DNDaiki Nishioka

Daiki Nishioka

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Daiki Nishioka has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Investigating the cochleagram preprocessing and the role of interfered spin-wave-based reservoir computing in speech recognition

    by Sota Hikasa, Wataru Namiki, Daiki Nishioka, Ryo Iguchi, Jiaxuan Chen, Maki Nishimura, Kazuya Terabe, Takashi Tsuchiya

    Recently, artificial intelligence (AI) technologies have been applied to a wide range of real-world applications. Speech recognition is one of the most important AI tasks and is regarded as a key application for edge-AI systems. Accordingly, speech recognition has been widely used as a benchmark task for evaluating the performance of physical reservoir computing (PRC). However, most PRC studies rely on frequency-feature-extraction methods, such as cochleagram, as input preprocessing. Although these preprocessing methods provide highly discriminative features, they make it difficult to isolate the contribution of the PRC itself. Consequently, the capability required for PRC-only speech recognition remains unclear. In this study, we investigated the processing capability required for PRC-only speech recognition by systematically comparing the presence and absence of cochleagram preprocessing and PRC. As the physical reservoir, we employed a nonlinear interfered spin-wave PRC exhibiting input-frequency-dependent responses. Two speech-recognition tasks, spoken-digit recognition and speaker classification, were evaluated under all combinations of cochleagram preprocessing and PRC processing. When cochleagram preprocessing was employed, both tasks achieved high-recognition accuracy. In contrast, using only the spin-wave PRC yielded approximately 84.6% accuracy for speaker classification, whereas spoken-digit recognition remained at 29.0%. Furthermore, the accuracy of spoken-digit recognition improved when the speaker was fixed, whereas speaker classification maintained relatively high accuracy even when the spoken digit was fixed. These results indicate that speaker classification and spoken-digit recognition require different types of processing in the present spin-wave PRC and provide useful insight into the processing capability required for PRC-only speech recognition.

  • Open Access

    Ion‐Gating Reservoir Computing for Preprocessing‐Free Speech Recognition from Throat Vibrations

    by Daiki Nishioka, Akito Tateyama, Hina Kitano, Takashi Nakanishi, Kazuya Terabe, Takashi Tsuchiya

    Physical reservoir computing offers a promising route to efficient edge‐AI, yet most reservoir‐based speech‐recognition demonstrations still rely on microphones and digital preprocessing. Here, we report a real‐time spoken‐digit recognition system that directly processes throat vibrations by integrating a π–gel‐electret mechano‐electric generator (MEG) sensor with a multi‐channel ion‐gel/graphene ion‐gating reservoir (IGR). The MEG, a free‐deformable electret‐based vibration sensor, converts articulation‐induced throat‐surface vibrations into voltage signals, which are then transformed into pulse sequences and applied directly to the IGR gate without any spectral or handcrafted feature extraction. Channel‐dependent Dirac‐point shifts, nonlinear electric‐double‐layer dynamics, and distinct relaxation behaviors in the IGR expand the one‐dimensional MEG output into high‐dimensional reservoir states, which are decoded using a simple linear classifier. This hybrid MEG–IGR system achieves an impressive real‐time spoken‐digit recognition accuracy of 96.8%, demonstrating that ion‐gating reservoirs can efficiently extract discriminative spatiotemporal features from raw biomechanical signals. By eliminating frequency‐domain preprocessing and enabling compact, low‐power front‐end computation, the approach provides a viable pathway for on‐device speech interfaces. Beyond speech recognition, direct throat‐vibration sensing opens opportunities for robust human–machine interfaces, assistive communication technologies, and secure authentication systems based on spoof‐resistant biomechanical signatures.


  • Open Access

    Computational performance at the edge-of-chaos in the spin-wave interference-based physical reservoir computing

    by Maki Nishimura, Daiki Nishioka, Wataru Namiki, Sota Hikasa, Ryo Iguchi, Kazuya Terabe, Takashi Tsuchiya

    The edge of chaos (EoC) optimizes information processing in nonlinear dynamical systems and is crucial for high computational performance in physical reservoir computing (PRC). This study experimentally investigates a spin-wave interference-based PRC (SWI-PRC) on a YIG single crystal, tuned by external magnetic fields and input pulse intervals. Using phase-space reconstruction and Lyapunov analysis, we identify the EoC and a second optimal regime (second EoC). Performance evaluation through nonlinear waveform transformation tasks shows up to 97% accuracy near the EoC, linking the maximum Lyapunov exponent to computational performance. These findings offer design insights for enhancing information-processing capabilities in edge computing application.


  • Analysis of physical and virtual nodes of ion-gating reservoir for network size reduction

    by Hina Kitano, Daiki Nishioka, Kazuya Terabe, Takashi Tsuchiya

    The rapid expansion of AI applications has intensified concerns regarding excessive energy consumption and training speed. To address these issues, physical reservoir computing (PRC), an energy-efficient machine learning framework, is a suitable approach. However, the network remains highly redundant, and the training efficiency has not yet been fully optimized. To improve training efficiency, we optimized the reservoir size of the electric double layer transistor ion-gating reservoir, a PRC device, using a backward method while evaluating performance on the NARMA2 task. This approach successfully reduced the number of nodes by nearly half without degrading accuracy. Analysis of the remaining nodes revealed that those retaining information from previous input steps contribute most strongly to computation. The ability to reduce node count without loss of performance suggests the potential for faster training and lower power consumption. These findings offer a practical strategy for developing compact and energy-efficient PRC systems suitable for edge-AI applications.


  • Open Access

    High-performance reservoir computing utilizing spin wave interfered with physical masking wave

    by Wataru Namiki, Daiki Nishioka, Kazuya Terabe, Takashi Tsuchiya

    Physical reservoir computing is a promising approach to implement edge-computing. However, realizing the compact reservoir with high-performance is a difficult challenge. Herein, we demonstrated a reservoir computing utilizing spin wave interfered with physical masking wave to improve the reservoir performance. The physical masking was enabled merely by introducing binary or four-valued spin waves from the exciter. On a 10th-order nonlinear autoregressive moving average task, the reservoir successfully reduced the prediction error from 0.164 to 0.152 by introducing the physical masking. The reservoir with physical masking is a significant step closer to the realization of interfered spin wave-based edge-computing.

  • High-accuracy prediction for the NARMA task achieved by eight detectors in nonlinearly interfered spin waves-based physical reservoir computing

    by Maki Nishimura, Wataru Namiki, Daiki Nishioka, Sota Hikasa, Ryo Iguchi, Kazuya Terabe, Takashi Tsuchiya

    Physical reservoir computing enables highly efficient artificial intelligence hardware by replacing neural reservoirs with physical systems exhibiting nonlinearity, short-term memory, and high dimensionality. Spin-wave interference has been predicted to achieve high computational performance through multiple detectors, but performance beyond two channels has not been examined experimentally. In this study, we evaluate the nonlinear autoregressive moving average (NARMA) task performance of a spin-wave reservoir with up to eight detectors and quantify its short-term memory capacity (MC). The normalized mean square error by variance for the NARMA10 task decreased from 0.155 with two channels to 0.130 with eight detectors. Additionally, the MC increased monotonically as the number of detectors was expanded from 2 to 8, demonstrating the effectiveness of spatial multiplexing. These findings confirm that increasing the number of detectors effectively enhances computational capability and provides a promising route toward advanced spin-wave reservoir computing hardware.


  • Open Access

    Physical masking-induced enhancement of information processing capacity in a redox-type ion-gating reservoir

    by Daiki Nishioka, Kaoru Shibata, Wataru Namiki, Kazuya Terabe, Takashi Tsuchiya

    We analyzed the computational mechanism of redox-type ion-gating reservoirs (Redox-IGRs)—a class of physical reservoir computing (PRC) devices that utilize redox dynamics induced by ion gating for information processing—operated with physical masking (PM), in which a simple triangular drain voltage dynamically modulates the conductance of the device. The periodic drain perturbation enriches the temporal diversity of the conductance response, leading to enhanced nonlinear dynamics. Information-processing-capacity (IPC) analysis revealed that PM markedly increases nonlinear capacity while maintaining linear memory capacity, resulting in a total IPC increase from 11 to 20. This doubling of IPC indicates an expansion of the reservoir’s effective dimensionality and explains the improved performance observed in nonlinear dynamical system prediction tasks. These findings demonstrate that PM effectively enhances the expressive power of Redox-IGRs and provides a simple, general strategy for boosting the high-dimensional dynamics of PRC systems.


  • Enhanced computing performance of MoS2-based Raman-ion-gating reservoir achieved by combining reservoir states from current response and resonant Raman scattering

    by Yoshitaka Shingaya, Daiki Nishioka, Kazuya Terabe, Takashi Tsuchiya

    Reservoir computing (RC) is promising for achieving low power consumption neuromorphic devices. In this study, we developed an all-solid-state electric double layer transistor using multilayer MoS2 to realize high-performance physical RC. We have demonstrated the high performance of a MoS2-based Raman-ion-gating reservoir, in which gate voltage-dependent resonant Raman scattering spectra of MoS2 were used as computational resources in addition to drain and gate current responses. Our device achieved good performance, such as >97% accuracy in various nonlinear waveform transformations and 97.8% accuracy in solving a second-order nonlinear dynamic equation. Information processing capacity was evaluated to elucidate the origin of the high performance of our system.


  • Open Access

    Two Orders of Magnitude Reduction in Computational Load Achieved by Ultrawideband Responses of an Ion-Gating Reservoir

    by Daiki Nishioka, Hina Kitano, Wataru Namiki, Satofumi Souma, Kazuya Terabe, Takashi Tsuchiya

    The rising energy demands of conventional AI systems underscore the need for efficient computing technologies, such as brain-inspired computing. Physical reservoir computing (PRC), leveraging the nonlinear dynamics of physical systems for information processing, has emerged as a promising approach for neuromorphic computing. However, current PRC systems are constrained by narrow responsive time scales and limited performance. To address these challenges, an ion-gel/graphene electric double layer (EDL) transistor-based ion-gating reservoir (IGR) was developed. This IGR achieves a highly tunable and ultrawide time-scale response through the coexistence of fast EDL dynamics at the ion-gel/graphene interface and slower molecular adsorption dynamics on the graphene surface. Consequently, the system demonstrates an exceptionally broad responsive range, from 1 MHz to 20 Hz, while maintaining a high information processing capacity and adaptability across multiple time scales. The IGR achieved deep learning (DL)-level accuracy in chaotic time series prediction tasks while reducing computational resource requirements to 1/100 of those needed by DL. Principal component analysis reveals the IGR's superior performance stems from its high-dimensionality, driven by the ultrawideband responses of the EDL along with the ambipolar behavior of graphene. The proposed IGR represents a significant step forward in providing low-power, high-performance computing solutions, particularly for resource-constrained edge environments.


  • Open Access

    Physical reservoir computing with graphene-based solid electric double layer transistor and the information processing capacity analysis

    by Hina Kitano, Daiki Nishioka, Kazuya Terabe, Takashi Tsuchiya

    Physical reservoir computing (PRC) is helpful for power reduction in machine learning technology, although the challenge is to improve computational performance. In this study, we developed a PRC device utilizing ion-electron coupled dynamics in an electric double layer transistor (EDLT) consisting of monolayer graphene channels and a Li+ conducting inorganic oxide thin film. The ambipolar transfer characteristics of graphene channels in the EDLT obtained complex and diverse drain current responses, providing high information processing capacity and high PRC performance in the nonlinear autoregressive moving average (NARMA) task.