Physical Sciences and Mathematics Commons^™

Yoga Pose Classification Using Deep Learning, Shruti Kothari

Master's Projects

Human pose estimation is a deep-rooted problem in computer vision that has exposed many challenges in the past. Analyzing human activities is beneficial in many fields like video- surveillance, biometrics, assisted living, at-home health monitoring etc. With our fast-paced lives these days, people usually prefer exercising at home but feel the need of an instructor to evaluate their exercise form. As these resources are not always available, human pose recognition can be used to build a self-instruction exercise system that allows people to learn and practice exercises correctly by themselves. This project lays the foundation for building such a system ...

An Ai For A Modification Of Dou Di Zhu, Xuesong Luo

Master's Projects

We describe our implementation of AIs for the Chinese game Dou Di Zhu. Dou Di Zhu is a three-player game played with a standard 52 card deck together with two jokers. One player acts as a landlord and has the advantage of receiving three extra cards, the other two players play as peasants. We designed and implemented a Deep Q-learning Neural Network (DQN) agent to play the Dou Di Zhu. At the same time, we also designed and made a pure Q-learning based agent as well as a Zhou rule-based agent to compare with our main agent. We show the ...

Ai Quantification Of Language Puzzle To Language Learning Generalization, Harita Shroff

Master's Projects

Online language learning applications provide users multiple ways/games to learn a new language. Some of the ways include rearranging words in the foreign language sentences, filling in the blanks, providing flashcards, and many more. Primarily this research focused on quantifying the effectiveness of these games in learning a new language. Secondarily my goal for this project was to measure the effectiveness of exercises for transfer learning in machine translation. Currently, very little research has been done in this field except for the research conducted by the online platforms to provide assurance to their users [12]. Machine learning has been ...

Housing Market Crash Prediction Using Machine Learning And Historical Data, Parnika De

Master's Projects

The 2008 housing crisis was caused by faulty banking policies and the use of credit derivatives of mortgages for investment purposes. In this project, we look into datasets that are the markers to a typical housing crisis. Using those data sets we build three machine learning techniques which are, Linear regression, Hidden Markov Model, and Long Short-Term Memory. After building the model we did a comparative study to show the prediction done by each model. The linear regression model did not predict a housing crisis, instead, it showed that house prices would be rising steadily and the R-squared score of ...

Rehearsal Scheduling Problem, Thuan Bao

Master's Projects

Scheduling is a common task that plays a crucial role in many industries such as manufacturing or servicing. In a competitive environment, effective scheduling is one of the key factors to reduce cost and increase productivity. Therefore, scheduling problems have been studied by many researchers over the past thirty years. Rehearsal scheduling problem (RSP) is similar to the popular resource-constrained project scheduling problem (RCPSP); however, it does not have activity precedence constraints and the resources’ availabilities are not fixed during processing time. RSP can be used to schedule rehearsal in theatre industry or to schedule group scheduling when each member ...

Non-Equilibrium Growth Of Metal Clusters On A Layered Material: Cu On Mos2, Dapeng Jing, Ann Lii-Rosales, King C. Lai, Qiang Li, Jaeyoun Kim, Michael C. Tringides, James W. Evans, Patricia A. Thiel

Chemistry Publications

We use a variety of experimental techniques to characterize Cu clusters on bulk MoS2 formed via physical vapor deposition of Cu in ultrahigh vacuum, at temperatures ranging from 300 K to 900 K. We find that large facetted clusters grow at elevated temperatures, using high Cu exposures. The cluster size distribution is bimodal, and under some conditions, large clusters are surrounded by a denuded zone. We propose that defect-mediated nucleation, and coarsening during deposition, are both operative in this system. At 780 K, a surprising type of facetted cluster emerges, and at 900 K this type predominates: pyramidal clusters with ...

Heavy Metals In Particulate Matter In Spokane County, Delaney M. White

2020 Symposium Posters

Heavy metals in particulate matter (e.g., dust) have multiple negative health ramifications for humans including cancer, infertility, and reduced lung function. The Spokane Regional Clean Air Agency (SRCAA) has seven air quality monitoring stations around Spokane County to measure total levels of PM2.5 (particles with a diameter less than 2.5 micrometers) and PM10 (particles with a diameter less than 10 micrometers). For comparison, the width of a human hair is between 50 and 70 micrometers. The objective of this research is to examine the heavy metal composition of the particulate matter including elements such as lead, copper ...

Comparison Of Word2vec With Hash2vec For Machine Translation, Neha Gaikwad

Master's Projects

Machine Translation is the study of computer translation of a text written in one human language into text in a different language. Within this field, a word embedding is a mapping from terms in a language into small dimensional vectors which can be processed using mathematical operations. Two traditional word embedding approaches are word2vec, which uses a Neural Network, and hash2vec, which is based on a simpler hashing algorithm. In this project, we have explored the relative suitability of each approach to sequence to sequence text translation using a Recurrent Neural Network (RNN). We also carried out experiments to test ...

Improved Chinese Language Processing For An Open Source Search Engine, Xianghong Sun

Master's Projects

Natural Language Processing (NLP) is the process of computers analyzing on human languages. There are also many areas in NLP. Some of the areas include speech recognition, natural language understanding, and natural language generation.

Information retrieval and natural language processing for Asians languages has its own unique set of challenges not present for Indo-European languages. Some of these are text segmentation, named entity recognition in unsegmented text, and part of speech tagging. In this report, we describe our implementation of and experiments with improving the Chinese language processing sub-component of an open source search engine, Yioop. In particular, we rewrote ...

Frost Tolerance, Deacclimation And Reacclimation Traits In Perennial Ryegrass, Mats Höglind, Hans Martin Hanslin

International Grassland Congress Proceedings

The ability of perennial grasses to harden and maintain frost tolerance throughout the winter is crucial for winter survival. This includes the ability to resist deacclimation during transient mild spells in winter, and the ability to reacclimate when cold temperatures return. The latter traits are especially critical in regions with cycles of freezing and thawing, and lack of a stable, insulating snowcover that can protect the plants from extreme air temperatures. Such conditions are typical for many coastal areas in Northern Eurasia and America, such as the southwestern coast of Norway. The climate is changing and one of the consequences ...

Importance Of Grassland Management For Carbon Sequestration And To Mitigate Climate Change: A Review, Poonam Yadav, Sheela Choudhary, Sunil Dutt Choudhary, Praveen Kaushik

International Grassland Congress Proceedings

Grasslands, including rangelands, shrub lands, pastureland, and cropland sown with pasture and fodder crops, covered approximately 3.5 billion ha in 2000, representing 26 percent of the world land area and 70 percent of the world agricultural area, and containing about 20 percent of the world’s soil carbon stocks (Ramankutty et al., 2008). All ecosystems- forested ecosystems, agro-ecosystems, grassland, ecosystems etc. take up atmospheric CO₂ and mineral nutrients and transform them into organic products In undisturbed ecosystems, the carbon balance tends to be positive: carbon uptake through photosynthesis exceeds losses from respiration, even in mature, old-growth forest ecosystems ...

Effect Of Topographical Condition On Radioactive Cesium Pollution Of Herbaceous Plants In A Mountainous Grazing Pasture After Fukushima Dai-Ichi Nuclear Power Plant Accident, Shin-Ichiro Ogura, Masanori Saito

International Grassland Congress Proceedings

The Great East Japan Earthquake on 11 March 2011, followed by tsunami, incurred the accident of the Fukushima Dai-Ichi Nuclear Power Station (NPS). The radioactive fallout was dispersed by wind and deposited in large part of eastern Japan by rainfall or snowfall after the accident (Chino et al., 2011; Katata et al., 2012; Terada et al., 2012). That caused extensive pollution by radioactive cesium (Cs) (the sum of 134Cs and 137Cs) in agricultural lands (MEXT, 2011) including permanent pastures and meadows. In mountainous areas, it can be thought that radioactive Cs migrated from convex to concave regions by snow melting ...

Sandy Buck '78: Seeing Light Amidst The Gloom, Gerry Boyle

Colby Magazine

"If you look at the macro you could come to a grinding halt and throw your hand up. But when you look at the local, and even state and regional levels, there are reasons for hope." -Sandy Buck '78

Gail Carlson: Inspiring Students To Step Up, Gerry Boyle

Colby Magazine

"When you become a doomsday person, when you're really pessimistic, it's because you can't see that you can make a difference." -Gail Carlson, associate professor of environmental studies

Modeling The Effects Of Fentanyl And Narcan On The Opioid Epidemic In Allegheny County Using Mathematics, Lindsay Moskal, Lauren Sines, Rachael Neilan Ph.D.

Undergraduate Research and Scholarship Symposium

Starting in the 1990s, physicians across the United States have increasingly prescribed opioid pain relievers, which has given rise to the current opioid epidemic. As a result, there has been a drastic increase in the number of overdose fatalities. In 2017, the number of opioid overdose deaths peaked and the U.S. declared the crisis as a public health emergency. One state that has contributed significantly to this epidemic is Pennsylvania, which ranks first for the greatest number of overdose deaths and third for the highest death rate. In fact, Allegheny County has witnessed an overdose death rate that is ...

Modeling The Effects Of Fentanyl And Narcan On The Opioid Epidemic In Allegheny County Using Mathematics, Lindsay Moskal, Lauren Sines, Rachael Neilan Ph.D.

Undergraduate Research and Scholarship Symposium

Starting in the 1990s, physicians across the United States have increasingly prescribed opioid pain relievers, which has given rise to the current opioid epidemic. As a result, there has been a drastic increase in the number of overdose fatalities. In 2017, the number of opioid overdose deaths peaked and the U.S. declared the crisis as a public health emergency. One state that has contributed significantly to this epidemic is Pennsylvania, which ranks first for the greatest number of overdose deaths and third for the highest death rate. In fact, Allegheny County has witnessed an overdose death rate that is ...

D-Orbital Occupancy Of Transition Metal Oxides By X-Ray Absorption Near Edge Structure (Xanes), Eric Kurywczak

Seton Hall University Dissertations and Theses (ETDs)

XANES L₂ and L₃-edge X-Ray Absorption Near Edge Spectra (XANES) for 4d and 5d row transition metals (TM) oxides are assumed to be directly reflecting unoccupied d orbitals influenced by the local symmetry of the metal ion. XANES L₂- and L₃-edge data analysis through non-linear curve fitting allows for a unique, efficient look at the structural eccentricities of transition metal oxides. In this way it is possible to determine the oxidation state of a material as well as its site symmetry. We have used non-linear least-squares fitting across the near-edge region of ...

Prediction Of Drug-Drug Interaction Potential Using Machine Learning Approaches, Joseph Scavetta

Theses and Dissertations

Drug discovery is a long, expensive, and complex, yet crucial process for the benefit of society. Selecting potential drug candidates requires an understanding of how well a compound will perform at its task, and more importantly, how safe the compound will act in patients. A key safety insight is understanding a molecule's potential for drug-drug interactions. The metabolism of many drugs is mediated by members of the cytochrome P450 superfamily, notably, the CYP3A4 enzyme. Inhibition of these enzymes can alter the bioavailability of other drugs, potentially increasing their levels to toxic amounts. Four models were developed to predict CYP3A4 ...

Emerging Technologies In Healthcare: Analysis Of Unos Data Through Machine Learning, Reyhan Merekar

Student Theses

The healthcare industry is primed for a massive transformation in the coming decades due to emerging technologies such as Artificial Intelligence (AI) and Machine Learning. With a practical application to the UNOS (United Network of Organ Sharing) database, this Thesis seeks to investigate how Machine Learning and analytic methods may be used to predict one-year heart transplantation outcomes. This study also sought to improve on predictive performances from prior studies by analyzing both Donor and Recipient data. Models built with algorithms such as Stacking and Tree Boosting gave the highest performance, with AUC’s of 0.6810 and 0.6804 ...

Real-Time Ad Click Fraud Detection, Apoorva Srivastava

Master's Projects

With the increase in Internet usage, it is now considered a very important platform for advertising and marketing. Digital marketing has become very important to the economy: some of the major Internet services available publicly to users are free, thanks to digital advertising. It has also allowed the publisher ecosystem to flourish, ensuring significant monetary incentives for creating quality public content, helping to usher in the information age. Digital advertising, however, comes with its own set of challenges. One of the biggest challenges is ad fraud. There is a proliferation of malicious parties and software seeking to undermine the ecosystem ...