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.
Software development projects rely on issue tracking systems at the core of tracking maintenance tasks such as bug reports, and enhancement requests. Incoming issue-reports on these issue tracking systems must be managed in an effective manner. First, they must be labelled and then assigned to a particular developer with relevant expertise. This handling of issue-reports is critical and requires thorough scanning of the text entered in an issue-report making it a labor-intensive task. In this paper, we present a unified framework called MaintainoMATE, which is capable of automatically categorizing the issue-reports in their respective category and further assigning the issue-reports to a developer with relevant expertise. We use the Bidirectional Encoder Representations from Transformers (BERT), as an underlying model for MaintainoMATE to learn the contextual information for automatic issue-report labeling and assignment tasks. We deploy the framework used in this work as a GitHub application. We empirically evaluate our approach on GitHub issue-reports to show its capability of assigning labels to the issue-reports. We were able to achieve an F1-score close to 80\%, which is comparable to existing state-of-the-art results. Similarly, our initial evaluations show that we can assign relevant developers to the issue-reports with an F1 score of 54\%, which is a significant improvement over existing approaches. Our initial findings suggest that MaintainoMATE has the potential of improving software quality and reducing maintenance costs by accurately automating activities involved in the maintenance processes. Our future work would be directed towards improving the issue-assignment module.