###### tags: `論文摘要` `穩定性` `LFP`

# Decoding Hand Kinematics from Local Field Potentials Using Long Short-Term Memory (LSTM) Network
* 時間: 2019
* Conference: IEEE EMBS Conference on Neural Engineering
* Link: https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8717045
* MLA: Ahmadi, Nur, Timothy G. Constandinou, and Christos-Savvas Bouganis. "Decoding hand kinematics from local field potentials using long short-term memory (lstm) network. In 2019 9th International IEEE." EMBS Conference on Neural Engineering (NER).

## 概論
該篇指出目前BMI遇到的兩個問題。
首先記錄到的spk會隨時間而減少，故而降低解碼器表現；
其次由於fs較高的緣故，故而detect或者sorting spk訊號，亦或是傳輸raw data都將變得十分耗費功率，進而減少晶片電池壽命。
故而該篇論文使用較為低頻的LFP訊號進行解碼，藉此減少硬體運算成本及增加其長期穩定性。