The phase-sensitive time-domain reflectometer (φ-OTDR) has been popularly used for events detection over a long period of time. In this study, the events classification methods based on convolutional neural networks (CNNs) with different features, i.e., the temporal-spatial features and time-frequency features, are compared and analyzed comprehensively in φ-OTDR. The developed CNNs aim at distinguishing three typical events: wind blowing, knocking, and background noise. The classification accuracy based on temporal-spatial images is higher than that based on time-frequency images (99.49% versus 98.23%). The work here sets a meaningful reference for feature extraction and application in the pattern recognition of φ-OTDR.

Stokes vectors direct detection (SV-DD) is an effective solution for short-reach optical communications. In this Letter, we investigate two-dimensional-modulation direct-detection systems based on three Stokes vector receivers (SVRs). The influences of three key factors including the states-of-polarization (SOP), the splitting ratio of the coupler, and the excess loss (EL) are studied in detail. It is shown that the splitting ratio for achieving optimum performance will be changed with SOP and EL conditions. Among these SVRs, the 3×3 coupler-based receiver with its optimal splitting ratio shows the best bit error rate performance and stability against the change of SOP.