Background: Transcutaneous auricular vagus nerve stimulation (taVNS) has emerged as a potential modulator of cognitive behavior that activates the locus coeruleus-noradrenaline (LC-NA) system. Previous studies explore...
详细信息
Usability and design of serious game technologies have been widely investigated as academic interventions tools for children with autism. However, besides the technology, the sociocultural and institutional context al...
详细信息
Analysts need to process large amounts of data in order to extract concepts, themes, and plans of action based upon their findings. Different display technologies offer varying levels of space and interaction methods ...
Analysts need to process large amounts of data in order to extract concepts, themes, and plans of action based upon their findings. Different display technologies offer varying levels of space and interaction methods that change the way users can process data using them. In a comparative study, we investigated how the use of single traditional monitor, a large, high-resolution two-dimensional monitor, and immersive three-dimensional space using the Immersive Space to Think approach impact the sensemaking process. We found that user satisfaction grows and frustration decreases as available space increases. We observed specific strategies users employ in the various conditions to assist with the processing of datasets. We also found an increased usage of spatial memory as space increased, which increases performance in artifact position recall tasks. In future systems supporting sensemaking, we recommend using display technologies that provide users with large amounts of space to organize information and analysis artifacts.
Trustworthy Graph Neural Networks (GNNs) for EEG emotion recognition should identify emotions accurately and elucidate corresponding rationales. Current GNNs have achieved notable performance by dynamically modeling e...
详细信息
The performance of training-based spatial filtering methods for steady-state visual evoked potential (SSVEP) decoding heavily relies on the availability of sufficient and high-quality calibration data. Limited calibra...
详细信息
ISBN:
(数字)9798350391916
ISBN:
(纸本)9798350391923
The performance of training-based spatial filtering methods for steady-state visual evoked potential (SSVEP) decoding heavily relies on the availability of sufficient and high-quality calibration data. Limited calibration data can lead to suboptimal spatial filters and low signal-to-noise ratios in individual SSVEP templates, ultimately degrading the decoding accuracy and efficiency. To address this challenge, we propose a novel data augmentation method called Shift Aliasing Signal (SAS), which generates synthetic SSVEP epochs by estimating a mixing matrix from the available training data and applying time-shift operations while maintaining the essential features of SSVEP signals, such as their phase-locked nature and frequency-specific patterns. The SAS method introduces meaningful variations to enhance the training dataset. We integrate the SAS method with state-of-the-art training-based spatial filtering methods to create a powerful decoding framework for SSVEP-based brain-computer interface (BCI) systems. Extensive experiments on benchmark datasets demonstrate that the proposed SAS method significantly improves classification accuracy and information transfer rate, particularly in scenarios with limited calibration data, outperforming state-of-the-art training-based spatial filtering methods and other data augmentation techniques.
This paper presents our solution to the 2023 3DUI Contest challenge. Our goal was to provide an immersive VR experience to engage users in privately securing and accessing information in the Metaverse while improving ...
详细信息
This paper presents our solution to the 2023 3DUI Contest challenge. Our goal was to provide an immersive VR experience to engage users in privately securing and accessing information in the Metaverse while improving authentication-related interactions inside our virtual environment. To achieve this goal, we developed an authentication method that uses a virtual environment's individual assets as security tokens. To improve the token selection process, we introduce the HOG interaction technique. HOG combines two classic interaction techniques, Hook and Go-Go, and improves approximate object targeting and further obfuscation of user password token selections. We created an engaging mystery-solving mini-game to demonstrate our authentication method and interaction technique.
The ability to collaborate with other people across barriers created by time and/or space is one of the greatest features of modern communication. Immersive technologies are positioned to enhance this ability to colla...
详细信息
The ability to collaborate with other people across barriers created by time and/or space is one of the greatest features of modern communication. Immersive technologies are positioned to enhance this ability to collaborate even further. However, we do not have a firm understanding of how specific immersive technologies, or components thereof, alter the ability for two or more people to communicate, and hence collaborate. In this work-in-progress position paper, we propose a new framework for immersive collaboration experiences and provide an example of how it could be used to understand a hybrid collaboration among two co-located users and one remote user. We are seeking feedback from the community before conducting a formal evaluation of the framework. We also present some future work that this framework could facilitate.
Vision-based semantic scene completion task aims to predict dense geometric and semantic 3D scene representations from 2D images. However, 3D modeling from a single view is an ill-posed problem, limited by the field o...
详细信息
This paper presents a lightweight algorithm for feature extraction, classification of seven different emotions, and facial expression recognition in a real-time manner based on static images of the human face. In this...
详细信息
暂无评论