Tibor Haller demonstrates the CML Framework at IEEE WiMob 2026
Tibor Haller presented our demonstration Tracing a DSM-5 Depression Assessment from Score to Formula on Edge Hardware at IEEE WiMob 2026 in Avignon, France, 14 to 16 October. Congratulations, Tibor!
The demo implements the Contextual Multimodal Linkage (CML) Framework from Tibor’s Master’s thesis, Explainable Multimodal-based Depression Awareness at the Edge. The framework maps speech and network biomarkers onto the nine DSM-5 indicators of a depressive episode through five closed-form layers, so every assessment can be traced from the verdict to the operator, inputs, and weights that produced it. It runs on a commodity mini-PC with no cloud connection. In the demo, a user runs an assessment over a seeded 14-day workload, inspects the supporting indicators, then changes the context profile and observes the same evidence re-weighted. The data are synthetic and no detection accuracy is claimed. The object of the demonstration is the decision procedure.
The thesis behind the demo was an excellent piece of work. It delivered the framework, a complete open-source implementation with a dashboard (code, video), and the demonstration paper itself.
Copy & share
Edit if you like, then copy and paste into your post.