Neurogica's Two Research Papers Selected for Oral Presentation at ICASSP 2026

Neurogica Inc. (Headquarters: Shibuya-ku, Tokyo; CEO: Aidan Zephyr Peak) is pleased to announce that two of its research papers have been accepted for oral presentation at ICASSP 2026 (to be held in Barcelona, Spain), one of the most prestigious international conferences in the fields of audio, acoustics, and signal processing. The accepted papers are 'DecompSSM,' which improves the accuracy of multivariate time-series forecasting, and 'PENGUIN,' which enables the reconstruction of multiple vital signs from PPG (photoplethysmogram) signals. Both have been selected for 'Oral' presentation. About ICASSP: ICASSP (International Conference on Acoustics, Speech, and Signal Processing) is one of the world's largest international conferences on signal processing and its applications, organized by the IEEE Signal Processing Society. Only papers that pass rigorous peer review from universities and companies worldwide are accepted. Overview of Accepted Papers: 1. Multivariate Time-series Forecasting Model 'DecompSSM'. Title: A Decomposition-based State Space Model for Multivariate Time-series Forecasting. Authors: Junya Nagashima, Shuntaro Suzuki, Osamu Koyama, Shinnosuke Hirano. Research Results: Multivariate time-series data such as weather, power, and finance are difficult to predict due to mixed trends, cycles, and noise. We proposed 'DecompSSM,' which uses a deep state space model to learn by decomposing data into trend, seasonality, and residuals. This AI model achieves higher accuracy than conventional models in analyzing complex correlated data. 2. Vital Sign Reconstruction Framework 'PENGUIN'. Title: PENGUIN: General Vital Sign Reconstruction from PPG with Flow Matching State Space Model. Authors: Shuntaro Suzuki, Osamu Koyama, Shinnosuke Hirano, Junya Nagashima. Research Results: PPG signals from smartwatches are low-cost but prone to noise. We devised 'PENGUIN,' which integrates 'flow matching' into a state space model. This enables high-precision reconstruction of ECG, blood pressure, and respiratory status from noisy PPG signals, promising to improve the reliability of continuous health monitoring. Future Outlook: The technologies 'DecompSSM' and 'PENGUIN' are expected to contribute to improving healthcare products and industrial data forecasting. Neurogica will continue to provide solutions for real-world challenges through AI model development.