Computational Engineering Commons^™

Ensemble Learning Framework For Predicting Close Proximity Tire–Pavement Noise On Expressways, Woo Young Cho, Jin Hwan Kim, Guk Gon Song, Kyungnam Kim, Youngguk Seo

Faculty Articles

Traffic noise is a critical public health concern affecting millions of highway users and adjacent residents worldwide. In response, many transportation agencies have adopted functional surface materials to reduce noise at the source on pavement, but assessing their effectiveness remains expensive and logistically challenging. Close Proximity (CPX) testing quantifies tire-pavement noise but requires specialized equipment costing $50,000-$126,000 and is limited to existing pavement, preventing proactive noise assessment during pavement design. This study develops machine learning models to predict CPX noise levels from readily available pavement characteristics, eliminating the need for costly tests during design and planning phases. To train and …

Id-More Vision: Real-Data Machine-Learning Assessment For A Digital-Twin-Inspired, Xr-Ready Rehabilitation Prototype, Rickey L. Clark

Master's Theses

Rehabilitation assessment often relies on periodic observation, while many XR prototypes show scripted rather than recorded-motion evidence. iD-MORE Vision is an offline pipeline trained on KIMORE and IRDS and linked through JSON packets to a two-mode Unity desktop prototype. Both datasets include controls and rehabilitation participants with neurologic, musculoskeletal, or mobility impairments. This improves relevance but does not clinically validate the system.

Under fixed subject-wise splits, the primary five-seed Random Forest predicted KIMORE clinician scores with MAE 6.087 ± 0.044 cTS and R² 0.568 ± 0.006; the subject-level R² interval crossed zero. The primary IRDS five-run CUDA GRU averaged 0.877 …

Contemporary Cybersecurity Challenges In Emerging Technologies: A Systematic Literature Analysis, Faztudo Languisse Prof

Journal of Cybersecurity Education, Research and Practice

The accelerating convergence of artificial intelligence (AI), the Internet of Things (IoT), cloud computing, blockchain, and quantum computing has fundamentally transformed the global threat landscape, introducing cybersecurity challenges of unprecedented complexity and scale. This systematic literature review synthesizes findings from peer-reviewed publications, institutional reports, and regulatory documents published primarily between 2020 and 2025 to provide an integrated analysis of contemporary cybersecurity challenges across five key emerging technology domains. The review identifies critical vulnerabilities inherent to each domain, documents the evolution of threat actors and attack methodologies — including AI-powered ransomware, adversarial machine learning, and harvest-now-decrypt-later quantum attacks — and evaluates …

Prism (Proxy Recognition And Inclusion Scoring Method), Destiny Raburnel, Crystal Tubbs, Md Abdullah Al Hafiz Khan

Symposium of Student Scholars

AI-driven automated hiring tools are reshaping how companies find talent, but they often reproduce the hidden biases embedded in their training data. Our project, PRISM (Proxy Recognition and Inclusion Scoring Method), investigates how subtle demographic signals, specifically first names associated with gender and race, influence AI resume screening even when candidates have identical qualifications. We built a controlled dataset of resumes that are identical in every way except for the applicant's first name, with each resume using a racially neutral surname to isolate how first names alone affect scoring. We tested these resumes against job postings in technology, healthcare, and …

A Random Forest Classifier Model For Predicting The Impact Of Viral Infections On Adults With Chronic Conditions, Fungai Jacqueline Kiwa, Martin Muduva

African Conference on Information Systems and Technology

This study investigates the impact of viral infections on adults with chronic illnesses, focusing on the development of a Random Forest classifier model. The research aims to predict outcomes among individuals with conditions like diabetes, cancer, and tuberculosis, analyzing severity, age groups, and travel patterns. The study aims to assist healthcare professionals in resource allocation and patient prioritization based on disease severity. It reviews literature on viral infection risks for chronic illness patients and explores machine learning applications in infectious disease management. Methodologically, the study adopts a structured approach similar to the Cross-Industry Standard Process for Data Mining (CRISP -DM) …

Ai Bioelectricity Management System, Fungai Jacqueline Kiwa, Tawanda Bundukutu, Thoko Matnell Mawoyo, Batsiranai Linda Chiduku, Martin Muduva, Belinda Ndlovu

African Conference on Information Systems and Technology

This document emphasizes on the generation of electricity from trees and its usability in all the sectors of Zimbabwe. The research focused on positively changing the lives of citizens through the provision of uninterrupted and reliable bioelectricity. The literature review was completely and accurately performed through finding out the current news associated with the use of trees in producing electricity and the use of AI to manage the flow. The Scrum’s development model was adopted and followed during the research project to address issues like transparency, early mitigation of risks and constant feedback. The Scrum-model is one of the best …

Medical Imaging Dataset Management Leveraging Deep Learning Frameworks In Breast Cancer Screening, Inchan Hwang

Dissertations

In the domain of Computer-Aided Diagnosis (CADx) for breast cancer diagnosis through mammography, prevailing models have traditionally been trained and validated using old film-based mammography. However, contemporary U.S. hospital practices involve the utilization of Full Field Digital Mammography (FFDM), offering more detailed images captured at various angles than old film-scanned mammography. Despite this shift, the existing body of research predominantly focuses on old-film based datasets, the implications of FFDM for CADx systems have not been understood. This dissertation addresses the issues emerged from FFDM such as data augmentation between old film-based set and new FFDM whether they are more effective …

Predictive Maintenance Of Base Transceiver Station Power System Using Xgboost Algorithm: A Case Study Of Econet Wireless, Zimbabwe, Tavengwa Masamha

African Conference on Information Systems and Technology

Faults incurred by Base Transceiver Stations pose challenges to telecommunication organisations. Mostly the faults are due to BTS failures. BTS power system failures can have a significant impact on organizational performance in the telecommunications industry. These failures can cause disruptions in mobile network coverage, leading to dropped calls, slow data speeds, and difficulty connecting to the network. ECONET Zimbabwe has been experiencing unprecedented BTS power system failures for the past five years. Team Data Science Process was the pillar of the study methodology. The XGBoost algorithm was employed to develop a predictive model for the maintenance of Base Transceiver Station …

Factors Affecting The Adoption Of Information And Communication Technologies In Africa: Literature Review, Edison Wazoel Lubua

African Conference on Information Systems and Technology

This paper synthesised the literature on the adoption of Information and Communication Technology within Africa. The purpose was to determine factors (reported by the literature) determining technology adoption and use, in Africa. The paper used the systematic literature review. The study analysed the factors descriptively. Based on the analysis, the following are the main five factors reported to affect the adoption and use of Information Technology in Africa: Lack of ICT knowledge, unreliable infrastructure, high cost of adoption, the perceived usefulness of ICT, and the perceived ease of use. The government and technology implementing organisation has the key role to …

Security And Privacy Analysis Of Wearable Health Device, Abm Kamrul Islam Riad

Symposium of Student Scholars

Wearable technology allows for consumers to record their healthcare data for either personal or clinical use via portable devices. As advancements in this technology continue to rise, the use of these devices has become more widespread. In this paper, we examine the significant security and privacy features of three health tracker devices: Fitbit, Jawbone and Google Glass. We also analyze the devices' strength and how the devices communicate via its Bluetooth pairing process with mobile devices. We explore possible malicious attacks through Bluetooth networking. The outcomes of this analysis illustrate how these devices allow third parties to access sensitive information, …

Motion Detection On A Frequency Jumping Rfid Signal ​ Using Machine Learning, Trevor Stanca

Symposium of Student Scholars

Radio Frequency IDentification (RFID) is a well-known technology in wireless communication. It is hypothesized that the capabilities of RFID can be extended by reading an ID number and detecting movement around the reader during the read. Following regulatory standards, this study presents the foundation for a software defined RFID reader that may simultaneously detects and classifies the type of movement during the interrogation operation. A frequency hopping signal in unlicensed 5.8GHz can be analyzed using machine learning to extract a Doppler profile. We effectively collect information about an object through RFID by potentially detecting the speed of the object or …

Source Localization Of Electroencephalogram (Eeg) Waves With Convolutional Neural Network, Terence Onyewuenyi

Symposium of Student Scholars

This paper investigates the use of deep learning as a means for quantification and source localization of prioritizing electroencephalogram (EEG) waves for the purpose of detecting different eye states of human subjects. The Convolutional Deep Learning tool is trained to recognize EEG reading corresponding to a set of different eye movements as generated by watching different action scenes. The results also predict whether the subjects' eyes are open or closed. Source localization is performed next on the EEG data to focus on the different EEG components which primarily contribute to the activity. This was done by using a convolutional neural …

The Future Of Artificial Intelligence, Alex Guerra

Emerging Writers

Whether we like it or not Artificial Intelligence (AI) is coming, and we are not ready for it. AI has unimaginable potential and will revolutionize the world over the next few decades, but with this great potential we are faced with choices that could prove detrimental to humanity. This article examines the challenges AI presents and explores possible solutions to make AI align with human interests.

Efficient Data Mining Algorithm Network Intrusion Detection System For Masked Feature Intrusions, Kassahun Admkie, Kassahun Admkie Tekle

African Conference on Information Systems and Technology

Most researches have been conducted to develop models, algorithms and systems to detect intrusions. However, they are not plausible as intruders began to attack systems by masking their features. While researches continued to various techniques to overcome these challenges, little attention was given to use data mining techniques, for development of intrusion detection. Recently there has been much interest in applying data mining to computer network intrusion detection, specifically as intruders began to cheat by masking some detection features to attack systems. This work is an attempt to propose a model that works based on semi-supervised collective classification algorithm. For …

On Intelligent Mitigation Of Process Starvation In Multilevel Feedback Queue Scheduling, Joseph E. Brown

Master of Science in Computer Science Theses

CPU time-share process schedulers for computer operating systems have existed since Corbato published his paper on the Compatible Time Sharing System in 1962 [8]. With this new type of scheduler came the need to effectively divide CPU time between N processes, where N could be 2 or more processes. Modern time-sharing process schedulers which have been developed in the decades since have been designed to favor shorter, interactive processes over long-running processes, especially when incoming demand for CPU time exceeds supply and process starvation is inevitable. These schedulers, including Linux CFS, FreeBSD Ule, and the Solaris Fair Share Scheduler, are …