A 1024-Channel 268 nW/pixel 36x36 μm²/ch Data-Compressive Neural Recording IC for High-Bandwidth Brain-Computer Interfaces

This paper presents a neural recording IC featuring lossy compression during digitization, thus preventing data deluge and enabling a compact active digital pixel design. The wired-OR-based compression discards unwanted baseline samples while allowing the reconstruction of spike samples. The IC features a 32x32 MEA with 36 μ m pixel pitch and...

A human-centric machine learning based personalized route choice prediction in navigation systems

Real-world route navigation data indicate that nontrivial portion of drivers do not prefer the system-recommended best routes. Current navigation systems have simplified assumptions about drivers’ route choice preferences and do not adequately accommodate drivers’ heterogeneous route choice preferences, mainly because of: (i) difficulty in...