Digital Commons Network^™

Diagnosing Breast Cancer With A Neural Network, John Cullen

Undergraduate Journal of Mathematical Modeling: One + Two

Fine needle aspiration (FNA) is a minimally invasive biopsy technique that can be used to successfully diagnose types of cancer, including breast cancer. Immediately, it is difficult for a human to spot any trends in the cell level data gathered during a fine needle aspiration procedure. One way to predict the type of tumor a patient has, is to use a computer to develop a mathematical model based on known data. This project utilizes the Diagnostic Wisconsin Breast Cancer Database (DWBCDB) to create an accurate mathematical model that predicts the type of a patient’s tumor (Malignant or Benign). A neural …

A Novel Approach For Classifying Gene Expression Data Using Topic Modeling, Soon Jye Kho, Himi Yalamanchili, Michael L. Raymer, Amit Sheth

Kno.e.sis Publications

Understanding the role of differential gene expression in cancer etiology and cellular process is a complex problem that continues to pose a challenge due to sheer number of genes and inter-related biological processes involved. In this paper, we employ an unsupervised topic model, Latent Dirichlet Allocation (LDA) to mitigate overfitting of high-dimensionality gene expression data and to facilitate understanding of the associated pathways. LDA has been recently applied for clustering and exploring genomic data but not for classification and prediction. Here, we proposed to use LDA inclustering as well as in classification of cancer and healthy tissues using lung cancer …

Intelligent Feature Selection For Detecting Http/2 Denial Of Service Attacks, Erwin Adi, Zubair Baig

Australian Information Security Management Conference

Intrusion-detection systems employ machine learning techniques to classify traffic into attack and legitimate. Network flooding attacks can leverage the new web communications protocol (HTTP/2) to bypass intrusion-detection systems. This creates an urgent demand to understand HTTP/2 characteristics and to devise customised cyber-attack detection schemes. This paper proposes Step Sister; a technique to generate an optimum network traffic feature set for network intrusion detection. The proposed technique demonstrates that a consistent set of features are selected for a given HTTP/2 dataset. This allows intrusion-detection systems to classify previously unseen network traffic samples with fewer false alarm than when techniques used in …

Detection Of Diffuse Seafloor Venting Using A Structured Light Laser Sensor: 1. Development Of A Classification Based Detection Method, Clara Smart, Chris Roman, Steven Carey

Ocean Engineering Faculty Publications

Systematic and remote detection of diffuse hydrothermal venting is complex yet necessary to establish a comprehensive understanding the distribution, contribution, and context of fluid flow within hydrothermal systems. Diffuse flow is characterized by both low temperature and low flow rates and cannot be consistently distinguished during extensive systematic surveys using current vehicle-mounted visual, acoustic, or environmental sensors. The remotely operated vehicle-mounted structured light laser sensor is sensitive to fluid density anomalies and seafloor characteristics. Presented advancements to the detection algorithm include the development and implementation of intensity normalization routines and a support vector machine classification algorithm. The resulting comprehensive maps …

Presenting A Labelled Dataset For Real-Time Detection Of Abusive User Posts, Hao Chen, Susan Mckeever, Sarah Jane Delany

Conference papers

Social media sites facilitate users in posting their own personal comments online. Most support free format user posting, with close to real-time publishing speeds. However, online posts generated by a public user audience carry the risk of containing inappropriate, potentially abusive content. To detect such content, the straightforward approach is to filter against blacklists of profane terms. However, this lexicon filtering approach is prone to problems around word variations and lack of context. Although recent methods inspired by machine learning have boosted detection accuracies, the lack of gold standard labelled datasets limits the development of this approach. In this work, …

A Comparison Of Feature Extraction Techniques For Malware Analysis, Mohammad Imran, Muhammad Tanvir Afzal, Muhammad Abdul Qadir

Turkish Journal of Electrical Engineering and Computer Sciences

The manifold growth of malware in recent years has resulted in extensive research being conducted in the domain of malware analysis and detection, and theories from a wide variety of scientific knowledge domains have been applied to solve this problem. The algorithms from the machine learning paradigm have been particularly explored, and many feature extraction methods have been proposed in the literature for representing malware as feature vectors to be used in machine learning algorithms. In this paper we present a comparison of several feature extraction techniques by first applying them on system call logs of real malware, and then …

Late Fusion Of Facial Dynamics For Automatic Expression Recognition, Alessandra Bandrabur, Laura Florea, Cornel Florea, Matei Mancas

Turkish Journal of Electrical Engineering and Computer Sciences

Installment of a facial expression is associated with contractions and extensions of specific facial muscles. Noting that expression is about changes, we present a model for expression classification based on facial landmarks dynamics. Our model isolates the trajectory of facial fiducial points by wrapping them up in relevant features and discriminating among various alternatives with a machine learning classification system. The used features are geometric and temporal-based and the classification system is represented by a late fusion framework that combines several neural networks with binary responses. The proposed method is robust, being able to handle complex expression classes.

Hoeffding Tree Algorithms For Anomaly Detection In Streaming Datasets: A Survey, Asmah Muallem, Sachin Shetty, Jan W. Pan, Juan Zhao, Biswajit Biswal

Computational Modeling & Simulation Engineering Faculty Publications

This survey aims to deliver an extensive and well-constructed overview of using machine learning for the problem of detecting anomalies in streaming datasets. The objective is to provide the effectiveness of using Hoeffding Trees as a machine learning algorithm solution for the problem of detecting anomalies in streaming cyber datasets. In this survey we categorize the existing research works of Hoeffding Trees which can be feasible for this type of study into the following: surveying distributed Hoeffding Trees, surveying ensembles of Hoeffding Trees and surveying existing techniques using Hoeffding Trees for anomaly detection. These categories are referred to as compositions …

A Neural Network Approach To Visibility Range Estimation Under Foggy Weather Conditions, Hazar Chaabani, Faouzi Kamoun, Hichem Bargaoui, Fatma Outay, Ansar Ul Haque Yasar

All Works

© 2017 The Authors. Published by Elsevier B.V. The degradation of visibility due to foggy weather conditions is a common trigger for road accidents and, as a result, there has been a growing interest to develop intelligent fog detection and visibility range estimation systems. In this contribution, we provide a brief overview of the state-of-the-art contributions in relation to estimating visibility distance under foggy weather conditions. We then present a neural network approach for estimating visibility distances using a camera that can be fixed to a roadside unit (RSU) or mounted onboard a moving vehicle. We evaluate the proposed solution …

Towards A Relative-Pitch Neural Network System For Chorale Composition And Harmonization, Samuel P. Goree

Honors Papers

Computational creativity researchers interested in applying machine learning to computer composition often use the music of J.S. Bach to train their systems. Working with Bach, though, requires grappling with the conventions of tonal music, which can be difficult for computer systems to learn. In this paper, we propose and implement an alternate approach to composition and harmonization of chorales based on pitch-relative note encodings to avoid tonality altogether. We then evaluate our approach using a survey and expert analysis, and find that pitch-relative encodings do not significantly affect human-comparability, likability or creativity. However, an extension of this model that better …

Exploring Subpixel Learning Algorithms For Estimating Global Land Cover Fractions From Satellite Data Using High Performance Computing, Uttam Kumar, Sangram Ganguly, Ramakrishna R. Nemani, Kumar S. Raja, Cristina Milesi, Ruchita Sinha, Andrew Michaelis, Petr Votava, Hirofumi Hashimoto, Shuang Li, Weile Wang, Subodh Kalia, Shreekant Gayaka

School of Natural Sciences Faculty Publications and Presentations

Land cover (LC) refers to the physical and biological cover present over the Earth’s surface in terms of the natural environment such as vegetation, water, bare soil, etc. Most LC features occur at finer spatial scales compared to the resolution of primary remote sensing satellites. Therefore, observed data are a mixture of spectral signatures of two or more LC features resulting in mixed pixels. One solution to the mixed pixel problem is the use of subpixel learning algorithms to disintegrate the pixel spectrum into its constituent spectra. Despite the popularity and existing research conducted on the topic, the most appropriate …

Applications Of Machine Learning And Computer Vision For Smart Infrastructure Management In Civil Engineering, Shounak Mitra

Master's Theses and Capstones

Machine Learning and Computer Vision are the two technologies that have innovative applications in diverse fields, including engineering, medicines, agriculture, astronomy, sports, education etc. The idea of enabling machines to make human like decisions is not a recent one. It dates to the early 1900s when analogies were drawn out between neurons in a human brain and capability of a machine to function like humans. However, major advances in the specifics of this theory were not until 1950s when the first experiments were conducted to determine if machines can support artificial intelligence. As computation powers increased, in the form of …

Application Of Machine Learning Models To Cftr Enhancer Discovery, James M.J. Lawlor

Theses

Cystic Fibrosis is a Mendelian genetic disorder causing production of hyper- viscous mucus, which damages organs including the lungs and digestive system, and is the result of absent or defective production of the chloride transport protein CFTR. CFTR expression varies between organs, developmental stages, and individuals. We develop and optimize a machine learning pipeline to identify enhancers—binding sites for regulatory proteins—near CFTR. We segment A549, Caco-2, Calu-3, and PANC-1 genomes, train a sequence-based classifier on the predicted enhancer segments, and use the classifier score to predict sequence variants’ enhancer activities. Our optimizations appreciably improve the resulting enhancer predictions. We present …

Substantiating Big Data In Health Care, Nathan Cortez

Faculty Journal Articles and Book Chapters

Predictive analytics and "big data" are emerging as important new tools for diagnosing and treating patients. But as data collection becomes more pervasive, and as machine learning and analytical methods become more sophisticated, the companies that traffic in health-related big data will face competitive pressures to make more aggressive claims regarding what their programs can predict. Already, patients, practitioners, and payors are inundated with claims that software programs, "apps," and other forms of predictive analytics can help solve some of the health care system's most pressing problems. This article considers the evidence and substantiation that we should require of these …

Using Mediawiki, The Semantic Mediawiki Extension And Relfinder For Heritage Data Management: A Rock Art Case Study, Robert A. Haubt

Staff Scholarship - Australia & Dubai

This paper looks at the usefulness of the MediaWiki and relevant wiki extensions for rock art data management and research. The paper follows a framework provided by the Global Rock Art Database www.rockartdatabase.com and examines a new database model for a semantic data management approach. Through practical examples it explores the usefulness of wikis in the data management life cycle from data planning to collection, storage and dissemination and examines interconnections within each phase of the cycle. The paper proposes a combined use of the Semantic MediaWiki extension and the RelFinder for visualization of semantic relationships, which could assist researchers …

Understanding Pubmed Search Results Using Topic Models And Interactive Information Visualization, Zhiguo Yu

Dissertations and Theses (Open Access)

With data increasing exponentially, extracting and understanding information, themes and relationships from larger collections of documents is becoming more and more important to researchers in many areas. PubMed, which comprises more than 25 million citations, uses Medical Subject Headings (MeSH) to index articles to better facilitate their management, searching and indexing. However, researchers are still challenged to find and then get a meaningful overview of a set of documents in a specific area of interest. This is due in part to several limitations of MeSH terms, including: the need to monitor and expand the vocabulary; the lack of concept coverage …

User-Centric Traffic Engineering In Software Defined Networks, Taimur Bakhshi

School of Engineering, Computing and Mathematics Theses

Software defined networking (SDN) is a relatively new paradigm that decouples individual network elements from the control logic, offering real-time network programmability, translating high level policy abstractions into low level device configurations. The framework comprises of the data (forwarding) plane incorporating network devices, while the control logic and network services reside in the control and application planes respectively. Operators can optimize the network fabric to yield performance gains for individual applications and services utilizing flow metering and application-awareness, the default traffic management method in SDN. Existing approaches to traffic optimization, however, do not explicitly consider user application trends. Recent SDN …

Audio-Based Productivity Forecasting Of Construction Cyclic Activities, Chris A. Sabillon

College of Graduate Studies: Theses & Dissertations

Due to its high cost, project managers must be able to monitor the performance of construction heavy equipment promptly. This cannot be achieved through traditional management techniques, which are based on direct observation or on estimations from historical data. Some manufacturers have started to integrate their proprietary technologies, but construction contractors are unlikely to have a fleet of entirely new and single manufacturer equipment for this to represent a solution. Third party automated approaches include the use of active sensors such as accelerometers and gyroscopes, passive technologies such as computer vision and image processing, and audio signal processing. Hitherto, most …

Integration And Evaluation Of Automated Pavement Distress Data In Indot’S Pavement Management System, Majed Alinizzi, Julie Yu Qiao, Amr Kandil, Hubo Cai, Samuel Labi

JTRP Technical Reports

This study was in two parts. The first part established and demonstrated a framework for pavement data integration. This is critical for fulfilling QC/QA needs of INDOT’s pavement management system, because the precision of the physical location references is a prerequisite for the reliable collection and interpretation of pavement data. Such consistency is often jeopardized because the data are collected at different years, and are affected by changes in the vendor, inventory, or referencing system or reference points. This study therefore developed a “lining-up” methodology to address this issue. The applicability of the developed methodology was demonstrated using 2012-2014 data …

A Survey On Automated Food Monitoring And Dietary Management Systems, Vieira Bruno, Silva Resende, Juan Cui

School of Computing: Faculty Publications

Healthy diet with balanced nutrition is key to the prevention of life-threatening diseases such as obesity, cardiovascular disease, and cancer. Recent advances in smartphone and wearable sensor technologies have led to a proliferation of food monitoring applications based on automated food image processing and eating episode detection, with the goal to conquer drawbacks of the traditional manual food journaling that is time consuming, inaccurate, underreporting, and low adherent. In order to provide users feedback with nutritional information accompanied by insightful dietary advice, various techniques in light of the key computational learning principles have been explored. This survey presents a variety …

K-Mer Analysis Pipeline For Classification Of Dna Sequences From Metagenomic Samples, Russell Kaehler

Graduate Student Theses, Dissertations, & Professional Papers

Biological sequence datasets are increasing at a prodigious rate. The volume of data in these datasets surpasses what is observed in many other fields of science. New developments wherein metagenomic DNA from complex bacterial communities is recovered and sequenced are producing a new kind of data known as metagenomic data, which is comprised of DNA fragments from many genomes. Developing a utility to analyze such metagenomic data and predict the sample class from which it originated has many possible implications for ecological and medical applications. Within this document is a description of a series of analytical techniques used to process …

Bruise Detection In Apples Using 3d Infrared Imaging And Machine Learning Technologies, Zilong Hu

Dissertations, Master's Theses and Master's Reports

Bruise detection plays an important role in fruit grading. A bruise detection system capable of finding and removing damaged products on the production lines will distinctly improve the quality of fruits for sale, and consequently improve the fruit economy. This dissertation presents a novel automatic detection system based on surface information obtained from 3D near-infrared imaging technique for bruised apple identification. The proposed 3D bruise detection system is expected to provide better performance in bruise detection than the existing 2D systems.

We first propose a mesh denoising filter to reduce noise effect while preserving the geometric features of the meshes. …

Plantcv V2: Image Analysis Software For High-Throughput Plant Phenotyping, Malia A. Gehan, Noah Fahlgren, Arash Abbasi, Jeffrey C. Berry, Steven T. Callen, Leonardo Chavez, Andrew N. Doust, Max J. Feldman, Kerrigan B. Gilbert, John G. Hodge, J. Steen Hoyer, Andy Lin, Suxing Liu, César Lizárraga, Argelia Lorence, Michael Miller, Eric Platon, Monica Tessman, Tony Sax

Department of Agronomy and Horticulture: Faculty Publications

Systems for collecting image data in conjunction with computer vision techniques are a powerful tool for increasing the temporal resolution at which plant phenotypes can be measured non-destructively. Computational tools that are flexible and extendable are needed to address the diversity of plant phenotyping problems. We previously described the Plant Computer Vision (PlantCV) software package, which is an image processing toolkit for plant phenotyping analysis. The goal of the PlantCV project is to develop a set of modular, reusable, and repurposable tools for plant image analysis that are open-source and community-developed. Here we present the details and rationale for major …

Deep Learning Method Vs. Hand-Crafted Features For Lung Cancer Diagnosis And Breast Cancer Risk Analysis, Wenqing Sun

Open Access Theses & Dissertations

Breast cancer and lung cancer are two major leading causes of cancer deaths, and researchers have been developing computer aided diagnosis (CAD) system to automatically diagnose them for decades. In recent studies, we found that the techniques in CAD system can also be used for breast cancer risk analysis, like feature design and machine learning. Also we noticed that with the development of deep learning methods, the performance of CAD system can be improved by using computer automatically generated features. To explore these possibilities, we conducted a series of studies: the first two studies focused on transferring the original CAD …

Rapidly Deployed And Assembled Tensegrity System: An Augmented Design Approach, Phillip Anzalone, Stephanie Bayard, Ralph S. Steenblik

Publications and Research

The Rapidly Deployable and Assembled Tensegrity (RDAT) project enables the efficient automated design and deployment of differential-geometry tensegrity structures through computation-driven design-to-installation workflow. RDAT employs the integration of parametric and solid-modeling methods with production by streamlining computer numerically controlled manufacturing through novel detailing and production techniques to develop an efficient manufacturing and assembly system. The RDAT project emerges from the Authors' research in academia and professional practice focusing on computationally produced full-scale performative building systems and their innovative uses in the building and construction industry.

Parkinson's Symptoms Quantification Using Wearable Sensors, Md Nafiul Alam

Theses and Dissertations

Parkinson’s disease (PD) is a common neurodegenerative disorder affecting more than one million people in the United States and seven million people worldwide. Motor symptoms such as tremor, slowness of movements, rigidity, postural instability, and gait impairment are commonly observed in PD patients. Currently, Parkinsonian symptoms are usually assessed in clinical settings, where a patient has to complete some predefined motor tasks. Then a physician assigns a score based on the United Parkinson’s Disease Rating Scale (UPDRS) after observing the motor task. However, this procedure suffers from inter subject variability. Also, patients tend to show fewer symptoms during clinical visit, …

Evaluating Machine Learning Classifiers For Defensive Cyber Operations, Michael D. Rich, Robert F. Mills, Thomas E. Dube, Steven K. Rogers

Military Cyber Affairs

Today’s defensive cyber sensors are dominated by signature-based analytical methods that require continuous maintenance and lack the ability to detect unknown threats. Anomaly detection offers the ability to detect unknown threats, but despite over 15 years of active research, the operationalization of anomaly detection and machine learning for Defensive Cyber Operations (DCO) is lagging. This article provides an introduction to machine learning concepts with a focus on the unique challenges to using machine learning for DCO. Traditional machine learning evaluation methods are challenged in favor of a value-focused evaluation method that incorporates evaluator-specific weights for classifier and sensitivity threshold selection …

Machine Learning Based Datacenter Monitoring Framework, Ravneet Singh Sidhu

Computer Science and Engineering Theses - Archive

Monitoring the health of large data centers is a major concern with the ever-increasing demand of grid/cloud computing and the higher need of computational power. In a High Performance Computing (HPC) environment, the need to maintain high availability makes monitoring tasks and hardware more daunting and demanding. As data centers grow it becomes hard to manage the complex interactions between different systems. Many open source systems have been implemented which give specific state of any individual machine using Nagios, Ganglia or Torque monitoring software. In this work we focus on the detection and prediction of data center anomalies by using …

Integrative Approaches For Large-Scale Biomedical Data Analysis, Ashis Kumer Biswas

Computer Science and Engineering Dissertations - Archive

Advancement of the Next Generation Sequencing (NGS), also known as the High Throughput Sequencing (HTS) technologies allow researchers investigate genome, transcriptome, or epigenome of any organism from any perspective, thereby contributing to the enrichment of the biomedical data repositories for many of the lesser known phenomena. The regulatory activities inside genome by the non-coding RNAs (ncRNAs), the transcribed product of the long-neglected "junk DNA" molecules is one such phenomenon. While large-scale data about the ncRNAs are becoming publicly available, the computational challenges are being imposed to the bioinformaticians for efficient mining to get reliable answers to few subtle questions. Given …

Predicting Malignant Nodules From Screening Ct Scans, Samuel Hawkins, Hua Wang, Ying Liu, Alberto Garcia, Olya Stringfield, Henry Krewer, Qiang Li, Dmitry Cherezov, Matthew Schabath, Lawrence O. Hall, Robert J. Gillies

Computer Science and Engineering Faculty Publications

Objectives

The aim of this study was to determine whether quantitative analyses (“radiomics”) of low-dose computed tomography lung cancer screening images at baseline can predict subsequent emergence of cancer.

Methods

Public data from the National Lung Screening Trial (ACRIN 6684) were assembled into two cohorts of 104 and 92 patients with screen-detected lung cancer and then matched with cohorts of 208 and 196 screening subjects with benign pulmonary nodules. Image features were extracted from each nodule and used to predict the subsequent emergence of cancer.

Results

The best models used 23 stable features in a random forests classifier and could …