Data Pre-Processing. Data preprocessing involves cleaning and transforming raw data to enhance its quality and usability for analysis, typically including tasks such as handling missing values, outlier detection, normalization, and feature scaling. This step is crucial for ensuring accurate and reliable results in data analysis and modeling.
Data Pre-Processing. 2.3.1. Affymetrix GeneChip⃝c xxXXX Array Intensity .CEL files were obtained from the scan images and imported to the Affymetrix⃝c xxXXX QC Tool software (Version 1.0.33.0) to quantify the signal value. Quality control (QC) was assessed by plotting the average intensity of the oligo spike-in and background probe sets (included in the control target content) across all of the arrays. According to Xxxxxxxxxx, oligo spike-in 2, 23, 29, 31 and 36 probe sets should present a value of more than 1000 intensity units to accept array quality. The xxXXX arrays were detected using the Affymetrix detection algorithm, based on the non-parametric Wilcoxon rank-sum test, applied independently on each array and probe/probe set; a p-value greater than 0.06 stands for “not detected above background” [19]. For data normalization, the “default” method was used, obtaining log2 expression values (expression values data matrix) from the raw data (intensity values data matrix). Briefly, this method involved the following three steps: grouping the background probes intensities based on GCcontent, where the median intensity of each bin was the correction value for each probe with the same GC content; a quantile normalization and, finally, a median polish summarization. To obtain a single intensity value for each xxXXX mapped on the log2 array, intensity measures for replicated spots were averaged.
Data Pre-Processing. The first five minutes from each recording file was excluded to allow blood vessels in the wrist time to adapt to compression from the E4’s sensors (Xxxxxx et al., 2015). Recordings for each day of participation were segmented into 20- 40- and 60-minute epochs using an automated script written in Python and categorised as on- or off-shift. All participants had at least one day meeting this criterion. To reduce the risk of sampling bias, data were resampled 1,000 times and 10 random samples of on-shift and off-shift recordings were extracted for all participants for each day of participation. Aggregate results for these random samples were then calculated and reported below.
