Computer Engineering Commons^™

A Cloud Computing-Based Dashboard For The Visualization Of Motivational Interviewing Metrics, E Jinq Heng

Browse all Theses and Dissertations

Motivational Interviewing (MI) is an evidence-based brief interventional technique that has been demonstrated to be effective in triggering behavior change in patients. To facilitate behavior change, healthcare practitioners adopt a nonconfrontational, empathetic dialogic style, a core component of MI. Despite its advantages, MI has been severely underutilized mainly due to the cognitive overload on the part of the MI dialogue evaluator, who has to assess MI dialogue in real-time and calculate MI characteristic metrics (number of open-ended questions, close-ended questions, reflection, and scale-based sentences) for immediate post-session evaluation both in MI training and clinical settings. To automate dialogue assessment and …

Can We Make Our Robot Play Soccer? Influence Of Collaborating With Preservice Teachers And Fifth Graders On Undergraduate Engineering Students' Learning During A Robotic Design Process (Work In Progress), Krishnanand Kaipa, Jennifer Kidd, Julia Noginova, Francisco Cima, Stacie Ringleb, Orlando Ayala, Pilar Pazos, Kristie Gutierrez, Min Jung Lee

Mechanical & Aerospace Engineering Faculty Publications

This work-in-progress paper describes engineering students’ experiences in an NSF-funded project that partnered undergraduate engineering students with pre-service teachers to plan and deliver robotics lessons to fifth graders at a local school. This project aims to address an apparent gap between what is taught in academia and industry’s expectations of engineers to integrate perspectives from outside their field to solve modern societal problems requiring a multidisciplinary approach. Working in small teams over Zoom, participating engineering, education, and fifth grade students designed, built, and coded bio-inspired COVID companion robots. The goal for the engineering students was to build new interprofessional skills, …

Biomimetic Design, Modeling, And Adaptive Control Of Robotic Gripper For Optimal Grasping, Mushtaq Al-Mohammed

Electronic Theses and Dissertations, 2020-2023

Grasping is an essential skill for almost every assistive robot. Variations in shape and/or weight of different objects involved in Activities of Daily Living (ADL) lead to complications, especially, when the robot is trying to grip novel objects for which it has no prior information –too much force will deform or crush the object while too little force will lead to slipping and possibly dropped objects. Thus, successful grasping requires the gripper to immobilize an object with the minimal force. In Chapter 2, we present the design, analysis, and experimental implementation of an adaptive control to facilitate 1-click grasping of …

Energy And Area Efficient Machine Learning Architectures Using Spin-Based Neurons, Hossein Pourmeidani

Electronic Theses and Dissertations, 2020-2023

Recently, spintronic devices with low energy barrier nanomagnets such as spin orbit torque-Magnetic Tunnel Junctions (SOT-MTJs) and embedded magnetoresistive random access memory (MRAM) devices are being leveraged as a natural building block to provide probabilistic sigmoidal activation functions for RBMs. In this dissertation research, we use the Probabilistic Inference Network Simulator (PIN-Sim) to realize a circuit-level implementation of deep belief networks (DBNs) using memristive crossbars as weighted connections and embedded MRAM-based neurons as activation functions. Herein, a probabilistic interpolation recoder (PIR) circuit is developed for DBNs with probabilistic spin logic (p-bit)-based neurons to interpolate the probabilistic output of the neurons …

Modeling Document Classification To Automate Mental Health Diagnosis, William M. Tadlock

EWU Masters Thesis Collection

The objective of this study is to determine if diagnosis documents can be used with document classification to automatically diagnose mental health conditions. Document classification allows text documents to be analyzed and organized into their appropriate classes based on the features and words presented in the text. One application of this is within the medical field to automatically classify different patient diagnosis based on medical or patient notes. This research applied mental health diagnosis documents to automatically diagnose a group of patients with a mental health condition based on text-based survey data. This classification was approached through several feature engineering …

Using Long Short-Term Memory Networks To Make And Train Neural Network Based Pseudo Random Number Generator, Aditya Harshvardhan

Electronic Theses and Dissertations

Neural Networks have been used in many decision-making models and been employed in computer vision, and natural language processing. Several works have also used Neural Networks for developing Pseudo-Random Number Generators [2, 4, 5, 7, 8]. However, despite great performance in the National Institute of Standards and Technology (NIST) statistical test suite for randomness, they fail to discuss how the complexity of a neural network affects such statistical results. This work introduces: 1) a series of new Long Short- Term Memory Network (LSTM) based and Fully Connected Neural Network (FCNN – baseline [2] + variations) Pseudo Random Number Generators (PRNG) …

Towards Cloud-Based Cost-Effective Serverless Information System, Isaac C. Angle

EWU Masters Thesis Collection

E-commerce information systems are becoming increasingly popular for businesses to adopt. In this work, we propose a serverless information system that will reduce costs for small businesses trying to create an e-commerce website. The proposed serverless system is built entirely in Amazon Web Services (AWS). The proposed serverless system allows businesses to pay for the use of cloud resources on a per-order granularity. This model reduces the cost of the information system when compared to a traditional cloud-based system. As e-commerce websites become more vital for small businesses, a cost effective serverless approach is promising.

Formation Control With Bounded Controls And Collision Avoidance: Theory And Application To Quadrotor Unmanned Air Vehicles, Zachary S. Lippay

Theses and Dissertations--Mechanical and Aerospace Engineering

This dissertation presents new results on multi-agent formation control and applies the new control algorithms to quadrotor unmanned air vehicles. First, this dissertation presents a formation control algorithm for double-integrator agents, where the formation is time varying and the agents’ controls satisfy a priori bounds (e.g., the controls accommodate actuator saturation). The main analytic results provide sufficient conditions such that all agents converge to the desired time-varying relative positions with one another and the leader, and have a priori bounded controls (if applicable). We also present results from rotorcraft experiments that demonstrate the algorithm with time-varying formations and bounded controls. …

Detecting User Emotions From Audio Conversations With The Smart Assistants, Sunanda Guha

Graduate Theses/Dissertations

With the proliferation of smart home devices like Google Home or Amazon Alexa, significant research endeavors are being carried out to improve the user experience while interacting with these smart assistants. One such dimension in this endeavor is ongoing research on successful emotion detection from short voice commands used in smart home environment. Besides facial expression and body language, etc., speech plays a pivotal role in the classification of emotions when it comes to smart home application. Upon successful implementation of accurate emotion recognition, the smart devices will be able to intelligently and empathetically suggest appropriate actions based on the …

Deepfakes, Shallowfakes, And The Need For A Private Right Of Action, Eric Kocsis

Dickinson Law Review (2017-Present)

For nearly as long as there have been photographs and videos, people have been editing and manipulating them to make them appear to be something they are not. Usually edited or manipulated photographs are relatively easy to detect, but those days are numbered. Technology has no morality; as it advances, so do the ways it can be misused. The lack of morality is no clearer than with deepfake technology.

People create deepfakes by inputting data sets, most often pictures or videos into a computer. A series of neural networks attempt to mimic the original data set until they are nearly …

Book Review: This Is How They Tell Me The World Ends: The Cyberweapons Arms Race (2020) By Nicole Perlroth, Amy C. Gaudion

Dickinson Law Review (2017-Present)

No abstract provided.

Design And Control Of Quasi-Direct Drive Actuation For Lightweight And Versatile Wearable Robots, Shuangyue Yu

Dissertations and Theses

Wearable robots have shown great potential for augmenting the physical capabilities of humans in lab settings. However, wearable robots for augmenting the physical capabilities of humans under community-based conditions are the new frontier of robotics. Furthermore, the design and control are still considered to be grand challenges for providing physical augmentation for humans. In terms of design, the state-of-the-art exoskeletons are typically rigid, bulky, and limited to lab settings. In terms of control, most of the rhythmic controllers are not versatile and are focused only on steady-state walking assistance.

The motivation behind my research is to improve both the design …

Intelligent Voice Guidance In Vr: Understanding The Value Of Nlp In Virtual Environments, Zhiyu Xiao

Dartmouth College Master’s Theses

Virtual assistants such as Google Assistant, Alexa and Siri emerged because of the growth of NLP(natural language processing) technology. At the same time, virtual reality has developed rapidly in recent years and has become a crucial tool in engineering product development procedures. However, people feel overwhelmed in some complicated VR environments. Thus, this thesis tries to incorporate NLP technology into the VR environment and explores the value of intelligent voice guidance in VR environments. In this thesis, a car repair training system with intelligent voice guidance is designed: users can utilize voice to perform various tasks in this system, such …

C2 Microservices Api: Ch4rl3sch4l3m4gn3, Thai H. Nguyễn

School of Computer Science & Engineering Undergraduate Publications

In the 21^st century, cyber-based attackers such as advance persistent threats are leveraging bots in the form of botnets to conduct a plethora of cyber-attacks. While there are several social engineering techniques used to get targets to unknowingly download these bots, it is the command-and-control techniques advance persistent threats use to control their bots that is of critical interest to the author. In this research paper, the author aims to develop a command-and-control microservice application programming interface infrastructure to facilitate botnet command-and-control attack simulations. To achieve this the author will develop a simple bot skeletal framework, utilize the latest …

Improving Network Policy Enforcement Using Natural Language Processing And Programmable Networks, Pinyi Shi

Theses and Dissertations--Computer Science

Computer networks are becoming more complex and challenging to operate, manage, and protect. As a result, Network policies that define how network operators should manage the network are becoming more complex and nuanced. Unfortunately, network policies are often an undervalued part of network design, leaving network operators to guess at the intent of policies that are written and fill in the gaps where policies don’t exist. Organizations typically designate Policy Committees to write down the network policies in the policy documents using high-level natural languages. The policy documents describe both the acceptable and unacceptable uses of the network. Network operators …

Design, Development And Benchmarking Of Machine Learning Algorithms In Biomedical Applications, Qi Sun

Theses and Dissertations--Computer Science

Machine learning algorithms are becoming the most effective methods for knowledge discovery from high dimensional datasets. Machine learning seeks to construct predictive models through the analysis of large-scale heterogeneous data. While machine learning has been widely used in many domains including computer vision, natural language processing, product recommendation, its application in biomedical science for clinical diagnosis and treatment is only emerging. However, the wealthy amount of data in the biomedical domain offers not only challenges but also opportunities for machine learning. In this dissertation, we focus on three biomedical applications from vastly different domains to understand the opportunities and challenges …

Protocols And Architecture For Privacy-Preserving Authentication And Secure Message Dissemination In Vehicular Ad Hoc Networks, Shafika Showkat Moni

Theses and Dissertations--Computer Science

The rapid development in the automotive industry and wireless communication technologies have enhanced the popularity of Vehicular ad hoc networks (VANETs). Today, the automobile industry is developing sophisticated sensors that can provide a wide range of assistive features, including accident avoidance, automatic lane tracking, semi-autonomous driving, suggested lane changes, and more. VANETs can provide drivers a safer and more comfortable driving experience, as well as many other useful services by leveraging such technological advancements. Even though this networking technology enables smart and autonomous driving, it also introduces a plethora of attack vectors. However, the main issues to be sorted out …

An Automated Framework To Debug System-Level Concurrency Failures, Tarannum Shaila Zaman

Theses and Dissertations--Computer Science

The ever-increasing parallelism in computer systems has made software more prone to concurrency failures, causing problems during both pre- and post-development. Debugging concurrent programs is difficult because of the non-deterministic behavior and the specific sequences of interleaving in the execution flow. Debugging is a technique where programmers reproduce the bug, identify the root cause, and then take necessary steps to remove the bug from the system. The failure information may come from the bug reports of the testing phase or the production runs. In both cases, there should be steps taken to reproduce and localize the failure. However, reproducing and …

Deep Residual Policy Reinforcement Learning As A Corrective Term In Process Control For Alarm Reduction: A Preliminary Report, Ammar N. Abbas, Georgios C. Chasparis, John Kelleher

Articles

Conventional process controllers (such as proportional integral derivative controllers and model predictive controllers) are simple and effective once they have been calibrated for a given system. However, it is difficult and costly to re-tune these controllers if the system deviates from its normal conditions and starts to deteriorate. Recently, reinforcement learning has shown a significant improvement in learning process control policies through direct interaction with a system, without the need of a process model or the system characteristics, as it learns the optimal control by interacting with the environment directly. However, developing such a black-box system is a challenge when …

Ensemble Approach To The Semantic Segmentation Of Satellite Images, Brendan Kent

Dissertations

Automatic classification and segmentation of land use land cover(LULC) is extremely important for understanding the relationship between humans and nature. Human pressures on the environment have drastically accelerated in the last decades, risking biodiversity and ecosystem services. Remote sensing via satellite imagery is an excellent tool to study LULC. Research has shown that deep learning encoder-decoder architectures have achieved worthy results in the area of LULC, however the application of an ensemble approach has not been well quantified. Studies have shown it to be useful in the area of medical imaging. Ensembling by pooling together predictions to produce better predictions …

The Lognometer: A New Normalized And Computerized Device For Assessing The Neurodevelopment Of Fine Motor Control In Children, Christian O'Reilly, Rejean Plamondon, Nadir Faci

Publications

Motor skills are fundamental for the development of children. Neurodevelopmental tests currently used by professionals for measuring motor control maturity exhibit several limitations. To address some of these, we have designed the Lognometer, a tablet-based device that can run computerized neuromotor tests. To normalize this tool against a representative population, we collected handwritten triangles from 780 children. We used the Sigma-Lognormal model and a prototype-based parameter estimation algorithm to analyze these movements. To ensure clinical acceptance, we developed an explainable solution relying on statistical regression. We evaluated how well the proposed lognormal decomposition captures the motor control maturation between 6 …

Ksat: Knowledge-Infused Self Attention Transformer - Integrating Multiple Domain-Specific Contexts, Kaushik Roy, Yuxin Zi, Vignesh Narayanan, Manas Gaur, Amit P. Sheth

Publications

Domain-specific language understanding requires integrating multiple pieces of relevant contextual information. For example, we see both suicide and depression related behavior (multiple contexts) in the text “I have a gun and feel pretty bad about my life, and it wouldn’t be the worst thing if I didn’t wake up tomorrow”. Domain specificity in self-attention architectures is handled by fine-tuning on excerpts from relevant domain specific resources (datasets and external knowledge - medical textbook chapters on mental health diagnosis related to suicide and depression). We propose a modified self-attention architecture Knowledge infused Self Attention Transformer (KSAT) that achieves the integration of …

An Analysis On Network Flow-Based Iot Botnet Detection Using Weka, Cian Porteous

Dissertations

Botnets pose a significant and growing risk to modern networks. Detection of botnets remains an important area of open research in order to prevent the proliferation of botnets and to mitigate the damage that can be caused by botnets that have already been established. Botnet detection can be broadly categorised into two main categories: signature-based detection and anomaly-based detection. This paper sets out to measure the accuracy, false-positive rate, and false-negative rate of four algorithms that are available in Weka for anomaly-based detection of a dataset of HTTP and IRC botnet data. The algorithms that were selected to detect botnets …

Dark Patterns: Effect On Overall User Experience And Site Revisitation, Deon Soul Calawen

Dissertations

Dark patterns are user interfaces purposefully designed to manipulate users into doing something they might not otherwise do for the benefit of an online service. This study investigates the impact of dark patterns on overall user experience and site revisitation in the context of airline websites. In order to assess potential dark pattern effects, two versions of the same airline website were compared: a dark version containing dark pattern elements and a bright version free of manipulative interfaces. User experience for both websites were assessed quantitatively through a survey containing a User Experience Questionnaire (UEQ) and a System Usability Scale …

Evaluating The Performance Of Vision Transformer Architecture For Deepfake Image Classification, Devesan Govindasamy

Dissertations

Deepfake classification has seen some impressive results lately, with the experimentation of various deep learning methodologies, researchers were able to design some state-of-the art techniques. This study attempts to use an existing technology “Transformers” in the field of Natural Language Processing (NLP) which has been a de-facto standard in text processing for the purposes of Computer Vision. Transformers use a mechanism called “self-attention”, which is different from CNN and LSTM. This study uses a novel technique that considers images as 16x16 words (Dosovitskiy et al., 2021) to train a deep neural network with “self-attention” blocks to detect deepfakes. It creates …

An Investigation Of The Relationship Between Subjective Mental Workload And Objective Indicators Of User Activity, Greg Byrne

Dissertations

Whilst the concept of physical workload is intuitively understood and readily applicable in system design, the same cannot be said of mental workload (MWL), despite its importance in our increasingly technological society. Despite its origin in the mid 20th century, the very concept of ”mental workload” is still a topic of debate in the literature, although it can be loosely defined as “the amount of mental work necessary for a person to complete a task” (Miller, 1956; Longo, 2014). Several methods have been utilized to measure of MWL, including physiological methods such as neuro-imagery, performance-based metrics, and subjective measures via …

Direct And Constructivist Approaches For The Design Of Instruction In Well-Structured Domains: A Comparison Of Efficiency Via Mental Workload And Performance., Giuliano Orru

Dissertations

This doctoral research investigates the efficiency of two instructional designs: a design based on the direct-instruction approach to learning and its extension with a collaborative activity based upon the community of inquiry approach to learning. This is motivated by the educational challenge associated with the improvement of the learning phase. The goal is to investigate the extent to which highly guided communities of inquiry, when added to direct-instruction teaching methods, can actually improve the efficiency of learners. A total of 577 students participated in the experiments across 24 third-level classes that were divided into two groups. A control group of …

Kg-Cnn: Augmenting Convolutional Neural Networks With Knowledge Graphs For Multi-Class Image Classification, Aidan O'Neill

Dissertations

Computer vision is slowly becoming more and more prevalent in daily life. Tesla has recently announced that it plans to scale up the manufacturing of their Robotaxis by 2024, with this increase in self-driving vehicles being just one example, the importance of computer vision is growing year by year. Vision can be easy to take for granted, as most humans grow up using vision as their primary way of absorbing environmental information. The way humans process and classify visual information differs significantly from how current computer vision systems process and organise visual information. The human brain can use its past …

The Impact Of Emotion Focused Features On Svm And Mlr Models For Depression Detection, Alexandria Mulligan

Dissertations

Major depressive disorder (MDD) is a common mental health diagnosis with estimates upwards of 25% of the United States population remain undiagnosed. Psychomotor symptoms of MDD impacts speed of control of the vocal tract, glottal source features and the rhythm of speech. Speech enables people to perceive the emotion of the speaker and MDD decreases the mood magnitudes expressed by an individual. This study asks the questions: “if high level features deigned to combine acoustic features related to emotion detection are added to glottal source features and mean response time in support vector machines and multivariate logistic regression models, would …

Evaluating The Performance Impact Of Fine-Tuning Optimization Strategies On Pre-Trained Distilbert Models Towards Hate Speech Detection In Social Media, Aidan Mcgovern

Dissertations

Hate speech can be defined as forms of expression that incite hatred or encourage violence towards a person or group based on race, religion, gender, or sexual orientation. Hate speech has gravitated towards social media as its primary platform, and its propagation represents profound risks to both the mental well-being and physical safety of targeted groups. Countermeasures to moderate hate speech face challenges due to the volumes of data generated in social media, leading companies, and the research community to evaluate methods to automate its detection. The emergence of BERT and other pre-trained transformer-based models for transfer learning in the …