Computer Sciences Commons^™

Glacier Segmentation In Satellite Images For Hindu Kush Himalaya Region, Bibek Aryal

Open Access Theses & Dissertations

Climate change poses a risk to individuals whose livelihoods depend on the health of glacier ecosystems. Monitoring glaciers in the Himalayan Hindu Kush (HKH) region is of high importance especially when we consider the impact of recent climate change on them. Our work aims to provide an automated method to outline glaciers using machine learning techniques and publicly available remote sensing imagery.In this work, we present ways to delineate glaciers from Landsat-7 imagery using various machine learning and computer vision techniques. The multi-step methodology that we present in this work is generalizable across different types of satellite and overhead imagery, …

Towards The Development Of A Cohesive Design-Driven Code Quality Metrics, Omar Masmali

Open Access Theses & Dissertations

Software complexity is an indicator of expected future maintenance and sustainability. Excessive complexity suggests that software or a component of software has a design or implementation that is difficult to understand, modify, and maintain. Several complexity measures have been developed by researchers to identify and characterize degrees of complexity. Code smells are widely adopted as indicators for low code quality. Many studies have adopted fixed threshold values for code smells and other quality metrics. These fixed threshold values often ignore the uniqueness of each software system and the unique roles each component play. Moreover, these thresholds are largely fixed throughout …

Coordinated Container Migration And Base Station Handover In Mobile Edge Computing, Mao V. Ngo, Tie Luo, Hieu T. Hoang, Q. S. Tony Quek

Computer Science Faculty Research & Creative Works

Offloading computationally intensive tasks from mobile users (MUs) to a virtualized environment such as containers on a nearby edge server, can significantly reduce processing time and hence end-to-end (E2E) delay. However, when users are mobile, such containers need to be migrated to other edge servers located closer to the MUs to keep the E2E delay low. Meanwhile, the mobility of MUs necessitates handover among base stations in order to keep the wireless connections between MUs and base stations uninterrupted. In this paper, we address the joint problem of container migration and base-station handover by proposing a coordinated migration-handover mechanism, with …

Could A Robot Be Your Psychotherapist?, Benjamin Huston

Graduate School of Professional Psychology: Doctoral Papers and Masters Projects

As technology has advanced over the years, it has been integrated into psychotherapy and changed the way that people receive mental health care (Schopp, Demiris, & Glueckauf, 2006). Many of these advances, such as telehealth practices, were seen as unsustainable until the public Internet offered broader access to technology-based care in the 1990s (Schopp, Demiris, & Glueckauf, 2006). These technology-based practices have since grown in popularity and with a recent increase in telehealth practices, text-based therapies, and applications to aid in mental health practices, modern therapy looks very different than it did even ten years ago (Fiske, Henningsen, & Buyx, …

Geoaware - A Simulation-Based Framework For Synthetic Trajectory Generation From Mobility Patterns, Jameson D. Morgan

Browse all Theses and Dissertations

Recent advances in location acquisition services have resulted in vast amounts of trajectory data; providing valuable insight into human mobility. The field of trajectory data mining has exploded as a result, with literature detailing algorithms for (pre)processing, map matching, pattern mining, and the like. Unfortunately, obtaining trajectory data for the design and evaluation of such algorithms is problematic due to privacy, ethical, dataset size, researcher access, and sampling frequency concerns. Synthetic trajectories provide a solution to such a problem as they are cheap to produce and are derived from a fully controllable generation procedure. Citing deficiencies in modern synthetic trajectory …

Extracting Information From Subroutines Using Static Analysis Semantics, Luke A. Burnett

Browse all Theses and Dissertations

Understanding how a system component can interact with other services can take an immeasurable amount of time. Reverse engineering embedded and large systems can rely on understanding how components interact with one another. This process is time consuming and can sometimes be generalized through certain behavior.We will be explaining two such complicated systems and highlighting similarities between them. We will show that through static analysis you can capture compiler behavior and apply it to the understanding of a function, reducing the total time required to understand a component of whichever system you are learning.

Predicting Subjective Sleep Quality Using Objective Measurements In Older Adults, Reza Sadeghi

Browse all Theses and Dissertations

Humans spend almost a third of their lives asleep. Sleep has a pivotal effect on job performance, memory, fatigue recovery, and both mental and physical health. Sleep quality (SQ) is a subjective experience and reported via patients’ self-reports. Predicting subjective SQ based on objective measurements can enhance diagnosis and treatment of SQ defects, especially in older adults who are subject to poor SQ. In this dissertation, we assessed enhancement of subjective SQ prediction using an easy-to-use E4 wearable device, machine learning techniques and identifying disease-specific risk factors of abnormal SQ in older adults. First, we designed a clinical decision support …

Identifying Knowledge Gaps Using A Graph-Based Knowledge Representation, Daniel P. Schmidt

Browse all Theses and Dissertations

Knowledge integration and knowledge bases are becoming more and more prevalent in the systems we use every day. When developing these knowledge bases, it is important to ensure the correctness of the information upon entry, as well as allow queries of all sorts; for this, understanding where the gaps in knowledge can arise is critical. This thesis proposes a descriptive taxonomy of knowledge gaps, along with a framework for automated detection and resolution of some of those gaps. Additionally, the effectiveness of this framework is evaluated in terms of successful responses to queries on a knowledge base constructed from a …

Android Game, Ryan Weston

Williams Honors College, Honors Research Projects

The purpose of this project was to create an endless runner game for Android coded in Java and XML and developed in Android Studio. In the game, the player controls a frog that jumps from lily pad to lily pad to avoid logs moving toward the player. The player must also maneuver the lily pads as they can randomly disappear. There are three difficulties in the game that vary the disappearance rate of lily pads as well as the frequency and acceleration rate of the log obstacles. The game also has a scoring system and saves the high score locally …

Catgame: A Tool For Problem Solving In Complex Dynamic Systems Using Game Theoretic Knowledge Distribution In Cultural Algorithms, And Its Application (Catneuro) To The Deep Learning Of Game Controller, Faisal Waris

Wayne State University Dissertations

Cultural Algorithms (CA) are knowledge-intensive, population-based stochastic optimization methods that are modeled after human cultures and are suited to solving problems in complex environments. The CA Belief Space stores knowledge harvested from prior generations and re-distributes it to future generations via a knowledge distribution (KD) mechanism. Each of the population individuals is then guided through the search space via the associated knowledge. Previously, CA implementations have used only competitive KD mechanisms that have performed well for problems embedded in static environments. Relatively recently, CA research has evolved to encompass dynamic problem environments. Given increasing environmental complexity, a natural question arises …

Exploring Virtual Worlds With Cultural Algorithms: Ancient Alpena-Amberley Land Bridge, Thomas Joseph Palazzolo

Wayne State University Dissertations

In this thesis the Land Bridge system (DEEPDIVE) is described. The goal of the project is to use Artificial Intelligence technology to aid Archaeologists in the discovery of ancient prehistoric sites, now underwater. The example used here is the Alpena-Amberley Land Bridge that stretched across Lake Huron from Alpena in Michigan to Amberley in Ontario. During the Ice Age (around 10,000 years ago) it was above water for several thousand years. It was postulated that during that time it was used as a migration pathway for caribou, a major food source then. AI techniques were used to create a virtual …

Improving Predictive Modeling Via Effective Feature Selection And Representation Learning, Xiangrui Li

Wayne State University Dissertations

Predictive modeling (a.k.a. supervised learning) is a machine learning paradigm that has enormous important applications for real-world problems. With the recent surge of data in volume and complexity, effectively capturing the information in input features that is relevant to targets is critical to the success of predictive modeling. Tackling this challenge requires different techniques depending on the specific applications. In this thesis, we develop several methods to improve the performance of predictive models.

Specifically, in the case of small $n$, large $p$ problem, we propose two sparsity-inducing regularization methods for multi-class logistic regression and finite mixture of linear regression, respectively. …

Tiling Optimization For Nested Loops On Gpus, Yuanzhe Li

Wayne State University Dissertations

Optimizing nested loops has been considered as an important topic and widely studied in parallel programming. With the development of GPU architectures, the performance of these computations can be significantly boosted with the massively parallel hardware.

General matrix-matrix multiplication is a typical example where executing such an algorithm on GPUs outperforms the performance obtained on other multicore CPUs. However, achieving ideal performance on GPUs usually requires a lot of human effort to manage

the massively parallel computation resources. Therefore, the efficient implementation of optimizing nested loops on GPUs became a popular topic in recent years. We present our work based …

Securing Arm Platform: From Software-Based To Hardware-Based Approaches, Zhenyu Ning

Wayne State University Dissertations

With the rapid proliferation of the ARM architecture on smart mobile phones and Internet of Things (IoT) devices, the security of ARM platform becomes an emerging problem. In recent years, the number of malware identified on ARM platforms, especially on Android, shows explosive growth. Evasion techniques are also used in these malware to escape from being detected by existing analysis systems.

In our research, we first present a software-based mechanism to increase the accuracy of existing static analysis tools by reassembleable bytecode extraction. Our solution collects bytecode and data at runtime, and then reassemble them offline to help static analysis …

Low-Power Wide-Area Network Design, Md Mahbubur Rahman

Wayne State University Dissertations

Low-Power Wide-Area Network (LPWAN) is an enabling technology for long-range, low-power, and low-cost Internet of Things (IoT) and Cyber-Physical Systems (CPS) applications. Due to their escalating demand in the IoT/CPS applications, recently, multiple LPWAN technologies have been developed that operate in the cellular/licensed (e.g., 5G, LTE Cat M1, and NB-IoT) and unlicensed/ISM (e.g., LoRa and SigFox) bands. To avoid the crowd in the limited ISM band (where most LPWANs operate) and the cost of the licensed band, we propose a novel LPWAN technology called Sensor Network Over White Spaces (SNOW) by utilizing the TV white spaces. White spaces refer to …

Real-Time Control Over Wireless Networks, Venkata Prashant Modekurthy

Wayne State University Dissertations

Industrial internet of Things (IIoT) are gaining popularity for use in large-scale applications such as oil-field management (e.g., 74×8km2 East Texas Oil-field), smart farming, smart manufac- turing, smart grid, and data center power management. These applications require the wireless stack to provide a scalable, reliable, low-power and low-latency communication. To realize a predictable and reliable communication in a highly unreliable wireless environment, industrial wireless standards use a centralized wireless stack design. In a centralized wireless stack design, a central manager generates routes and a communication schedule for a multi-channel time divi- sion multiple access communication (TDMA) based medium access control …

Towards Personalized Medicine: Computational Approaches For Drug Repurposing And Cell Type Identification, Azam Peyvandipour

Wayne State University Dissertations

The traditional drug discovery process is extremely slow and costly. More than 90% of drugs fail to pass beyond the early stage of development and toxicity tests, and many of the drugs that go through early phases of the clinical trials fail because of adverse reactions, side effects, or lack of efficiency. In spite of unprecedented investments in research and development (R&D), the number of new FDA-approved drugs remains low, reflecting the limitations of the current R&D model.

In this context, finding new disease indications for existing drugs sidesteps these issues and can therefore increase the available therapeutic choices at …

Automated Process Of Quantifying Scientific Images Using Fiji, Olivia Casimir

Summer Community of Scholars Posters (RCEU and HCR Combined Programs)

No abstract provided.

Creating And Deploying Automated Software Test Procedures With Regression Testing, Austen Seidler

Summer Community of Scholars Posters (RCEU and HCR Combined Programs)

No abstract provided.

Benchmarking Machine Learning Methods For Molecular Property Prediction, Govinda Bahadur Kc

Open Access Theses & Dissertations

Machine learning (ML) techniques have been widely applied in a variety of areas ranging from pattern recognition, natural language processing, and computer games to self-driving cars, clinical diagnostics, and molecular structure prediction easing day to day life of human beings. Drug discovery is an expensive, complex, and time taking process. Currently, the pharma industry is hoping to leverage machine learning methods in expediting the drug discovery process. Molecular property prediction is one of the most important tasks in drug discovery. While developing a new drug relies on a proper understanding of molecular properties, there has been great interest in the …

Brian Valdez - Dynamics And Control Of A 3-Dof Manipulator With Deep Learning Feedback, Brian Orlando Valdez

Open Access Theses & Dissertations

With the ever-increasing demands in the space domain and accessibility to low-cost small satellite platforms for educational and scientific projects, efforts are being made in various technology capacities including robotics and artificial intelligence in microgravity. The MIRO Center for Space Exploration and Technology Research (cSETR) prepares the development of their second nanosatellite to launch to space and it is with that opportunity that a 3-DOF robotic arm is in development to be one of the payloads in the nanosatellite. Analyses, hardware implementation, and testing demonstrate a potential positive outcome from including the payload in the nanosatellite and a deep learning …

Gaming Lan Setup With Local And Remote Access And Downloads, Ethelyn Tran

Williams Honors College, Honors Research Projects

The Gaming LAN Setup project aims to design and implement a basic functioning, hardened network that could be utilized locally and remotely to allow users access to respective servers for the option to host a session or join. Users will have the ability to securely log into the internal network to download files via a web interface. The network allows the designated user to take a management position in order to perform basic penetration testing and discover vulnerabilities through various scans to maintain the network

Budget Remote Access Vpn & Nas, Dylan J. Simmons

Williams Honors College, Honors Research Projects

In the modern business environment, many companies use a VPN service, in order to allow employees to work from home, while maintaining a secure connection to the network and blocking out any hackers. The main goal of this project is to create a VPN service into a secured network and allow the users to access their folders on the network drive. However, smaller businesses can't afford to spend a fortune on these necessities. For this reason, this project will utilize open source, or free software and firmware that any company would be able to run, no matter the budget. By …

Telecommunications Database, Tristan Hess

Williams Honors College, Honors Research Projects

The final goal of this project was to create a web application that is specifically tailored to make management of data for the Telecommunications department easier. The software that the department uses for phone service generates monthly reports that cannot be stored into their current database system. The Telecommunications Database project is a four-tier web application that was developed to store the monthly report information and alleviate the burden of manually searching through the reports for information. The web application implements basic database functionality for searching, inserting, updating, and deleting data contained in the monthly reports. Advanced searching functionality and …

Virtual Reality Environment Recreation, Ryan Douglas

Williams Honors College, Honors Research Projects

This project will consist of a virtual reality based program that is capable of showing the user both the modern day state of a site of historic or archaeological significance, along with a recreation of what said site or area may have looked like in the past, primarily during the time that gave the site its historical significance. The virtual reality program itself is to be run on modern day Windows hardware and used with the VIVE virtual reality head-mounted display and controllers. Alongside the completed program, the creation of the environments themselves will be documented, resulting in an organized …

Development And Field Testing Of A Mall For Filipino With A Reusable Framework For Mobile-Based Drills, Jenilyn Agapito, Dominique Marie Antoinette Manahan, Ma. Monica L. Moreno, Jose Isidro Beraquit, Ingrid Yvonne Herras, Kevin Arnel C. Mora, Johanna Marion R. Torres, Ma. Mercedes T. Rodrigo

Department of Information Systems & Computer Science Faculty Publications

This paper describes the development and field testing of Ibigkas! Filipino, a mobile game that exercises learners’ fluency in identifying synonyms (kasingkahulugan) and antonyms (kasalungat) in the Filipino language. Twenty-four students from Grades 4, 5, and 6 were invited to play and answer comprehension tests to determine whether the game helped them improve their understanding of the content. Self-report questionnaires assessed the extent to which they enjoyed it. Additionally, three teachers were invited to a focus group discussion (FGD) to gather their insights about the game and how they may use it in their classes. Self-report feedback from students showed …

Troika Generative Adversarial Network (T-Gan): A Synthetic Image Generator That Improves Neural Network Training For Handwriting Classification, Joe Anthony M. Milan, Proceso L. Fernandez Jr

Department of Information Systems & Computer Science Faculty Publications

Training an artificial neural network for handwriting classification requires a sufficiently sized annotated dataset in order to avoid overfitting. In the absence of sufficient instances, data augmentation techniques are normally considered. In this paper, we propose the troika generative adversarial network (T-GAN) for data augmentation to address the scarcity of publicly labeled handwriting datasets. T-GAN has three generator subnetworks architectured to have some weight-sharing in order to learn the joint distribution from three specific domains. We used T-GAN to augment the data from a subset of the IAM Handwriting Database. We then compared this with other data augmentation techniques by …

Predicting Stag And Hare Hunting Behaviors Using Hidden Markov Model, Rex Bringula, Ma. Mercedes T. Rodrigo

Department of Information Systems & Computer Science Faculty Publications

In this paper, we used Hidden Markov Model (HMM) to describe the gaming behaviors of students and whether they will exhibit “stag” or “hare” hunting behavior in a mobile game for mathematics learning. We found that there is a 99% probability that the students will stay either as stag or hare hunters. Our results also suggest that they would choose arithmetic problems involving addition. These game behaviors are not beneficial to learning because they are only exhibiting mathematical skills they already know. The results of the study show that stag and hare hunters have unique traits that separate the one …

Interactive Ecosystem For Surgical Training In A Realistic Mixed-Reality, Ehsan Azimi

Link Foundation Modeling, Simulation and Training Fellowship Reports

In many surgical procedures, surgeons rely on their general knowledge of anatomy and relatively crude measurements, which have inevitable uncertainties in locating internal anatomical targets. One example procedure that is frequently performed in neurosurgery is ventriculostomy (also called external ventricular drainage), where the surgeon inserts a catheter into the ventricle to drain cerebrospinal fluid (CSF). In this procedure, often performed bedside and therefore without image guidance, the surgeon makes measurements relative to cranial features to determine where to drill into the skull and then attempts to insert a catheter as perpendicular to the skull as possible. Although it is one …

Pseudo-Data Generation For Improving Clinical Named Entity Recognition, Jeffrey T. Smith

Theses and Dissertations

One of the primary challenges for clinical Named Entity Recognition (NER) is the availability of annotated training data. Technical and legal hurdles prevent the creation and release of corpora related to electronic health records (EHRs). In this work, we look at the imapct of pseudo-data generation on clinical NER using gazetteering and thresholding utilizing a neural network model. We report that gazetteers can result in the inclusion of proper terms with the exclusion of determiners and pronouns in preceding and middle positions. Gazetteers that had higher numbers of terms inclusive to the original dataset had a higher impact. We also …