1 code implementation • 4 Jul 2022 • Yuki Hashimoto, Akira Furui, Koji Shimatani, Maura Casadio, Paolo Moretti, Pietro Morasso, Toshio Tsuji
In this study, we propose an automated GMs classification method, which consists of preprocessing networks that remove unnecessary background information from GMs videos and adjust the infant's body position, and a subsequent motion classification network based on a two-stream structure.
no code implementations • 12 Nov 2021 • Akira Furui, Tomoyuki Akiyama, Toshio Tsuji
The covariance matrix of the Gaussian distribution is weighted with a latent scale parameter, which is also a random variable, resulting in the stochastic fluctuations of covariances.
no code implementations • 21 Jul 2021 • Akira Furui, Takuya Igaue, Toshio Tsuji
These results indicated the validity of the proposed method and its applicability to EMG-based control systems.
no code implementations • 2 Jul 2020 • Akira Furui, Ryota Onishi, Akihito Takeuchi, Tomoyuki Akiyama, Toshio Tsuji
Experiments using simulated and real EEG data demonstrated the validity of the model and its applicability to epileptic seizure detection.
no code implementations • 14 Nov 2019 • Hideaki Hayashi, Taro Shibanoki, Toshio Tsuji
In this study, a discriminative model based on the multivariate Johnson $S_\mathrm{U}$ translation system is transformed into a linear combination of coefficients and input vectors using log-linearization.
no code implementations • 14 Nov 2019 • Hideaki Hayashi, Taro Shibanoki, Keisuke Shima, Yuichi Kurita, Toshio Tsuji
This paper proposes a probabilistic neural network developed on the basis of time-series discriminant component analysis (TSDCA) that can be used to classify high-dimensional time-series patterns.