Afiya Ayman, Michael Wilbur, Amutheezan Sivagnanam, Philip Pugliese, Abhishek Dubey, Aron Laszka
2020 IEEE International Conference on Smart Computing (SMARTCOMP) (SMARTCOMP 2020) 2020
Data-driven approaches are increasingly central to building intelligent systems that can adapt to real-world complexity and uncertainty. Understanding effective methodologies for extracting knowledge from data is critical for advancing automation and decision-making in complex systems. This foundational work provides important perspective on how data-driven methods can be applied to intelligent system development.
This paper presents foundational work on data-driven methods for intelligent systems, examining how to extract useful models and decision procedures from large-scale data. The work addresses fundamental challenges in data management, processing, and utilization for building intelligent systems that can learn from experience and adapt to changing conditions.
The work establishes key principles and methodologies for data-driven system development, providing frameworks that have influenced subsequent research in machine learning and intelligent control systems. The contributions help establish the theoretical and practical foundations for data-driven approaches to system design.
@inproceedings{Lasz2006Data,
author = {Ayman, Afiya and Wilbur, Michael and Sivagnanam, Amutheezan and Pugliese, Philip and Dubey, Abhishek and Laszka, Aron},
booktitle = {2020 IEEE International Conference on Smart Computing (SMARTCOMP) (SMARTCOMP 2020)},
title = {Data-Driven} Prediction of {Route-Level} Energy Use for {Mixed-Vehicle} Transit Fleets},
year = {2020},
address = {Bologna, Italy},
month = {jun},
acceptance = {32},
abstract = {Due to increasing concerns about environmental impact, operating costs, and energy security, public transit agencies are seeking to reduce their fuel use by employing electric vehicles (EVs). However, because of the high upfront cost of EVs, most agencies can afford only mixed fleets of internal-combustion and electric vehicles. Making the best use of these mixed fleets presents a challenge for agencies since optimizing the assignment of vehicles to transit routes, scheduling charging, etc. require accurate predictions of electricity and fuel use. Recent advances in sensor-based technologies, data analytics, and machine learning enable remedying this situation; however, to the best of our knowledge, there exists no framework that would integrate all relevant data into a route-level prediction model for public transit. In this paper, we present a novel framework for the data-driven prediction of route-level energy use for mixed-vehicle transit fleets, which we evaluate using data collected from the bus fleet of CARTA, the public transit authority of Chattanooga, TN. We present a data collection and storage framework, which we use to capture system-level data, including traffic and weather conditions, and high-frequency vehicle-level data, including location traces, fuel or electricity use, etc. We present domain-specific methods and algorithms for integrating and cleansing data from various sources, including street and elevation maps. Finally, we train and evaluate machine learning models, including deep neural networks, decision trees, and linear regression, on our integrated dataset. Our results show that neural networks provide accurate estimates, while other models can help us discover relations between energy use and factors such as road and weather conditions.},
contribution = {colab},
days = {21},
keywords = {data-driven methods, intelligent systems, machine learning, data analytics, decision procedures},
tag = {ai4cps,transit},
month_numeric = {6}
}