Closed-Loop Decoder Adaptation on Intermediate Time-Scales Facilitates Rapid BMI Performance Improvements Independent of Decoder Initialization Conditions
Closed-Loop Decoder Adaptation on Intermediate Time-Scales Facilitates Rapid BMI Performance Improvements Independent of Decoder Initialization Conditions
复制标题
DOI：
10.1109/tnsre.2012.2185066
复制
发表时间：
2012-07-01
影响因子：
4.9
通讯作者：
Carmena, Jose M.
中科院分区：
文献类型：
--
作者：
Orsborn, Amy L.;Dangi, Siddharth;Carmena, Jose M.
闭环解码器自适应（Closed-loop decoder adaptation，CLDA）在改善闭环脑机接口（brain-machine interface，BMI）性能方面有很大的潜力。开发适应算法能够快速提高性能，独立于初始性能，可能是至关重要的临床应用中，患者有有限的运动和感觉能力，由于运动缺陷。给定闭环BMI中固有的主体-解码器交互，当初始性能受限时，解码器自适应时间尺度可能特别重要。在这里，我们提出了SmoothBatch，CLDA算法更新解码器参数的1-2分钟的时间尺度上使用指数加权滑动平均。该算法通过一只非人类灵长类动物执行中心向外到达BMI任务进行了实验测试。SmoothBatch以四种不同的离线解码能力接种：1）光标的视觉观察（n = 20），2）同侧手臂运动（n = 8），3）基线神经活动（n = 17）和4）任意权重（n= 11）。SmoothBatch快速提高了性能，无论播种如何，性能在13.1 +/- 5.5分钟内从0.018 +/- 0.133成功/分钟提高到>8成功/分钟（n = 56）。在解码器自适应停止后，该主题保持了高性能。此外，性能的改善被SmoothBatch收敛所证实，这表明CLDA涉及主体和解码器之间的共同适应过程。
Closed-loop decoder adaptation (CLDA) shows great promise to improve closed-loop brain-machine interface (BMI) performance. Developing adaptation algorithms capable of rapidly improving performance, independent of initial performance, may be crucial for clinical applications where patients have limited movement and sensory abilities due to motor deficits. Given the subject-decoder interactions inherent in closed-loop BMIs, the decoder adaptation time-scale may be of particular importance when initial performance is limited. Here, we present SmoothBatch, a CLDA algorithm which updates decoder parameters on a 1-2 min time-scale using an exponentially weighted sliding average. The algorithm was experimentally tested with one nonhuman primate performing a center-out reaching BMI task. SmoothBatch was seeded four ways with varying offline decoding power: 1) visual observation of a cursor (n = 20), 2) ipsilateral arm movements (n = 8), 3) baseline neural activity (n = 17), and 4) arbitrary weights (n= 11). SmoothBatch rapidly improved performance regardless of seeding, with performance improvements from 0.018 +/- 0.133 successes/min to >8 successes/min within 13.1 +/- 5.5 min (n = 56). After decoder adaptation ceased, the subject maintained high performance. Moreover, performance improvements were paralleled by SmoothBatch convergence, suggesting that CLDA involves a co-adaptation process between the subject and the decoder.