This chapter contains a summary of the paper in Ref. [1], in which the challenges in detecting gravitational-wave (GW) signals, especially when only one detector is operating, are discussed. The single detector case is particularly difficult to analyse since a very useful tool to distinguish astrophysical signals from instrumental glitches cannot be used, i.e. the temporal coincidence between detectors. Neural network classifiers are explored, including convolutional neural networks, temporal convolutional networks, and inception time, specifically tailored for time-series data processing. The classifiers are trained on a subset of data from the LIGO Livingston detector during the first observing run (O1) to identify segments containing binary black hole merger signatures. Their performances are evaluated and compared. Subsequently, these trained classifiers are applied to the remaining O1 data, particularly focusing on single-detector times, with the most promising candidate from this search identified at the time 2016-01-04 12:24:17 UTC.