1,720,971 research outputs found
Supplemental_Tables_792195 - Treatment History of Youth At-Risk for Serious Mental Illness
No full textSupplemental_Tables_792195 for Treatment History of Youth At-Risk for Serious Mental Illness by Megan S. Farris, Glenda MacQueen, Benjamin I. Goldstein, JianLi Wang, Sidney H. Kennedy, Signe Bray, Catherine Lebel, and Jean Addington in The Canadian Journal of Psychiatry</p
sj-docx-1-aut-10.1177_13623613211064372 – Supplemental material for Autism interest intensity in early childhood associates with executive functioning but not reward sensitivity or anxiety symptoms
No full textSupplemental material, sj-docx-1-aut-10.1177_13623613211064372 for Autism interest intensity in early childhood associates with executive functioning but not reward sensitivity or anxiety symptoms by Kate J Godfrey, Svenja Espenhahn, Mehak Stokoe, Carly McMorris, Kara Murias, Adam McCrimmon, Ashley D Harris and Signe Bray in Autism</p
sj-docx-1-cpa-10.1177_07067437231195959 - Supplemental material for Factors Associated with Transition to Serious Mental Illness
No full textSupplemental material, sj-docx-1-cpa-10.1177_07067437231195959 for Factors Associated with Transition to Serious Mental Illness by Sara Jalali, Lu Liu, JianLi Wang and
Sidney H. Kennedy, Glenda MacQueen, Catherine Lebel, Benjamin l. Goldstein, Signe Bray, Jean Addington in The Canadian Journal of Psychiatry</p
Classification results with feature spaces including oxy-Hb only (blue), deoxy-Hb only (green), both oxy-Hb and deoxy-Hb (red), CBSI corrected oxy-Hb (cyan), and total (oxy-Hb+deoxy-Hb, pink).
No full text<p>A) accuracy, B) onset delay, and C) offset delay. Compared to the oxy-Hb only feature space, incorporating both oxy-Hb and deoxy-Hb improves the accuracy by 2.4% and reduces the onset delay by 0.3s. The total Hb signal gave the worst classification results; due to poor accuracy, we did not calculate the onset and offset delay for total-Hb.</p
Classification accuracy, onset delay and offset delay as a function of the length of history incorporated into the feature space.
No full text<p>A) Classification accuracy improves up to 1s, and then plateaus. B) Onset delay is reduced from 6s to 3.5s when 0.5s history is incorporated. Longer history doesn't reduce the onset delay further. C) Offset delay is reduced by 1s. Error bars indicate standard error across trials.</p
Including signals from multiple channels into the feature space improves accuracy and reduces delay in participant 1.
No full text<p>A) accuracy, B) onset delay, and C) offset delay. We ordered all 48 channels by decreasing CNR, and then included one additional channel in each round in that order. For this participant the accuracy peaked at 9 channels and then declined due to overfitting. With 9 channels, the onset delay is reduced to 1.2s and the offset delay is reduced to 0.7s.</p
Classification results for all participants.
No full text<p>A) accuracy, B) onset delay C) offset delay. The largest boost in accuracy and drop in delay occurs when history is included in the feature space. For some participants (#1 and #6), including deoxy-Hb or including signals from other channels also improved the performance. Comparing the classifier with the full feature space (history of oxy-Hb and deoxy-Hb, and other channels) to the baseline classifier, the average increase in accuracy is 7.7% (p = 0.004, one sample T test, degree of freedom = 5), the average reduction in onset delay is 2.4s (p = 0.02), and the average reduction in offset delay is 1.3s (p = 0.003).</p
Including first and second order gradients doesn't improve classification performance.
No full text<p>A) accuracy, B) onset delay, and C) offset delay are nearly identical with classifiers based on amplitude, and first or second order gradients.</p
Classification results for the baseline classifier (top row) and a classifier with signal history included in the feature space (bottom row).
No full text<p>The rectangular blue waveform indicates the onset and offset of finger tapping. A,C) The time series of oxy-Hb concentration change in channel 13 in participant 1 is plotted. The time points which are classified as active are plotted in red, and inactive in black. B,D) The time series and classification result of trial 11 is shown in more detail. The feature space of the baseline classifier is simply the amplitude of oxy-Hb in channel 13 (i.e. one dimensional), which essentially classifies based on a single threshold. It's evident from panels A and B that the classified active state (red) is delayed from the true active state (between the vertical blue lines). The onset classification delay in trial 11 is about 6s, and the offset delay is 1.6s. With 2s history of the oxy-Hb signal in channel 13 incorporated into the feature space (C and D, 21-dimensional feature space), the delay is reduced to 4s (onset) and 0.2s (offset).</p
- …
