used to determine the feasibility of these methods for applications requiring real-time capabilities and low power consumption.