Search for: All records

Generative models, such as Variational Autoencoders (VAEs), are increasingly employed for atypical pattern detection in brain imaging. During training, these models learn to capture the underlying patterns within “normal” brain images and generate new samples from those patterns. Neurodivergent states can be observed by measuring the dissimilarity between the generated/reconstructed images and the input images. This paper leverages VAEs to conduct Functional Connectivity (FC) analysis from functional Magnetic Resonance Imaging (fMRI) scans of individuals with Autism Spectrum Disorder (ASD), aiming to uncover atypical interconnectivity between brain regions. In the first part of our study, we compare multiple VAE architectures—Conditional VAE, Recurrent VAE, and a hybrid of CNN parallel with RNN VAE—aiming to establish the effectiveness of VAEs in application FC analysis. Given the nature of the disorder, ASD exhibits a higher prevalence among males than females. Therefore, in the second part of this paper, we investigate if introducing phenotypic data could improve the performance of VAEs and, consequently, FC analysis. We compare our results with the findings from previous studies in the literature. The results showed that CNN-based VAE architecture is more effective for this application than the other models.

 

As the influence of social robots in people’s daily lives grows, research on understanding people’s perception of robots including sociability, trust, acceptance, and preference becomes more pervasive. Research has considered visual, vocal, or tactile cues to express robots’ emotions, whereas little research has provided a holistic view in examining the interactions among different factors influencing emotion perception. We investigated multiple facets of user perception on robots during a conversational task by varying the robots’ voice types, appearances, and emotions. In our experiment, 20 participants interacted with two robots having four different voice types. While participants were reading fairy tales to the robot, the robot gave vocal feedback with seven emotions and the participants evaluated the robot’s profiles through post surveys. The results indicate that (1) the accuracy of emotion perception differed depending on presented emotions, (2) a regular human voice showed higher user preferences and naturalness, (3) but a characterized voice was more appropriate for expressing emotions with significantly higher accuracy in emotion perception, and (4) participants showed significantly higher emotion recognition accuracy with the animal robot than the humanoid robot. A follow-up study ([Formula: see text]) with voice-only conditions confirmed that the importance of embodiment. The results from this study could provide the guidelines needed to design social robots that consider emotional aspects in conversations between robots and users. 

This work describes the design of real-time dance-based interaction with a humanoid robot, where the robot seeks to promote physical activity in children by taking on multiple roles as a dance partner. It acts as a leader by initiating dances but can also act as a follower by mimicking a child’s dance movements. Dances in the leader role are produced by a sequence-to-sequence (S2S) Long Short-Term Memory (LSTM) network trained on children’s music videos taken from YouTube. On the other hand, a music orchestration platform is implemented to generate background music in the follower mode as the robot mimics the child’s poses. In doing so, we also incorporated the largely unexplored paradigm of learning-by-teaching by including multiple robot roles that allow the child to both learn from and teach to the robot. Our work is among the first to implement a largely autonomous, real-time full-body dance interaction with a bipedal humanoid robot that also explores the impact of the robot roles on child engagement. Importantly, we also incorporated in our design formal constructs taken from autism therapy, such as the least-to-most prompting hierarchy, reinforcements for positive behaviors, and a time delay to make behavioral observations. We implemented a multimodal child engagement model that encompasses both affective engagement (displayed through eye gaze focus and facial expressions) as well as task engagement (determined by the level of physical activity) to determine child engagement states. We then conducted a virtual exploratory user study to evaluate the impact of mixed robot roles on user engagement and found no statistically significant difference in the children’s engagement in single-role and multiple-role interactions. While the children were observed to respond positively to both robot behaviors, they preferred the music-driven leader role over the movement-driven follower role, a result that can partly be attributed to the virtual nature of the study. Our findings support the utility of such a platform in practicing physical activity but indicate that further research is necessary to fully explore the impact of each robot role. 

Human emotions are expressed through multiple modalities, including verbal and non-verbal information. Moreover, the affective states of human users can be the indicator for the level of engagement and successful interaction, suitable for the robot to use as a rewarding factor to optimize robotic behaviors through interaction. This study demonstrates a multimodal human-robot interaction (HRI) framework with reinforcement learning to enhance the robotic interaction policy and personalize emotional interaction for a human user. The goal is to apply this framework in social scenarios that can let the robots generate a more natural and engaging HRI framework. 

Decades of scientific research have been conducted on developing and evaluating methods for automated emotion recognition. With exponentially growing technology, there is a wide range of emerging applications that require emotional state recognition of the user. This paper investigates a robust approach for multimodal emotion recognition during a conversation. Three separate models for audio, video and text modalities are structured and fine-tuned on the MELD. In this paper, a transformer-based crossmodality fusion with the EmbraceNet architecture is employed to estimate the emotion. The proposed multimodal network architecture can achieve up to 65% accuracy, which significantly surpasses any of the unimodal models. We provide multiple evaluation techniques applied to our work to show that our model is robust and can even outperform the state-of-the-art models on the MELD. 

This paper presents a method for extracting novel spectral features based on a sinusoidal model. The method is focused on characterizing the spectral shapes of audio signals using spectra peaks in frequency sub-bands. The extracted features are evaluated for predicting the levels of emotional dimensions, namely arousal and valence. Principal component regression, partial least squares regression, and deep convolutional neural network (CNN) models are used as prediction models for the levels of the emotional dimensions. The experimental results indicate that the proposed features include additional spectral information that common baseline features may not include. Since the quality of audio signals, especially timbre, plays a major role in affecting the perception of emotional valence in music, the inclusion of the presented features will contribute to decreasing the prediction error rate.