Confidence Estimation Using Machine Learning in Immersive Learning Environments

Tao, Yudong; Coltey, Erik; Wang, Tianyi; Alonso, Miguel Ángel Verdugo; Shyu, Mei‐Ling; Chen, Shu‐Ching; Alhaffar, Hadi; Elias, Albert; Bogosian, Biayna; Vassigh, Shahin

doi:10.1109/mipr49039.2020.00058

Cited by 10 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, CNNs can extract facial traits that are indicative of particular emotions from facial expressions taken by virtual avatars or head-mounted displays. The processing of sequential data, such as voice recordings or physiological signals, using RNNs, on the other hand, enables the identification of temporal patterns linked to various emotional states [8]. But in order to fully realize the potential of ML in immersive emotion recognition, a number of issues must be resolved.…”

Section: Introductionmentioning

confidence: 99%

Enhancing the Potential of Machine Learning for Immersive Emotion Recognition in Virtual Environment

2024

ICST Transactions on Scalable Information Systems

View full text Add to dashboard Cite

Emotion recognition is an immense challenge for immersive technology. In order to detect the emotions of the user, we use machine learning methods and techniques to use the potential of the Virtual Environment and to improve the user Experience. Emotion recognition plays an important role in developing realistic and emotionally immersive experiences in augmented reality (AR) and virtual reality (VR) settings by instantly adjusting interactions, content, and visuals based on the accurate detection and interpretation of users’ emotions. Immersive systems can enhance user experience through various machine learning algorithms and methods used for emotion recognition, which are examined in this article. Upon novel idea, challenges and potential applications of incorporating emotion recognition in immersive virtual environments with Machine Learning (ML) Techniques and the benefits of tailoring powerful immersive experiences with ML methods were highlighted, and also the study discusses potential advancements in identifying the user’s emotion recognition in the future by modeling an Architecture, as well as how the ML techniques were enhanced for virtual environment is discussed.

show abstract

Section: Introductionmentioning

confidence: 99%

Enhancing the Potential of Machine Learning for Immersive Emotion Recognition in Virtual Environment

2024

ICST Transactions on Scalable Information Systems

View full text Add to dashboard Cite

show abstract

“…Adaptive automation has widely been used to facilitate human task performance and efficiency [1], [2], [3], by using human performance feedback to predict decisionmaking behavior and adapt the automation to the human [4], [5]. Cognitive factors, including self-confidence, play an important role in the design of effective human-automation interaction [6], [7], [8], [9] and how humans learn [10], [11], [12], [13]. Overconfidence and underconfidence both undermine learning, thereby motivating the need for calibration of users' self-confidence to their skill level [14], [9], [15].…”

Section: Introductionmentioning

confidence: 99%

Classification of Human Learning Stages via Kernel Distribution Embeddings

Yuh,

Ortiz,

Sommer-Kohrt

et al. 2024

IEEE Open J. Control. Syst.

View full text Add to dashboard Cite

Adaptive automation, automation which is responsive to the human's performance via the alteration of control laws or level of assistance, is an important tool for training humans to attain new skills when operating dynamical systems. When coupled with cognitive feedback, adaptive automation has the potential to further facilitate human training, but requires precise assessments of human progression through various learning stages. This is challenging because of the underlying dynamics, as well as the stochasticity inherent to human action. We propose a data-driven approach to assess learning stages in a complex quadrotor landing task that is responsive to stochastic, human-in-the-loop quadrotor dynamics. We represent each learning stage as a distribution of canonical trajectories for that learning stage, then employ kernel distribution embeddings in combination with a rule-based heuristic, to determine which canonical distribution a sample landing trajectory is closest to. We demonstrate our approach on experimental human subject data, and use our approach to evaluate the efficacy of cognitively-based adaptive automation designed to calibrate self-confidence. Our approach is more accurate than standard classification methods, such as nearest centroid assignment, which rely on metrics that are not inherently suited to analysis of trajectories of stochastic dynamical systems. INDEX TERMS Cyberphysical systems, Cognitive systems and control, Human-in-the-loop systems, Rulebased classification, Kernel methods

show abstract

“…The patient's mental state and cognitive progress can be better perceived by analyzing voice and video footage of the eyes and body language, 9 and the learning status can be estimated based on the multimodal data collected in these environments. 10 Although many advancements have been made to improve the quality of services, there are still large amounts of work in the concept of remote health and education applications.…”

mentioning

confidence: 99%

Multimedia Research for Response and Management of COVID-19 and Future Pandemics

Chen

2021

IEEE MultiMedia

Self Cite

View full text Add to dashboard Cite

Coronavirus Disease 2019 (COVID-19) has been affecting most of the countries and impacting almost every aspect of people's lives. More than one hundred million confirmed cases and two million deaths have been reported due to COVID-19 as of February 2021. While our society suffers an unanticipated epidemic, researchers and engineers have developed various technologies to manage this global emergency. Specifically, multimedia tools, techniques, and applications have been developed and played essential roles in facilitating the recovery, resilience, and management of COVID-19, including pandemic status monitoring and impact prediction, enhancing public awareness and telehealth, etc. However, there are many challenges that require further investigation and research to better manage COVID-19 and prepare for future pandemics.

show abstract

Confidence Estimation Using Machine Learning in Immersive Learning Environments

Cited by 10 publications

References 17 publications

Enhancing the Potential of Machine Learning for Immersive Emotion Recognition in Virtual Environment

Enhancing the Potential of Machine Learning for Immersive Emotion Recognition in Virtual Environment

Classification of Human Learning Stages via Kernel Distribution Embeddings

Multimedia Research for Response and Management of COVID-19 and Future Pandemics

Contact Info

Product

Resources

About