Hirotaka Uchitomi

Dr. Hirotaka Uchitomi


Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 August 2023 in Scientific Reports
Verified
Journal Article
Open access
PDF file
HUHirotaka Uchitomi
Hirotaka Uchitomi
XMXianwen Ming
Xianwen Ming
CZChangyu Zhao
Changyu Zhao
TOTaiki Ogata
Taiki Ogata
YMYoshihiro Miyake
Yoshihiro Miyake
Data-augmentation methods have emerged as a viable approach for improving the state-of-the-art performances for classifying mild Parkinson’s disease using deep learning with time-series data from an inertial measurement unit, considering the limited amount of training datasets available in the medical field. This study investigated effective data-augmentation methods to classify mild Parkinson’s disease and healthy participants with deep learning using a time-series gait dataset recorded via a shank-worn inertial measurement unit. Four magnitude-domain-transformation and three time-domain-transformation data-augmentation methods, and four methods involving mixtures of the aforementioned methods were applied to a representative convolutional neural network for the classification, and their performances were compared. In terms of data-augmentation, compared with baseline classification accuracy without data-augmentation, the magnitude-domain transformation performed better than the time-domain transformation and mixed-data augmentation. In the magnitude-domain transformation, the rotation method significantly contributed to the best performance improvement, yielding accuracy and F1-score improvements of 5.5 and 5.9%, respectively. The augmented data could be varied while maintaining the features of the time-series data obtained via the sensor for detecting mild Parkinson’s in gait; this data attribute may have caused the aforementioned trend. Notably, the selection of appropriate data extensions will help improve the classification performance for mild Parkinson’s disease.

4 October 2023 in Frontiers in Human Neuroscience
Verified
Journal Article
Open access
YMYuki Miyamoto
Yuki Miyamoto
HUHirotaka Uchitomi
Hirotaka Uchitomi
YMYoshihiro Miyake
Yoshihiro Miyake
Humanness is an important characteristic for facilitating interpersonal communication, particularly through avatars in the metaverse. In this study, we explored the mirror neuron system (MNS) as a potential neural basis for perceiving humanness in avatars. Although previous research suggests that the MNS may be influenced by human-like shape and motion, the results have been inconsistent due to the diversity and complexity of the MNS investigation. Therefore, this study aims to investigate the effects of shape and motion humanness in avatars on MNS activity. Participants viewed videos of avatars with four different shapes (HumanShape, AngularShape, AbbreviatedShape, and ScatteredShape) and two types of motion (HumanMotion and LinearMotion), and their μ-wave attenuation in the electroencephalogram was evaluated. Results from a questionnaire indicated that HumanMotion was perceived as human-like, while AbbreviatedShape and ScatteredShape were seen as non-human-like. AngularShape’s humanity was indefinite. The MNS was activated as expected for avatars with human-like shapes and/or motions. However, for non-human-like motions, there were differences in activity trends depending on the avatar shape. Specifically, avatars with HumanShape and ScatteredShape in LinearMotion activated the MNS, but the MNS was indifferent to AngularShape and AbbreviatedShape. These findings suggest that when avatars make non-human-like motions, the MNS is activated not only for human-like appearance but also for the scattered and exaggerated appearance of the human body in the avatar shape. These findings could enhance inter-avatar communication by considering brain activity.

14 September 2023 in Brain Sciences
Verified
Journal Article
Open access
PDF file
CGChenguang Gao
Chenguang Gao
HUHirotaka Uchitomi
Hirotaka Uchitomi
YMYoshihiro Miyake
Yoshihiro Miyake
Emotion recognition is crucial in understanding human affective states with various applications. Electroencephalography (EEG)—a non-invasive neuroimaging technique that captures brain activity—has gained attention in emotion recognition. However, existing EEG-based emotion recognition systems are limited to specific sensory modalities, hindering their applicability. Our study innovates EEG emotion recognition, offering a comprehensive framework for overcoming sensory-focused limits and cross-sensory challenges. We collected cross-sensory emotion EEG data using multimodal emotion simulations (three sensory modalities: audio/visual/audio-visual with two emotion states: pleasure or unpleasure). The proposed framework—filter bank adversarial domain adaptation Riemann method (FBADR)—leverages filter bank techniques and Riemannian tangent space methods for feature extraction from cross-sensory EEG data. Compared with Riemannian methods, filter bank and adversarial domain adaptation could improve average accuracy by 13.68% and 8.36%, respectively. Comparative analysis of classification results proved that the proposed FBADR framework achieved a state-of-the-art cross-sensory emotion recognition performance and reached an average accuracy of 89.01% ± 5.06%. Moreover, the robustness of the proposed methods could ensure high cross-sensory recognition performance under a signal-to-noise ratio (SNR) ≥ 1 dB. Overall, our study contributes to the EEG-based emotion recognition field by providing a comprehensive framework that overcomes limitations of sensory-oriented approaches and successfully tackles the difficulties of cross-sensory situations.

11 September 2024 in Scientific Reports
Verified
Journal Article
Open access
PDF file
GTGuoran Tan
Guoran Tan
HUHirotaka Uchitomi
Hirotaka Uchitomi
RIRyo Isobe
Ryo Isobe
YMYoshihiro Miyake
Yoshihiro Miyake
Gait guidance systems that synchronize the gait rhythm with an avatar in a mixed reality (MR) environment are attracting attention owing to their rehabilitation applications. More effective gait guidance can be achieved by changing body sensations for the sense of embodiment (SoE), which refers to the feeling of owning, controlling, and being inside a body in MR. This study investigated full-body synchronous motion between a human and a virtual avatar to enhance the SoE in walking with actual position changes in the real world. The full-body motion and gait rhythm were measured using body-worn inertial measurement units and a visual avatar was provided through a transparent head-mounted display. The results showed that the SoE of the participants was enhanced under higher synchronization conditions. In addition, questionnaire results showed that the SoE in the synchronous condition was significantly higher than that in the asynchronous condition, and the SoE in the self-avatar condition was significantly higher than that in the other-avatar condition. This indicates that a higher synchronization level with the appearance of an avatar leads to a stronger SoE in the human perception mechanism, which is important for potential application in medical or other fields.

16 May 2023 in Sensors
Verified
Journal Article
Open access
PDF file
CGChenguang Gao
Chenguang Gao
HUHirotaka Uchitomi
Hirotaka Uchitomi
YMYoshihiro Miyake
Yoshihiro Miyake
This study aimed to reveal the influence of emotional valence and sensory modality on neural activity in response to multimodal emotional stimuli using scalp EEG. In this study, 20 healthy participants completed the emotional multimodal stimulation experiment for three stimulus modalities (audio, visual, and audio-visual), all of which are from the same video source with two emotional components (pleasure or unpleasure), and EEG data were collected using six experimental conditions and one resting state. We analyzed power spectral density (PSD) and event-related potential (ERP) components in response to multimodal emotional stimuli, for spectral and temporal analysis. PSD results showed that the single modality (audio only/visual only) emotional stimulation PSD differed from multi-modality (audio-visual) in a wide brain and band range due to the changes in modality and not from the changes in emotional degree. The most pronounced N200-to-P300 potential shifts occurred in monomodal rather than multimodal emotional stimulations. This study suggests that emotional saliency and sensory processing efficiency perform a significant role in shaping neural activity during multimodal emotional stimulation, with the sensory modality being more influential in PSD. These findings contribute to our understanding of the neural mechanisms involved in multimodal emotional stimulation.

3 October 2024 in Scientific Reports
Verified
Journal Article
Open access
PDF file
JQJingyu Quan
Jingyu Quan
HUHirotaka Uchitomi
Hirotaka Uchitomi
RSRyo Shigeyama
Ryo Shigeyama
CGChenguang Gao
Chenguang Gao
TOTaiki Ogata
Taiki Ogata
YMYoshihiro Miyake
Yoshihiro Miyake
High-sensitivity acceleration sensors have been independently developed by our research group to detect vibrations that are > 10 dB smaller than those detected by conventional commercial sensors. This study is the first to measure high-frequency micro-vibrations in muscle fibers, termed micro-mechanomyogram (MMG) in patients with Parkinson’s disease (PwPD) using a high-sensitivity acceleration sensor. We specifically measured the extensor pollicis brevis muscle at the base of the thumb in PwPD and healthy controls (HC) and detected not only low-frequency MMG (< 15 Hz) but also micro-MMG (≥ 15 Hz), which was preciously undetectable using commercial acceleration sensors. Analysis revealed remarkable differences in the frequency characteristics of micro-MMG between PwPD and HC. Specifically, during muscle power output, the low-frequency MMG energy was greater in PwPD than in HC, while the micro-MMG energy was smaller in PwPD compared to HC. These results suggest that micro-MMG detected by the high-sensitivity acceleration sensor provides crucial information for distinguishing between PwPD and HC. Moreover, a deep learning model trained on both low-frequency MMG and micro-MMG achieved a high accuracy (92.19%) in classifying PwPD and HC, demonstrating the potential for a diagnostic system for PwPD using micro-MMG.