Computer Engineering Commons^™

Double Dual Convolutional Neural Network (D2cnn): A Deep Learning Model Based On Feature Extraction For Skin Cancer Classification, Raya Sattar Shahadh, Belal Al-Khateeb

Iraqi Journal for Computer Science and Mathematics

Artificial intelligence, especially in the field of ``deep learning'', is still promising when it comes to skin cancer detection and diagnosis. Among deep learning algorithms, convolutional neural networks (CNNs) give a high level of accuracy in identifying and classifying different types of skin cancer. CNNs have a strong coordination due to understanding the important features from medical images that are extracted from convolutional layers. However, there is still a problem which is the high imbalance in the dataset with high noise in the images. This paper presents a new solution that combines different architectural structures of convolutional neural networks (CNNs) …

Federated Learning-Driven Iot And Edge Cloud Networks For Smart Wheelchair Systems In Assistive Robotics, Mazin Abed Mohammed, Mohd Khanapi Abd Ghani, Abdullah Lakhan, Bourair Al-Attar, Waleed Khaled

Iraqi Journal for Computer Science and Mathematics

These days, assistive robotics and their applications for people with disabilities have become a revolutionary field in medical care. It combines edge-cutting technologies such as the Internet of Things (IoT), edge computing networks, and federated learning, offering the best services to disabled people for mobility and navigation in the environment. However, in the state of the art, many conceptual models are presented, and less effort is put into the practical implementation of assistive robots for disabled people in the environment. With this motivation, we propose an intelligent assistive robotics wheelchair system that enhances disabled care in federated learning-enabled IoT and …

State Of The Grid: Cybersecurity Best Practices For The Utility Industry, Corban Garcia

SACAD: Scholarly Activities

Developing a strong cybersecurity posture is essential for protecting critical infrastructure, especially in the utility industry. This study analyzes a multi-layered cybersecurity approach that integrates risk management, technology, governance, and workforce training. Based on an examination of industry literature, six key steps were identified. These include assessing security posture, developing policies, implementing security controls, employee training, incident response planning, and regular audits. Each step plays a vital role in mitigating cyber threats and ensuring operational resilience. A comparative analysis of cybersecurity frameworks and real-world incidents highlights the necessity of proactive security strategies. Without these foundational steps, organizations face greater risks …

Layout-Aware Quantum Circuitry And Algorithmic Extensions To Grover's Algorithm, Ali Al-Bayaty

Dissertations and Theses

Lov K. Grover introduced, in 1996, Grover's algorithm as a quantum search algorithm to find all solutions for quantum oracles representing classical problems. My research observed that the Grover diffusion operator of Grover's algorithm gives wrong solutions when Boolean oracles are designed in some logical structures. Therefore, I invented the new "controlled-diffusion operator" for Boolean oracles as a new approach for Grover's algorithm that always correctly solves the problem of Grover's algorithm.

Another important problem in quantum computing is designing reliable and cost-effective quantum gates using reversible binary logic. In classical logic design, the stage of logic design can be …

The "Distributed Ghost" With Independence - A Study On Computational Ability Of Skewed Asynchronous Cellular Automata, Shrey Salvi, Shlok Shelat, Sumit Adak, Souvik Roy

Northeast Journal of Complex Systems (NEJCS)

This paper explores the computational ability of ``distributed ghost" cellular automata (CA) \cite{10.1162/artl_e_00450} after introducing independence in the updating scheme. Traditionally, the CA system dictates all cells to update together following the concept of the global clock. To introduce independence in the system, CA researchers have introduced the notion of fully asynchronous updating scheme with atomicity property where, again, the CA system dictates two neighbouring cells not to update together. In this study, we explore the skewed asynchronous system after breaking the atomicity property. Specifically, we study the computational ability of the proposed skewed asynchronous system in the context of …

Efficacy Of Immersive Virtual Reality Gameplay In Environmental Attitude Change: The Case Of Abandoned Offshore Oil Platforms In Santa Barbara, Arun Prasad Srinivasan Manoharan

Master's Theses

Public perception plays an important role in shaping conservation policies and decisions, especially in contested environmental spaces. Offshore oil platforms, historically viewed as environmental hazards, have been found to serve as marine habitats that support diverse marine life. However, public perception remains largely negative, influenced by concerns over pollution from past oil spill accidents. Traditional environmental education methods, such as lectures and documentaries, often fail to engage audiences effectively or shift entrenched opinions. This study explores the efficacy of immersive Virtual Reality (VR) gameplay in changing environmental attitudes, specifically in the context of abandoned offshore oil platforms in Santa Barbara, …

Choosing Robust Leadership: Encompassing The Best-Of-N Model And Swarm Intelligence Optimization For Heterogeneous Multiple Autonomous Unmanned Aerial Vehicle Systems, Kudamuhandiramlage Harith Kolitha Warnakulasooriya

Shelby Hall Graduate Research Forum Presentations

Presentation slides for a presentation given at the 1st annual Shelby Hall Graduate Research Forum at the University of South Alabama.

Image Forensics And Alteration Detection Using Image Preprocessing-Assisted Deep Learning Models, Rabindra Pokharel

Theses (2016-Present)

Technological advancements, combined with the widespread availability of digital images, have resulted in ubiquitous image forgery. The instances of forged images used for political propaganda, legal evidence manipulation, defamation of individuals, pornographic image creation of celebrities, and other actions that can cause social turmoil are proliferating. Verifying the integrity and authenticity of digital images is impractical for humans, necessitating the development of a robust image forgery detection model. This thesis demonstrates methods for copy-move, splicing, and deepfake image forgery detections by combining Error Level Analysis (ELA), Discrete Cosine Transformation (DCT), or Discrete Fourier Transformation (DFT) with a Deep Learning Convolutional …

Explainable Ai(Xai) In Genomic Medicine: Interpreting The Impact Of Genetic Variants On Breast Cancer Prognosis, Tooba Maryam Marith

Theses (2016-Present)

This study explores the integration of eXplainable Artificial Intelligence (XAI) techniques in genomic medicine to improve breast cancer prognosis and treatment decision-making. Using data from The Cancer Genome Atlas (TCGA), the research establishes a baseline through traditional machine learning (ML) models, including Random Forest (RF), Support Vector Classifier (SVC), Decision Tree, Naïve Bayes, K-Nearest Neighbors (KNN), and XGBoost. These models are evaluated for their predictive performance in assessing patient outcomes based on genetic variations. TCGA is a comprehensive public database that provides multidimensional genomic and clinical data for various cancer types, including breast cancer. It offers detailed molecular characterizations, such …

Are Emojis The New Words? A Sentiment Analysis Of Social Media Brand Conversations, Yashodhan Karulkar, Dev T. Vora, Siddharth Vaddepalli, Yash Thakur

Journal of International Technology and Information Management

Emojis have become an increasingly important aspect of consumer-brand interactions in the Indian subcontinent. However, the impact of emoji use on brand image and mental health remains underexplored, particularly in emerging economies like India, where structured research on this topic is limited. To address this gap, the present study analyzes over 4,600 consumer tweets related to 19 prominent brands across eleven industries. Using VADER sentiment analysis, the research develops a metric to assess consumer sentiment and brand engagement in relation to emoji usage. The findings indicate that effective integration of emojis contributes to positive consumer sentiment and enhanced brand engagement. …

Harmonicthreads – An Interface That Supports Accessibility In Musical Interaction, Ellie Nguyen, Miyuki Weldon, Franceli L. Cibrian

Engineering Faculty Articles and Research

Traditional musical instruments often can create boundaries due to their cost, training, mobility, and cognitive requirements, making musical expression inaccessible. To address this challenge, we developed HarmonicThreads, a novel pervasive computing interface consisting of a responsive, flexible fabric. HarmonicThreads provides a tactile and auditory experience, allowing users to easily create and control sounds. Using embedded sensors and real-time processing, HarmonicThreads interprets the user's natural movements and interactions to create adaptable musical outputs. This enables context-aware musical interaction, demonstrating the potential of pervasive interfaces in reducing barriers and making musical expression more accessible.

Jamming-Tolerant Low-Rate Wireless Personal Area Network For Detection Sensor Networks, Michael A. Eddy

Theses and Dissertations

This research evaluates the impact of electronic warfare, particularly jamming, on an audio-based drone detection wireless sensor network (WSN) using Monte Carlo simulations. A six-node IEEE 802.15.4 network, with five edge nodes and a central sink, is tested against jamming probabilities ranging from 0-100% in 5% increments across 30 iterations per configuration. Results show that packet delivery ratio (PDR) degrades linearly at approximately 20% per jammed node, while detection performance often exceeds PDR. Even at 80% jamming, detection success rates remain above 57%, highlighting resilience despite network degradation. The study reveals that jamming effectiveness depends on node placement relative to …

Palindrome: A Bi-Directional Multi-Object Detection Framework For Relative Navigation And Autonomous Docking, Liam A. Weinfurtner

Theses and Dissertations

This work introduces a bi-directional, multi-object detection framework that integrates pose estimates from both receiver- and tanker-mounted cameras to improve accuracy and redundancy. A modular YOLO-based detection pipeline is trained using synthetic and real imagery, leveraging a bootstrap transfer learning approach to enhance sim-to-real performance. System evaluation in both virtual and real-world environments demonstrates improved detection robustness, pose estimation accuracy, and scalability. These advancements contribute to the development of AI-driven vision systems for AAR and other autonomous docking applications.

Industry Applications Society And Conferences [President’S Message], Ayman El-Refaie

Electrical and Computer Engineering Faculty Research and Publications

No abstract provided.

Development And Validation Of An Artificial Intelligence System For Surgical Case Length Prediction, Adhitya Ramamurthi, Bhabishya Neupane, Priya Deshpande, Ryan Hanson, Kellie R. Brown, Kathleen K. Christians, Douglas B. Evans, Anai N. Kothari

Electrical and Computer Engineering Faculty Research and Publications

Background

Accurate case length estimation is a vital part of optimizing operating room use; however, significant inaccuracies exist with current solutions. The purpose of this study was to develop and validate an artificial intelligence system for improved surgical case length prediction by applying natural language processing and machine-learning methods.

Methods

All inpatient elective surgical cases longer than 30 minutes completed between 2017 and 2023 at a single, quaternary care hospital were considered. Data were split into training, test, and hold-out validation for model training and testing. Linear regression, CategoricalBoost, and feed-forward neural network each were trained and used embeddings created …

Modeling Of Analog-To-Digital Converter In Signal Processing, Ravshan Aliev, A.U. Djalilov

Chemical Technology, Control and Management

This article is devoted to the study of the modeling process of analog-to-digital converters (ADCs) that process signals, one of the main parts of control system elements and devices. As we know, ADCs are an important part of modern control systems. During the research, the main stages of analog signal conversion were analyzed, i.e. discretization, quantization, coding. A classification of analog-to-digital conversion methods was made and the advantages and disadvantages of each were identified. Also, the characteristics and parameters of ADC were studied, their impact on ADCs performance was evaluated, and it was determined that certain characteristics should be taken …

Methods For Detecting Anomalies In Network Traffic Based On One-Class Svm Technology, Komil Kerimov, Sardor Kurbanov, Zarina Azizova

Chemical Technology, Control and Management

This article is dedicated to the research and application of the One-Class Support Vector Machines method for detecting anomalies in network traffic. It examines the problems of detecting anomalies in network traffic and proposes a methodology for using One-Class SVM, including an overview of the main concepts and formulas of the algorithm. A discussion of the results of One-Class SVM is presented, including interpretation, advantages, limitations and possible directions for development of the proposed technique, as well as the practical significance of using the proposed method for detecting anomalies in network traffic.

Two-Key Dependent Permutation (Tkdp) And Its Applications In Information Security, Arulmani K

Theses and Dissertations

Two-Key Dependent Permutation (TKDP) algorithm for generating permutation sequences of fixed sizes, TKDP based Symmetric Block Cipher (TKDPSBC) and TKDP Audio encryption are being proposed in this thesis. TKDP algorithm is capable of generating different sequences for different key pairs. This makes it suitable for constructing dynamic S-boxes and P-boxes that have more degree of randomness and non-linearity to resist cryptanalytic attacks. Rigorous statistical tests validate the efficacy of the generated permutation sequences, affirming their suitability for cryptographic applications in conjunction with Fiestel network-based block ciphers. TKDPSBC encrypts a plaintext block into a ciphertext block of the same size. TKDP …

Increasing Guard Band Size To Decrease Interference In V2x Communication, Nakira Oglesby, Mackenzie Prescott, Billy Kihei, Ph.D.

Symposium of Student Scholars

As technologies evolve and new devices are introduced, the demand for fast and reliable vehicle-to-everything (V2X) communication increases. As this demand increases, the interference level in the 5.9GHz Dedicated Short Range Communications (DSRC) band will inevitably increase. And thus, the task of somehow minimizing this interference becomes increasingly important as time passes. This report investigates the effects of increasing the guard band size of the lower 5.9 GHz DSRC band on the adjacent channel interference from Unlicensed National Information Infrastructure 4 band (U-NII-4) devices and to try and see if there is a significant decrease in the interference level. The …

Lab: Developing Explainable Multimodal Ai Models With Hands-On Lab On The Life-Cycle Of Rare Event Prediction In Manufacturing, Chathurangi Shyalika, Ruwan Wickramarachchi, Revathy Venkataramanan, Dhaval Patel, Amit Sheth

Faculty Publications

In the age of Industry 4.0 and smart automation, unplanned downtime is costing industries over $50 billion annually. Even with preventive maintenance, industries like automotive lose more than $2 million per hour due to downtime caused by unexpected or "rare'' events. The extreme rarity of these events makes their detection and prediction a significant challenge for AI practitioners. Factors such as the lack of high-quality data, methodological gaps in the literature, and limited practical experience with multimodal data exacerbate the difficulty of rare event detection and prediction. This lab will provide hands-on experience to learn how to address these challenges …