Computer Sciences Commons^™

Rating By Ranking: An Improved Scale For Judgement-Based Labels, Jack O'Neill, Sarah Jane Delany, Brian Mac Namee

Conference papers

Labels representing value judgements are commonly elicited using an interval scale of absolute values. Data collected in such a manner is not always reliable. Psychologists have long recognized a number of biases to which many human raters are prone, and which result in disagreement among raters as to the true gold standard rating of any particular object. We hypothesize that the issues arising from rater bias may be mitigated by treating the data received as an ordered set of preferences rather than a collection of absolute values. We experiment on real-world and artificially generated data, finding that treating label ratings …

Enhancing Security Incident Response Follow-Up Efforts With Lightweight Agile Retrospectives, George Grispos, William Bradley Glisson, Tim Storer

Interdisciplinary Informatics Faculty Publications

Security incidents detected by organizations are escalating in both scale and complexity. As a result, security incident response has become a critical mechanism for organizations in an effort to minimize the damage from security incidents. The final phase within many security incident response approaches is the feedback/follow-up phase. It is within this phase that an organization is expected to use information collected during an investigation in order to learn from an incident, improve its security incident response process and positively impact the wider security environment. However, recent research and security incident reports argue that organizations find it difficult to learn …

Enrollment Decision-Making In U.S. Forestry And Related Natural Resource Degree Programs, Mark Rouleau, Terry Sharik, Samantha Whitens, Adam Wellstead

Michigan Tech Publications, Part 1

This article investigates enrollment decision-making trends among students currently enrolled in forestry and related natural resource (FRNR) degree programs in the United States. We conducted an online survey administered to all student participants attending the Society of American Foresters (SAF) National Convention in Salt Lake City, UT, in 2014 to obtain our enrollment decision-making data. Students were asked to rank the enrollment factors they considered most important to their decision to enroll, and factors that caused them to hesitate when enrolling in their degree program. We found that the “typical” FRNR enrollee was a person who enjoyed being outdoors and …

Systematic Adaptation Of Dynamically Generated Source Code Via Domain-Specific Examples, Myoungkyu Song, Eli Tilevich

Computer Science Faculty Publications

In modern web-based applications, an increasing amount of source code is generated dynamically at runtime. Web applications commonly execute dynamically generated code (DGC) emitted by third-party, black-box generators, run at remote sites. Web developers often need to adapt DGC before it can be executed: embedded HTML can be vulnerable to cross-site scripting attacks; an API may be incompatible with some browsers; and the program's state created by DGC may not be persisting. Lacking any systematic approaches for adapting DGC, web developers resort to ad-hoc techniques that are unsafe and error-prone. This study presents an approach for adapting DGC systematically that …

Automated Breast Cancer Diagnosis Using Deep Learning And Region Of Interest Detection (Bc-Droid), Richard Platania, Jian Zhang, Shayan Shams, Kisung Lee, Seungwon Yang, Seung Jong Park

Computer Science Faculty Research & Creative Works

Detection of suspicious regions in mammogram images and the subsequent diagnosis of these regions remains a challenging problem in the medical world. There still exists an alarming rate of misdiagnosis of breast cancer. This results in both over treatment through incorrect positive diagnosis of cancer and under treatment through overlooked cancerous masses. Convolutional neural networks have shown strong applicability to various image datasets, enabling detailed features to be learned from the data and, as a result, the ability to classify these images at extremely low error rates. In order to overcome the difficulty in diagnosing breast cancer from mammogram images, …

Home Away From Home, Mohammed Abdul Baseer, Theophilus O. Ilevbare, Shujath Mohammed, Hussain Mohammed

All Capstone Projects

Affordable rental housing plays an important role in meeting the housing needs of feasibility and short-term stay. This project is intended to assist individuals looking for affordable rental housing throughout their location, preferences and budget during their short term stay.

The purpose of this project is to develop an e-commerce site “Home away from Home” that provides easy-to-use search tool that lets a user to look for rental housing using a wide variety of criteria and special mapping features such as find colour photos and detailed information about each unit. It also provides link to resources and accommodating instruments, for …

Home Away From Home, Santosh Kumar Ampolu, Devi Prathyusha Manchella, Divya Swarup Nadella, Prashanth Goud Yarlagadda

All Capstone Projects

Home Away From Home is an e-Commerce application for short-term rentals of homes or apartments. This application presents a Web portal for property owners to advertise their properties and lease them to renters for short-term stays.

As the global sharing economy grows more owners of premium properties discover the benefit of sharing their furnished homes. Making use of your home as an asset, when travelling or working interstate or overseas for extended periods, makes perfect sense to savvy owners.

Maintaining your home and keeping it safe is very important to us and we make sure we leave nothing to chance. …

Home Away From Home, Nirupa Naidu Bandaru, Sruthilaya Gadiparthi, Pradeep Mandava, Shivanadhuni Prashanth

All Capstone Projects

Home away from home is the application of Electronic commerce. It would be a source for the people, who would like to take homes or apartments by electronic payments. This website would be the best place to give advertisement for their properties to renters for temporary stays.

This application would be the website, which give authority to users to log in/sign up pages for renter and owner along with the welcome screen for all three roles-Admin, Owner, Renter. Admin role would be consisting of Renter User Management, Owner User Management, and Locations management. Owner role would be creating listing which …

Home Away From Home, Swaroop Varun Kumar Lucas, Jaweed Ahmed Mohammed, Mudassir Ali Syed, Trividram Reddy Vanipenta

All Capstone Projects

This e-commerce web application, Home Away From Home, offers the information for short-term rentals of homes or apartments based on the place of interest. As its name suggests, the rental properties are as comfortable as one’s own home.

The main idea behind this application is to make rentals more interactive, user friendly and dynamic. At website’s frontend, users can search results by selecting either locations, place type or both. This site also provides preferred features of selected home/apartment, dynamically displays top places based on user ratings. This application maintains centralized database which is populated both administrator and home owners. Owners …

Home Away From Home, Vinay Kodela, Moinuddin Khan Mohammed, Rafi Mohammed, Anil Kumar Pilli

All Capstone Projects

The implementation of this application is important because people are facing problems to give rent to the tenants and even the tenants are also not able to find the houses which will suit to their needs. If we talk about the owners, they are unable to provide the information about their house like number of rooms, facilities available, in which area it is, what is the rent and all. They are not finding the right people to give the house for rent. Similarly, to find a house for their needs, tenants has to go all around in the area where …

Real-Time Indoor Tracking System With Bluetooth Signals Using Data Mining Techniques, Esfandiar Yari

Theses and Dissertations

Indoor localization or finding the exact position of an object or a person inside a building accurately is still a big challenge and not a single standard technique has been yet accepted tackling this issue. The satellite based Global Positioning System (GPS) technology cannot be used for indoor localization successfully since the signal attenuation caused by construction materials makes it lose significant power indoors, affecting the accuracy of the positioning. There has been a number ‘non-radio’ and ‘radio signal’ techniques developed to find the location of an object indoors with different levels of accuracies, but most of them are developed …

Home Away From Home, Shesha Sai Kumar Kurelli, Vamsi Krishna Lingamaneni, Abubakr Mohammed, Aravind Reddy Patlolla

All Capstone Projects

HomeAway is an online business application allowing renters to book their accommodations for rentals of homes or Apartments. This online application allows the owners to update their properties for advertisements and lease them to renters.

This website has user friendly functionalities providing services to the customers, owners, and administrators. Just a click away from your destination that quickly you get the best offers as we directly interact with the owners for the benefit of Customers. The service goal of HomeAway project being providing some luxury living, a sense of freedom, caring your loved ones and communities our website goes an …

Fatrec Workshop On Responsible Recommendation Proceedings, Michael Ekstrand, Amit Sharma

Computer Science Faculty Publications and Presentations

We sought with this workshop, to foster a discussion of various topics that fall under the general umbrella of responsible recommendation: ethical considerations in recommendation, bias and discrimination in recommender systems, transparency and accountability, social impact of recommenders, user privacy, and other related concerns. Our goal was to encourage the community to think about how we build and study recommender systems in a socially-responsible manner.

Recommendation systems are increasingly impacting people's decisions in different walks of life including commerce, employment, dating, health, education and governance. As the impact and scope of recommendations increase, developing systems that tackle issues of …

A Longitudinal Study Of Privacy Awareness In The Digital Age And The Influence Of Knowledge, Therese L. Williams

Theses and Dissertations

Privacy, in the modern connected world, has become a much discussed topic in society ranging from privacy concerns to impacts, attitudes, practices and technologies. In today’s environment of vast social media and revelations of government spying, personal privacy is being highlighted as either non-existent or something that can be achieved to different degrees with knowledge or awareness of how our private information is collected and used. This research strives to answer the question "Using Alan Westin's privacy categories, what is the general awareness of privacy issues in social media and smartphone usage and how does it change when knowledge is …

Improving Pure-Tone Audiometry Using Probabilistic Machine Learning Classification, Xinyu Song

McKelvey School of Engineering Graduate Student Theses & Dissertations

Hearing loss is a critical public health concern, affecting hundreds millions of people worldwide and dramatically impacting quality of life for affected individuals. While treatment techniques have evolved in recent years, methods for assessing hearing ability have remained relatively unchanged for decades. The standard clinical procedure is the modified Hughson-Westlake procedure, an adaptive pure-tone detection task that is typically performed manually by audiologists, costing millions of collective hours annually among healthcare professionals. In addition to the high burden of labor, the technique provides limited detail about an individual’s hearing ability, estimating only detection thresholds at a handful of pre-defined pure-tone …

Game Design & Development Curriculum: History & Future Directions, Elizabeth L. Lawley, Roger Altizer, Tracy Fullerton, Andrew Phelps, Constance Steinkuehler

Presentations and other scholarship

It has been nearly twenty years since the first undergraduate degree program in computer game development was established in 1998. Since that time, the number and size of programs in game design and development have grown at a rapid pace. While there were early efforts to establish curricular guidelines for the field, these face a number of challenges given the diverse range of academic homes for game-related programs. This panel will address the history of curricular development in the field, both in individual programs and across institutions. It will also explore the potential risks and rewards of developing curricular and/or …

Information Theoretic Study Of Gaussian Graphical Models And Their Applications, Ali Moharrer

LSU Doctoral Dissertations

In many problems we are dealing with characterizing a behavior of a complex stochastic system or its response to a set of particular inputs. Such problems span over several topics such as machine learning, complex networks, e.g., social or communication networks; biology, etc. Probabilistic graphical models (PGMs) are powerful tools that offer a compact modeling of complex systems. They are designed to capture the random behavior, i.e., the joint distribution of the system to the best possible accuracy. Our goal is to study certain algebraic and topological properties of a special class of graphical models, known as Gaussian graphs. First, …

Dual Modality Code Explanations For Novices: Unexpected Results, Briana B. Morrison

Computer Science Faculty Proceedings & Presentations

The research in both cognitive load theory and multimedia principles for learning indicates presenting information using both diagrams and accompanying audio explanations yields better learning performance than using diagrams with text explanations. While this is a common practice in introductory programming courses, often called "live coding," it has yet to be empirically tested. This paper reports on an experiment to determine if auditory explanations of code result in improved learning performance over written explanations. Students were shown videos explaining short code segments one of three ways: text only explanations, auditory only explanations, or both text and auditory explanations, thus replicating …

Card Tricks: A Workflow For Scalability And Dynamic Content Creation Using Paper2d And Unreal Engine 4, Owen Gottlieb, Dakota Herold, Edward Amidon

Presentations and other scholarship

In this paper, we describe the design and technological methods of

our dynamic sprite system in Lost & Found, a table-top-to-mobile

card game designed to improve literacy regarding prosocial

aspects of religious legal systems, specifically, collaboration and

cooperation. Harnessing the capabilities of Unreal Engine’s

Paper2D system, we created a dynamic content creation pipeline

that empowered our game designers so that they could rapidly

iterate on the game’s systems and balance externally from the

engine. Utilizing the Unreal Blueprint component system we were

also able to modularize each actor during runtime as data may be

changed. The technological approach behind Lost …

Implementing An Environmental Citizen Science Project: Strategies And Concerns From Educators’ Perspectives, Yurong He, Andrea Wiggins

Information Systems and Quantitative Analysis Faculty Publications

Citizen science seems to have a natural alignment with environmental and science education, but incorporating citizen science projects into education practices is still a challenge for educators from different education contexts. Based on participant observation and interview data, this paper describes the strategies educators identified for implementing an environmental citizen science project in different education contexts (i.e., classroom teaching, aquarium exhibits, and summer camp) and discusses the practical concerns influencing independent implementation by educators. The results revealed different implementation strategies that are shaped by four categories of constraints: 1) organizational and institutional policies, 2) educators’ time and material resources, 3) …

Towards A Privacy Rule Conceptual Model For Smart Toys, Laura Rafferty, Patrick C. K. Hung, Marcelo Fantinato, Sarajane Marques Peres, Farkhund Iqbal, Sy-Yen Kuo, Shih-Chia Huang

All Works

A smart toy is defined as a device consisting of a physical toy component that connects to one or more toy computing services to facilitate gameplay in the cloud through networking and sensory technologies to enhance the functionality of a traditional toy. A smart toy in this context can be effectively considered an Internet of Things (IoT) with Artificial Intelligence (AI) which can provide Augmented Reality (AR) experiences to users. In this paper, the first assumption is that children do not understand the concept of privacy and the children do not know how to protect themselves online, especially in a …

Machine Learning Based Protein Sequence To (Un)Structure Mapping And Interaction Prediction, Sumaiya Iqbal

LSU New Orleans Theses and Dissertations

Proteins are the fundamental macromolecules within a cell that carry out most of the biological functions. The computational study of protein structure and its functions, using machine learning and data analytics, is elemental in advancing the life-science research due to the fast-growing biological data and the extensive complexities involved in their analyses towards discovering meaningful insights. Mapping of protein’s primary sequence is not only limited to its structure, we extend that to its disordered component known as Intrinsically Disordered Proteins or Regions in proteins (IDPs/IDRs), and hence the involved dynamics, which help us explain complex interaction within a cell that …

Lightweight Environment For Cyber Security Education, Vivek Oliparambil Shanmughan

LSU New Orleans Theses and Dissertations

The use of physical systems and Virtual Machines has become inefficient and expensive for creating tailored, hands-on exercises for providing cyber security training. The main purpose of this project is to directly address these issues faced in cyber security education with the help of Docker containers. Using Docker, a lightweight and automated platform was developed for creating, sharing, and managing hands-on exercises. With the help of orchestration tools, this platform provides a centralized point to monitor and control the systems and exercises with a high degree of automation. In a classroom/lab environment, this infrastructure enables instructors and students not only …

Forensic Analysis Of G Suite Collaborative Protocols, Shane Mcculley

LSU New Orleans Theses and Dissertations

Widespread adoption of cloud services is fundamentally changing the way IT services are delivered and how data is stored. Current forensic tools and techniques have been slow to adapt to new challenges and demands of collecting and analyzing cloud artifacts. Traditional methods focusing only on client data collection are incomplete, as the client may have only a (partial) snapshot and misses cloud-native artifacts that may contain valuable historical information.

In this work, we demonstrate the importance of recovering and analyzing cloud-native artifacts using G Suite as a case study. We develop a tool that extracts and processes the history of …

Automatic Forensic Analysis Of Pccc Network Traffic Log, Saranyan Senthivel

LSU New Orleans Theses and Dissertations

Most SCADA devices have a few built-in self-defence mechanisms and tend to implicitly trust communications received over the network. Therefore, monitoring and forensic analysis of network traffic is a critical prerequisite for building an effective defense around SCADA units. In this thesis work, We provide a comprehensive forensic analysis of network traffic generated by the PCCC(Programmable Controller Communication Commands) protocol and present a prototype tool capable of extracting both updates to programmable logic and crucial configuration information. The results of our analysis shows that more than 30 files are transferred to/from the PLC when downloading/uplloading a ladder logic program using …

Hybrid Recommender Systems With Deep Learning, Fei Li

LSU Master's Theses

As one of the most popular recommendation algorithms, collaborative filtering (CF) suggests items favored by like-minded based on user ratings. However, CF performs worse for users and items with fewer ratings, which is known as the cold-start problem. On the other hand, the auxiliary information of items such as images and reviews can be helpful for relieving the cold-start issue and improving recommendation accuracy. How to effectively extract features from heterogeneous auxiliary information and integrate them with collaborative filtering remains a big challenge. In this thesis, we propose a tightly-coupled hybrid recommender system named Fusion-MF-Mix via a deep fusion framework, …

Ancr—An Adaptive Network Coding Routing Scheme For Wsns With Different-Success-Rate Links †, Xiang Ji, Anwen Wang, Chunyu Li, Chun Ma, Yao Peng, Dajin Wang, Qingyi Hua, Feng Chen, Dingyi Fang

Department of Computer Science Faculty Scholarship and Creative Works

As the underlying infrastructure of the Internet of Things (IoT), wireless sensor networks (WSNs) have been widely used in many applications. Network coding is a technique in WSNs to combine multiple channels of data in one transmission, wherever possible, to save node’s energy as well as increase the network throughput. So far most works on network coding are based on two assumptions to determine coding opportunities: (1) All the links in the network have the same transmission success rate; (2) Each link is bidirectional, and has the same transmission success rate on both ways. However, these assumptions may not be …

Detect Rumors In Microblog Posts Using Propagation Structure Via Kernel Learning, Jing Ma, Wei Gao, Kam-Fai Wong

Research Collection School Of Computing and Information Systems

How fake news goes viral via social media? How does its propagation pattern differ from real stories? In this paper, we attempt to address the problem of identifying rumors, i.e., fake information, out of microblog posts based on their propagation structure. We firstly model microblog posts diffusion with propagation trees, which provide valuable clues on how an original message is transmitted and developed over time. We then propose a kernel-based method called Propagation Tree Kernel, which captures high-order patterns differentiating different types of rumors by evaluating the similarities between their propagation tree structures. Experimental results on two real-world datasets demonstrate …

Comparison Of Visual Datasets For Machine Learning, Kent Gauen, Ryan Dailey, John Laiman, Yuxiang Zi, Nirmal Asokan, Yung-Hsiang Lu, George K. Thiruvathukal, Mei-Ling Shyu, Shu-Ching Chen

Computer Science: Faculty Publications and Other Works

One of the greatest technological improvements in recent years is the rapid progress using machine learning for processing visual data. Among all factors that contribute to this development, datasets with labels play crucial roles. Several datasets are widely reused for investigating and analyzing different solutions in machine learning. Many systems, such as autonomous vehicles, rely on components using machine learning for recognizing objects. This paper compares different visual datasets and frameworks for machine learning. The comparison is both qualitative and quantitative and investigates object detection labels with respect to size, location, and contextual information. This paper also presents a new …

Effect Of Label Noise On The Machine-Learned Classification Of Earthquake Damage, Jared Frank, Umaa Rebbapragada, James Bialas, Thomas Oommen, Timothy C. Havens

Michigan Tech Publications, Part 1

Automated classification of earthquake damage in remotely-sensed imagery using machine learning techniques depends on training data, or data examples that are labeled correctly by a human expert as containing damage or not. Mislabeled training data are a major source of classifier error due to the use of imprecise digital labeling tools and crowdsourced volunteers who are not adequately trained on or invested in the task. The spatial nature of remote sensing classification leads to the consistent mislabeling of classes that occur in close proximity to rubble, which is a major byproduct of earthquake damage in urban areas. In this study, …