ZYZhiwei Yu

Zhiwei Yu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Zhiwei Yu has a total of 13 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Screen-Based Multimodal Virtual Classroom Interface for Understanding Behavioral Sensory Responses in Autistic Adolescents: A Pilot Study

    by Zhiwei Yu, Suzannah Iadarola, Samantha Daley, Zhi Zheng

    Autism impacts at least 1 in 100 children worldwide, with about 90% experiencing sensory processing difficulties. Virtual Reality (VR), which can precisely deliver controlled sensory stimuli, has emerged as a promising tool for studying sensory experiences. However, VR systems using a head-mounted display may cause discomfort and exacerbate sensory challenges for autistic children. Screen-based VR could offer a viable alternative, but research on designing multimodal sensory delivery systems that simulate real-life experiences remains limited. As a result, the impact of on-screen VR on children’s behavioral sensory responses is not well understood. Therefore, as a pilot study to fill this gap, we designed a novel screen-based Multimodal Virtual Classroom Interface (MVCI) system. MVCI was designed to deliver well-controlled visual, auditory, and tactile stimuli that closely mimic a real classroom environment. The pilot study involved 9 autistic adolescents and 17 typically developing (TD) adolescents, all of whom reported 100% acceptance of the system. Quantitative behavioral analysis demonstrated that, even with the small sample size, the on-screen interaction showed significant differences (p < 0.05) between the two groups in terms of eye gaze, fine motor movements, and eye-hand alignment. Additionally, several behavioral patterns were strongly correlated with participants’ sensory profiles and ADHD symptom severity (p < 0.05, rs > 0.7). Using a novel Fixation Sequence Modeling (FSM) framework, we were able to predict participants’ near-future performance with high accuracy (97-98% proximity) based on their granular behavioral responses.


  • Open Access

    A Computation Model to Estimate Interaction Intensity through Non-Verbal Behavioral Cues: A Case Study of Intimate Couples under the Impact of Acute Alcohol Consumption

    by Zhiwei Yu, Cory Crane, Linlin Chen, Maria Testa, Zhi Zheng

    This work introduced a novel analysis method to estimate interaction intensity, i.e., the level of positivity/negativity of interaction, for intimate couples (married and heterosexual) under the impact of alcohol, which has great influences on behavioral health. Non-verbal behaviors are critical in interpersonal interactions. However, whether computer vision-detected non-verbal behaviors can effectively estimate the interaction intensity of intimate couples is still unexplored. In this work, we proposed novel measurements and investigated their feasibility to estimate interaction intensities through machine learning regression models. Analyses were conducted based on a conflict-resolution conversation video dataset of intimate couples before and after acute alcohol consumption. Results showed the estimation error was at the lowest in the no-alcohol state but significantly increased if the model trained using no-alcohol data was applied to after-alcohol data, indicating that alcohol altered the interaction data in the feature space. While training a model using rich after-alcohol data is ideal to address the performance decrease, data collection in such a risky state is challenging in real life. Thus, we proposed a new State-Induced Domain Adaptation (SIDA) framework, which allows for improving estimation performance using only a small after-alcohol training dataset, pointing to a future direction of addressing data scarcity issues.

  • Open Access

    Understanding Stress in Children with ASD and Their Caregivers in Daily Life: A Feasibility Study Using Mobile Devices

    by Zhiwei Yu, Mingma Tendu Sherpa, Suzannah Iadarola, Kenneth Shamlian, Samantha Daley, Grace Levine, Peter Bajorski, Zhi Zheng

    Caregivers of children with ASD experience more parenting stress than caregivers of typically developing children. Parenting stress is traditionally evaluated through questionnaires, which do not catch details about when and what exact stressful events occur during a day. This article introduces a data recording framework using mobileHCI based self-report and physiological signal collection to fill this gap. We designed an EasyConnect mobile app to allow caregivers of ASD to conveniently log stressful events using an e-survey. Meanwhile, a wearable physiological sensor was applied to collect Photoplethysmography (PPG) and Electrodermal Activity (EDA) signals. These signals were synchronized with the self-reports to analyze if there was any relation between physiological patterns and self-reported stress. Results collected from 8 families showed that: 1) the proposed framework successfully facilitated data collection; 2) EDA-based stress indicators were detected and associated with stress self-reports. Practical aspects and indications for future works are also discussed.