The process of designing a floorplan is highly iterative and requires extensive human labor. Currently, there are a number of computer programs that aid humans in floorplan design. These programs, however, are limited in their inability to fully automate the creative process. Such automation would allow a professional to quickly generate many possible floorplan solutions, greatly expediting the process. However, automating this creative process is very difficult because of the many implicit and explicit rules a model must learn in order create viable floorplans. In this paper, we propose a method of floorplan generation using two machine learning models: a sequential model that generates rooms within the floorplan, and a graph-based model that finds adjacencies between generated rooms. Each of these models can be altered such that they are each capable of producing a floorplan independently; however, we find that the combination of these models outperforms each of its pieces, as well as a statistic-based approach.

Concept Maps (CMs) are considered a well-known pedagogy technique in creating curriculum, educating, teaching, and learning. Determining comprehension of concepts result from comparisons of candidate CMs against a master CM, and evaluate "goodness". Past techniques for comparing CMs have revolved around the creation of a subjective rubric. We propose a novel CM scoring scheme called MAnanA based on a Fuzzy Similarity Scaling (FSS) score to vastly remove the subjectivity of the rubrics in the process of grading a CM. We evaluate our framework against a predefined rubric and test it with CM data collected from the Introduction to Computer Security course at the University of New Orleans (UNO), and found that the scores obtained via MAnanA captured the trend that we observed from the rubric via peak matching. Based on our evaluation, we believe that our framework can be used to objectify CM analysis.

Facial recognition is the process in which a sample face can be correctly identified by a machine amongst a group of different faces. With the never-ending need for improvement in the fields of security, surveillance, and identification, facial recognition is becoming increasingly important. Considering this importance, it is imperative that the correct faces are recognized and the error rate is as minimal as possible. Despite the wide variety of current methods for facial recognition, there is no clear cut best method. This project reviews and examines three different methods for facial recognition: Eigenfaces, Fisherfaces, and Local Binary Patterns to determine which method has the highest accuracy of prediction rate. The three methods are reviewed and then compared via experiments. OpenCV, CMake, and Visual Studios were used as tools to conduct experiments. Analysis were conducted to identify which method has the highest accuracy of prediction rate with various experimental factors. By feeding a number of sample images of different people which serve as experimental subjects. The machine is first trained to generate features for each person among the testing subjects. Then, a new image was tested against the “learned” data and be labeled as one of the subjects. With experimental data analysis, the Eigenfaces method was determined to have the highest prediction rate of the three algorithms tested. The Local Binary Pattern Histogram (LBP) was found to have the lowest prediction rate. Finally, LBP was selected for the algorithm improvement. In this project, LBP was improved by identifying the most significant regions of the histograms for each person in training time. The weights of each region are assigned depending on the gray scale contrast. At recognition time, given a new face, different weights are assigned to different regions to increase prediction rate and also speed up the real time recognition. The experimental results confirmed the performance improvement.

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 trials per activity per person. A comparison of this BLSTM model is made with the Unidirectional LSTM model. It is observed that there is a significant improvement in the accuracy for recognition of all 27 activities in the case of BLSTM than LSTM.

Identifying new potential treatment options for medical conditions that cause human disease burden is a central task of biomedical research. Since all candidate drugs cannot be tested with animal and clinical trials, in vitro approaches are first attempted to identify promising candidates. Likewise, identifying other essential relations (e.g., causation, prevention) between biomedical entities is also critical to understand biomedical processes. Hence, it is crucial to develop automated relation prediction systems that can yield plausible biomedical relations to expedite the discovery process. In this dissertation, we demonstrate three approaches to predict treatment relations between biomedical entities for the drug repositioning task using existing biomedical knowledge bases. Our approaches can be broadly labeled as link prediction or knowledge base completion in computer science literature. Specifically, first we investigate the predictive power of graph paths connecting entities in the publicly available biomedical knowledge base, SemMedDB (the entities and relations constitute a large knowledge graph as a whole). To that end, we build logistic regression models utilizing semantic graph pattern features extracted from the SemMedDB to predict treatment and causative relations in Unified Medical Language System (UMLS) Metathesaurus. Second, we study matrix and tensor factorization algorithms for predicting drug repositioning pairs in repoDB, a general purpose gold standard database of approved and failed drug–disease indications. The idea here is to predict repoDB pairs by approximating the given input matrix/tensor structure where the value of a cell represents the existence of a relation coming from SemMedDB and UMLS knowledge bases. The essential goal is to predict the test pairs that have a blank cell in the input matrix/tensor based on the shared biomedical context among existing non-blank cells. Our final approach involves graph convolutional neural networks where entities and relation types are embedded in a vector space involving neighborhood information. Basically, we minimize an objective function to guide our model to concept/relation embeddings such that distance scores for positive relation pairs are lower than those for the negative ones. Overall, our results demonstrate that recent link prediction methods applied to automatically curated, and hence imprecise, knowledge bases can nevertheless result in high accuracy drug candidate prediction with appropriate configuration of both the methods and datasets used.

Machine learning offers many powerful tools for prediction. One of these tools, the binary classifier, is often considered a black box. Although its predictions may be accurate, we might never know why the classifier made a particular prediction. In the first half of this dissertation, I review the state of the art of interpretable methods (methods for explaining why); after noting where the existing methods fall short, I propose a new method for a particular type of black box called additive networks. I offer a proof of trustworthiness for this new method (meaning a proof that my method does not "make up" the logic of the black box when generating an explanation), and verify that its explanations are sound empirically. Sparse coding is part of a family of methods that are believed, by many researchers, to not be black boxes. In the second half of this dissertation, I review sparse coding and its application to the binary classifier. Despite the fact that the goal of sparse coding is to reconstruct data (an entirely different goal than classification), many researchers note that it improves classification accuracy. I investigate this phenomenon, challenging a common assumption in the literature. I show empirically that sparse reconstruction is not necessarily the right intermediate goal, when our ultimate goal is classification. Along the way, I introduce a new sparse coding algorithm that outperforms competing, state-of-the-art algorithms for a variety of important tasks.

In today's nanoscale era, scaling down to even smaller feature sizes poses a significant challenge in the device fabrication, the circuit, and the system design and integration. On the other hand, nanoscale technology has also led to novel materials and devices with unique properties. The memristor is one such emergent nanoscale device that exhibits non-linear current-voltage characteristics and has an inherent memory property, i.e., its current state depends on the past. Both the non-linear and the memory property of memristors have the potential to enable solving spatial and temporal pattern recognition tasks in radically different ways from traditional binary transistor-based technology. The goal of this thesis is to explore the use of memristors in a novel computing paradigm called "Reservoir Computing" (RC). RC is a new paradigm that belongs to the class of artificial recurrent neural networks (RNN). However, it architecturally differs from the traditional RNN techniques in that the pre-processor (i.e., the reservoir) is made up of random recurrently connected non-linear elements. Learning is only implemented at the readout (i.e., the output) layer, which reduces the learning complexity significantly. To the best of our knowledge, memristors have never been used as reservoir components. We use pattern recognition and classification tasks as benchmark problems. Real world applications associated with these tasks include process control, speech recognition, and signal processing. We have built a software framework, RCspice (Reservoir Computing Simulation Program with Integrated Circuit Emphasis), for this purpose. The framework allows to create random memristor networks, to simulate and evaluate them in Ngspice, and to train the readout layer by means of Genetic Algorithms (GA). We have explored reservoir-related parameters, such as the network connectivity and the reservoir size along with the GA parameters. Our results show that we are able to efficiently and robustly classify time-series patterns using memristor-based dynamical reservoirs. This presents an important step towards computing with memristor-based nanoscale systems.

Decision-related activities, such as bottom-up and top-down policy development, analysis, and planning, stand to benefit from the development and application of computer-based models that are capable of representing spatiotemporal social human behavior in local contexts. This is especially the case with our efforts to understand and search for ways to mitigate the context-specific effects of climate change, in which case such models need to include interacting social and ecological components. The development and application of such models has been significantly hindered by the challenges in designing artificial agents whose behavior is grounded in both empirical evidence and theory and in testing the ability of artificial agents to represent the behavior of real-world decision-makers. This dissertation advances our ability to develop such models by overcoming these challenges through the creation of: (a) three new frameworks, (b) two new methods, and (c) two new open-source modeling tools. The three new frameworks include: (a) the SOSIEL framework, which provides a theoretically-grounded blueprint for the development of a new generation of cognitive, multi-agent, and knowledge-based models that consist of agents empowered with cognitive architectures; (b) a new framework for analyzing the bounded rationality of decision-makers, which offers insight into and facilitates the analysis of the relationship between a decision situation and a decision-maker's decision; and (c) a new framework for analyzing the doubly-bounded rationality (DBR) of artificial agents, which does the same for the relationship between a decision situation and an artificial agent's decision. The two new methods include: (a) the SOSIEL method for acquiring and operationalizing decision-making knowledge, which advances our ability to acquire, process, and represent decision-making knowledge for cognitive, multi-agent, and knowledge-based models; and (b) the DBR method for testing the ability of artificial agents to represent human decision-making. The two open-source modeling tools include: (a) the SOSIEL platform, which is a cognitive, multi-agent, and knowledge-based platform for simulating human decision-making; and (b) an application of the platform as the SOSIEL Human Extension (SHE) to an existing forest-climate change model, called LANDIS-II, allowing for the analysis of co-evolutionary human-forest-climate interactions. To provide a context for examples and also guidelines for knowledge acquisition, the dissertation includes a case study of social-ecological interactions in an area of the Ukrainian Carpathians where LANDIS-II with SHE are currently being applied. As a result, this dissertation advances science by: (a) providing a theoretical foundation for and demonstrating the implementation of a next generation of models that are cognitive, multi-agent, and knowledge-based; and (b) providing a new perspective for understanding, analyzing, and testing the ability of artificial agents to represent human decision-making that is rooted in psychology.

This thesis proposes a series of multi-label learning algorithms for classification and feature selection implemented on the Apache Spark distributed computing model. Five approaches for determining the optimal architecture to speed up multi-label learning methods are presented. These approaches range from local parallelization using threads to distributed computing using independent or shared memory spaces. It is shown that the optimal approach performs hundreds of times faster than the baseline method. Three distributed multi-label k nearest neighbors methods built on top of the Spark architecture are proposed: an exact iterative method that computes pair-wise distances, an approximate tree-based method that indexes the instances across multiple nodes, and an approximate local sensitive hashing method that builds multiple hash tables to index the data. The results indicated that the predictions of the tree-based method are on par with those of an exact method while reducing the execution times in all the scenarios. The aforementioned method is then used to evaluate the quality of a selected feature subset. The optimal adaptation for a multi-label feature selection criterion is discussed and two distributed feature selection methods for multi-label problems are proposed: a method that selects the feature subset that maximizes the Euclidean norm of individual information measures, and a method that selects the subset of features maximizing the geometric mean. The results indicate that each method excels in different scenarios depending on type of features and the number of labels. Rigorous experimental studies and statistical analyses over many multi-label metrics and datasets confirm that the proposals achieve better performances and provide better scalability to bigger data than the methods compared in the state of the art.

Large quantities of high-level radioactive waste were generated during WWII. This waste is being stored in facilities such as double-shell tanks in Washington, and the Waste Isolation Pilot Plant in New Mexico. Due to the dangerous nature of radioactive waste, these facilities must undergo periodic inspections to ensure that leaks are detected quickly. In this work, we provide a set of methodologies to aid in the monitoring and inspection of these hazardous facilities. This allows inspection of dangerous regions without a human operator, and for the inspection of locations where a person would not be physically able to enter. First, we describe a robot equipped with sensors which uses a modified A* path-planning algorithm to navigate in a complex environment with a tether constraint. This is then augmented with an adaptive informative path planning approach that uses the assimilated sensor data within a Gaussian Process distribution model. The model's predictive outputs are used to adaptively plan the robot's path, to quickly map and localize areas from an unknown field of interest. The work was validated in extensive simulation testing and early hardware tests. Next, we focused on how to assign tasks to a heterogeneous set of robots. Task assignment is done in a manner which allows for task-robot dependencies, prioritization of tasks, collision checking, and more realistic travel estimates among other improvements from the state-of-the-art. Simulation testing of this work shows an increase in the number of tasks which are completed ahead of a deadline. Finally, we consider the case where robots are not able to complete planned tasks fully autonomously and require operator assistance during parts of their planned trajectory. We present a sampling-based methodology for allocating operator attention across multiple robots, or across different parts of a more sophisticated robot. This allows few operators to oversee large numbers of robots, allowing for a more scalable robotic infrastructure. This work was tested in simulation for both multi-robot deployment, and high degree-of-freedom robots, and was also tested in multi-robot hardware deployments. The work here can allow robots to carry out complex tasks, autonomously or with operator assistance. Altogether, these three components provide a comprehensive approach towards robotic deployment within the deactivation and decommissioning tasks faced by the Department of Energy.