• The Red Pen: Applying Computer Vision to Automate the Grading of Traditional Assignments 

  Guggenheimer, Brian (2016)

  This paper explores the limits of how established computer vision techniques can be applied to the problem of grading simple assignments. The goal is to allow teachers to be able to keep a traditional assessment format but ...
• K-Robust Nearest Neighbor Search and Classification 

  Feinberg, Jason (2016)

  The nearest neighbor problem is one of the most important problems in computational geometry. Many of the solutions to this problem suffer from the "curse of dimensionality" that makes the runtime increase exponentially ...
• Using Phrase-Structure Rules in Extractive Text Summarization 

  Hopkins, Daniel (2016)

  Document summarization has become increasingly important since the explosion of data creation that began in the mid-20th century. Improving automated text summarization is essential in order to provide methods of generating ...
• Pipelined Parallelogram Tiling and Loop Restructuring Using Chapel Iterators 

  Rush, Blair (2016)

  We are often interested in improving the performance of our programs in any way we can. Loop reconstruction is a common tool for improving performance. There are many different types of loop restructuing techniques depending ...
• Gesture Recognition using Electromyographic, Spatial and Temporal Input Data 

  Gabriel, Dorvil (2016)

  With the advancement of technology, electromyographic (EMG) and spatial data recognition is having a growing impact on accessible computing. I designed a customizable script that uses a combination of EMG, spatial and ...
• Dynamic Arm Orientation Detection During Body Motion as a Computer Interface: An Elegant Approach for a More Technological Age 

  Firmani, Marcus (2016)

  Gestures serve an important role in human-computer interfaces, and advancing technology such as virtual and augmented reality makes 3-D gestures an increasingly important and powerful means of interaction. Robust gesture ...
• Factors Affecting Stencil Code Performance 

  Zhou, Ting (2016)

  In the field of scientific computation, loop tiling is an indispensable technique for improving cache performance, and thereby the overall performance of the code. Research so far has predominantly been focusing on optimizing ...
• Auditing Deep Neural Networks and Other Black-box Models 

  Falk, Casey (2016)

  In this era of self-driving cars, smart watches, and voice-commanded speakers, machine learning is ubiquitous. Recently, deep learning has shown impressive success in solving many machine learning problems related to image ...
• Automatic Emotion Detection Technology for Autism Therapy 

  Uriostegui, Hector Ricardo (2016)

  Emotion recognition technology is being used to provide feedback to advertisers, sharing emotions through social media, and providing assistance to those who struggle to detect emotions. Affectiva is one of the companies ...
• Viability of Using the Leap Motion Controller in an Indirect Interaction Physical Rehabilitation Activity as an Alternative to a Direct Interaction Activity 

  Ta, Julie (2016)

  This thesis explores the potential of two input devices, the Leap Motion Controller and a touchscreen laptop, for use in conjunction with augmented reality in physical therapy activities for patients who suffer from motor ...
• Auditing Deep Neural Networks to Understand Recidivism Predictions 

  Smith, Brandon (2016)

  In recent years, deep neural network models have proven to be incredibly accurate on many classification benchmarks. Due to this high accuracy, many non-technical fields are interested in using these models to assist in ...
• Indirect Discrimination in the Age of Big Data 

  Rybeck, Gabriel (2016)

  Rapid advancements in the use of big data to make automated decisions may result in indirect discrimination. For example, Larson et al. (2015) find that the Princeton Review charges different prices by zip code resulting ...
• Computational Modeling of Musical Enculturation: An Investigation of Multicultural Music Learning Using Self-Organizing Maps 

  Pazdera, Jesse (2016)

  Past research has shown that children are able to implicitly learn the underlying melodic structure of their native culture's musical system, even without formal musical training. Although implicit musical learning has ...
• O(n) First-Order Queries on Graph Classes with Bounded Expansion 

  Okun, Harry (2016)

  We collect the proofs and lemmas which enable linear time algorithms for first-order sentences on graph classes with bounded expansion. Bounded expansion is a property limiting the edge to vertex ratio of a graph and its ...
• Optimizing a Machine Learning System for Materials Discovery 

  Martin-Noble, Geoffrey (2016)

  Advanced functional materials are crucial for addressing numerous challenges in medicine, communications, and energy. As highlighted by the White House Materials Genome Initiative, computational tools are critical for ...
• The Viterbi Algorithm and Sign Language Recognition 

  Perkoff, Elana (2015)

  This paper analyzes the Viterbi algorithm and its application to Sign Language Recognition. The Viterbi algorithm is used as a maximum a posteriori approach to solving the decoding problem of Hidden Markov Models (HMM). ...
• The Efficiency of Programming Through Automated Speech Recognition 

  English, Matt (2015)

  The goal of this thesis is to present information which will support programming through speech recognition by finding a limit for the size of commands in the given language of the program. This limit is the point at which ...
• Decomposition of Graphs into Biconnected and Triconnected Components 

  Caspari, Adam (2015)

  One of the most fundamental concepts in graph theory is connectivity, or the property that a path exists between two vertices in a given graph. The property of connectivity may be extended into biconnectivity and ...
• Computational Fairness: Preventing Machine-Learned Discrimination 

  Feldman, Michael (2015)

  Machine learning algorithms called classifiers make discrete predictions about new data by training on old data. These predictions may be hiring or not hiring, good or bad credit, and so on. The training data may contain ...
• Laziness in C++ 

  Mendelsohn, Richard (2015)

  The goal of this thesis is to create a suitable standard for evaluating lazy evaluation techniques, and to use this standard to compare existing methods of lazy evaluation in C++. For our standard we will create a rigorous ...

View more