Computer Engineering Commons^™

Three-Dimensional Environmentally Sustainable Neuromorphic Computing System Based On Natural Organic Memristor, Mohammed Rafeeq Khan

Graduate Theses and Dissertations (2019 - present)

A three-dimensional neuromorphic (3D) computing architecture based on environmentally sustainable natural organic honey memristors is proposed in this thesis. A set of comprehensive and experimental results indicate that the proposed systems exhibit remarkable inference accuracy, consistently surpassing the 90% threshold, even with different challenges such as device variations and nonlinearity. This study also considers four different conductance drift situations, the effects of analog-to-digital converter (ADC) quantization, and multiple algorithms, such as VGG8 and DenseNet-40. The deliverable of this thesis will test the stability of the proposed systems and explore their potential applications and scalability in real-world situations.

Dynamic Key-Based Privacy-Preserving Authentication Scheme For Internet Of Drones, Zain Chaudhary

Honors Theses

The Internet of Drones (IoD) proliferation has catalyzed transformative changes across various industries, from agriculture to urban management. However, expanding drone networks also presents significant security challenges concerning secure communication and authentication. This paper introduces a robust privacy-preserving key-based authentication scheme tailored explicitly for the IoD, utilizing a matrix key generated by Hierarchical Message Authentication Codes (HMAC) and the SHA-256 algorithm to address these vulnerabilities. Our system enhances security by ensuring each drone in the network can authenticate securely and reliably with a central unit, preventing unauthorized access and securing communications against common threats like eavesdropping and impersonation attacks. Our …

Benchmarking Pretrained Models For Speech Emotion Recognition: A Focus On Xception, Ahmed Hassan, Tehroom Masood, Hassan A. Ahmed, H. M. Shahzad, Hafiz Muhammad T. Khushi

Business Faculty Publications

Speech emotion recognition (SER) is an emerging technology that utilizes speech sounds to identify a speaker’s emotional state. Computational intelligence is receiving increasing attention from academics, health, and social media applications. This research was conducted to identify emotional states in verbal communication. We applied a publicly available dataset called RAVDEES. The data augmentation process involved adding noise, applying time stretching, shifting, and pitch, and extracting the features zero cross rate (ZCR), chroma shift, Mel-Frequency Cepstral Coefficients (MFCC), and a spectrogram. In addition, we used many pretrained deep learning models, such as VGG16, ResNet50, Xception, InceptionV3, and DenseNet121. Out of all …

Identifying Redundant Audio Content Over Cloud Environment Using Deduplication Techniques, Venkatesh K

Theses and Dissertations

Cloud computing has become an integral part of modern internet-based services, with users relying heavily on cloud environments as primary storage solutions. However, the exponential growth in data volume presents a challenge (i.e) the proliferation of duplicated content within cloud repositories. Deduplication techniques provide a promising approach to mitigate this issue. This research focuses on detecting redundant audio content within a cloud environment, specifically targeting the sharing of extensive audio files, such as those in Waveform Audio File Format (WAV). The study proposes the Refined Super Subset Identification Algorithm (RSSIA) to efficiently identify redundant content and segments within existing audio …

Data Security In The Apple Ecosystem: An Evaluation, Kayrene Woods

Cybersecurity Undergraduate Research Showcase

This study provides a comprehensive evaluation of data security within the Apple ecosystem, focusing on the company’s privacy policies, user perceptions, and the effectiveness of its App Store review processes. Employing an interdisciplinary methodology, the research examines Apple’s commitment to data protection, emphasizing transparency and user trust. A survey of user experiences revealed varying levels of engagement and understanding of Apple’s privacy practices, with only 32.8% of respondents having read the Privacy Policy and mixed opinions on its clarity. Additionally, concerns persist about third-party app security, with 39.7% of users expressing apprehension and skepticism about Apple’s App Store review process. …

Designing Customized Loss Functions For Training Deep Neural Networks, Ali Pourramezan Fard

Electronic Theses and Dissertations

This dissertation explores the critical role of loss functions in enhancing the predictive performance of deep machine learning models. Loss functions are an integral element of all the ongoing advances we witness daily in this domain. I design custom loss functions and their impacts on various machine learning tasks, particularly in computer vision.

In the first stage of my research, I aim to improve the prediction performance of deep learning models by providing them with more precise feedback associated with task requirements. This led me to create the concept of assistive loss functions. My first proposed loss function, inspired by …

Investigating Spatiotemporal Trends Using Precursory Signatures: Implications To Develop Short-Term Earthquake Forecasting Techniques In Sumatra-Andaman Region, Ramya Jeyaraman J

Theses and Dissertations

Earthquake forecasting is a challenging field due to Earth's heterogeneous nature. This research aims to develop a short-term earthquake forecasting model by analyzing spatiotemporal trends and precursory signatures in the Sumatra-Andaman region, known for its high seismic activity and tsunami risk. The study adopts an interdisciplinary approach, integrating solid earth tides (SET), micro shocks, and outgoing longwave radiation (OLR) to gain deeper insights into seismic nucleation processes. The research begins by using Singular Spectral Analysis (SSA) to identify potential seismically vulnerable areas through the analysis of irregularities in SET.

A spatiotemporal analysis of micro shocks is conducted to assess the …

Training An Ai To Detect Injection Attacks Using A Hands On Approach, Aedan Tredinnick

Cybersecurity Undergraduate Research Showcase

This paper presents a practical approach to training an AI model to detect injection attacks, focusing on the creation of a manufactured dataset via structured hands-on methods. By establishing a vulnerable web server using XAMPP and DVWA (Damn Vulnerable Web Application), the research aims to simulate various injection attacks and capture relevant network traffic data. The paper discusses the methodology of data collection, AI model development, and performance evaluation.

Importance Of Soft Skills Comparative Study With Cybersecurity Professionals In The Manufacturing And Finance Critical Sectors, Stanley Mierzwa, Mary Lind

Center for Cybersecurity

Cybersecurity professionals require and will benefit from having strong and competent technical and soft skills, knowledge, and abilities. Cyber-attacks continue to plague our organizations and businesses, and finding the individuals with the skills needed for industry teams to contend with these broad and varying types of breaches is essential. This research article will outline the results of a comparative quantitative study that compares the importance of soft skills or nontechnical competencies by information security and cybersecurity professionals in the finance and manufacturing critical infrastructure sectors. This research study used a validated survey instrument from a previous seminal study to capture …

Nature Inspired Optimization For Spectrum Sensing And Allocation In Cognitive Radio Networks, Saravanan R

Theses and Dissertations

Cognitive radio (CR) refers to intelligent radio technology that scans its environment to optimize spectrum use and adjusts its parameters accordingly. It employs a communication system that is aware of its surroundings, including spectrum usage and availability. A key aspect of CR is identifying idle channels by analyzing traffic patterns using effective learning strategies.

However, CRNs face challenges such as cross-layer design issues, spectrum sensing errors, hidden node problems, and complex spectrum management. Spectrum sensing is critical for accessing unused radio spectrum while minimizing interference. Efficient sensing techniques must be cost-effective, fast, and capable of detecting weak primary signals. Although …

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. …

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 …

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 …

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, …

Machine Learning-Based Stress Detection Using Smartphones And Wearable Sensors, Robert Burns, Kassandra Martinez-Mejia

College of Engineering Summer Undergraduate Research Program

Stress and mental health have been considered increasing global concerns in modern society, including some of the illnesses responsible for a large proportion of comorbidities and deaths worldwide, such as depression and cardiovascular disease. Recently, smartphones, smartwatches, and smart wristbands have become an integral part of our lives and have reached widespread usage [1]. This raised the question of whether we can detect and prevent stress with smartphones and wearable sensors wirelessly. The challenge of such an approach is that the weak ECG signal is prone to errors, and the battery life of the smart devices is limited. In this …

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 …

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, …

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.

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, …

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.

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 …