Computer Engineering Commons^™

Impaired Speech Recognition Of Neurological Disorder Persons Using Machine Learning And Deep Learning Techniques, Vishnika Veni S

Theses and Dissertations

Speech Assistive Tools have emerged in recent years to support individuals with cognitive and neurological disorders in the field of assistive technology. People affected by neurological disorders such as autism, stroke, cerebral palsy, dysarthria, Parkinson’s disease, and brain injury often find it difficult to articulate desired sounds, resulting in impaired speech. As the population of impaired speakers continues to increase every year, there is a strong need to develop intelligent speech recognition systems for affected individuals. The primary objective of this research is to develop an Impaired Speech Recognition (ISR) system for the Tamil language. Word Recognition Accuracy (WRA) is …

Examining Consumers' Selective Information Privacy Disclosure Behaviors In An Organization's Secure E-Commerce Systems, Patrick I. Offor

Cybersecurity Graduate Research Symposium

No abstract provided.

Towards An Iot-Enabled Digital Earth For Sdgs: The Data Quality Challenge, Msb Syed, Paula Kelly, Paul Stacey, Damon Berry

Articles

Digital Earth (DE), a technology offering real-time visualisation of Earth's processes, has shown promising results in aiding decision-making for a sustainable world, raising awareness about individual impacts on our planet, and supporting the United Nations Sustainable Development Goals (UN SDGs) agenda. However, both DE and SDGs face a common obstacle: Data Quality (DQ). This review investigates the challenge of DQ in the context of DE for SDGs and explores how IoT can address this challenge and extend the reach of DE to support SDGs. Furthermore, the study discusses three core aspects; first, the potential of IoT as a data source …

Mouasla: Integrating Iot And Ai For An Intelligent Trans-Portation Payment System, Hany El-Ghaish Dr., Haitham Darweesh

Journal of Engineering Research

Smart payment systems have emerged as vital components of global public transportation, offering passengers a more efficient and convenient fare payment method. The Mouasla system addresses traditional payment limitations through IoT devices and AI-backed backend services. Features of Mouasla It employs RFID smart card and IoT features from the device to ensure all components such as a card reader function, driver functions, charging units function, and payment are combined with this system alongside a mobile application for quick access backend services. Each passenger dataset is analyzed by an AI-powered backend service to provide insight that can be used to improve …

A Parallel Methodology For Early Fake News Detection Based On Hybrid Features On Social Media, Asmaa Mohemed Elsaieed Dr

Journal of Engineering Research

The increased use of social media platforms has made it easier to publish and distribute news items, but it has also opened up new opportunities for distributing fake news. Fake news is information that has been written with the goal of misleading or deceiving readers. As a result, there is a need for efficient false news identification tools where the information can be gathered from the text of posts or from publicly available social data (such as user information or feedback on articles or the social network). The detection of fake news in its early stages is a major challenge. …

Digital Assessments For Children And Adolescents With Adhd: A Scoping Review, Franceli L. Cibrian, Elissa M. Monteiro, Kimberley D. Lakes

Engineering Faculty Articles and Research

Introduction: In spite of rapid advances in evidence-based treatments for attention deficit hyperactivity disorder (ADHD), community access to rigorous gold-standard diagnostic assessments has lagged far behind due to barriers such as the costs and limited availability of comprehensive diagnostic evaluations. Digital assessment of attention and behavior has the potential to lead to scalable approaches that could be used to screen large numbers of children and/or increase access to high-quality, scalable diagnostic evaluations, especially if designed using user-centered participatory and ability-based frameworks. Current research on assessment has begun to take a user-centered approach by actively involving participants to ensure the development …

M3t-Lm: A Multi-Modal Multi-Task Learning Model For Jointly Predicting Patient Length Of Stay And Mortality, Junde Chen, Qing Li, Feng Liu, Yuxin Wen

Engineering Faculty Articles and Research

Ensuring accurate predictions of inpatient length of stay (LoS) and mortality rates is essential for enhancing hospital service efficiency, particularly in light of the constraints posed by limited healthcare resources. Integrative analysis of heterogeneous clinic record data from different sources can hold great promise for improving the prognosis and diagnosis level of LoS and mortality. Currently, most existing studies solely focus on single data modality or tend to single-task learning, i.e., training LoS and mortality tasks separately. This limits the utilization of available multi-modal data and prevents the sharing of feature representations that could capture correlations between different tasks, ultimately …

2024 Gateway Magazine, College Of Computing, Michigan Technological University

College of Computing Annual Magazines

Table of Contents

• 50 Years of Computer Science at Michigan Tech
• Data Science for a Changing Planet
• Healthcare Transformed
• Mechatronics Matters
• Powered by Michigan Tech Talent
• Esports: Bringing Everything Great about Sports to More People
• The Michigander Scholars Program: Electrifying Careers in Michigan
• College of Computing News

Development Of Brain Tumor Detection And Feature Extraction Through Deep Learning Approach, Sivapathi A

Theses and Dissertations

As the body's central control system, the human brain is susceptible to a wide variety of disorders, including tumors characterized by abnormal cell growth. It is imperative to detect these tumors as early as possible to plan effective treatment and improve patient outcomes. By using contemporary medical imaging methods, this research seeks to improve the accuracy and efficiency of brain tumor detection through the careful preprocessing and analysis of images, particularly Magnetic Resonance Imaging (MRI) [1]. To provide context for the subsequent research efforts, the challenges inherent in brain tumor detection are discussed comprehensively, including segmentation accuracy, small lesion detection, …

Optimizing Resume Authenticity And Ats Compatibility With Llm Feedback Integration, Katie He, Justin Lau

College of Engineering Summer Undergraduate Research Program

Resume generation using Large Language Models (LLMs) like ChatGPT is becoming increasingly popular for automating the creation of customized resumes, but significant user modification is often required before submission. Common issues include poor alignment with job descriptions, inflated qualifications, and lack of authenticity, which undermine the effectiveness of LLM-generated resumes. This project addresses these challenges by integrating feedback from Applicant Tracking Systems (ATS) to guide LLMs in producing resumes that accurately reflect an applicant’s qualifications and better align with job-specific requirements. By optimizing the model's output through ATS feedback, the project aims to create more authentic, tailored, and ATS-compatible resumes, …

Enhancing Semantic Search With Human-Crafted Knowledge In Sentence Embeddings, Zachary Weinfeld

College of Engineering Summer Undergraduate Research Program

Semantic search plays a critical role in many domains, with numerous algorithms developed to address it. A common approach involves using sentence transformers to generate embeddings for both search queries and documents, allowing for the comparison of their vectors. While many different embedding models are widely used, our approach integrates these models with human-crafted knowledge in a novel way, resulting in an improvement in the Mean Average Precision (MAP) scores. Traditional embeddings often rely heavily on the specific words used in a query or document. Our technique mitigates this dependency by refining the vectors to capture the overall semantic meaning, …

Advanced Grasping Sensor Technologies For Autonomous Robotic Apple Harvesting Using Tactile Data And Cnns, Chris Bae

College of Engineering Summer Undergraduate Research Program

This research investigates how to achieve an optimal grasp of an apple using a four-finger soft robotic grasper equipped with force-resistive sensors. Specifically, we sought to determine whether a convolutional neural network (CNN) could accurately classify the grasper's state and recommend adjustments ("in," "out," or "good" grasp) based on tactile data from the sensors. Spatiotemporal tactile images were developed from the sensors and fed into our CNN, achieving near 100% accuracy on unseen test data. This work suggests that CNN-based processing of tactile images can be a powerful tool for real-time control of soft robotic grippers.

Ai Integration For Intellisar, Eric Lee

College of Engineering Summer Undergraduate Research Program

IntelliSAR aims to integrate AI techniques into Search and Rescue (SAR) operations, building on the foundation laid by previous SURP initiatives. IntelliSAR’s core elements include a front-end for SAR forms, a comprehensive command center dashboard, and AI-driven components designed to enhance SAR decision-making. During summer, our efforts focused on streamlining the user interface by integrating various machine learning models into a unified, interactive dashboard. Our models predict critical factors such as missing persons’ behavior, potential locations, and resource requirements, with the goal of optimizing response times and improving the effectiveness of SAR teams.

Deep-Learning Based Microstructure Reconstruction And Generation, Cameron J. Maloney, Lucas Taliaferro

College of Engineering Summer Undergraduate Research Program

Characterizing the microstructural behavior of materials is crucial for understanding their properties and performance. Traditional imaging methods, such as optical microscopy and electron microscopy, are effective but costly and time-consuming. Computational approaches can reduce costs and time while expanding the accessibility of microstructural analysis through the generation of new microstructure images. Traditional computational approaches, namely descriptor-based approaches, are slow but effective in low-data scenarios. Modern approaches use machine learning (ML), which is faster but often requires a lot of data to approach the performance of descriptor-based methods. This research leverages a special data-efficient Generative Adversarial Network (GAN) architecture to artificially …

Neuro-Symbolic Ai For Deep Analysis Of Social Media Big Data, Vedant Khandelwal, Manas Gaur, Ugur Kursuncu, Valerie Shalin, Amit P. Sheth

Faculty Publications

This tutorial introduces a neuro-symbolic AI framework to analyze big data from social media platforms. Integrating human-curated knowledge through symbolic AI with the pattern recognition capabilities of neural networks enhances the adaptability and efficiency of traditional neural network approaches. Knowledge-guided zero-shot learning techniques enable swift adaption to new linguistic contexts and emerging events [6]. Participants will explore how to design, develop, and utilize these models in specific domains, such as public health surveillance, that require dynamic adaptation to new terminologies. This session The tutorial aims to equip attendees with practical skills and a deep understanding of how to apply neuro-symbolic …

Evaluating Ai Language Models For Patient Queries On Total Knee Replacement (Tkr), Brianna Guillen, Anesu Karen Murambadoro, Victoria Elizondo, Matthew Hnatow, Michael Sander

Research Colloquium

Introduction: Within the past few years, large language models (LLMs) (ChatGPT, LLaMa 3, Microsoft Copilot) have increasingly become a resource that patients engage with to learn about health care procedures, including total knee replacement (TKR). Previous studies have analyzed the efficacy of large language models in providing accurate and relevant responses to questions about various procedures. Our study aims to evaluate the clarity, validity, and understandability of LLMs to patient questions about total knee replacement and assess the consistency of these models and their effectiveness in providing accurate, valid, and guideline-adherent information to patients.

Methods: We selected 30 frequently asked …

Anomalous Transaction Detection In Bank Credit Card Data Using Machine Learning, Lerdinia Varaidzo Mapepa, Jerremiah Musariwa, Lucia Makwasha, Samuel Mugijima

African Conference on Information Systems and Technology

Illegal money changers pose a number of risks to the financial system, including but not limited to money laundering, fraud, and other under-the-carpet dealings intended to frustrate regulatory efforts for financial integrity. The efficiency and accuracy of anti-money laundering (AML) measures using machine learning (ML) models in the detection of suspicious patterns in bank card transactions are investigated in this paper. The key focus will be to develop an efficient machine learning framework that should be proficient in underlining main transactions dealing with illegal money changers and other similar fraudulent activities. The features indicative of illicit behaviour are determined by …

Prompt Engineering Principles For Generative Ai Use In Extension, Paul A. Hill, Lendel K. Narine, Aubree L. Miller

Journal of Extension

The prevalence of Generative AI (GenAI) and Large Language Models (LLMs) is increasing rapidly. For Extension professionals, the utilization of prompt engineering is key to leveraging GenAI and LLMs effectively. Prompt engineering involves crafting prompts that elicit desired LLM responses. This article discusses prompt engineering principles, providing examples and guidance. The application of prompt engineering in Extension is explored, showcasing its potential to enhance programs, deliver personalized advice, engage audiences, and disseminate research-based information. By learning prompt engineering skills, Extension professionals can harness the power of GenAI and LLMs, enhancing their ability to address complex challenges in the 21st century.

Seal Counting On Our Plages (S.C.O.O.P.), Kaanan Kharwa

Master's Theses

The Vertebrate Integrative Physiology (VIP) lab monitors the population of northern elephant seals at the largest mainland breeding colony, located at Piedras Blancas (San Simeon, CA). As the population expands, more human-seal interactions and conflicts over land use occur. The VIP lab's work informs California State Parks and helps with the management of the rookery. Currently, members of the VIP lab fly a drone over the beaches, capture multiple images, and manually count the seals, which takes around 14 to 21 hours of analysis per survey. Machine learning methods such as Convolutional Neural Networks (CNN) and Region-based Convolutional Neural Networks …

Enhancing Security And Privacy For Smarter Environment Through A Robust Cyber-Physical System Framework, Ramya S

Theses and Dissertations

As digital computing paradigm and practices have emerged in disciplines, devices with processors and sensors were rudimentary, performing independent tasks with limited power. The first computer processors were slow, bulky and consuming high energy, as sensors in thermometers and pressure gauges provide original, independent measurements without effective communication, 1999. It often required powerful, energy-efficient processors and advanced sensors to enable seamless communication and sophisticated data processing.

These devices, since smart home systems to industrial automation tools, which continuously collect, analyse and share data via the internet, facilitating if real-time management, predictive maintenance, and improved seamless experience are used, transforming everyday …

Ai In Healthcare: Early Diagnosis Of Skin Cancer Using Medical Image Processing And Deep Neural Networks, Nirmala V

Theses and Dissertations

Several cancer types are commonly prevalent, and skin cancer is one among them, becoming even more widespread worldwide in the last few decades. To diagnose skin cancer at an early stage and obtain appropriate therapy to treat it, there is a demand to know more about the disease’s characteristics or severity. Skin cancer is caused mainly by various reasons, including damage of the sun or tanning beds by ultraviolet light exposure.

Failing to treat skin cancer might substantially impair an individual’s quality of life as the victim. They likely to experience physical issues linked with the deformities caused by psychological …

Motion Based Analysis Of Ultrasound Imaging For The Study Of Musculoskeletal Tissue Bio Mechanics, Ananth Hari R

Theses and Dissertations

Ultrasound image analysis plays an important role in diagnosing musculoskeletal injuries and monitoring rehabilitation exercises. The first and foremost step in this analysis involves segmentation of region of interest from the ultrasound images. The segmentation of the musculoskeletal tissues from the ultrasound images is challenging due to the inherent drawback present in ultrasound like : (1) Poor image quality due to image corruption by speckle noise, shadows, and attenuation. (2) Dis-continuous boundaries due to orientation dependence during the acquisition of image. (3) Low contrast between nearby anatomical structures. Hence in order to overcome these drawbacks, there is a need for …

Abnormal Event Detection Using Hypergraph Based Multiple Objects Tracking Techniques In Surveillance Videos, Palanivel S

Theses and Dissertations

Abnormal event detection aims to identify the events that deviate from expected normal patterns. This work primarily focuses on detection of rare events in public places. The existing research challenges in a video-based surveillance systems for the vehicle have been analysed and presence of abnormal objects in traffic-oriented videos have been detected. A novel approach for event summarization and rare event detection has been proposed in this work. The key ingredient in this work is the incorporation of Hypergraph (HG) matching.

Despite the reasonable amount of success achieved by a large number of researchers over the globe, distinguishing important videos …

Review Of Fuzzy Models And Fuzzy Methods For Analysis Of Information In Conditions Of Emotional Decision Making, Latafat Gardashova, Royal Shirinov, Diana Boqdanova

Chemical Technology, Control and Management

In the modern world, decision-making often takes place in an environment of uncertainty and under the significant influence of emotional factors, which requires the use of special methods for analyzing information. This study is devoted to an overview of fuzzy models and methods that allow such factors to be taken into account when making decisions. In particular, the approaches based on fuzzy logic, fuzzy cognitive maps and fuzzy clustering methods that provide flexibility and adaptability in conditions of uncertainty are considered. The study analyzes examples of the application of these methods in various fields, including risk management, medical diagnostics and …

Ga-Gesrgan: Document Images Super Resolution Using Gabor Filters, Esrgan Models And Genetic Algorithms, Zakia Kezzoula, Djamel Gaceb, Ayoub Titoun

Emirates Journal for Engineering Research

In the last decade, we have witnessed significant progress in image super-resolution, thanks in particular to the emergence and improvement of deep learning models, which can adapt to the complexity of tasks and improve image quality. This article presents a novel approach to image super-resolution GA-GESRGAN to enhance the quality of document images through a multi-step methodology. Initially, document images are processed using Gabor filters to extract features across various spatial frequencies. These extracted features are then utilized to train Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) models. Once improved images are obtained through ESRGAN models, a Genetic Algorithm combines these …

Analyzing The Usability, Performance, And Cost-Efficiency Of Deploying Ml Models On Various Cloud Computing Platforms, Hongyu Wang

Masters Theses (Archived)

With the enhanced computing capabilities and accessibility to cloud resources, major cloud computing providers such as Google Cloud Platform (GCP), Amazon Web Services (AWS), and Microsoft Azure offer Machine Learning (ML) and AI services. Their primary purpose is to provide efficiency, scalability, and adaptability in modern software development and IT operations while reducing overall costs and operational complexity. However, prospective customers of the services often question which ML-AI service will best suit their organizational and business needs. This study compares and analyzes the usability, performance, and cost-efficiency of deploying Machine Learning (ML) models across three cloud platforms: GCP, AWS, and …

Activity Map Generation And Event-Based Sensor Processing With Spiking Autoencoders And Sparse Dictionary Learning, Jack Easton

Computer Science and Engineering Theses and Dissertations

This thesis explores the potential of Spiking Neural Networks (SNNs) in processing event sensor data and generating high-fidelity activity maps. Event sensors capture asynchronous binary events with high dynamic range, but traditional processing methods often fail to leverage their advantages fully. SNNs, with their asynchronous, event-driven nature, offer a promising alternative.

A Spiking Autoencoder (SAE) was employed in this thesis to handle the stochastic and sparse event data, integrating deep dictionary learning to enhance the feature space and improve activity map quality. The encoder, modeled after the VGG network, extracts features from event streams generated by speckle patterns, which are …

Improving Expressive Capacity Of Deep Neural Networks, Clayton Harper

Computer Science and Engineering Theses and Dissertations

Deep learning has had remarkable success in a variety of fields. However, architectures often rely on hyperparameter searches and heuristics for improved model performance. Performing hyperparameter searches is an arduous task--often time-consuming and potentially expensive to run on accelerated hardware. As a result, practitioners often rely on heuristics which may lead to sub-optimal results. In the context of deep learning, hyperparameters are set by the user prior to the training process and remain fixed. Deep learning uses gradient descent to learn complex feature representations from data, limiting human intervention. While the weights of the architecture can learn directly through data …

Crowdstrike Cyber Incident Vs. Past Major Cyber Incidents: Analysis And Solutions, Priyant Banerjee

Himalayan Research Papers Archive

On July 19, 2024, a technical malfunction in CrowdStrike’s Falcon sensor software led to a global ITdisruption, affecting millions of devices across multiple sectors. This incident, although not a direct cyber-attack, caused significant operational upheavals reminiscent of major past cyber incidents. This paperexplores the CrowdStrike incident in detail, compares it with previous major cyber events, and proposescomprehensive solutions to mitigate such risks in the future.The faulty update from CrowdStrike resulted in widespread system crashes, notably the "Blue Screen ofDeath," paralyzing operations in critical sectors such as healthcare, finance, and transportation. The paperexamines the immediate and cascading effects of the incident, …

Real-Time Gun Detection In Video Streams Using Yolo V8, Harish Kumar Reddy Kunchala

Electronic Theses, Projects, and Dissertations

In this research, we advance the domain of public safety by developing a machine learning model that utilizes the YOLO v8 architecture for real-time detection of firearms in video streams. A diverse and extensive dataset, capturing a range of firearms in varying lighting and backgrounds, was meticulously assembled and preprocessed to enhance the model's adaptability to real-world scenarios. Leveraging the YOLO v8 framework, known for its real-time object detection accuracy, the model was fine-tuned to accurately identify firearms across different shapes and orientations.

The training phase capitalized on GPU computing and transfer learning to expedite the learning process while preserving …