Jun Mou

Cross-Patch Guided Reconstruction With Graph Contrastive Learning for Smartphone-Based Early Parkinson’s Disease Detection

Self-supervised learning for time-series data has broad application potential in smartphone-based early disease detection. However, time-series data often exhibit complex dynamic patterns and spatiotemporal correlations. These characteristics make it difficult to capture discriminative features and reconstruct local fe...

Initial-offset boosted multistability in a novel memristor-regulated hyperchaotic neuron model

A Novel Second-Order Memristor-Coupled FHN Neuron Model with Synergistic Dynamics of Multistability

A novel second-order memristor is designed, the nonvolatile nature of the memristor is verified, and the key dynamical behaviors are reproduced through circuit simulation and a DSP-based hardware experimental platform, realizing the systematic research flow from theoretical modeling, numerical simulation to circuit imp...

Dynamics and DSP implementation of a wide-range locally active memristor–coupled Aihara neuron

These findings provide theoretical and experimental support for employing memristive single neuron coupling in the field of information encryption by identifying three novel dynamical features of the LAM-Aihara map: triangular waveform bursting firings, centrosymmetric coexisting attractors under different initial cond...

History, Development, and Principles of Representation Learning—An Introductory Survey

This survey deeply explains the basic principles of representation learning, and introduces its practical application cases in various fields, and points out the main limitations of current models and prospects the future research directions.