Computer Sciences Commons^™

Active Learning With Unreliable Annotations, Liyue Zhao

Electronic Theses and Dissertations

With the proliferation of social media, gathering data has became cheaper and easier than before. However, this data can not be used for supervised machine learning without labels. Asking experts to annotate sufficient data for training is both expensive and time-consuming. Current techniques provide two solutions to reducing the cost and providing sufficient labels: crowdsourcing and active learning. Crowdsourcing, which outsources tasks to a distributed group of people, can be used to provide a large quantity of labels but controlling the quality of labels is hard. Active learning, which requires experts to annotate a subset of the most informative or …

An Exploration Of Unmanned Aerial Vehicle Direct Manipulation Through 3d Spatial Interaction, Kevin Pfeil

Electronic Theses and Dissertations

We present an exploration that surveys the strengths and weaknesses of various 3D spatial interaction techniques, in the context of directly manipulating an Unmanned Aerial Vehicle (UAV). Particularly, a study of touch- and device- free interfaces in this domain is provided. 3D spatial interaction can be achieved using hand-held motion control devices such as the Nintendo Wiimote, but computer vision systems offer a different and perhaps more natural method. In general, 3D user interfaces (3DUI) enable a user to interact with a system on a more robust and potentially more meaningful scale. We discuss the design and development of various …

A Compiler-Based Framework For Automatic Extraction Of Program Skeletons For Exascale Hardware/Software Co-Design, Amruth Rudraiah Dakshinamurthy

Electronic Theses and Dissertations

The design of high-performance computing architectures requires performance analysis of largescale parallel applications to derive various parameters concerning hardware design and software development. The process of performance analysis and benchmarking an application can be done in several ways with varying degrees of fidelity. One of the most cost-effective ways is to do a coarse-grained study of large-scale parallel applications through the use of program skeletons. The concept of a “program skeleton” that we discuss in this paper is an abstracted program that is derived from a larger program where source code that is determined to be irrelevant is removed for …

Discriminative Dictionary Learning With Spatial Constraints, Muhammad Nazar Khan

Electronic Theses and Dissertations

In this thesis, we investigate the use of dictionary learning for discriminative tasks on natural images. Our contributions can be summarized as follows: • We introduce discriminative deviation based learning to achieve principled handling of the reconstruction-discrimination tradeoff that is inherent to discriminative dictionary learning. • Since natural images obey a strong smoothness prior, we show how spatial smoothness constraints can be incorporated into the learning formulation by embedding dictionary learning into Conditional Random Field (CRF) learning. We demonstrate that such smoothness constraints can lead to state-of-the-art performance for pixel-classification tasks. • Finally, we lay down the foundations of super-latent …

Using Freebase, An Automatically Generated Dictionary, And A Classifier To Identify A Person's Profession In Tweets, Abraham Hall

Electronic Theses and Dissertations

Algorithms for classifying pre-tagged person entities in tweets into one of eight profession categories are presented. A classifier using a semi-supervised learning algorithm that takes into consideration the local context surrounding the entity in the tweet, hash tag information, and topic signature scores is described. In addition to the classifier, this research investigates two dictionaries containing the professions of persons. These two dictionaries are used in their own classification algorithms which are independent of the classifier. The method for creating the first dictionary dynamically from the web and the algorithm that accesses this dictionary to classify a person into one …

Automatically Acquiring A Semantic Network Of Related Concepts, Sean Szumlanski

Electronic Theses and Dissertations

We describe the automatic acquisition of a semantic network in which over 7,500 of the most frequently occurring nouns in the English language are linked to their semantically related concepts in the WordNet noun ontology. Relatedness between nouns is discovered automatically from lexical co-occurrence in Wikipedia texts using a novel adaptation of an information theoretic inspired measure. Our algorithm then capitalizes on salient sense clustering among these semantic associates to automatically disambiguate them to their corresponding WordNet noun senses (i.e., concepts). The resultant concept-to-concept associations, stemming from 7,593 target nouns, with 17,104 distinct senses among them, constitute a large-scale semantic …

Mexsvms: Mid-Level Features For Scalable Action Recognition, Du Tran, Lorenzo Torresani

Computer Science Technical Reports

This paper introduces MEXSVMs, a mid-level representation enabling efficient recognition of actions in videos. The entries in our descriptor are the outputs of several movement classifiers evaluated over spatial-temporal volumes of the image sequence, using space-time interest points as low-level features. Each movement classifier is a simple exemplar-SVM, i.e., an SVM trained using a single positive video and a large number of negative sequences. Our representation offers two main advantages. First, since our mid-level features are learned from individual video exemplars, they require minimal amount of supervision. Second, we show that even simple linear classification models trained on our global …

Gene Set Based Ensemble Methods For Cancer Classification, William Evans Duncan

LSU Doctoral Dissertations

Diagnosis of cancer very often depends on conclusions drawn after both clinical and microscopic examinations of tissues to study the manifestation of the disease in order to place tumors in known categories. One factor which determines the categorization of cancer is the tissue from which the tumor originates. Information gathered from clinical exams may be partial or not completely predictive of a specific category of cancer. Further complicating the problem of categorizing various tumors is that the histological classification of the cancer tissue and description of its course of development may be atypical. Gene expression data gleaned from micro-array analysis …

The Grace Programming Language Draft Specification Version 0.3.1261, Andrew P. Black, Kim B. Bruce, James Noble

Computer Science Faculty Publications and Presentations

This is a specification of the Grace Programming Language. This specification is notably incomplete, and everything is subject to change.

Application Of Swarm And Reinforcement Learning Techniques To Requirements Tracing, Hakim Sultanov

Theses and Dissertations--Computer Science

Today, software has become deeply woven into the fabric of our lives. The quality of the software we depend on needs to be ensured at every phase of the Software Development Life Cycle (SDLC). An analyst uses the requirements engineering process to gather and analyze system requirements in the early stages of the SDLC. An undetected problem at the beginning of the project can carry all the way through to the deployed product.

The Requirements Traceability Matrix (RTM) serves as a tool to demonstrate how requirements are addressed by the design and implementation elements throughout the entire software development lifecycle. …

Automatic Detection Of Abnormal Behavior In Computing Systems, James Frank Roberts

Theses and Dissertations--Computer Science

I present RAACD, a software suite that detects misbehaving computers in large computing systems and presents information about those machines to the system administrator. I build this system using preexisting anomaly detection techniques. I evaluate my methods using simple synthesized data, real data containing coerced abnormal behavior, and real data containing naturally occurring abnormal behavior. I find that the system adequately detects abnormal behavior and significantly reduces the amount of uninteresting computer health data presented to a system administrator.

Context Aware Privacy Preserving Clustering And Classification, Nirmal Thapa

Theses and Dissertations--Computer Science

Data are valuable assets to any organizations or individuals. Data are sources of useful information which is a big part of decision making. All sectors have potential to benefit from having information. Commerce, health, and research are some of the fields that have benefited from data. On the other hand, the availability of the data makes it easy for anyone to exploit the data, which in many cases are private confidential data. It is necessary to preserve the confidentiality of the data. We study two categories of privacy: Data Value Hiding and Data Pattern Hiding. Privacy is a huge concern …

A Novel Computational Framework For Transcriptome Analysis With Rna-Seq Data, Yin Hu

Theses and Dissertations--Computer Science

The advance of high-throughput sequencing technologies and their application on mRNA transcriptome sequencing (RNA-seq) have enabled comprehensive and unbiased profiling of the landscape of transcription in a cell. In order to address the current limitation of analyzing accuracy and scalability in transcriptome analysis, a novel computational framework has been developed on large-scale RNA-seq datasets with no dependence on transcript annotations. Directly from raw reads, a probabilistic approach is first applied to infer the best transcript fragment alignments from paired-end reads. Empowered by the identification of alternative splicing modules, this framework then performs precise and efficient differential analysis at automatically detected …

Approximate Sequence Alignment, Xuanting Cai

LSU Master's Theses

Given a collection of strings and a query string, the goal of the approximate string matching is to efficiently find the strings in the collection, which are similar to the query string. In this paper, we focus on edit distance as a measure to quantify the similarity between two strings. Existing q-gram based methods use inverted lists to index the q-grams of the given string collection. These methods begin with generating the q-grams of the query string, disjoint or overlapping, and then merge the inverted lists of these q-grams. Several filtering techniques have been proposed to segment inverted lists in …

Parallel Suffix Tree Construction For Genome Sequence Using Hadoop, Umesh Chandra Satish

LSU Master's Theses

Indexing the genome is the basis for many of the bioinformatics applications. Read mapping (sequence alignment) is one such application to align millions of short reads against reference genome. Several tools like BLAST, SOAP, BOWTIE, Cloudburst, and Rapid Parallel Genome Indexing with MapReduce use indexing technique for aligning short reads. Many of the contemporary alignment techniques are time consuming, memory intensive and cannot be easily scaled to larger genomes. Suffix tree is a popular data structure which can be used to overcome the demerits of other alignment techniques. However, constructing the suffix tree is highly memory intensive and time consuming. …

Bayesian Inference Application To Burglary Detection, Ishan Singh Bhale

LSU Master's Theses

Real time motion tracking is very important for video analytics. But very little research has been done in identifying the top-level plans behind the atomic activities evident in various surveillance footages [61]. Surveillance videos can contain high level plans in the form of complex activities [61]. These complex activities are usually a combination of various articulated activities like breaking windshield, digging, and non-articulated activities like walking, running. We have developed a Bayesian framework for recognizing complex activities like burglary. This framework (belief network) is based on an expectation propagation algorithm [8] for approximate Bayesian inference. We provide experimental results showing …

Detection Of Interesting Traffic Accident Patterns By Association Rule Mining, Harisha Donepudi

LSU Master's Theses

In recent years, the accident rate related to traffic is high. Analyzing the crash data and extracting useful information from it can help in taking respective measures to decrease this rate or prevent the crash from happening. Related research has been done in the past which involved proposing various measures and algorithms to obtain interesting crash patterns from the crash records. The main problem is that large numbers of patterns were produced and vast number of these patterns would be obvious or not interesting. A deeper analysis of the data is required in order to get the interesting patterns. In …

The Turning, Stretching And Boxing Technique: A Direction Worth Looking Towards, Mark Dunne

Doctoral

3D avatar user interfaces (UI) are now used for many applications, a growing area for their use is serving location sensitive information to users as they need it while visiting or touring a building. Users communicate directly with an avatar rendered to a display in order to ask a question, get directions or partake in a guided tour and as a result of this kind of interaction with avatar UI, they have become a familiar part of modern human-computer interaction (HCI). However, if the viewer is not in the sweet spot (defined by Raskar et al. (1999) as a stationary …

Discrete Event Simulation-Based Performance Evaluation Of Internet Routing Protocols, Fati̇h Çeli̇k, Ahmet Zengi̇n, Bülent Çobanoğlu

Turkish Journal of Electrical Engineering and Computer Sciences

This paper presents a discrete event system specification (DEVS)-based comparative performance analysis between the open shortest path first (OSPF) protocol and the routing information protocol (RIP), together with the border gateway protocol (BGP), using DEVS-Suite. In order to evaluate the OSPF and RIP's scalability performance, several network models are designed and configured with the OSPF and RIP, in combination with the BGP. Evaluations of the proposed routing protocols are performed based on the metrics, such as the execution time, convergence time, turnaround time, throughput, and efficiency across an increasing size and complexity through the simulated network models. The evaluation results …

Rigidity Analysis Of Protein Biological Assemblies And Periodic Crystal Structures, Filip Jagodzinski, Pamela Clark, Jessica Grant, Tiffany Liu, Samantha Monastra, Ileana Streinu

Computer Science: Faculty Publications

Background: We initiate in silico rigidity-theoretical studies of biological assemblies and small crystals for protein structures. The goal is to determine if, and how, the interactions among neighboring cells and subchains affect the flexibility of a molecule in its crystallized state. We use experimental X-ray crystallography data from the Protein Data Bank (PDB). The analysis relies on an effcient graph-based algorithm. Computational experiments were performed using new protein rigidity analysis tools available in the new release of our KINARI-Web server http:// kinari.cs.umass.edu. Results: We provide two types of results: on biological assemblies and on crystals. We found that when only …

Towards Accurate Modeling Of Noncovalent Interactions For Protein Rigidity Analysis, Naomi Fox, Ileana Streinu

Computer Science: Faculty Publications

Background: Protein rigidity analysis is an efficient computational method for extracting flexibility information from static, X-ray crystallography protein data. Atoms and bonds are modeled as a mechanical structure and analyzed with a fast graph-based algorithm, producing a decomposition of the flexible molecule into interconnected rigid clusters. The result depends critically on noncovalent atomic interactions, primarily on how hydrogen bonds and hydrophobic interactions are computed and modeled. Ongoing research points to the stringent need for benchmarking rigidity analysis software systems, towards the goal of increasing their accuracy and validating their results, either against each other and against biologically relevant (functional) parameters. …

Design, Construction And Load Testing Of The Pat Daly Road Bridge In Washington County, Mo, With Internal Glass Fiber Reinforced Polymers Reinforcement, Zhibin Lin, Mostafa Fakharifar, Chenglin Wu, Genda Chen, Wesley James Bevans, Arun Vijay Kumar Gunasekaran, Sahra Sedigh

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

The overarching goal of this project is to deploy and assess an innovative corrosion-free bridge construction technology for long-term performance of new and existing bridges. The research objective of this project is to conduct a comprehensive study (instrumentation, construction, both laboratory and field evaluation) of a rapidly constructed and durable, three-span bridge with cast-in-place cladding steel reinforced concrete substructure and precast concrete decks/girders reinforced with glass fiber reinforced polymers (GFRP). The bridge has one conventional concrete-girder span, one conventional steel-girder span, and one innovative concrete box-girder span. The conventional concrete and steel girders were used to demonstrate the effective use …

Information Security Challenge Of Qr Codes, Nik Thompson, Kevin Lee

Journal of Digital Forensics, Security and Law

The discipline of information security must adapt to new technologies and methods of interaction with those technologies. New technologies present both challenges and opportunities for the security professional, especially for areas such as digital forensics. Challenges can be in the form of new devices such as smartphones or new methods of sharing information, such as social networks. One such rapidly emerging interaction technology is the use of Quick Response (QR) codes. These offer a physical mechanism for quick access to Web sites for advertising and social interaction. This paper argues that the common implementation of QR codes potentially presents security …

Measuring Inconsistency Methods For Evidentiary Value, Fred Cohen

Journal of Digital Forensics, Security and Law

Many inconsistency analysis methods may be used to detect altered records or statements. But for admission as evidence, the reliability of the method has to be determined and measured. For example, in China, for evidence to be admitted, it has to have 95% certainty of being correct,1 and that certainty must be shown to the court, while in the US, evidence is admitted if it is more probative than prejudicial (a >50% standard).2 In either case, it is necessary to provide a measurement of some sort in order to pass muster under challenges from the other side. And in most …

Technology Corner Visualising Forensic Data: Evidence (Part 1), Damian Schofield, Ken Fowle

Journal of Digital Forensics, Security and Law

Visualisation is becoming increasingly important for understanding information, such as investigative data (for example: computing, medical and crime scene evidence) and analysis (for example: network capability assessment, data file reconstruction and planning scenarios). Investigative data visualisation is used to reconstruct a scene or item and is used to assist the viewer (who may well be a member of the general public with little or no understanding of the subject matter) to understand what is being presented. Analysis visualisations, on the other hand, are usually developed to review data, information and assess competing scenario hypotheses for those who usually have an …

How Often Is Employee Anger An Insider Risk I? Detecting And Measuring Negative Sentiment Versus Insider Risk In Digital Communications, Eric Shaw, Maria Payri, Michael Cohn, Ilene R. Shaw

Journal of Digital Forensics, Security and Law

This research introduced two new scales for the identification and measurement of negative sentiment and insider risk in communications in order to examine the unexplored relationship between these two constructs. The inter-rater reliability and criterion validity of the Scale of Negativity in Texts (SNIT) and the Scale of Insider Risk in Digital Communications (SIRDC) were established with a random sample of email from the Enron archive and criterion measures from established insiders, disgruntled employees, suicidal, depressed, angry, anxious, and other sampled groups. In addition, the sensitivity of the scales to changes over time as the risk of digital attack increased …

Table Of Contents

Journal of Digital Forensics, Security and Law

No abstract provided.

Technology Corner: Visualising Forensic Data: Evidence Guidelines (Part 2), Damian Schofield, Ken Fowle

Journal of Digital Forensics, Security and Law

Visualisation is becoming increasingly important for understanding information, such as investigative data (for example: computing, medical and crime scene evidence) and analysis (for example, network capability assessment, data file reconstruction and planning scenarios). Investigative data visualisation is used to reconstruct a scene or item and is used to assist the viewer (who may well be a member of the general public with little or no understanding of the subject matter) to understand what is being presented. Analysis visualisations, on the other hand, are usually developed to review data, information and assess competing scenario hypotheses for those who usually have an …

How Often Is Employee Anger An Insider Risk Ii? Detecting And Measuring Negative Sentiment Versus Insider Risk In Digital Communications–Comparison Between Human Raters And Psycholinguistic Software, Eric Shaw, Maria Payri, Michael Cohn, Ilene R. Shaw

Journal of Digital Forensics, Security and Law

This research uses two recently introduced observer rating scales, (Shaw et al., 2013) for the identification and measurement of negative sentiment (the Scale for Negativity in Text or SNIT) and insider risk (Scale of Indicators of Risk in Digital Communication or SIRDC) in communications to test the performance of psycholinguistic software designed to detect indicators of these risk factors. The psycholinguistic software program, WarmTouch (WT), previously used for investigations, appeared to be an effective means for locating communications scored High or Medium in negative sentiment by the SNIT or High in insider risk by the SIRDC within a randomly selected …

Trends In Android Malware Detection, Kaveh Shaerpour, Ali Dehghantanha, Ramlan Mahmod

Journal of Digital Forensics, Security and Law

This paper analyzes different Android malware detection techniques from several research papers, some of these techniques are novel while others bring a new perspective to the research work done in the past. The techniques are of various kinds ranging from detection using host based frameworks and static analysis of executable to feature extraction and behavioral patterns. Each paper is reviewed extensively and the core features of each technique are highlighted and contrasted with the others. The challenges faced during the development of such techniques are also discussed along with the future prospects for Android malware detection. The findings of the …