Yutaro Hirao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yutaro Hirao has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
Anatole Lecuyer
1 shared publicationFerran Argelaguet
1 shared publication- Hideaki Uchiyama
Cybernetics and Reality Engineering Laboratory, Nara Institute of Science and Technology, Ikoma, Nara, Japan
1 shared publication - Huakun Liu
Nara Institute of Science and Technology
1 shared publication - Katsutoshi Masai
Kyushu University Fukuoka Fukuoka Japan
1 shared publication - Kiyoshi Kiyokawa
Cybernetics and Reality Engineering Laboratory, Nara Institute of Science and Technology, Ikoma, Nara, Japan
1 shared publication
Latest Publications
- Open Access
Mind Your Vision: Multimodal Estimation of Refractive Disorders Using Electrooculography and Eye Tracking
Refractive errors are among the most common visual impairments globally, yet their diagnosis often relies on active user participation and clinical oversight. This study explores a passive method for estimating refractive power using two eye movement recording techniques: electrooculography (EOG) and video-based eye tracking. Using a publicly available dataset recorded under varying diopter conditions, we trained Long Short-Term Memory (LSTM) models to classify refractive power from unimodal (EOG or eye tracking) and multimodal configuration. We assess performance in both subject-dependent and subject-independent settings to evaluate model personalization and generalizability across individuals. Results show that the multimodal model consistently outperforms unimodal models, achieving the highest average accuracy in both settings: 96.207\% in the subject-dependent scenario and 8.882\% in the subject-independent scenario. However, generalization remains limited, with classification accuracy only marginally above chance in the subject-independent evaluations. Statistical comparisons in the subject-dependent setting confirmed that the multimodal model significantly outperformed the EOG and eye-tracking models. However, no statistically significant differences were found in the subject-independent setting. Our findings demonstrate both the potential and current limitations of eye movement data-based refractive error estimation, contributing to the development of continuous, non-invasive screening methods using EOG signals and eye-tracking data.
Open AccessMind Your Vision: Multimodal Estimation of Refractive Disorders Using Electrooculography and Eye Tracking
Refractive errors are among the most common visual impairments globally, yet their diagnosis often relies on active user participation and clinical oversight. This study explores a passive method for estimating refractive power using two eye movement recording techniques: electrooculography (EOG) and video-based eye tracking. Using a publicly available dataset recorded under varying diopter conditions, we trained Long Short-Term Memory (LSTM) models to classify refractive power from unimodal (EOG or eye tracking) and multimodal configuration. We assess performance in both subject-dependent and subject-independent settings to evaluate model personalization and generalizability across individuals. Results show that the multimodal model consistently outperforms unimodal models, achieving the highest average accuracy in both settings: 96.207\% in the subject-dependent scenario and 8.882\% in the subject-independent scenario. However, generalization remains limited, with classification accuracy only marginally above chance in the subject-independent evaluations. Statistical comparisons in the subject-dependent setting confirmed that the multimodal model significantly outperformed the EOG and eye-tracking models. However, no statistically significant differences were found in the subject-independent setting. Our findings demonstrate both the potential and current limitations of eye movement data-based refractive error estimation, contributing to the development of continuous, non-invasive screening methods using EOG signals and eye-tracking data.
- Open Access
Move or Push? Studying Pseudo-Haptic Perceptions Obtained with Motion or Force Input
Pseudo-haptics techniques are interesting alternatives for generating haptic perceptions, which entails the manipulation of haptic perception through the appropriate alteration of primarily visual feedback in response to body movements. However, the use of pseudo-haptics techniques with a motion-input system can sometimes be limited. This paper investigates a novel approach for extending the potential of pseudo-haptics techniques in virtual reality (VR). The proposed approach utilizes a reaction force from force-input as a substitution of haptic cue for the pseudo-haptic perception. The paper introduced a manipulation method in which the vertical acceleration of the virtual hand is controlled by the extent of push-in of a force sensor. Such a force-input manipulation of a virtual body can not only present pseudo-haptics with less physical spaces and be used by more various users including physically handicapped people, but also can present the reaction force proportional to the user's input to the user. We hypothesized that such a haptic force cue would contribute to the pseudo-haptic perception. Therefore, the paper endeavors to investigate the force-input pseudo-haptic perception in a comparison with the motion-input pseudo-haptics. The paper compared force-input and motion-input manipulation in a point of achievable range and resolution of pseudo-haptic weight. The experimental results suggest that the force-input manipulation successfully extends the range of perceptible pseudo-weight by 80\% in comparison to the motion-input manipulation. On the other hand, it is revealed that the motion-input manipulation has 1 step larger number of distinguishable weight levels and is easier to operate than the force-input manipulation.
Open AccessMove or Push? Studying Pseudo-Haptic Perceptions Obtained with Motion or Force Input
Pseudo-haptics techniques are interesting alternatives for generating haptic perceptions, which entails the manipulation of haptic perception through the appropriate alteration of primarily visual feedback in response to body movements. However, the use of pseudo-haptics techniques with a motion-input system can sometimes be limited. This paper investigates a novel approach for extending the potential of pseudo-haptics techniques in virtual reality (VR). The proposed approach utilizes a reaction force from force-input as a substitution of haptic cue for the pseudo-haptic perception. The paper introduced a manipulation method in which the vertical acceleration of the virtual hand is controlled by the extent of push-in of a force sensor. Such a force-input manipulation of a virtual body can not only present pseudo-haptics with less physical spaces and be used by more various users including physically handicapped people, but also can present the reaction force proportional to the user's input to the user. We hypothesized that such a haptic force cue would contribute to the pseudo-haptic perception. Therefore, the paper endeavors to investigate the force-input pseudo-haptic perception in a comparison with the motion-input pseudo-haptics. The paper compared force-input and motion-input manipulation in a point of achievable range and resolution of pseudo-haptic weight. The experimental results suggest that the force-input manipulation successfully extends the range of perceptible pseudo-weight by 80\% in comparison to the motion-input manipulation. On the other hand, it is revealed that the motion-input manipulation has 1 step larger number of distinguishable weight levels and is easier to operate than the force-input manipulation.