Computer Sciences Commons^™

Analysing The Effects Of Data Augmentation And Free Parameters For Text Classification With Recurrent Convolutional Neural Networks, Jonathan Quijas

Open Access Theses & Dissertations

Convolutional neural networks have seen much success in computer vision and natural language processing tasks. When training convolutional neural networks for text classification tasks, a common technique is to transform an input sequence of words into a dense matrix of word embeddings, or words represented as dense vectors, using table lookup operations. This enables the inputs to be represented in a way that the well-known convolution/pooling operations can be applied to them in a manner similar to images. These word embeddings may be further incorporated into the neural network itself as a trainable layer to allow fine-tuning, usually leading to …

Investigating The Impact Of Unsupervised Feature-Extraction From Multi-Wavelength Image Data For Photometric Classification Of Stars, Galaxies And Qsos, Annika Lindh

Conference papers

Accurate classification of astronomical objects currently relies on spectroscopic data. Acquiring this data is time-consuming and expensive compared to photometric data. Hence, improving the accuracy of photometric classification could lead to far better coverage and faster classification pipelines. This paper investigates the benefit of using unsupervised feature-extraction from multi-wavelength image data for photometric classification of stars, galaxies and QSOs. An unsupervised Deep Belief Network is used, giving the model a higher level of interpretability thanks to its generative nature and layer-wise training. A Random Forest classifier is used to measure the contribution of the novel features compared to a set …

Review Classification, Balraj Aujla

Computer Science and Software Engineering

The goal of this project is to find a way to analyze reviews and determine the sentiment of a review. It uses various machine learning techniques in order to achieve its goals such as SVMs and Naive Bayes. Overall the purpose is to learn many different machine learning techniques, determine which ones would be useful for the project, then compare the results. Research is the foremost goal of the project, and it is able to determine the better algorithm for review classification, naive bayes or an SVM. In addition, an SVM which actually gave review’s scores rather than just classifying …

Fundamentals Of Machine Learning For Neural Machine Translation, John D. Kelleher

Conference papers

This paper presents a short introduction to neural networks and how they are used for machine translation and concludes with some discussion on the current research challenges being addressed by neural machine translation (NMT) research. The primary goal of this paper is to give a no-tears introduction to NMT to readers that do not have a computer science or mathematical background. The secondary goal is to provide the reader with a deep enough understanding of NMT that they can appreciate the strengths of weaknesses of the technology. The paper starts with a brief introduction to standard feed-forward neural networks (what …

Significant Permission Identification For Android Malware Detection, Lichao Sun

School of Computing: Dissertations, Theses, and Student Research

A recent report indicates that a newly developed malicious app for Android is introduced every 11 seconds. To combat this alarming rate of malware creation, we need a scalable malware detection approach that is effective and efficient. In this thesis, we introduce SigPID, a malware detection system based on permission analysis to cope with the rapid increase in the number of Android malware. Instead of analyzing all 135 Android permissions, our approach applies 3-level pruning by mining the permission data to identify only significant permissions that can be effective in distinguishing benign and malicious apps. Based on the identified significant …

Applying Machine Learning To Predict Stock Value, Joseph Lemley, Yishui Liu, Dipayan Banik, Sadia Afroze

Symposium Of University Research and Creative Expression (SOURCE)

The purpose of this study was to compare machine learning techniques for short term stock prediction and evaluate their effectiveness. Stock value analysis is an important element of modern economies. The ability to predict future stock prices from historical price values is of tremendous interest to investors. The prediction of stock performance is still an unsolved problem with a variety of techniques being proposed. Real stock values are affected by many elements, some of which cannot be measured. In this study, we limit our analysis to stock closing prices. We use these prices to predict the future stock value using …

Learning With Scalability And Compactness, Wenlin Chen

McKelvey School of Engineering Graduate Student Theses & Dissertations

Artificial Intelligence has been thriving for decades since its birth. Traditional AI features heuristic search and planning, providing good strategy for tasks that are inherently search-based problems, such as games and GPS searching. In the meantime, machine learning, arguably the hottest subfield of AI, embraces data-driven methodology with great success in a wide range of applications such as computer vision and speech recognition. As a new trend, the applications of both learning and search have shifted toward mobile and embedded devices which entails not only scalability but also compactness of the models. Under this general paradigm, we propose a series …

Visualization Of Deep Convolutional Neural Networks, Dingwen Li

McKelvey School of Engineering Graduate Student Theses & Dissertations

Deep learning has achieved great accuracy in large scale image classification and scene recognition tasks, especially after the Convolutional Neural Network (CNN) model was introduced. Although a CNN often demonstrates very good classification results, it is usually unclear how or why a classification result is achieved. The objective of this thesis is to explore several existing visualization approaches which offer intuitive visual results. The thesis focuses on three visualization approaches: (1) image masking which highlights the region of image with high influence on the classification, (2) Taylor decomposition back-propagation which generates a per pixel heat map that describes each pixel's …

Discovering Adverse Drug Interaction Using Convex Optimization Techniques, Mohammadreza Rezaie

Theses and Dissertations

Healthcare organizations generate massive quantities of data which are often convolved with valuable hidden insights. In order to discover new adverse drug events (ADEs) the data mining techniques are employed extensively, but the computational complexity of the traditional data analytics platforms makes the need to migrate to a scalable analytics platform. The goal in experiments is predicting the possibility of certain interactions given a prescribed set of drugs. In this work, we used Spark platform and MLlib library as an alternative scalable solution that we found them scalable, easy to work with and with reasonable modeling accuracy. We utilized Hadoop …

The New Issues In Classification Problems, Md Mahmudul Hasan

Open Access Theses & Dissertations

The data involved with science and engineering getting bigger everyday. To study and organize a big amount of data is difficult without classification. In machine learning, classification is the problem of identifying a given data from a set of categories. There are several classification technique people using to classify a given data. In our work we present a sparse representation technique to perform classification. The popularity of this technique motivates us to use on our collected samples. To find a sparse representation, we used an $l_1$-minimization algorithm which is a convex relaxation algorithm proven very efficient by researchers. The purpose …

Using Diversity Ensembles With Time Limits To Handle Concept Drift, Robert M. Van Camp

CCAC Theses and Dissertations

While traditional supervised learning focuses on static datasets, an increasing amount of data comes in the form of streams, where data is continuous and typically processed only once. A common problem with data streams is that the underlying concept we are trying to learn can be constantly evolving. This concept drift has been of interest to researchers the last few years and there is a need for improved machine learning algorithms that are capable of dealing with concept drifts. A promising approach involves using an ensemble of a diverse set of classifiers. The constituent classifiers are re-trained when a concept …

Care-Chair: Opportunistic Health Assessment With Smart Sensing On Chair Backrest, Rakesh Kumar

Masters Theses

"A vast majority of the population spend most of their time in a sedentary position, which potentially makes a chair a huge source of information about a person's daily activity. This information, which often gets ignored, can reveal important health data but the overhead and the time consumption needed to track the daily activity of a person is a major hurdle. Considering this, a simple and cost-efficient sensory system, named Care-Chair, with four square force sensitive resistors on the backrest of a chair has been designed to collect the activity details and breathing rate of the users. The Care-Chair system …

Evaluation Of Supervised Machine Learning For Classifying Video Traffic, Farrell R. Taylor

CCAC Theses and Dissertations

Operational deployment of machine learning based classifiers in real-world networks has become an important area of research to support automated real-time quality of service decisions by Internet service providers (ISPs) and more generally, network administrators. As the Internet has evolved, multimedia applications, such as voice over Internet protocol (VoIP), gaming, and video streaming, have become commonplace. These traffic types are sensitive to network perturbations, e.g. jitter and delay. Automated quality of service (QoS) capabilities offer a degree of relief by prioritizing network traffic without human intervention; however, they rely on the integration of real-time traffic classification to identify applications. Accordingly, …

Idiom Token Classification Using Sentential Distributed Semantics, Giancarlo Salton, Robert J. Ross, John D. Kelleher

Conference papers

Idiom token classification is the task of deciding for a set of potentially idiomatic phrases whether each occurrence of a phrase is a literal or idiomatic usage of the phrase. In this work we explore the use of Skip-Thought Vectors to create distributed representations that encode features that are predictive with respect to idiom token classification. We show that classifiers using these representations have competitive performance compared with the state of the art in idiom token classification. Importantly, however, our models use only the sentence containing the tar- get phrase as input and are thus less dependent on a potentially …

Predicting Intraday Financial Market Dynamics Using Takens' Vectors; Incorporating Causality Testing And Machine Learning Techniques, Abubakar-Sadiq Bouda Abdulai

Electronic Theses and Dissertations

Traditional approaches to predicting financial market dynamics tend to be linear and stationary, whereas financial time series data is increasingly nonlinear and non-stationary. Lately, advances in dynamical systems theory have enabled the extraction of complex dynamics from time series data. These developments include theory of time delay embedding and phase space reconstruction of dynamical systems from a scalar time series. In this thesis, a time delay embedding approach for predicting intraday stock or stock index movement is developed. The approach combines methods of nonlinear time series analysis with those of causality testing, theory of dynamical systems and machine learning (artificial …

Sudden Cardiac Arrest Prediction Through Heart Rate Variability Analysis, Luke Joseph Plewa

Master's Theses

The increase in popularity for wearable technologies (see: Apple Watch and Microsoft Band) has opened the door for an Internet of Things solution to healthcare. One of the most prevalent healthcare problems today is the poor survival rate of out-of hospital sudden cardiac arrests (9.5% on 360,000 cases in the USA in 2013). It has been proven that heart rate derived features can give an early indicator of sudden cardiac arrest, and that providing an early warning has the potential to save many lives. Many of these new wearable devices are capable of providing this warning through their heart rate …

Modeling Visual Features To Recognize Biological Motion: A Developmental Approach, Giulio Sandini, Nicoletta Noceti, Alessia Vignolo, Alessandra Sciutti, Francesco Rea, Alessandro Verri, Francesca Odone

MODVIS Workshop

In this work we deal with the problem of designing and developing computational vision models – comparable to the early stages of the human development – using coarse low-level information.

More specifically, we consider a binary classification setting to characterize biological movements with respect to non-biological dynamic events. To this purpose, our model builds on top of the optical flow estimation, and abstract the representation to simulate the limited amount of visual information available at birth. We take inspiration from known biological motion regularities explained by the Two-Thirds Power Law, and design a motion representation that includes different low-level features, …

Evaluating Defect Prediction Using A Massive Set Of Metrics, Xiao Xuan, David Lo, Xin Xia, Yuan Tian

Research Collection School Of Computing and Information Systems

To evaluate the performance of a within-project defect prediction approach, people normally use precision, recall, and F-measure scores. However, in machine learning literature, there are a large number of evaluation metrics to evaluate the performance of an algorithm, (e.g., Matthews Correlation Coefficient, G-means, etc.), and these metrics evaluate an approach from different aspects. In this paper, we investigate the performance of within-project defect prediction approaches on a large number of evaluation metrics. We choose 6 state-of-the-art approaches including naive Bayes, decision tree, logistic regression, kNN, random forest and Bayesian network which are widely used in defect prediction literature. And we …

Contrast Pattern Aided Regression And Classification, Vahid Taslimitehrani

Browse all Theses and Dissertations

Regression and classification techniques play an essential role in many data mining tasks and have broad applications. However, most of the state-of-the-art regression and classification techniques are often unable to adequately model the interactions among predictor variables in highly heterogeneous datasets. New techniques that can effectively model such complex and heterogeneous structures are needed to significantly improve prediction accuracy. In this dissertation, we propose a novel type of accurate and interpretable regression and classification models, named as Pattern Aided Regression (PXR) and Pattern Aided Classification (PXC) respectively. Both PXR and PXC rely on identifying regions in the data space where …

Unsupervised Learning And Image Classification In High Performance Computing Cluster, Itauma Itauma

Wayne State University Theses

Feature learning and object classification in machine learning have become very active research areas in recent decades. Identifying good features has various benefits for object classification in respect to reducing the computational cost and increasing the classification accuracy. In addition, many research studies have focused on the use of Graphics Processing Units (GPUs) to improve the training time for machine learning algorithms. In this study, the use of an alternative platform, called High Performance Computing Cluster (HPCC), to handle unsupervised feature learning, image and speech classification and improve the computational cost is proposed.

HPCC is a Big Data processing and …

Effective Auto Encoder For Unsupervised Sparse Representation, Faria Mahnaz

Wayne State University Theses

High dimensionality and the sheer size of unlabeled data available today demand

new development in unsupervised learning of sparse representation. Despite of recent

advances in representation learning, most of the current methods are limited when

dealing with large scale unlabeled data. In this study, we propose a new unsupervised

method that is able to learn sparse representation from unlabeled data efficiently. We

derive a closed-form solution based on the sequential minimal optimization (SMO)

for training an auto encoder-decoder module, which efficiently extracts sparse and

compact features from any data set with various size. The inference process in the

proposed learning …

Geographic Relevance For Travel Search: The 2014-2015 Harvey Mudd College Clinic Project For Expedia, Inc., Hannah Long

Scripps Senior Theses

The purpose of this Clinic project is to help Expedia, Inc. expand the search capabilities it offers to its users. In particular, the goal is to help the company respond to unconstrained search queries by generating a method to associate hotels and regions around the world with the higher-level attributes that describe them, such as “family- friendly” or “culturally-rich.” Our team utilized machine-learning algorithms to extract metadata from textual data about hotels and cities. We focused on two machine-learning models: decision trees and Latent Dirichlet Allocation (LDA). The first appeared to be a promising approach, but would require more resources …

Features For Ranking Tweets Based On Credibility And Newsworthiness, Jacob W. Ross

Browse all Theses and Dissertations

We create a robust and general feature set for learning to rank algorithms that rank tweets based on credibility and newsworthiness. In previous works, it has been demonstrated that when the training and testing data are from two distinct time periods, the ranker performs poorly. We improve upon previous work by creating a feature set that does not over fit a particular year or set of topics. This is critical given how people utilize social media changes as time progresses, and the topics discussed vary. In addition, we are constantly gaining new tweet data. Thus, it is important to be …

Novel Classification Of Slow Movement Objects In Urban Traffic Environments Using Wideband Pulse Doppler Radar, Berta Rodriguez Hervas

Open Access Theses & Dissertations

Every year thousands of people are involved in traffic accidents, some of which are fatal. An important percentage of these fatalities are caused by human error, which could be prevented by increasing the awareness of drivers and the autonomy of vehicles. Since driver assistance systems have the potential to positively impact tens of millions of people, the purpose of this research is to study the micro-Doppler characteristics of vulnerable urban traffic components, i.e. pedestrians and bicyclists, based on information obtained from radar backscatter, and to develop a classification technique that allows automatic target recognition with a vehicle integrated system. For …

Graph-Based Regularization In Machine Learning: Discovering Driver Modules In Biological Networks, Xi Gao

Theses and Dissertations

Curiosity of human nature drives us to explore the origins of what makes each of us different. From ancient legends and mythology, Mendel's law, Punnett square to modern genetic research, we carry on this old but eternal question. Thanks to technological revolution, today's scientists try to answer this question using easily measurable gene expression and other profiling data. However, the exploration can easily get lost in the data of growing volume, dimension, noise and complexity. This dissertation is aimed at developing new machine learning methods that take data from different classes as input, augment them with knowledge of feature relationships, …

Data Analytics For Power Utility Storm Planning, Lan Lin, Aldo Dagnino, Derek Doran, Swapna S. Gokhale

Kno.e.sis Publications

As the world population grows, recent climatic changes seem to bring powerful storms to populated areas. The impact of these storms on utility services is devastating. Hurricane Sandy is a recent example of the enormous damages that storms can inflict on infrastructure, society, and the economy. Quick response to these emergencies represents a big challenge to electric power utilities. Traditionally utilities develop preparedness plans for storm emergency situations based on the experience of utility experts and with limited use of historical data. With the advent of the Smart Grid, utilities are incorporating automation and sensing technologies in their grids and …

Element Detection In Japanese Comic Book Panels, Toshihiro Kuboi

Master's Theses

Comic books are a unique and increasingly popular form of entertainment combining visual and textual elements of communication. This work pertains to making comic books more accessible. Specifically, this paper explains how we detect elements such as speech bubbles present in Japanese comic book panels. Some applications of the work presented in this paper are automatic detection of text and its transformation into audio or into other languages. Automatic detection of elements can also allow reasoning and analysis at a deeper semantic level than what’s possible today. Our approach uses an expert system and a machine learning system. The expert …

Predicting Music Genre Preferences Based On Online Comments, Andrew J. Sinclair

Master's Theses

Communication Accommodation Theory (CAT) states that individuals adapt to each other’s communicative behaviors. This adaptation is called “convergence.” In this work we explore the convergence of writing styles of users of the online music distribution plat- form SoundCloud.com. In order to evaluate our system we created a corpus of over 38,000 comments retrieved from SoundCloud in April 2014. The corpus represents comments from 8 distinct musical genres: Classical, Electronic, Hip Hop, Jazz, Country, Metal, Folk, and World. Our corpus contains: short comments, frequent misspellings, little sentence struc- ture, hashtags, emoticons, and URLs. We adapt techniques used by researchers analyzing other …

A Computational Model Of Memetic Evolution: Optimizing Collective Intelligence, Noah Welsh

All Dissertations

The purpose of this study was to create an adaptive agent based simulation modeling the processes of creative collaboration. This model aided in the development of a new evolutionary based framework through which education scholars, academics, and professionals in all disciplines and industries can work to optimize their collective ability to find creative solutions to complex problems. The basic premise follows that the process of idea exchange, parallels the role sexual reproduction in biological evolution and is essential to society's collective ability to solve complex problems. The study outlined a set of assumptions used to develop a new theory of …

Challenges For Mapreduce In Big Data, Katarina Grolinger, Michael Hayes, Wilson A. Higashino, Alexandra L'Heureux, David S. Allison, Miriam A.M. Capretz

Electrical and Computer Engineering Publications

In the Big Data community, MapReduce has been seen as one of the key enabling approaches for meeting continuously increasing demands on computing resources imposed by massive data sets. The reason for this is the high scalability of the MapReduce paradigm which allows for massively parallel and distributed execution over a large number of computing nodes. This paper identifies MapReduce issues and challenges in handling Big Data with the objective of providing an overview of the field, facilitating better planning and management of Big Data projects, and identifying opportunities for future research in this field. The identified challenges are grouped …