Scientific Research Publishing

A Lightweight Self-Supervised Representation Learning Framework for Depression Risk Profiling from Synthetic Daily Behavioural Trajectories ()

Detecting behavioural signatures of depression from everyday digital traces is a central challenge in computational ...
IEEE

Matrix Reshaping for Reduced Sensing Cost and Improved Data Inference in Sparse Mobile Sensing Environments

Abstract: Mobile crowd sensing (MCS) has emerged as a promising sensing paradigm with the widespread adoption of smartphones. However, one of the key bottlenecks in MCS lies in the high sensing cost ...
IEEE

Enhancing BOTDR SNR using Learned-Dictionary Sparse Reconstruction of Brillouin Gain Spectrum Matrix

Abstract: A method of enhancing signal-to-noise ratio (SNR) in Brillouin optical time domain reflectometer (BOTDR) is proposed using sparse reconstruction of the Brillouin gain spectrum (BGS) matrix.