适用于高性能系统的多进程解压缩软件(A multiprocess decompression software for high-performance system)

A compact U-Net-inspired convolutional neural network with 740,551 parameters, designed to predict non-apnea sleep arousals from full-length multi-channel polysomnographic recordings at 5-millisecond resolution. Achieves similar performance to DeepSleep with lower computational cost.

Using Dynamic Programming (DP) method to optimize a 0/1 Knapsack Problem for Amazon shopping list.

Measure the time for large-scale operations and contribute to the exploration of computational efficiency.

Boost Python's performance using Cython – a bridge between Python's simplicity and C's efficiency. Explore and learn how Cython accelerates code execution.

Machine Learning Research to Advance Simulation Science

Switchable Contact Model (SCM) modification of LIGGGHTS-PFM code to represent complex porous boundaries and improved primitive geometry functions for fix wall/gran function. SCM enables the representation of repetitive porous structures without the use of meshing owing to the new primitive wall definitions ycylinder/plane_cinite_porous.