A5044216365- Muscle activation and electromyography studies
- Mobile Crowdsensing and Crowdsourcing
- Motor Control and Adaptation
- EEG and Brain-Computer Interfaces
- Hemispheric Asymmetry in Neuroscience
- Spam and Phishing Detection
- Ethics and Social Impacts of AI
- Misinformation and Its Impacts
- Opinion Dynamics and Social Influence
- Explainable Artificial Intelligence (XAI)
- Hate Speech and Cyberbullying Detection
- Natural Language Processing Techniques
- Neuroscience and Neural Engineering
University of Colorado Denver
2023
Tokyo Institute of Technology
2019-2023
National Institute of Information and Communications Technology
2020
Surface ElectroMyoGraphy (EMG) signals from the forearm used in prosthetic hand and finger control systems require precise anatomy data of muscles that are small located deep within forearm. The main problem this method is signal quality depends on placement EMG sensor, which can significantly affects accuracy precision to estimate joint angles or forces. Moreover, case amputees, location unknown needed be identified manually for recording. As a result, most modern hands utilize limited...
Misinformation is a global problem in modern social media platforms with few solutions known to be effective. Social have offered tools raise awareness of information, but these are closed systems that not been empirically evaluated. Others developed novel and strategies, most studied out context using static stimuli, researcher prompts, or low fidelity prototypes. We offer new anti-misinformation agent grounded theories metacognition was evaluated within Twitter. report on pilot study...
The illusion of consensus occurs when people believe there is across multiple sources, but the sources are same and thus no "true" consensus. We explore this phenomenon in context an AI-based intelligent agent designed to augment metacognition on social media. Misinformation, especially platforms like Twitter, a global problem for which currently good solution. As explainable AI (XAI) system, provides explanations its decisions misinformed nature media content. In late-breaking study, we...
In this study, seven-channel electromyography signal-based two-dimensional wrist joint movement estimation with and without handgrip motions was carried out. Electromyography signals were analyzed using the synergy-based linear regression model musculoskeletal model; they subsequently compared respect to single combined movements handgrip. Using each one of motion grip trial as a training set, exhibited statistically significant performance 0.7891 ± 0.0844 Pearson correlation coefficient...
As virtual assistants continue to be taken up globally, there is an ever-greater need for these speech-based systems communicate naturally in a variety of languages. Crowdsourcing initiatives have focused on multilingual translation big, open data sets use natural language processing (NLP). Yet, often not one-to-one, and biases can trickle in. In this late-breaking work, we focus the case pronouns translated between English Japanese crowdsourced Tatoeba database. We found that masculine...
Although several previous studies on laterality of upper limb motor control have reported functional differences, this conclusion has not been agreed upon. It may be conjectured that the inconsistent results were caused because was observed in multi-joint tasks could generate different inter-joint coordination for each arm. Resolving this, we employed a single wrist joint tracking task to reduce effect dynamics and examined differences between dominant non-dominant hands terms control....