Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Institution
- Keyword
-
- Machine Learning (2)
- Air combat (1)
- Algorithm design (1)
- Applied statistics (1)
- Approximate dynamic programming (ADP) (1)
-
- Artificial intelligence (1)
- Bayesian networks (1)
- COVID-19 (1)
- Combinatorial Optimization (1)
- Conditional Gradient Sliding (1)
- Convex Optimization (1)
- Cost function approximation (CFA) (1)
- Data Sceince (1)
- Decision Support System (1)
- Frank-Wolfe (1)
- HIV (1)
- Iinformation systems (1)
- Information Science (1)
- Lightning (1)
- Markov Decision Process (1)
- Markov decision process (MDP) (1)
- Markov decision processes (1)
- Mesh adaptive direct search (MADS) (1)
- Mixed-Integer Programming (1)
- Neural networks (1)
- Operations Research (1)
- Pandemic Control (1)
- Predictive Analytics (1)
- Programming (1)
- Reinforcement Learning (1)
Articles 1 - 9 of 9
Full-Text Articles in Physical Sciences and Mathematics
Integrated Machine Learning And Optimization Approaches, Dogacan Yilmaz
Integrated Machine Learning And Optimization Approaches, Dogacan Yilmaz
Dissertations
This dissertation focuses on the integration of machine learning and optimization. Specifically, novel machine learning-based frameworks are proposed to help solve a broad range of well-known operations research problems to reduce the solution times. The first study presents a bidirectional Long Short-Term Memory framework to learn optimal solutions to sequential decision-making problems. Computational results show that the framework significantly reduces the solution time of benchmark capacitated lot-sizing problems without much loss in feasibility and optimality. Also, models trained using shorter planning horizons can successfully predict the optimal solution of the instances with longer planning horizons. For the hardest data set, …
On Variants Of Sliding And Frank-Wolfe Type Methods And Their Applications In Video Co-Localization, Seyed Hamid Nazari
On Variants Of Sliding And Frank-Wolfe Type Methods And Their Applications In Video Co-Localization, Seyed Hamid Nazari
All Dissertations
In this dissertation, our main focus is to design and analyze first-order methods for computing approximate solutions to convex, smooth optimization problems over certain feasible sets. Specifically, our goal in this dissertation is to explore some variants of sliding and Frank-Wolfe (FW) type algorithms, analyze their convergence complexity, and examine their performance in numerical experiments. We achieve three accomplishments in our research results throughout this dissertation. First, we incorporate a linesearch technique to a well-known projection-free sliding algorithm, namely the conditional gradient sliding (CGS) method. Our proposed algorithm, called the conditional gradient sliding with linesearch (CGSls), does not require the …
Supervised Representation Learning For Improving Prediction Performance In Medical Decision Support Applications, Phawis Thammasorn
Supervised Representation Learning For Improving Prediction Performance In Medical Decision Support Applications, Phawis Thammasorn
Graduate Theses and Dissertations
Machine learning approaches for prediction play an integral role in modern-day decision supports system. An integral part of the process is extracting interest variables or features to describe the input data. Then, the variables are utilized for training machine-learning algorithms to map from the variables to the target output. After the training, the model is validated with either validation or testing data before making predictions with a new dataset. Despite the straightforward workflow, the process relies heavily on good feature representation of data. Engineering suitable representation eases the subsequent actions and copes with many practical issues that potentially prevent the …
Decision-Analytic Models Using Reinforcement Learning To Inform Dynamic Sequential Decisions In Public Policy, Seyedeh Nazanin Khatami
Decision-Analytic Models Using Reinforcement Learning To Inform Dynamic Sequential Decisions In Public Policy, Seyedeh Nazanin Khatami
Doctoral Dissertations
We developed decision-analytic models specifically suited for long-term sequential decision-making in the context of large-scale dynamic stochastic systems, focusing on public policy investment decisions. We found that while machine learning and artificial intelligence algorithms provide the most suitable frameworks for such analyses, multiple challenges arise in its successful adaptation. We address three specific challenges in two public sectors, public health and climate policy, through the following three essays. In Essay I, we developed a reinforcement learning (RL) model to identify optimal sequence of testing and retention-in-care interventions to inform the national strategic plan “Ending the HIV Epidemic in the US”. …
Bayesian Convolutional Neural Network With Prediction Smoothing And Adversarial Class Thresholds, Noah M. Miller
Bayesian Convolutional Neural Network With Prediction Smoothing And Adversarial Class Thresholds, Noah M. Miller
Theses and Dissertations
Using convolutional neural networks (CNNs) for image classification for each frame in a video is a very common technique. Unfortunately, CNNs are very brittle and have a tendency to be over confident in their predictions. This can lead to what we will refer to as “flickering,” which is when the predictions between frames jump back and forth between classes. In this paper, new methods are proposed to combat these shortcomings. This paper utilizes a Bayesian CNN which allows for a distribution of outputs on each data point instead of just a point estimate. These distributions are then smoothed over multiple …
Approximate Dynamic Programming For An Unmanned Aerial Vehicle Routing Problem With Obstacles And Stochastic Target Arrivals, Kassie M. Gurnell
Approximate Dynamic Programming For An Unmanned Aerial Vehicle Routing Problem With Obstacles And Stochastic Target Arrivals, Kassie M. Gurnell
Theses and Dissertations
The United States Air Force is investing in artificial intelligence (AI) to speed analysis in efforts to modernize the use of autonomous unmanned combat aerial vehicles (AUCAVs) in strike coordination and reconnaissance (SCAR) missions. This research examines an AUCAVs ability to execute target strikes and provide reconnaissance in a SCAR mission. An orienteering problem is formulated as anMarkov decision process (MDP) model wherein a single AUCAV must optimize its target route to aid in eliminating time-sensitive targets and collect imagery of requested named areas of interest while evading surface-to-air missile (SAM) battery threats imposed as obstacles. The AUCAV adjusts its …
Comparison Of Lightning Warning Radii Distributions, Michael M. Maestas
Comparison Of Lightning Warning Radii Distributions, Michael M. Maestas
Theses and Dissertations
Previous research investigating lightning warning radii about the Cape Canaveral space launch facilities have focused on reducing these radii from either 5 nautical miles (NM) to 4 NM or from 6 NM to 5 NM depending on the structures being protected. Some of these findings have suggested the possibility of both a seasonal difference (warm versus cold) and lightning detection events (cloud-to-ground lightning (CG) or total lightning (TL)) impacting these radii and associated risk levels. Utilizing the 2017-2020 data provided by the 45th Weather Squadron at Patrick Space Force Base via the Mesoscale Eastern Range Lightning Information System (MERLIN), this …
Team Air Combat Using Model-Based Reinforcement Learning, David A. Mottice
Team Air Combat Using Model-Based Reinforcement Learning, David A. Mottice
Theses and Dissertations
We formulate the first generalized air combat maneuvering problem (ACMP), called the MvN ACMP, wherein M friendly AUCAVs engage against N enemy AUCAVs, developing a Markov decision process (MDP) model to control the team of M Blue AUCAVs. The MDP model leverages a 5-degree-of-freedom aircraft state transition model and formulates a directed energy weapon capability. Instead, a model-based reinforcement learning approach is adopted wherein an approximate policy iteration algorithmic strategy is implemented to attain high-quality approximate policies relative to a high performing benchmark policy. The ADP algorithm utilizes a multi-layer neural network for the value function approximation regression mechanism. One-versus-one …
Efficient Numerical Optimization For Parallel Dynamic Optimal Power Flow Simulation Using Network Geometry, Rylee Sundermann
Efficient Numerical Optimization For Parallel Dynamic Optimal Power Flow Simulation Using Network Geometry, Rylee Sundermann
Electronic Theses and Dissertations
In this work, we present a parallel method for accelerating the multi-period dynamic optimal power flow (DOPF). Our approach involves a distributed-memory parallelization of DOPF time-steps, use of a newly developed parallel primal-dual interior point method, and an iterative Krylov subspace linear solver with a block-Jacobi preconditioning scheme. The parallel primal-dual interior point method has been implemented and distributed in the open-source PETSc library and is currently available. We present the formulation of the DOPF problem, the developed primal dual interior point method solver, the parallel implementation, and results on various multi-core machines. We demonstrate the effectiveness our proposed block-Jacobi …