• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

使用欠完备自编码器实现紧凑且低功耗的神经尖峰压缩。

Compact and Low-Power Neural Spike Compression Using Undercomplete Autoencoders.

出版信息

IEEE Trans Neural Syst Rehabil Eng. 2019 Aug;27(8):1529-1538. doi: 10.1109/TNSRE.2019.2929081. Epub 2019 Jul 16.

DOI:10.1109/TNSRE.2019.2929081
PMID:31331895
Abstract

Implantable microsystems that collect and transmit neural data are becoming very useful entities in the field of neuroscience. Limited by high data rates, on-chip compression is often required to transmit the recorded data without causing power dissipation at levels that would damage sensitive brain tissue. This paper presents a data compression system designed for brain-computer interfaces (BCIs) based on undercomplete autoencoders. To the best of our knowledge, the proposed system is the first to achieve an average spike reconstruction quality of 14-dB signal-to-noise-and-distortion ratio (SNDR) at a 32× compression ratio (CR), 18-dB SNDR at a 16× CR, 22-dB SNDR at an 8× CR, and 35-dB SNDR at a 4× CR of neural spikes. The spike detection and autoencoder-based compression modules are designed and implemented in a standard 45-nm CMOS process. The post-synthesis simulation results report that the compression module consumes between 1.4 and 222.5 [Formula: see text] of power per channel and takes between 0.018 and 0.082mm of silicon area, depending on the desired CR and number of channels.

摘要

用于收集和传输神经数据的植入式微系统在神经科学领域正变得非常有用。由于数据速率较高,为了在不引起功耗的情况下传输记录的数据,往往需要在片上进行压缩,以免损坏敏感的脑组织。本文提出了一种基于欠完备自动编码器的脑机接口(BCI)数据压缩系统。据我们所知,该系统在 32×压缩比(CR)、16×CR、8×CR 和 4×CR 下,实现了平均尖峰重建质量为 14dB 信噪比和失真比(SNDR),在 18dB SNDR 下实现了 16×CR,在 22dB SNDR 下实现了 8×CR,在 35dB SNDR 下实现了 4×CR 的神经尖峰。尖峰检测和基于自动编码器的压缩模块是在标准的 45nm CMOS 工艺中设计和实现的。综合后的仿真结果表明,压缩模块每个通道消耗的功率在 1.4 到 222.5 [Formula: see text]之间,占用的硅面积在 0.018 到 0.082mm 之间,具体取决于所需的 CR 和通道数量。

相似文献

1
Compact and Low-Power Neural Spike Compression Using Undercomplete Autoencoders.使用欠完备自编码器实现紧凑且低功耗的神经尖峰压缩。
IEEE Trans Neural Syst Rehabil Eng. 2019 Aug;27(8):1529-1538. doi: 10.1109/TNSRE.2019.2929081. Epub 2019 Jul 16.
2
A Vector Quantization-Based Spike Compression Approach Dedicated to Multichannel Neural Recording Microsystems.基于矢量量化的尖峰压缩方法,专用于多通道神经记录微系统。
Int J Neural Syst. 2022 Mar;32(3):2250001. doi: 10.1142/S0129065722500010. Epub 2021 Dec 20.
3
A method for compression of intra-cortically-recorded neural signals dedicated to implantable brain-machine interfaces.一种用于压缩皮层内记录的神经信号的方法,该方法专用于可植入式脑机接口。
IEEE Trans Neural Syst Rehabil Eng. 2015 May;23(3):485-97. doi: 10.1109/TNSRE.2014.2355139. Epub 2014 Sep 12.
4
Low-power hardware for neural spike compression in BMIs.用于脑机接口中神经尖峰压缩的低功耗硬件。
Annu Int Conf IEEE Eng Med Biol Soc. 2013;2013:2156-9. doi: 10.1109/EMBC.2013.6609961.
5
Efficient in Vivo Neural Signal Compression Using an Autoencoder-Based Neural Network.基于自动编码器神经网络的高效体内神经信号压缩。
IEEE Trans Biomed Circuits Syst. 2024 Jun;18(3):691-701. doi: 10.1109/TBCAS.2024.3359994. Epub 2024 May 28.
6
A closed-loop compressive-sensing-based neural recording system.一种基于闭环压缩感知的神经记录系统。
J Neural Eng. 2015 Jun;12(3):036005. doi: 10.1088/1741-2560/12/3/036005. Epub 2015 Apr 15.
7
A Hardware-Efficient Scalable Spike Sorting Neural Signal Processor Module for Implantable High-Channel-Count Brain Machine Interfaces.一种用于可植入高通道数脑机接口的硬件高效可扩展尖峰排序神经信号处理器模块
IEEE Trans Biomed Circuits Syst. 2017 Aug;11(4):743-754. doi: 10.1109/TBCAS.2017.2679032. Epub 2017 May 24.
8
Data compression in brain-machine/computer interfaces based on the Walsh-Hadamard transform.基于沃尔什-哈达玛变换的脑机/计算机接口中的数据压缩
IEEE Trans Biomed Circuits Syst. 2014 Feb;8(1):129-37. doi: 10.1109/TBCAS.2013.2258669.
9
A 0.7 V, 40 nW Compact, Current-Mode Neural Spike Detector in 65 nm CMOS.一款采用65纳米互补金属氧化物半导体(CMOS)技术的0.7伏、40纳瓦紧凑型电流模式神经尖峰探测器。
IEEE Trans Biomed Circuits Syst. 2016 Apr;10(2):309-18. doi: 10.1109/TBCAS.2015.2432834. Epub 2015 Jul 7.
10
A Streaming PCA VLSI Chip for Neural Data Compression.用于神经数据压缩的流形主成分分析 VLSI 芯片。
IEEE Trans Biomed Circuits Syst. 2017 Dec;11(6):1290-1302. doi: 10.1109/TBCAS.2017.2717281. Epub 2017 Aug 14.

引用本文的文献

1
Exploring Synergies in Brain-Machine Interfaces: Compression vs. Performance.探索脑机接口中的协同效应:压缩与性能
bioRxiv. 2025 Feb 3:2025.02.03.636273. doi: 10.1101/2025.02.03.636273.
2
A hardware-efficient on-implant spike compression processor based on VQ-DAE for brain-implantable microsystems.一种基于VQ-DAE的用于脑植入式微系统的硬件高效植入式尖峰压缩处理器。
Med Biol Eng Comput. 2025 Feb 8. doi: 10.1007/s11517-025-03317-x.
3
68-channel neural signal processing system-on-chip with integrated feature extraction, compression, and hardware accelerators for neuroprosthetics in 22 nm FDSOI.
采用22纳米全耗尽型绝缘层上硅(FDSOI)技术、集成特征提取、压缩和硬件加速器的用于神经假体的68通道神经信号处理片上系统。
Front Neurosci. 2024 Oct 23;18:1432750. doi: 10.3389/fnins.2024.1432750. eCollection 2024.
4
Low-Power Lossless Data Compression for Wireless Brain Electrophysiology.无线脑电生理的低功耗无损数据压缩。
Sensors (Basel). 2022 May 12;22(10):3676. doi: 10.3390/s22103676.