Search Results for author: Mohammad Ali

Found 8 papers, 3 papers with code

Model Predictive Control with Infeasible Reference Trajectories

no code implementations10 Sep 2021 Ivo Batkovic, Mohammad Ali, Paolo Falcone, Mario Zanon

Model Predictive Control (MPC) formulations are typically built on the requirement that a feasible reference trajectory is available.

Develop Health Monitoring and Management System to Track Health Condition and Nutrient Balance for School Students

no code implementations25 Oct 2020 Mohammad Ali

Health Monitoring and Management System (HMMS) is an emerging technology for decades.

Human-Computer Interaction

Multi-Dialect Arabic BERT for Country-Level Dialect Identification

1 code implementation COLING (WANLP) 2020 Bashar Talafha, Mohammad Ali, Muhy Eddin Za'ter, Haitham Seelawi, Ibraheem Tuffaha, Mostafa Samir, Wael Farhan, Hussein T. Al-Natsheh

Our winning solution itself came in the form of an ensemble of different training iterations of our pre-trained BERT model, which achieved a micro-averaged F1-score of 26. 78% on the subtask at hand.

Dialect Identification Language Modelling

Safe Trajectory Tracking in Uncertain Environments

no code implementations30 Jan 2020 Ivo Batkovic, Mohammad Ali, Paolo Falcone, Mario Zanon

In Model Predictive Control (MPC) formulations of trajectory tracking problems, infeasible reference trajectories and a-priori unknown constraints can lead to cumbersome designs, aggressive tracking, and loss of recursive feasibility.

Learning When to Drive in Intersections by Combining Reinforcement Learning and Model Predictive Control

no code implementations1 Aug 2019 Tommy Tram, Ivo Batkovic, Mohammad Ali, Jonas Sjöberg

In this paper, we propose a decision making algorithm intended for automated vehicles that negotiate with other possibly non-automated vehicles in intersections.

Decision Making

Learning Negotiating Behavior Between Cars in Intersections using Deep Q-Learning

no code implementations24 Oct 2018 Tommy Tram, Anton Jansson, Robin Grönberg, Mohammad Ali, Jonas Sjöberg

Moreover, inferring information over time is important to distinguish between different intentions and is shown by comparing the collision rate between a Deep Recurrent Q-Network at 0. 85% and a Deep Q-learning at 1. 75%.

Q-Learning

Randomization inference with general interference and censoring

1 code implementation6 Mar 2018 Wen Wei Loh, Michael G. Hudgens, John D. Clemens, Mohammad Ali, Michael E. Emch

Permitting right censored outcomes is challenging because standard randomization-based tests of the null hypothesis of no treatment effect assume that whether an individual is censored does not depend on treatment.

Methodology

Cannot find the paper you are looking for? You can Submit a new open access paper.