Open Access. Powered by Scholars. Published by Universities.®

Engineering Commons™

Open Access. Powered by Scholars. Published by Universities.®

Machine Learning

Selected Works

Articles 1 - 4 of 4

Full-Text Articles in Engineering

Hybrid Agent Based Simulation With Adaptive Learning Of Travel Mode Choices For University Commuters (Wip), Nagesh Shukla, Albert Munoz, Jun Ma, Nam Huynh Apr 2015

Hybrid Agent Based Simulation With Adaptive Learning Of Travel Mode Choices For University Commuters (Wip), Nagesh Shukla, Albert Munoz, Jun Ma, Nam Huynh

Nagesh Shukla

This paper presents a methodology for developing a hybrid agent-based micro-simulation model to capture the impacts of commuter travel mode choices on a University campus transport network. The proposed methodology involves: (i) developing realistic population of commuter agents (students and staff); (ii) assigning activity lists and travel mode choices to agents using machine learning method; and, (iii) traffic micro-simulation of the study area transport network. This furthers the understanding of current transport modal distributions, factors affecting the travel mode choice decisions, and, network performance through a number of hypothetical travel scenarios.

Go to article

Hybrid Agent Based Simulation With Adaptive Learning Of Travel Mode Choices For University Commuters (Wip), Nagesh Shukla, Albert Munoz, Jun Ma, Nam Huynh Feb 2014

Hybrid Agent Based Simulation With Adaptive Learning Of Travel Mode Choices For University Commuters (Wip), Nagesh Shukla, Albert Munoz, Jun Ma, Nam Huynh

Albert Munoz

This paper presents a methodology for developing a hybrid agent-based micro-simulation model to capture the impacts of commuter travel mode choices on a University campus transport network. The proposed methodology involves: (i) developing realistic population of commuter agents (students and staff); (ii) assigning activity lists and travel mode choices to agents using machine learning method; and, (iii) traffic micro-simulation of the study area transport network. This furthers the understanding of current transport modal distributions, factors affecting the travel mode choice decisions, and, network performance through a number of hypothetical travel scenarios.

Go to article

Optimizing Parallel Belief Propagation In Junction Trees Using Regression, Lu Zheng, Ole J. Mengshoel Jul 2013

Optimizing Parallel Belief Propagation In Junction Trees Using Regression, Lu Zheng, Ole J. Mengshoel

Ole J Mengshoel

The junction tree approach, with applications in artificial intelligence, computer vision, machine learning, and statistics, is often used for computing posterior distributions in probabilistic graphical models. One of the key challenges associated with junction trees is computational, and several parallel computing technologies - including many-core processors - have been investigated to meet this challenge. Many-core processors (including GPUs) are now programmable, unfortunately their complexities make it hard to manually tune their parameters in order to optimize software performance. In this paper, we investigate a machine learning approach to minimize the execution time of parallel junction tree algorithms implemented on a …

Go to article

Mobile Computing: Challenges And Opportunities For Autonomy And Feedback, Ole J. Mengshoel, Bob Iannucci, Abe Ishihara May 2013

Mobile Computing: Challenges And Opportunities For Autonomy And Feedback, Ole J. Mengshoel, Bob Iannucci, Abe Ishihara

Ole J Mengshoel

Mobile devices have evolved to become computing platforms more similar to desktops and workstations than the cell phones and handsets of yesteryear. Unfortunately, today’s mobile infrastructures are mirrors of the wired past. Devices, apps, and networks impact one another, but a systematic approach for allowing them to cooperate is currently missing. We propose an approach that seeks to open key interfaces and to apply feedback and autonomic computing to improve both user experience and mobile system dynamics.

Go to article