Computer Engineering Commons^™

Forecasting Vegetation Health In The Mena Region By Predicting Vegetation Indicators With Machine Learning Models, Sachi Perera, Wenzhao Li, Erik Linstead, Hesham El-Askary

Mathematics, Physics, and Computer Science Faculty Articles and Research

Machine learning (ML) techniques can be applied to predict and monitor drought conditions due to climate change. Predicting future vegetation health indicators (such as EVI, NDVI, and LAI) is one approach to forecast drought events for hotspots (e.g. Middle East and North Africa (MENA) regions). Recently, ML models were implemented to predict EVI values using parameters such as land types, time series, historical vegetation indices, land surface temperature, soil moisture, evapotranspiration etc. In this work, we collected the MODIS atmospherically corrected surface spectral reflectance imagery with multiple vegetation related indices for modeling and evaluation of drought conditions in the MENA …

Supporting Coordination Of Children With Asd Using Neurological Music Therapy: A Pilot Randomized Control Trial Comparing An Elastic Touch-Display With Tambourines, Franceli L. Cibrian, Melisa Madrigal, Marina Avelais, Monica Tentori

Engineering Faculty Articles and Research

Aim

To evaluate the efficacy of Neurologic Music Therapy (NMT) using a traditional and a technological intervention (elastic touch-display) in improving the coordination of children with Autism Spectrum Disorder (ASD), as a primary outcome, and the timing and strength control of their movements as secondary outcomes.

Methods

Twenty-two children with ASD completed 8 NMT sessions, as a part of a 2-month intervention. Participants were randomly assigned to either use an elastic touch-display (experimental group) or tambourines (control group). We conducted pre- and post- assessment evaluations, including the Developmental Coordination Disorder Questionnaire (DCDQ) and motor assessments related to the control of …

Back To The Future With Higher Ed: A Sample Of Drupal Sites At Uga, Rachel S. Evans, Deborah Stanley, Delmaries I. Gray, Lauren Blais

Presentations

Consisting of a show and tell of a selection of large and small site installations from various departments, schools and colleges at the University of Georgia, panelists including back end and front end developers, public relations experts, librarians, and web coordinators will share their ship's timeline with Drupal versions and examples from the past, present and future. A moderator will then ask questions of panelists including: the biggest challenges they have faced with migrations and upgrades, the issues or blessings of more cohesive branding initiatives over the last few years, and their visions, concerns, and hopes for the future. In …

A Fortran-Keras Deep Learning Bridge For Scientific Computing, Jordan Ott, Mike Pritchard, Natalie Best, Erik Linstead, Milan Curcic, Pierre Baldi

Engineering Faculty Articles and Research

Implementing artificial neural networks is commonly achieved via high-level programming languages such as Python and easy-to-use deep learning libraries such as Keras. These software libraries come preloaded with a variety of network architectures, provide autodifferentiation, and support GPUs for fast and efficient computation. As a result, a deep learning practitioner will favor training a neural network model in Python, where these tools are readily available. However, many large-scale scientific computation projects are written in Fortran, making it difficult to integrate with modern deep learning methods. To alleviate this problem, we introduce a software library, the Fortran-Keras Bridge (FKB). This two-way …

Circus In Motion: A Multimodal Exergame Supporting Vestibular Therapy For Children With Autism, Oscar Peña, Franceli L. Cibrian, Monica Tentori

Engineering Faculty Articles and Research

Exergames are serious games that involve physical exertion and are thought of as a form of exercise by using novel input models. Exergames are promising in improving the vestibular differences of children with autism but often lack of adaptation mechanisms that adjust the difficulty level of the exergame. In this paper, we present the design and development of Circus in Motion, a multimodal exergame supporting children with autism with the practice of non-locomotor movements. We describe how the data from a 3D depth camera enables the tracking of non-locomotor movements allowing children to naturally interact with the exergame . A …

Exploring The Efficacy Of Transfer Learning In Mining Image‑Based Software Artifacts, Natalie Best, Jordan Ott, Erik J. Linstead

Engineering Faculty Articles and Research

Background

Transfer learning allows us to train deep architectures requiring a large number of learned parameters, even if the amount of available data is limited, by leveraging existing models previously trained for another task. In previous attempts to classify image-based software artifacts in the absence of big data, it was noted that standard off-the-shelf deep architectures such as VGG could not be utilized due to their large parameter space and therefore had to be replaced by customized architectures with fewer layers. This proves to be challenging to empirical software engineers who would like to make use of existing architectures without …

Emergency Department Systems Engineering: Modelling And Event Simulation, O Alharethi Salman Zayed

Student Works (2020-2029)

Emergency department systems are meant to ensure the timely delivery for essential healthcare services through complex systems. (ED) offers various services and have several components in its parts. Examined long previous research on system engineering and quality of healthcare resulting on these are influenced by operational management. Real time data are very helpful for decision making for any systems. Patient output feedback and satisfaction can be ensured with engineered management. EDs have become evident particularly in current scenario when the world is in the grip of the deadly COVID-19. All this implies that analysis is significant for improvement of services …

Artificial Intelligence And Game Theory Controlled Autonomous Uav Swarms, Janusz Kusyk, M. Umit Uyar, Kelvin Ma, Eltan Samoylov, Ricardo Valdez, Joseph Plishka, Sagor E. Hoque, Giorgio Bertoli, Jefrey Boksiner

Publications and Research

Autonomous unmanned aerial vehicles (UAVs) operating as a swarm can be deployed in austere environments, where cyber electromagnetic activities often require speedy and dynamic adjustments to swarm operations. Use of central controllers, UAV synchronization mechanisms or pre-planned set of actions to control a swarm in such deployments would hinder its ability to deliver expected services. We introduce artificial intelligence and game theory based flight control algorithms to be run by each autonomous UAV to determine its actions in near real-time, while relying only on local spatial, temporal and electromagnetic (EM) information. Each UAV using our flight control algorithms positions itself …

Two Techniques For Automated Logging Statement Evolution, Allan R. Spektor

Theses and Dissertations

This thesis presents and explores two techniques for automated logging statement evolution. The first technique reinvigorates logging statement levels to reduce information overload using degree of interest obtained via software repository mining. The second technique converts legacy method calls to deferred execution to achieve performance gains, eliminating unnecessary evaluation overhead.

Analysis Of Information Security Methods In Biosystems And Application Of Intelligent Tools In Information Security Systems, Sherzod Sayfullaev

Chemical Technology, Control and Management

In this paper, the methods of information protection in bio systems are studied. The paper considers the use of intelligent tools in information security systems and the use of adaptive information security systems. Several articles on the field of information protection in bio systems are analyzed. Disadvantages and advantages of neural network technologies in modern information security systems are described. The characteristics of bio systems and the specificity of DNA, the main features of the DNA code that provide information security and functional stability of bio systems data protection structure. Application of intelligent tools to create a comprehensive adaptive protection …

User Interface Design For Mobile Financial Services: Users Perspective, Belachew U. Regane

African Conference on Information Systems and Technology

Users belonging to different countries have different exposure and perception to trust the technology to adopt it. Users’ trust and adoption rates are challenging issues in mobile financial services. Thus, the purpose of the research is how to design a trustful user interface. Market research is conducted to collect data. Using the data, personas and use cases developed. The result of personas and use cases used to develop prototypes. Prototype A and B designed differently to give choice to users to investigate users' trust. Prototype A is designed to make it easy to use and clear workflow. Whereas prototype B …

A Comprehensive Study For Modern Models: Linking Requirements With Software Architectures, Sisay Yemata

African Conference on Information Systems and Technology

Several models recently have been addressed in software engineering for requirements transformation. However, such transformation models have encountered many problems due to the nature of requirements. In the classical transformation modeling, some requirements are discovered to be missing or erroneous at later stages, in addition to major assumptions that may affect the quality of the software. This has created a crucial need for new approaches to requirements transformation. In this paper, a comprehensive study is presented in the main modern models of linking requirements to software architectures. An extensive evaluation is conducted to investigate the capabilities of such modern models …

Efficient Data Mining Algorithm Network Intrusion Detection System For Masked Feature Intrusions, Kassahun Admkie, Kassahun Admkie Tekle

African Conference on Information Systems and Technology

Most researches have been conducted to develop models, algorithms and systems to detect intrusions. However, they are not plausible as intruders began to attack systems by masking their features. While researches continued to various techniques to overcome these challenges, little attention was given to use data mining techniques, for development of intrusion detection. Recently there has been much interest in applying data mining to computer network intrusion detection, specifically as intruders began to cheat by masking some detection features to attack systems. This work is an attempt to propose a model that works based on semi-supervised collective classification algorithm. For …

Born-Digital Preservation: The Art Of Archiving Photos With Script And Batch Processing, Rachel S. Evans, Leslie Grove, Sharon Bradley

Articles, Chapters and Online Publications

With our IT department preparing to upgrade the University of Georgia’s Alexander Campbell King Law Library (UGA Law Library) website from Drupal 7 to 8 this fall, a web developer, an archivist, and a librarian teamed up a year ago to make plans for preserving thousands of born-digital images. We wanted to harvest photographs housed only in web-based photo galleries on the law school website and import them into our repository’s collection. The problem? There were five types of online photo galleries, and our current repository did not include appropriate categories for all of the photographs. The solution? Expand our …

Machine Learning Applications In Power Systems, Xinan Wang

Electrical Engineering Theses and Dissertations

Machine learning (ML) applications have seen tremendous adoption in power system research and applications. For instance, supervised/unsupervised learning-based load forecasting and fault detection are classic ML topics that have been well studied. Recently, reinforcement learning-based voltage control, distribution analysis, etc., are also gaining popularity. Compared to conventional mathematical methods, ML methods have the following advantages: (i). better robustness against different system configurations due to its data-driven nature; (ii). better adaption to system uncertainties; (iii). less dependent on the modeling accuracy and validity of assumptions. However, due to the unique physics of the power grid, many problems cannot be directly solved …

A Survey On Exploring Key Performance Indicators, Amira Idrees

Future Computing and Informatics Journal

Key Performance Indicators (KPIs) allows gathering knowledge and exploring the best way to achieve organization goals. Many researchers have provided different ideas for determining KPI's either manually, and semi-automatic, or automatic which is applied in different fields. This work concentrates on providing a survey of different approaches for exploring and predicting key performance indicators (KPIs).

Creation Of Mobile Applications For The Shrines Of Al-Hakim Al-Termizi, Mavlyuda Xodjayeva, Turdali Jumayev, Alimjon Dadamuhamedov, Barno Saydakhmedova

The Light of Islam

We recognize that the sustainable development of tourism has great potential for the development of cultural and humanitarian ties around the world. We emphasize the importance of information technology in tourism, especially in the areas of advertising, marketing, differentiation and specialization of tourism products. In addition, we reaffirm our commitment to pilgrimage tourism for the individual growth of people and the strengthening of basic social norms and national values. The program uses modern programming languages such as Php, Java, C ++. Al-Hakim at-Termizi is one of the most famous places of worship in Uzbekistan, which is also known for its …

Conference Roundup: Smart Cataloging - Beginning The Move From Batch Processing To Automated Classification, Rachel S. Evans

Articles, Chapters and Online Publications

This article reviewed the Amigos Online Conference titled “Work Smarter, Not Harder: Innovating Technical Services Workflows” keynote session delivered by Dr. Terry Reese on February 13, 2020. Excerpt:

"As the developer of MarcEdit, a popular metadata suite used widely across the library community, Reese’s current work is focused on the ways in which libraries might leverage semantic web techniques in order to transform legacy library metadata into something new. So many sessions related to using new technologies in libraries or academia, although exciting, are not practical enough to put into everyday use by most librarians. Reese’s keynote, titled Smart Cataloging: …

Biometric Identification With Ecg Signals, Connor Lindstrom, Jonathan Wood, Jacob Torchia, Jonathan Lee

Electrical Engineering

This project introduces a new form of biometric identification with an ECG signal with the use of machine learning concepts. The ECG signal makes a good candidate for identification because of its unique characteristics that make it easy to distinguish individuals from one another. A patient who has previously had ECG scans stored in a database before, can be verified using this program. This project has the capability of identifying a person or verifying a person solely using their ECG signal. Utilizing this biometric identification, hospitals would be able to add to the reliability of their identification process. Additionally, companies …

Artificial Neural Network To Detect Alzheimer's In Mri Scans, James Alden Poirier, Michael Gary Tuttle

Electrical Engineering

Alzheimer’s Disease ranks (AD) as one of the most common diseases in America. Currently, detecting Alzheimer’s Disease relies upon reported symptoms, however changes in the brain can manifest years or decades before symptoms appear. In recent years, researchers have successfully utilized Artificial Neural Networks (ANN) for a variety of image classification tasks. Here, we train an ANN to detect Alzheimer’s Disease using magnetic resonance imaging (MRI) brain scans. Giving an MRI to both a neural network and a doctor will allow the doctor to be more confident in their answer, as well as double-check their answer with an objective report …

Reading Robot, Gillian Watts, Andrew Myers, Sabrinna Tan, Taylor Klein, Omeed Djassemi

General Engineering

Presently, there is an insufficient availability of human experts to assist students in reading competency and comprehension. Our team’s goal was to create an improved socially assistive robot for use by therapists, teachers, and parents to help children and adults develop reading skills while they do not have access to specialists. HAPI is a socially assistive robot that we created with the goal of helping students practice their reading comprehension skills. HAPI enables a student to improve their reading skills without an educator present, while enabling educators to review the student's performance remotely. Design constraints included: physical size, weight, duration …

Bootstrapping Massively Multiplayer Online Role Playing Games, Mitchell Miller

Master's Theses

Massively Multiplayer Online Role Playing Games (MMORPGs) are a prominent genre in today's video game industry with the most popular MMORPGs generating billions of dollars in revenue and attracting millions of players. As they have grown, they have become a major target for both technological research and sociological research. In such research, it is nearly impossible to reach the same player scale from any self-made technology or sociological experiments. This greatly limits the amount of control and topics that can be explored. In an effort to make up a lacking or non-existent player-base for custom-made MMORPG research scenarios A.I. agents, …

Analysis Of Human Affect And Bug Patterns To Improve Software Quality And Security, Md Rakibul Islam

LSU New Orleans Theses and Dissertations

The impact of software is ever increasing as more and more systems are being software operated. Despite the usefulness of software, many instances software failures have been causing tremendous losses in lives and dollars. Software failures take place because of bugs (i.e., faults) in the software systems. These bugs cause the program to malfunction or crash and expose security vulnerabilities exploitable by malicious hackers.

Studies confirm that software defects and vulnerabilities appear in source code largely due to the human mistakes and errors of the developers. Human performance is impacted by the underlying development process and human affects, such as …

Security Camera Using Raspberry Pi, Tejendra Khatri

Student Academic Conference

No abstract provided.

Predictive Analysis Of Ethanol Prices With Machine Learning, Benjamin Schilling

Student Academic Conference

Overview of a predictive analysis regression developed using machine learning alongside ETL process techniques.

Estimating The Tempo Of Audio Files, Parker Ostertag

Student Academic Conference

On the market today, there exists a multitude of software that allows for the detection and prediction of beats per minute (BPM) contained in audio files. There are both free and monetized versions of these programs, but there is one thing that they all have in common: they are inaccurate. This is simply because the science behind beat detection is unfinished, and may never be. In this project, I decided to use a method of audio peak detection to help me detect the tempo that may exist in any audio file. I started by researching existing programs and the science …

Ml-Medic: A Preliminary Study Of An Interactive Visual Analysis Tool Facilitating Clinical Applications Of Machine Learning For Precision Medicine, Laura Stevens, David Kao, Jennifer Hall, Carsten Görg, Kaitlyn Abdo, Erik Linstead

Engineering Faculty Articles and Research

Accessible interactive tools that integrate machine learning methods with clinical research and reduce the programming experience required are needed to move science forward. Here, we present Machine Learning for Medical Exploration and Data-Inspired Care (ML-MEDIC), a point-and-click, interactive tool with a visual interface for facilitating machine learning and statistical analyses in clinical research. We deployed ML-MEDIC in the American Heart Association (AHA) Precision Medicine Platform to provide secure internet access and facilitate collaboration. ML-MEDIC’s efficacy for facilitating the adoption of machine learning was evaluated through two case studies in collaboration with clinical domain experts. A domain expert review was also …

Less-Java, More Type Safety: Type Inference And Static Analysis In Less-Java, Charles D. Hines

Senior Honors Projects, 2020-current

Less-Java is an object-oriented programming language whose primary goal is to help new programmers learn programming. Some of the features of Less-Java that might make it better for beginners are static typing, implicit typing, low verbosity, and built-in support for unit testing. The primary focus of this project is on improving type inference (especially with regards to object-oriented programming) and adding static analysis in the Less-Java compiler.

Campuspartner: An Assistive Technology For Pedestrians With Mobility Impairments, Cynthia R. Zastudil

Senior Honors Projects, 2020-current

Route-planning applications such as Google Maps and Apple Maps are used by millions of people each month. However, these mapping applications are optimized for vehicle navigation, and although they provide pedestrian routing, the route customization options aren’t sufficient for pedestrian users, especially those with mobility impairments. CampusPartner is an assistive mobile application that was designed with the purpose of supporting people with mobility impairments in planning and previewing their walking routes. By viewing routes in advance, users can see an overview and detailed information about them as well as turn-by-turn instructions. CampusPartner integrates existing services, GraphHopper, OpenStreetMap, and Mapbox, to …

A Capacitive Sensing Gym Mat For Exercise Classification & Tracking, Adam Goertz

Computer Science and Computer Engineering Undergraduate Honors Theses

Effective monitoring of adherence to at-home exercise programs as prescribed by physiotherapy protocols is essential to promoting effective rehabilitation and therapeutic interventions. Currently physical therapists and other health professionals have no reliable means of tracking patients' progress in or adherence to a prescribed regimen. This project aims to develop a low-cost, privacy-conserving means of monitoring at-home exercise activity using a gym mat equipped with an array of capacitive sensors. The ability of the mat to classify different types of exercises was evaluated using several machine learning models trained on an existing dataset of physiotherapy exercises.