Engineering Commons^™

Credit Assignment For Collective Multiagent Rl With Global Rewards, Duc Thien Nguyen, Akshat Kumar, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

Scaling decision theoretic planning to large multiagent systems is challenging due to uncertainty and partial observability in the environment. We focus on a multiagent planning model subclass, relevant to urban settings, where agent interactions are dependent on their collective influence'' on each other, rather than their identities. Unlike previous work, we address a general setting where system reward is not decomposable among agents. We develop collective actor-critic RL approaches for this setting, and address the problem of multiagent credit assignment, and computing low variance policy gradient estimates that result in faster convergence to high quality solutions. We also develop difference …

Design And Implementation Of Decision Support For Traffic Management At Multipurpose Port Gates, Ketki Kulkarni, Hoong Chuin Lau, Hai Wang, Sathyavarathan Sivabalasingam, Trong Khiem Tran

Research Collection School Of Computing and Information Systems

Effective traffic management can help port operators gain a competitive edge in service level and efficient use of limited resources. One critical aspect of traffic management is gate operations management, ensuring a good customer experience to logistic carriers and considering the impact of congestion in and around the port. In this paper, we describe the design and implementation of a decision support tool to help gate operators plan for future scenarios with fluctuating demand and limited resources. We propose a simulation optimization framework which incorporates theoretical results from queuing theory to approximate complex multi-lane multi-server systems. Our major contribution in …

Using Non-Destructive Testing To Predict Bending Modulus Of Carbon Infiltrated-Carbon Nanotubes, Fred Stile Fagergren

Theses and Dissertations

Fabrication of carbon infiltrated carbon nanotubes (CI-CNT) can result in large mechanical property variation, and methods to characterize properties usually involve destructive testing. Finding a non-destructive way to test for stiffness of this material reduces the number of parts that have to be made. It also simplifies testing of complex parts. The stiffness of CI-CNT beams is related to the type of carbon material infiltrated between the carbon nanotubes (CNTs), how it interacts with the CNTs, and how much of it there is. The amount of material can be estimated using the density of the beam, and both the type …

Sensor-Based Human Activity Recognition Using Bidirectional Lstm For Closely Related Activities, Arumugam Thendramil Pavai

Electronic Theses, Projects, and Dissertations

Recognizing human activities using deep learning methods has significance in many fields such as sports, motion tracking, surveillance, healthcare and robotics. Inertial sensors comprising of accelerometers and gyroscopes are commonly used for sensor based HAR. In this study, a Bidirectional Long Short-Term Memory (BLSTM) approach is explored for human activity recognition and classification for closely related activities on a body worn inertial sensor data that is provided by the UTD-MHAD dataset. The BLSTM model of this study could achieve an overall accuracy of 98.05% for 15 different activities and 90.87% for 27 different activities performed by 8 persons with 4 …

Social Network For Software Developers, Sanket Prabhakar Jadhav

Electronic Theses, Projects, and Dissertations

This project is the design and implementation of a web-based message board for software developers. The purpose of “Social Network for Software Developers” is to connect inexperienced software developers with experienced software developers.

Crude Oil Prices Forecasting: Time Series Vs. Svr Models, Xin James He

Journal of International Technology and Information Management

This research explores the weekly crude oil price data from U.S. Energy Information Administration over the time period 2009 - 2017 to test the forecasting accuracy by comparing time series models such as simple exponential smoothing (SES), moving average (MA), and autoregressive integrated moving average (ARIMA) against machine learning support vector regression (SVR) models. The main purpose of this research is to determine which model provides the best forecasting results for crude oil prices in light of the importance of crude oil price forecasting and its implications to the economy. While SVR is often considered the best forecasting model in …

Table Of Contents Jitim Vol 27 Issue 3, 2018

Journal of International Technology and Information Management

Table of Contents

The Relationship Between Organizational Resources And Green It/S Adoption: A Rbv Approach, Lutfus Sayeed, Alberto Onetti

Journal of International Technology and Information Management

ABSTRACT

The objective of the present study was to empirically explore the impact of the implementation of Green IT/S measures on organizational resources in the US and European firms. The study examined the influence of reconfiguration of resources within a firm while adopting various Green IT/S practices and technologies. Green IT/S implementation requires resource commitment from organizations (Bose and Luo, 2011). What are these resources and how do they affect the extent of Green IT/S measures adopted by businesses? Resource Based View (RBV) of the firm was used as the theoretical framework of the study. The relationship between the adoption …

Feature-Based Transfer Learning In Natural Language Processing, Jianfei Yu

Dissertations and Theses Collection (Open Access)

In the past few decades, supervised machine learning approach is one of the most important methodologies in the Natural Language Processing (NLP) community. Although various kinds of supervised learning methods have been proposed to obtain the state-of-the-art performance across most NLP tasks, the bottleneck of them lies in the heavy reliance on the large amount of manually annotated data, which is not always available in our desired target domain/task. To alleviate the data sparsity issue in the target domain/task, an attractive solution is to find sufficient labeled data from a related source domain/task. However, for most NLP applications, due to …

Modeling Movement Decisions In Networks: A Discrete Choice Model Approach, Larry Lin Junjie

Dissertations and Theses Collection (Open Access)

In this dissertation, we address the subject of modeling and simulation of agents and their movement decision in a network environment. We emphasize the development of high quality agent-based simulation models as a prerequisite before utilization of the model as an evaluation tool for various recommender systems and policies. To achieve this, we propose a methodological framework for development of agent-based models, combining approaches such as discrete choice models and data-driven modeling.

The discrete choice model is widely used in the field of transportation, with a distinct utility function (e.g., demand or revenue-driven). Through discrete choice models, the movement decision …

Relationship Between Road Network Characteristics And Traffic Safety, Hatim Sharif, Samer Dessouky

Publications

The Transportation and Capital Improvement of the City of San Antonio, Texas Department of Transportation (TxDOT) and other related agencies often make several efforts based on traffic data to improve safety at intersections, but the number of intersection crashes is still on the high side. There is no one size fits all solution for intersections and the City is often usually confronted with doing best value option analysis on different solutions to choose the least expensive yet more advancements. The goal of this project was to obtain the relationship between road network characteristics and public safety with a focus on …

Use Of Ultra-High-Performance Fiber-Reinforced Concrete (Uhp-Frc) For Fast And Sustainable Repair Of Pavements, Shih-Ho Chao

Publications

This research presents a new methodology, which enables streets, roads, highways, bridges, and airfields to use an advanced fiber-reinforced concrete material, which can delay or prevent the deterioration of these transportation infrastructure when subjected to traffic and environmental loadings. The major problem of concrete is its considerable deterioration and limited service life due to its brittleness and limited durability. As a result, it requires frequent repair and eventual replacement, which consumes more natural resources. Ultra-high-performance fiber-reinforced concrete (UHP-FRC) introduces significant enhancement in the sustainability of concrete structures due to its dense microstructure and damage-tolerance characteristics. These characteristics can significantly reduce …

Simplified Approach For Structural Evaluation Of Flexible Pavements At The Network Level, Mena Souliman, Stefan Romanoschi, Samer Dessouky

Publications

Currently, there are few available simple procedures to identify structurally weak pavement sections utilizing Falling Weight Deflectometer (FWD) data at the network level (e.g., city, state or province). A simple method is required to determine the structural condition of pavement sections that can be directly implemented and automated in current pavement databases. The objective of this research study is to develop a simple analysis method to determine the structural condition of pavement sections utilizing the currently available non-destructive testing (NDT) deflection measurement devices at the network level that can be directly implemented and automated in the database of a typical …

A Comprehensive Reliability-Based Framework For Corrosion Damage Monitoring And Repair Design Of Reinforced Concrete Structures, Homero Castaneda, Aydin Karsilaya, Ayman Okeil, Mahmoud Reda Taha

Publications

In this work, we developed a comprehensive framework for corrosion management of reinforced concrete (RC) structures. This framework includes critical steps of an effective approach to quantify the damage evolution as well as providing the timeframe for effective maintenance/repair strategies for corrosion assessment in RC structures. The framework included several activities including the use of indirect and direct inspection tools, theoretical development for damage prediction, experimental measurements and theoretical development of repair time based on reliability. The uniqueness of the framework is the integration of deterministic modeling of corrosion damage evolution by using mechanistic analysis with statistical modeling on corrosion …

2018 Summer-Fall Graduate Recognition Program, Propulsion Research Center, Robert Frederick

PRC Graduate Recognition

This program includes the graduate recognition program for summer and fall 2018. Includes photographs, upcoming events, recent publications, and student profiles.

Effect Of Particle Breakage On Ballast Permanent Deformation — A Study Using The Discrete Element Method, Beema Dahal

Boise State University Theses and Dissertations

The ballast layer comprises relatively large (often as large as 63 mm) angular particles that mainly function to dissipate train-induced stresses from crossties to the underlying subgrade soils and to provide rapid drainage for surface water. Moreover, the ballast layer is also critical towards ensuring a smooth riding track profile, dampening dynamic loads, as well as providing lateral, longitudinal and vertical resistance against excessive track deformations. Under train loading and during track maintenance processes like tamping, individual ballast particles can undergo significant breakage leading to fouling of the ballast layer. The fouling mechanism leads to gradual deterioration in ballast shear …

Studying The Use Of Microbial Induced Calcite Precipitation As A Shallow Stabilization Alternative To Treat Expansive Soils, Tasria Rahman

Boise State University Theses and Dissertations

Expansive soils usually recognized as swell-shrink soils have been a problem for civil infrastructure for a long time. It has been a very common practice to use chemical stabilizers including cement and lime to stabilize expansive soils, especially for lightly loaded structures. However, due to the the detrimental effects of these stabilizers on the environment and several occurrences of premature failures after stabilizing with chemical additives, engineers are in search of sustainable stabilization alternatives. Microbial Induced Calcite Precipitation (MICP) is a promising process, which can improve the properties of expansive soil through calcite precipitation. Previous research has shown promise for …

A Novel Fpga Implementation Of Hierarchical Temporal Memory Spatial Pooler, Paul Jeffrey Mitchell

Boise State University Theses and Dissertations

There is currently a strong focus across the technological landscape to create machines capable of performing complex, objective based tasks in a manner similar to, or superior to a human. Many of the methods being explored in the machine intelligence space require large sets of labeled data to first train, and then classify inputs. Hierarchical Temporal Memory (HTM) is a biologically inspired machine intelligence framework which aims to classify and interpret streaming unlabeled data, without supervision, and be able to detect anomalies in such data.

In software HTM models, increasing the number of “columns” or processing elements to the levels …

Injecting Control Commands Through Sensory Channel: Attack And Defense, Farhad Rasapour

Boise State University Theses and Dissertations

Industrial Control System (ICS) is responsible for controlling and managing critical infrastructures like nuclear plants and power plants. ICS is equipped with various devices like communication media, Programmable Logic Controller (PLC), actuators, and sensors. Sensors are used to measure a physical phenomenon and send these measurements through the sensory channel to the control devices so they can make decisions on the movements of the actuators in the systems. While tampering with the sensor measurements has been the focus of many studies, there is some research that has concentrated on misusing a sensor and sensory channel as an axillary attack device …

Thermal Management Of Satellite Electronics Via Gallium Phase Change Heat Sink Devices, Brian O. Palmer

Theses and Dissertations

The purpose of this research was to determine the effectiveness and feasibility of additively manufactured heat sinks using gallium as a phase change material in the thermal management of satellite electronics. A design was created based on the footprint of an Astronautical Development, LLC Lithium 1 UHF radio and six heat sinks were additively manufactured; two each of stainless steel 316, Inconel 718, and ULTEM 9085. Each heat sink was filled with gallium for testing purposes. Models were created to simulate the behavior of the heat transfer and phase change processes occurring within the heat sink. Additionally, laboratory data was …

Carbon Nanotube Fibers: Mechanical Behavior And The Effects Of The Space Environment, Ryan A. Kemnitz

Theses and Dissertations

Carbon nanotube materials are promising multifunctional materials for incorporation into aerospace structures because of their high tensile strength, high electrical conductivity, and low density. This research aimed to characterize the mechanical failure mechanisms of carbon nanotube fibers and examine the effects of the space environment on their material properties. Tensile tests were conducted at varying strain rates and on fibers of varying gage lengths to examine the underlying molecular failure mechanisms and impact of defects on fiber strength. Tensile strength and elastic modulus were observed to increase with increasing strain rate and decrease with increasing gage lengths. The observed effects …

Improving Detection Of Dim Targets: Optimization Of A Moment-Based Detection Algorithm, Shannon R. Young

Theses and Dissertations

Wide area motion imagery (WAMI) sensor technology is advancing rapidly. Increases in frame rates and detector array sizes have led to a dramatic increase in the volume of data that can be acquired. Without a corresponding increase in analytical manpower, much of these data remain underutilized. This creates a need for fast, automated, and robust methods for detecting dim, moving signals of interest. Current approaches fall into two categories: detect-before-track (DBT) and track-before-detect (TBD) methods. The DBT methods use thresholding to reduce the quantity of data to be processed, making real time implementation practical but at the cost of the …

Modeling And Simulation Methodologies For Spinal Cord Stimulation., Saliya Kumara Kirigeeganage

Electronic Theses and Dissertations

The use of neural prostheses to improve health of paraplegics has been a prime interest of neuroscientists over the last few decades. Scientists have performed experiments with spinal cord stimulation (SCS) to enable voluntary motor function of paralyzed patients. However, the experimentation on the human spinal cord is not a trivial task. Therefore, modeling and simulation techniques play a significant role in understanding the underlying concepts and mechanics of the spinal cord stimulation. In this work, simulation and modeling techniques related to spinal cord stimulation were investigated. The initial work was intended to visualize the electric field distribution patterns in …

A Transfer Learning Approach For Sentiment Classification., Omar Abdelwahab

Electronic Theses and Dissertations

The idea of developing machine learning systems or Artificial Intelligence agents that would learn from different tasks and be able to accumulate that knowledge with time so that it functions successfully on a new task that it has not seen before is an idea and a research area that is still being explored. In this work, we will lay out an algorithm that allows a machine learning system or an AI agent to learn from k different domains then uses some or no data from the new task for the system to perform strongly on that new task. In order …

Physio-Chemical Degradation Of Concrete: A Ramification Of Coupled Freeze-Thaw And Sulfate Attack, Md Aminul Islam

Boise State University Theses and Dissertations

Concrete structures experience damage due to Sulfate Attack (SA) and Freeze-Thaw (F-T) in cold regions containing ample amount of sulfate species. The combined effect of SA and F-T is a multiscale multiphysics damaging process for cementitious materials involving complicated chemical reactions and phase transition inside concrete pores. This thesis is a compilation of two theoretical models describing the SA induced damage in an unsaturated cementitious medium and damage due to the combined effect of SA and F-T. The classical theory of phase change and a diffusion-reaction process is utilized in the development of the models. The validity of the proposed …

Effect Of Subsurface Conditions On Flexible Pavement Behavior: Non-Destructive Testing And Mechanistic Analysis, Md. Fazle Rabbi

Boise State University Theses and Dissertations

The behavior of flexible pavements under traffic and environmental loading can be significantly affected by subsurface conditions. Inadequate support conditions under the surface can lead to excessive pavement deformations, often leading to structural and functional failure. This research effort focused on assessing the effects of base/subbase and subgrade layer conditions on flexible pavement behavior. The results of this study are presented in the form of two journal manuscripts.

The first manuscript focuses on utilizing pavement structural and functional evaluation data in making pavement rehabilitation decisions. Visual distress surveys and Falling Weight Deflectometer (FWD) testing are often carried out by agencies …

Local Peer-To-Peer Communication To Improve Demand Response In Residential Neighborhoods, Ryan Schwartz

Boise State University Theses and Dissertations

Increased electricity production from intermittent renewables presents a challenge to utilities. Since the grid has little ability to store energy, fluctuations in solar and wind generation require either an increase in generation from expensive sources or a reduction of demand. Demand Response (DR) programs focus on the latter and are designed to increase grid flexibility by allowing grid operators to modify when or how customers use electricity. For residential customers, this typically means shedding load during periods of high demand through a central controller temporarily shutting off air conditioning (AC) compressors. This type of DR can cause spikes in demand …

Comparison Of Organic And Inorganic Solar Photovoltaic Systems, Khulan Orgil

Electrical Engineering

This senior project report addresses the consumer’s need for accurate and easily accessible information when making a solar panel purchasing decision. Thus, the project analyzes and compares the costs and benefits of organic and inorganic photovoltaic systems during their life cycle. The cost comparison includes analysis of the environmental and economic costs of materials, production, installation, and disposal. The benefit comparison includes analysis of the economic, environmental, and social benefits accrued during the system’s lifetime. With the project’s data, consumers can make more informed decisions to fit their specific needs.

Controlling Relative Humidity Using Glycerin, Juan Martinez

Civil Engineering Undergraduate Honors Theses

A series of tests were conducted to control relative humidity (RH) using a bubbler system that contained a series of glass jars and glass vials filled with different concentrations of glycerin. The relative humidity within the glass jars was measured. The total time interval for each laboratory test was 48 hours. During the first 24 hours a pump was used to bubble air through the glycerin solution. During the second 24 hours, the pump was turned off, and the RH within the system was monitored within the closed system. Target RH measurements from 100% to a 0% were obtained. The …

Establishing Delay-Based Criteria For Installing Traffic Signals At Two-Lane Roundabouts, Oluwaseun Ayomide Adegbaju

Masters Theses

A roundabout is a circular intersection where drivers travel counterclockwise around a center island in the United States. Roundabouts can be more beneficial than the conventional intersections because they increase the capacity of the intersection and reduce delays and crashes at the intersection. However, the performance of roundabouts can be severely affected by unbalanced traffic flows among the approaches. While the resulting delays can be mitigated by installing traffic signals, there is a lack of clear criteria on when to install a traffic signal at a roundabout. This research focuses on establishing criteria for installing traffic signals at two-lane roundabouts …