The dark secret of AI is that the models are black boxes. We can see what goes in (to an extent) and what comes out. In between, all accessibility to human insight, interpretation, and accountability is blacked out. And it starts with tokenization. Tokenization is the process of taking letters, words, paragraphs (or numbers, equations, …

I’ve raised the issue before with Andy Coggan. He has not given proper attribution to Peronnet and Thibault as the source model for his own model. The Peronnet and Tibault model is a reasonable model that is an extension of Ward-Smith which a modification of LLoyd which is an extension of Hill. Hill: P(t) = …

Michael J. Puchowicz, Jonathan Baker & David C. Clarke (2020) Development and field validation of an omni-domain power-duration model, Journal of Sports Sciences, DOI: 10.1080/02640414.2020.1735609 Purpose: To validate and compare a novel model based on the critical power (CP) concept that describes the entire domain of maximal mean power (MMP) data from cyclists. Methods: An omni-domain power-duration (OmPD) model was …

When I drill down in to data it’s no surprise when I catch small errors and discrepancies pop. But the thing that jumped out when drilling down into the Cobo ABP data http://veloclinic.com/cobo-athlete-biological-passport-visualization-and-discussion/ was that the Z-score model was apparently producing far wider cut offs than the actual ABP. Jeroen Swart pointed this out to …

Its blood data, so you know I have to take a look. The UCI broke its long biopassport sanction drought by going after a retired rider on a minor team best know for blowing things up at the Vuelta. The upshot is they handed the red (formerly gold) jersey to Froome who rode said Vuelta, …

https://journals.lww.com/acsm-msse/Abstract/2019/02000/Effects_of_EPO_on_Blood_Parameters_and_Running.10.aspx First off, I’ve only read the abstract and from that I’m just thinking what the hell was the point? But I could not not write that title so here you go. Allez.

Its like porn, difficult to define but you know it when you see it… Lets take a vote: Example 1 or Example 2 Flock, do your thing and make answers.

This post follows from the Accessing the Golden Cheetah OpenData post. This gist starts the process of developing an interval detection algorithm utilizing statistical change point detection. For python ‘ruptures’ is a library that offer several options for change point detection.

Athlete doping rarely happens in isolation. So why do ADAs try to tackle the problem that way? Consider this toy model of the social structure of a doping network. We may have individuals who may be Athletes, Trainers, Coaches, and Doctors. The individuals may instigate doping behavior, be reactive to doping behavior (dope if pressured, …

In the white is Skiba’s W’balance that you all know and love. I’ve combined this now with the interval discovery algorithm so that we can now visualize the change in W’bal by interval in green. ## R script will run on selection. ## ## GC.activity() ## GC.metrics(all=FALSE) ## ## Get the current ride or metrics …