记忆电阻器
计算机科学
稳健性(进化)
冯·诺依曼建筑
人工神经网络
噪音(视频)
非线性系统
横杆开关
人工智能
信号处理
电子工程
边缘计算
油藏计算
GSM演进的增强数据速率
计算机工程
计算机硬件
特征(语言学)
数据建模
特征提取
均方预测误差
深度学习
德拉姆
循环神经网络
实时计算
硬件体系结构
集成电路
深层神经网络
作者
Lun Lu,Ao Xu,Youpeng Wu,Mingxin Deng,Yi Sun,Zhiwei Li,Yinan Wang,Qingjiang Li
标识
DOI:10.1109/tbcas.2026.3662427
摘要
The prediction of epileptic seizures can significantly improve patients' quality of life by enabling timely preventive interventions. However, realizing automated real-time prediction on edge hardware remains challenging due to high computational complexity, inefficient temporal signal processing, and the von Neumann bottleneck. In this work, we propose a memristor-based multi-stage reservoir computing architecture that jointly addresses algorithmic and hardware limitations. Volatile memristors are employed in reservoir modules to perform nonlinear temporal feature extraction, avoiding error accumulation issues commonly observed in recurrent neural networks. Non-volatile memristor crossbar arrays are further integrated to implement in-memory analog multiply-accumulate operations, significantly reducing data movement and improving hardware efficiency. Owing to the proposed multi-stage structure, high prediction accuracy is achieved with only 1,700 trainable parameters. Moreover, comprehensive hardware-aware evaluations are conducted, including input noise injection, device-to-device and cycle-to-cycle variations to assess robustness against memristor non-idealities. Results demonstrate that the proposed system achieves over 97% accuracy in simulation and exceeds 95% accuracy in hardware experiments, while maintaining stable performance under substantial noise, making it a promising low-power solution for real-time seizure prediction on edge platforms.
科研通智能强力驱动
Strongly Powered by AbleSci AI