Maya-Vaidya P2: A Four-Head SoftLIF Spiking Neural Network for Wearable Pain Chronification Staging with Buddhi S-Curve Classification and Adaptive BCM Vairagya

Read full text
Authors: Venkatesh Swaminathan
Cited by: 14
References: 27

Abstract

Maya-Vaidya P2 presents a four-head Parallel SoftLIF Spiking Neural Network trained on raw wearable biosignals — electrodermal activity, blood volume pulse, accelerometer, and skin temperature from an Empatica E4 wristband — to predict pain chronification stage without any survey input at inference time, addressing a critical gap in chronic pain assessment for India's approximately 190 million sufferers. The system introduces an AdaptiveChronificationTracker using a frozen BCM synaptic rule, which receives no gradient supervision from any training head yet produces signal patterns that trend toward distinguishing chronic from acute pain stages. On the PhysioPain dataset under Leave-One-Subject-Out cross-validation across 84 subjects, the Buddhi stage classification head achieved 0.4302 accuracy — 29% above the 0.333 chance baseline — with a permutation test yielding p=0.068, a trend toward significance at this sample size. This result sits within the Maya-Vaidya Series and confirms the canonical Buddhi S-curve parameters (k=8.0, t₀=0.45) consistent with findings across 14 or more prior Maya substrates, reinforcing their empirical stability as a cross-substrate labelling standard. Maya-Vaidya P2 is an India-first neuromorphic research prototype, designed for clinical pain analysis in resource-constrained primary care settings, and is not a licensed medical device. Series: Part of the Maya-Vaidya Series — neuromorphic AI for clinical pain analysis. India-first. Research prototype only — NOT a licensed medical device. For medical emergencies in India: 112. Links: GitHub Repository (private — to request access: email research@nexuslearninglabs.in with subject Code Access Request — Maya-Vaidya-P2 and your research context) | Interactive Dashboard | FAQ | Full Series Index — venky2099.github.io Nexus Learning Labs, Bengaluru · UDYAM-KR-02-0122422 · BHASKAR IN-0526-9452JSORCID: 0000-0002-3315-7907 · VAIRAGYA_DECAY_RATE = 0.002315 (embedded in all canonical hyperparameters)Canary: MayaNexusVS2026NLL_Bengaluru_Narasimha

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
3 June 2026
Language
EN