Zahid Anwar

Dr. Zahid Anwar


Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 November 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
NANasir Ahtasham
Nasir Ahtasham
ZAZahid Anwar
Zahid Anwar
MMMuhammad Zubair Zubair Malik
Muhammad Zubair Zubair Malik
ZMZia Muhammad
Zia Muhammad
Drive-mode advisement requires both reliable classification and explicit rules for accepting and communicating recommendations. This paper presents a modular framework that links longitudinal vehicle signals to Eco, Tour, and Sport advisement, temporal mode acceptance, and simulated subsystem-command generation. The input design uses throttle position, engine speed, vehicle speed, and longitudinal acceleration, with an optional engineered throttle–engine-speed interaction. Logistic regression, nearest neighbors, and random forest are compared on 67,440 recorded samples using a fixed stratified random-row split and training-only preprocessing. The four-input random forest achieves 96.98% accuracy and a macro-averaged F1 score of 0.9683; the five-input reference achieves 96.81% accuracy. Controlled feature ablation and 180 throttle-perturbation runs characterize representation dependence and input sensitivity. The compiled five-input reference has a mean single-request host latency of 43.08 microseconds and 30.890 mebibytes of static model data. A MATLAB/Simulink implementation combines confidence gating, a dwell-time state machine, parameter lookup, command bounds, slew limits, and software controller-area-network encoding. Five baseline scenarios and a 45-run sensitivity sweep reproduce configured acceptance delays, suppress brief erroneous recommendations, and preserve command consistency. The results establish classification within the available recordings and an executed software advisory-to-command path.