Sichuan Tourism University

A lightweight attention-enhanced intrusion detection method for anomalous network traffic analysis

Network intrusion detection in complex traffic environments requires a careful balance between detection performance and computational efficiency, particularly when models are intended for resource-constrained scenarios. Existing deep learning-based intrusion detection methods ca...

Quantifying the Minimal Stable Footprint of Nanophotonic Inverse Design via Geometric Phase Sensitivity

ABSTRACT Adjoint‐based inverse design enables high‐performance nanophotonic devices but typically operates as a black box regarding design footprint, often resulting in spatially redundant or computationally expensive solutions. Here, we introduce a phase‐analytic framework that...

Multi-omics and machine learning reveal the mechanisms underlying cultivar-driven flavor differentiation in fermented ciba chili

Ciba chili quality is strongly influenced by raw material characteristics, but the cultivar-driven mechanisms underlying quality differentiation remain unclear. Ciba chili made from Inner Yellow New Generation (ICP), Lantern (LCP), and Devil's (DCP) peppers was comprehensively in...