Matching Items (699)

Filtering by

Clear all filters

131374-Thumbnail Image.png

Surface Mechanical Attrition Treatment (SMAT) of 7075 Aluminum Alloy to Induce a Protective Corrosion Resistant Layer

Description

This paper investigates Surface Mechanical Attrition Treatment (SMAT) and the influence of treatment temperature and initial sample surface finish on the corrosion resistance of 7075-T651 aluminum alloy. Ambient SMAT was performed on AA7075 samples polished to 80-grit initial surface roughness.

This paper investigates Surface Mechanical Attrition Treatment (SMAT) and the influence of treatment temperature and initial sample surface finish on the corrosion resistance of 7075-T651 aluminum alloy. Ambient SMAT was performed on AA7075 samples polished to 80-grit initial surface roughness. Potentiodynamic polarization and electrochemical impedance spectroscopy (EIS) tests were used to characterize the corrosion behavior of samples before and after SMAT. Electrochemical tests indicated an improved corrosion resistance after application of SMAT process. The observed improvements in corrosion properties are potentially due to microstructural changes in the material surface induced by SMAT which encouraged the formation of a passive oxide layer. Further testing and research are required to understand the corrosion related effects of cryogenic SMAT and initial-surface finish as the COVID-19 pandemic inhibited experimentation plans.

Contributors

Created

Date Created
2020-05

133339-Thumbnail Image.png

Prescription Information Extraction from Electronic Health Records using BiLSTM-CRF and Word Embeddings

Description

Medical records are increasingly being recorded in the form of electronic health records (EHRs), with a significant amount of patient data recorded as unstructured natural language text. Consequently, being able to extract and utilize clinical data present within these records

Medical records are increasingly being recorded in the form of electronic health records (EHRs), with a significant amount of patient data recorded as unstructured natural language text. Consequently, being able to extract and utilize clinical data present within these records is an important step in furthering clinical care. One important aspect within these records is the presence of prescription information. Existing techniques for extracting prescription information — which includes medication names, dosages, frequencies, reasons for taking, and mode of administration — from unstructured text have focused on the application of rule- and classifier-based methods. While state-of-the-art systems can be effective in extracting many types of information, they require significant effort to develop hand-crafted rules and conduct effective feature engineering. This paper presents the use of a bidirectional LSTM with CRF tagging model initialized with precomputed word embeddings for extracting prescription information from sentences without requiring significant feature engineering. The experimental results, run on the i2b2 2009 dataset, achieve an F1 macro measure of 0.8562, and scores above 0.9449 on four of the six categories, indicating significant potential for this model.

Contributors

Agent

Created

Date Created
2018-05

133880-Thumbnail Image.png

ReL GoalD (Reinforcement Learning for Goal Dependencies)

Description

In this project, the use of deep neural networks for the process of selecting actions to execute within an environment to achieve a goal is explored. Scenarios like this are common in crafting based games such as Terraria or Minecraft.

In this project, the use of deep neural networks for the process of selecting actions to execute within an environment to achieve a goal is explored. Scenarios like this are common in crafting based games such as Terraria or Minecraft. Goals in these environments have recursive sub-goal dependencies which form a dependency tree. An agent operating within these environments have access to low amounts of data about the environment before interacting with it, so it is crucial that this agent is able to effectively utilize a tree of dependencies and its environmental surroundings to make judgements about which sub-goals are most efficient to pursue at any point in time. A successful agent aims to minimizes cost when completing a given goal. A deep neural network in combination with Q-learning techniques was employed to act as the agent in this environment. This agent consistently performed better than agents using alternate models (models that used dependency tree heuristics or human-like approaches to make sub-goal oriented choices), with an average performance advantage of 33.86% (with a standard deviation of 14.69%) over the best alternate agent. This shows that machine learning techniques can be consistently employed to make goal-oriented choices within an environment with recursive sub-goal dependencies and low amounts of pre-known information.

Contributors

Agent

Created

Date Created
2018-05

133901-Thumbnail Image.png

Data Management Behind Machine Learning

Description

This thesis dives into the world of artificial intelligence by exploring the functionality of a single layer artificial neural network through a simple housing price classification example while simultaneously considering its impact from a data management perspective on both the

This thesis dives into the world of artificial intelligence by exploring the functionality of a single layer artificial neural network through a simple housing price classification example while simultaneously considering its impact from a data management perspective on both the software and hardware level. To begin this study, the universally accepted model of an artificial neuron is broken down into its key components and then analyzed for functionality by relating back to its biological counterpart. The role of a neuron is then described in the context of a neural network, with equal emphasis placed on how it individually undergoes training and then for an entire network. Using the technique of supervised learning, the neural network is trained with three main factors for housing price classification, including its total number of rooms, bathrooms, and square footage. Once trained with most of the generated data set, it is tested for accuracy by introducing the remainder of the data-set and observing how closely its computed output for each set of inputs compares to the target value. From a programming perspective, the artificial neuron is implemented in C so that it would be more closely tied to the operating system and therefore make the collected profiler data more precise during the program's execution. The program is designed to break down each stage of the neuron's training process into distinct functions. In addition to utilizing more functional code, the struct data type is used as the underlying data structure for this project to not only represent the neuron but for implementing the neuron's training and test data. Once fully trained, the neuron's test results are then graphed to visually depict how well the neuron learned from its sample training set. Finally, the profiler data is analyzed to describe how the program operated from a data management perspective on the software and hardware level.

Contributors

Agent

Created

Date Created
2018-05

133654-Thumbnail Image.png

In situ SEM Testing for Fatigue Crack Growth: Mechanical Investigation of Titanium

Description

Widespread knowledge of fracture mechanics is mostly based on previous models that generalize crack growth in materials over several loading cycles. The objective of this project is to characterize crack growth that occurs in titanium alloys, specifically Grade 5 Ti-6Al-4V,

Widespread knowledge of fracture mechanics is mostly based on previous models that generalize crack growth in materials over several loading cycles. The objective of this project is to characterize crack growth that occurs in titanium alloys, specifically Grade 5 Ti-6Al-4V, at the sub-cycle scale, or within a single loading cycle. Using scanning electron microscopy (SEM), imaging analysis is performed to observe crack behavior at ten loading steps throughout the loading and unloading paths. Analysis involves measuring the incremental crack growth and crack tip opening displacement (CTOD) of specimens at loading ratios of 0.1, 0.3, and 0.5. This report defines the relationship between crack growth and the stress intensity factor, K, of the specimens, as well as the relationship between the R-ratio and stress opening level. The crack closure phenomena and effect of microcracks are discussed as they influence the crack growth behavior. This method has previously been used to characterize crack growth in Al 7075-T6. The results for Ti-6Al-4V are compared to these previous findings in order to strengthen conclusions about crack growth behavior.

Contributors

Agent

Created

Date Created
2018-05

132562-Thumbnail Image.png

Simulation of Atomic Structure around Defects in Anatase

Description

Titanium dioxide is an essential material under research for energy and environmental applications, chiefly through its photocatalytic properties. These properties allow it to be used for water-splitting, detoxification, and photovoltaics, in addition to its conventional uses in pigmentation and

Titanium dioxide is an essential material under research for energy and environmental applications, chiefly through its photocatalytic properties. These properties allow it to be used for water-splitting, detoxification, and photovoltaics, in addition to its conventional uses in pigmentation and sunscreen. Titanium dioxide exists in several polymorphic structures, of which the most common are rutile and anatase. We focused on anatase for the purposes of this research, due to its promising results for hydrolysis.

Anatase exists often in its reduced form (TiO2-x), enabling it to perform redox reactions through the absorption and release of oxygen into/from the crystal lattice. These processes result in structural changes, induced by defects in the material, which can theoretically be observed using advanced characterization methods. In situ electron microscopy is one of such methods, and can provide a window into these structural changes. However, in order to interpret the structural evolution caused by defects in materials, it is often necessary and pertinent to use atomistic simulations to compare the experimental images with models.

In this thesis project, we modeled the defect structures in anatase, around oxygen vacancies and at surfaces, using molecular dynamics, benchmarked with density functional theory. Using a “reactive” forcefield designed for the simulation of interactions between anatase and water that can model and treat bonding through the use of bond orders, different vacancy structures were analyzed and simulated. To compare these theoretical, generated models with experimental data, the “multislice approach” to TEM image simulation was used. We investigated a series of different vacancy configurations and surfaces and generated fingerprints for comparison with TEM experiments. This comparison demonstrated a proof of concept for a technique suggesting the possibility for the identification of oxygen vacancy structures directly from TEM images. This research aims to improve our atomic-level understanding of oxide materials, by providing a methodology for the analysis of vacancy formation from very subtle phenomena in TEM images.

Contributors

Agent

Created

Date Created
2019-05

132774-Thumbnail Image.png

Using Machine Learning to Predict the NBA

Description

Machine learning is one of the fastest growing fields and it has applications in almost any industry. Predicting sports games is an obvious use case for machine learning, data is relatively easy to collect, generally complete data is available, and

Machine learning is one of the fastest growing fields and it has applications in almost any industry. Predicting sports games is an obvious use case for machine learning, data is relatively easy to collect, generally complete data is available, and outcomes are easily measurable. Predicting the outcomes of sports events may also be easily profitable, predictions can be taken to a sportsbook and wagered on. A successful prediction model could easily turn a profit. The goal of this project was to build a model using machine learning to predict the outcomes of NBA games.
In order to train the model, data was collected from the NBA statistics website. The model was trained on games dating from the 2010 NBA season through the 2017 NBA season. Three separate models were built, predicting the winner, predicting the total points, and finally predicting the margin of victory for a team. These models learned on 80 percent of the data and validated on the other 20 percent. These models were trained for 40 epochs with a batch size of 15.
The model for predicting the winner achieved an accuracy of 65.61 percent, just slightly below the accuracy of other experts in the field of predicting the NBA. The model for predicting total points performed decently as well, it could beat Las Vegas’ prediction 50.04 percent of the time. The model for predicting margin of victory also did well, it beat Las Vegas 50.58 percent of the time.

Contributors

Created

Date Created
2019-05

Structural Health Monitoring: Acoustic Emissions

Description

Non-Destructive Testing (NDT) is integral to preserving the structural health of materials. Techniques that fall under the NDT category are able to evaluate integrity and condition of a material without permanently altering any property of the material. Additionally,

Non-Destructive Testing (NDT) is integral to preserving the structural health of materials. Techniques that fall under the NDT category are able to evaluate integrity and condition of a material without permanently altering any property of the material. Additionally, they can typically be used while the material is in active use instead of needing downtime for inspection.
The two general categories of structural health monitoring (SHM) systems include passive and active monitoring. Active SHM systems utilize an input of energy to monitor the health of a structure (such as sound waves in ultrasonics), while passive systems do not. As such, passive SHM tends to be more desirable. A system could be permanently fixed to a critical location, passively accepting signals until it records a damage event, then localize and characterize the damage. This is the goal of acoustic emissions testing.
When certain types of damage occur, such as matrix cracking or delamination in composites, the corresponding release of energy creates sound waves, or acoustic emissions, that propagate through the material. Audio sensors fixed to the surface can pick up data from both the time and frequency domains of the wave. With proper data analysis, a time of arrival (TOA) can be calculated for each sensor allowing for localization of the damage event. The frequency data can be used to characterize the damage.
In traditional acoustic emissions testing, the TOA combined with wave velocity and information about signal attenuation in the material is used to localize events. However, in instances of complex geometries or anisotropic materials (such as carbon fibre composites), velocity and attenuation can vary wildly based on the direction of interest. In these cases, localization can be based off of the time of arrival distances for each sensor pair. This technique is called Delta T mapping, and is the main focus of this study.

Contributors

Created

Date Created
2019-05

132430-Thumbnail Image.png

Twitch Streamer-Game Recommender System

Description

Abstract
Matrix Factorization techniques have been proven to be more effective in recommender systems than standard user based or item based methods. Using this knowledge, Funk SVD and SVD++ are compared by the accuracy of their predictions of Twitch streamer

Abstract
Matrix Factorization techniques have been proven to be more effective in recommender systems than standard user based or item based methods. Using this knowledge, Funk SVD and SVD++ are compared by the accuracy of their predictions of Twitch streamer data.

Introduction
As watching video games is becoming more popular, those interested are becoming interested in Twitch.tv, an online platform for guests to watch streamers play video games and interact with them. A streamer is an person who broadcasts them-self playing a video game or some other thing for an audience (the guests of the website.) The site allows the guest to first select the game/category to view and then displays currently active streamers for the guest to select and watch. Twitch records the games that a streamer plays along with the amount of time that a streamer spends streaming that game. This is how the score is generated for a streamer’s game. These three terms form the streamer-game-score (user-item-rating) tuples that we use to train out models.
The our problem’s solution is similar to the purpose of the Netflix prize; however, as opposed to suggesting a user a movie, the goal is to suggest a user a game. We built a model to predict the score that a streamer will have for a game. The score field in our data is fundamentally different from a movie rating in Netflix because the way a user influences a game’s score is by actively streaming it, not by giving it an score based off opinion. The dataset being used it the Twitch.tv dataset provided by Isaac Jones [1]. Also, the only data used in training the models is in the form of the streamer-game-score (user-item-rating) tuples. It will be known if these data points with limited information will be able to give an accurate prediction of a streamer’s score for a game. SVD and SVD++ are the baseis of the models being trained and tested. Scikit’s Surprise library in Python3 is used for the implementation of the models.

Contributors

Agent

Created

Date Created
2019-05

Detecting Propaganda Bots on Twitter Using Machine Learning

Description

Propaganda bots are malicious bots on Twitter that spread divisive opinions and support political accounts. This project is based on detecting propaganda bots on Twitter using machine learning. Once I began to observe patterns within propaganda followers on

Propaganda bots are malicious bots on Twitter that spread divisive opinions and support political accounts. This project is based on detecting propaganda bots on Twitter using machine learning. Once I began to observe patterns within propaganda followers on Twitter, I determined that I could train algorithms to detect these bots. The paper focuses on my development and process of training classifiers and using them to create a user-facing server that performs prediction functions automatically. The learning goals of this project were detailed, the focus of which was to learn some form of machine learning architecture. I needed to learn some aspect of large data handling, as well as being able to maintain these datasets for training use. I also needed to develop a server that would execute these functionalities on command. I wanted to be able to design a full-stack system that allowed me to create every aspect of a user-facing server that can execute predictions using the classifiers that I design.
Throughout this project, I decided on a number of learning goals to consider it a success. I needed to learn how to use the supporting libraries that would help me to design this system. I also learned how to use the Twitter API, as well as create the infrastructure behind it that would allow me to collect large amounts of data for machine learning. I needed to become familiar with common machine learning libraries in Python in order to create the necessary algorithms and pipelines to make predictions based on Twitter data.
This paper details the steps and decisions needed to determine how to collect this data and apply it to machine learning algorithms. I determined how to create labelled data using pre-existing Botometer ratings, and the levels of confidence I needed to label data for training. I use the scikit-learn library to create these algorithms to best detect these bots. I used a number of pre-processing routines to refine the classifiers’ precision, including natural language processing and data analysis techniques. I eventually move to remotely-hosted versions of the system on Amazon web instances to collect larger amounts of data and train more advanced classifiers. This leads to the details of my final implementation of a user-facing server, hosted on AWS and interfacing over Gmail’s IMAP server.
The current and future development of this system is laid out. This includes more advanced classifiers, better data analysis, conversions to third party Twitter data collection systems, and user features. I detail what it is I have learned from this exercise, and what it is I hope to continue working on.

Contributors

Agent

Created

Date Created
2019-05