Computer Engineering Commons^™

Towards Neural Network Optimization: Addressing Issues With Corrupted Weights Within Models, Nick Najafizadeh

Master's Theses

Neural networks are a recent popular technology inspired from human brains. Much of their popularity arises from how they excel in reasoning and logic, and are generally rather efficient in their tasks. With those strengths, they are frequently used in transportation and business among many other fields. However, neural networks have many factors that can deteriorate their performance, one of the most critical being weight corruption. Therefore, it is of utmost importance to detect and handle them as soon as possible so as to minimize the negative impact on a network’s performance. The optimization of neural networks would be especially …

Pipeline Optimization Of Agentic Llms For Text-To-Sql, Peter Conant

Master's Theses

Current database interfaces limit users’ interaction to those with technical skills, creating timely roadblocks for non-technical professionals. Text-to-SQL aims to simplify database interactions by translating natural language questions into database queries, but long-standing challenges like question understanding, question-schema linking, and SQL generation have held the field back. In the AI era, foundational LLMs prove to be very capable of question understanding SQL, perform well in Schema Linking, Generation, and Evaluation tasks. However the cost to run these model is a hurdle for many organization with low funds and resources. Text-to-SQL solutions often operate across large enterprise size databases with, and …

Developing A Natural Language Interface For Knowledge Graphs, Ruth Assefa, Sarah Mendoza, Luke Voinov, Oyku Serap Ogut, Nurcan Yuruk

SMU Journal of Undergraduate Research

This paper proposes to solve the challenge of making databases more user-friendly by interfacing them with OpenAI's ChatGPT-3.5 model. We implemented this solution to assist researchers in easily finding others with similar research interests. Our study involves 184 researchers from 14 departments at Southern Methodist University (SMU). We collected researchers' areas of expertise and biographies and stored them in a Neo4j graph database. We used OpenAI's embedding models to create vector representations of the collected data, allowing for accurate similarity assessments via Neo4j's built-in algorithms. By integrating this system with LangChain, we enabled natural language queries. The results demonstrated high …

Analyzing Energy Use In 2d & 3d Imaging Systems And Workflows, Michael J. Bennett

Published Works

This study examines energy consumption in cultural heritage imaging systems and workflows, addressing a gap in sustainability research that has to date focused primarily on data storage infrastructure estimations. Using Home Assistant edge computing and Z-Wave smart plugs, seven distinct imaging systems were monitored over 203 hours, capturing 55,211 images, and rendering 2,448 objects. Results show an average energy requirement of 11.1 Wh per object, with an annual total of 747 kWh for digitization activities. Findings highlight opportunities to reduce energy demand and improve efficiency, such as automating continuous light shutoff and optimizing postprocessing routines that support institutional sustainability goals …

Privacy-Preserving Intrusion Detection For The Internet Of Medical Things Using Ensemble And Federated Learning, Theyab Alsolami

Electronic Theses and Dissertations

The rapid proliferation of the Internet of Medical Things (IoMT) has transformed healthcare by enabling continuous monitoring, intelligent diagnostics, and data-driven clinical decision-making. However, this increased connectivity has significantly expanded the attack surface of healthcare systems, exposing sensitive patient data and critical medical devices to cyber threats such as intrusion and data exfiltration attacks. Ensuring both strong security and strict privacy preservation in IoMT environments remains a fundamental and unresolved challenge.

This dissertation investigates the design and evaluation of robust and privacy-preserving intrusion detection systems (IDS) for IoMT networks using advanced machine learning techniques. The research first examines the effectiveness …

Singulars: Performing The Reverse Turing Test, Halim Madi

ELO (un)supervised 2026

Singulars is an ongoing series of performance systems in which I co-create poetry with a language model trained on an anthology of English poetry alongside my own writing. Across three works—carnation.exe, versus.exe, and reinforcement.exe—I stage live reinforcement loops in which my poems and the model’s responses compete for audience votes. The audience functions as an embodied feedback mechanism, shaping the evolution of both the machine and the human poet in real time.

This paper examines what happens when a poet becomes both author and training data. Drawing from creativity research, metacognition, and social cognition, I reflect …

Case Study: Feasibility Of Creating A Simulated Mobile Data Center For Cross-Disciplinary Academic Programs, Stanley Mierzwa, Christoper J. Schultz, Iassen Christov, Michael Fagioli, Thomas Ikeda, Reinaldo Jaramillo, Giolian Sanagustin

Center for Cybersecurity

This case study examines the potential to envision, create, and deploy a simulated mobile micro data center solution that can be easily replicated and transported between locations and educational settings. The coined term for this solution is the Mobile AI-Centered Data Center (Mobile ACDC), which provides students with a platform to construct, in a hands-on fashion, such a solution and navigate the product to gain greater competencies and understanding of the components found in a data center. Instructor and student feedback assessments from the pilot classroom modules and laboratory experiential learning activities indicate that such a solution helps to improve …

Proceedings: Nownet Arts Conference 2019, Sarah Rose Weaver, Chris Chafe, Scott Oshiro, Margaret Schedel

Journal of Network Music and Arts

Proceedings of the 2nd Annual NowNet Arts Conference 2019 “Social Purpose in Contemporary Network Arts.” The conference was held November 7–10, 2019. The primary in-person site was the Institute for Advanced Computational Science (IACS), Stony Brook University. Satellite in-person sites included Center for Computer Research in Music and Acoustics at Stanford University, Edinburgh Napier University, Orpheus Institute in Belgium, and Electronic Studios at the Technical University, Berlin. More locations participated remotely via the internet.

Proceedings: Nownet Arts Conference 2018, Sarah Rose Weaver, Chris Chafe, Margaret Schedel, Min Xiao-Fen

Journal of Network Music and Arts

Proceedings of the NowNet Arts Conference 2018, “Network Music: Artistic and Technological Strategies for Public and Private Networks.” This was the first of the NowNet Arts Conferences, which have been held annually from 2018 to the present. The conference took place from April 19–22, 2018, at the Institute for Advanced Computational Science (IACS), Stony Brook University, and at multiple remote locations connected via the internet.

Comparing Text Score Strategies For Online Music Making, Craig Pedersen, Lindsay R. Vickery, Stuart James

Journal of Network Music and Arts

This paper investigates a range of approaches to using text scores in online and networked music performance, focusing on their alignment with strategies proposed by Wilson (2020) for aesthetic and technical approaches to networked music performance. Text scores, emerging from the experimental music movement of the 1960s, communicate musical ideas through words rather than traditional notation, taking instructional, allusive, and hybrid forms. Although there are many aesthetic and pragmatic approaches to text score composition, the temporal openness of many such works makes the medium well-suited to the latency-challenged practice of telematic performance. The study evaluates four text scores—Craig Pedersen’s July …

Listening Ahead Ever So Slightly, Chris Chafe, Mike Dickey

Journal of Network Music and Arts

This paper presents a novel packet loss concealment system called “Regulator,” designed for interactive network audio applications, particularly server-mediated “jam rooms” in the cloud, where large ensembles of musicians perform together synchronously. The system addresses the critical challenge of maintaining continuous high-quality audio output while minimizing latency penalties in unreliable network environments including Wi-Fi. The Regulator architecture combines four core components: a central Regulator class orchestrating packet loss concealment operations; a BurgAlgorithm class implementing maximum entropy autoregressive prediction to reconstruct missing audio samples; a Channel class providing per-channel independent modeling for multi-channel streams; and a RegulatorWorker class offering asynchronous processing …

Pulse Before Sound: Reimagining Presence And Liveness In Telematic Music Performance Through Midi-Native Collaboration, Matt C. Bray

Journal of Network Music and Arts

Telematic Music Performance heralds a new paradigm for human creativity, seeking to extend the practical limits imposed by physical co-presence and to permit the cooperative, simultaneous creation of music among geographically remote collaborators. This paper examines how MIDI-native interaction provides a structurally robust alternative to audio-centric telematic systems constrained by latency, bandwidth, and waveform fidelity. Drawing on practice-led research, including over 34 hours of documented improvisation across 91 networked sessions in the SHOALZ series—a longitudinal Telemidi performance research initiative (2022–2024)—the study examines how the Telemidi system employs MIDI as a primary substrate for remote musical collaboration by establishing a synchronized …

Editorial, Sarah Rose Weaver

Journal of Network Music and Arts

No abstract provided.

Scalefusion: Hierarchical Feature Aggregation For Unified Multiscale Object Detection, Ayşenur Yaylaci, Berru Kaya, Mehmet Kiliçarslan

Turkish Journal of Electrical Engineering and Computer Sciences

Detecting objects across a wide range of scales, particularly small ones, remains a significant challenge in computer vision. Existing methods often improve small object detection at the cost of performance on larger objects or introduce significant computational overhead through external techniques like image slicing. This paper introduces ScaleFusion, a novel, unified, end-to-end object detection architecture designed to provide robust performance across all scales within a single model. The core of our approach is a hierarchical feature aggregation strategy structured like a tree. ScaleFusion processes an image by running a shared backbone network only on fine-grained patches at the lowest level …

A Holistic Approach For Workforce Scheduling And Routing, Kerem Can Manalp, Ansel Kaplan Erol, Kutluhan Erol, Cem Evrendi̇lek

Turkish Journal of Electrical Engineering and Computer Sciences

The workforce scheduling and routing problem (WSRP) involves assigning tasks across multiple locations while accounting for varying travel times, service durations, time windows, and skill requirements in a wide range of industries, from healthcare to telecommunications. This paper presents a mixed-integer programming model for the WSRP that balances the trade-off between cost and customer satisfaction using a score-generation function and subsequently evaluates the trade-off between solution quality and computation time for several algorithms on well-known datasets. We demonstrate that our model effectively balances cost, service-level agreement satisfaction, and task priorities while providing high-quality solutions in a timely manner. Observing that …

Dual-Stream Bilstm Framework With Histogram-Based Shape Features For Household Load Forecasting, Chang Xu, Wong Jee Keen Raymond, Hazlee Azil Illias, Hazlie Mokhlis

Turkish Journal of Electrical Engineering and Computer Sciences

This study proposes a dual-stream BiLSTM framework for household load forecasting that integrates time-series dynamics with histogram-based daily shape features. Unlike existing models relying on weather or external data, the proposed method extracts intrinsic load-shape information directly from normalized daily curves. A multihead attention module fuses temporal and shape representations, enabling adaptive weighting of informative dimensions. Experiments on three real-world datasets show consistent improvements over the baseline BiLSTM, with up to 30.12%, 24.27%, and 19.03% reductions in MAE, RMSE, and SMAPE, respectively. The results highlight the framework’s robustness and efficiency for fine-grained load forecasting without external inputs.

Class-Aligned Frequency Augmentation Using Variational Mode Decomposition Forfew-Shot Image Classification, Leila Boussaad

Turkish Journal of Electrical Engineering and Computer Sciences

Few-shot image classification benefits from data augmentation, yet most existing methods operate in pixel space with limited control over spectral semantics. We introduce a lightweight, frequency-guided augmentation strategy based on Variational Mode Decomposition (VMD). Our method constructs an offline, per-class ModeBank by decomposing downsampled luminance patches and retaining midband modes that encode class-specific texture patterns. During episodic training, VMD is never executed online: instead, for each support image, a same-class midband mode is selected and blended using PSNR-targeted scaling with a luminance energy cap, ensuring perceptual consistency. The augmentation is fast, reproducible, class-consistent, and integrates seamlessly into standard metric-based pipelines …

Efficient Edge Implementation Of Midasnet For Real-Time Depth Estimation In Indoor Robotics, Muhammed Yasi̇n Adiyaman, İsmai̇l Fai̇k Başkaya

Turkish Journal of Electrical Engineering and Computer Sciences

Real-time depth estimation is crucial in many vision-related tasks, including autonomous driving, 3D reconstruction, robotics, and simultaneous localization and mapping. In recent years, many methods have been proposed to solve depth maps from images by utilizing different modality setups like monocular vision, binocular vision, or sensor fusion. However, for real-time deployment on edge devices, complex methods are not suitable due to latency constraints and limited computation capacity. For edge implementation, models should be simple, minimal in size, and hardware-friendly. Considering these factors, we implemented MiDaSNet, which works on the simplest setup of monocular vision and utilizes hardware-friendly convolutional neural network-based …

A Revenue-Driven Approach For Enhanced Task Utilization In Vehicular Cloud Computing, Ashish Singh Saluja, Satyabrata Das, Sanjib Kumar Nayak, Sohan Kumar Pande

Turkish Journal of Electrical Engineering and Computer Sciences

Vehicular networks support intelligent transportation through vehicle-to-roadside Units (V2R) and vehicle-to-vehicle (V2V) communication but face challenges from dynamic topologies, limited RSU coverage, and bandwidth scarcity, which impact service delivery and revenue. RDA-ITU addresses these challenges by integrating V2R and V2V paradigms to maximize RSU revenue, enhance service availability, and improve system efficiency. It dynamically allocates services based on real-time network conditions and vehicle mobility, leveraging V2V relays to optimize both RSU-direct and cooperative communication. Through extensive simulations, RDA-ITU significantly outperforms four baselines: RBSM, VVMM-U, VVMM-LW, and VVMM-MA. It achieves 81.1% higher total revenue, 154.8% more completed requests, and 103.6% higher …

Resource Constraint Evacuation Route Planning A Capacity-Aware Charge-Encoded State-Space Approach, Praveen Borra

Electronic Theses and Dissertations

Emergency Management Information Systems (EMIS) are defined as a set of tools that assist decision-makers in risk assessment and disaster response for significant multi-hazard threats and disasters. Over the past several decades, EMIS have become increasingly important for understanding, managing, and governing transportation systems during large-scale emergency events. One of the primary objectives of EMIS is to efficiently utilize spatial and network datasets to support evacuation planning, identify critical transportation patterns during emergencies, and allocate resources effectively. However, the increasing complexity and scale of modern transportation systems present significant challenges in developing reliable evacuation planning solutions.

One of the most …

Evolutionary Neural Architecture Search: A Survey, Ferda Nur Özçeli̇k, Mehmet Önder Efe

Turkish Journal of Electrical Engineering and Computer Sciences

Deep Neural Networks (DNNs) have achieved remarkable success across diverse machine learning applications, yet designing effective architectures remains a laborious, expert-driven process. Neural Architecture Search (NAS) was introduced to automate this process, with Evolutionary NAS (ENAS) emerging as one of the most effective and widely adopted NAS paradigms. This survey provides a comprehensive and systematic review of 164 ENAS studies published between 2020 and 2024, categorized according to the specific evolutionary algorithm employed as the search strategy. Unlike prior surveys—which either treat evolutionary methods at a high level or focus on general NAS pipelines—this study is, to the best of …

Cnkg: Harnessing Large Language Models For Cognitive Neuroscience Knowledge Graph Construction, Ali Sarabadani, Kheirollah Rahsepar Fard, Hamid Dalvand

Turkish Journal of Electrical Engineering and Computer Sciences

Textual resources are among the most valuable sources of information in cognitive neuroscience (CN) for understanding and investigating brain activity and cognitive processes. Extracting and constructing knowledge graphs (KGs) from these texts can facilitate medical research by providing deeper insights into neurological diseases and brain function. In recent years, the use of large language models (LLMs) in natural language processing (NLP) has become increasingly widespread, significantly enhancing the extraction of meaningful information from large volumes of text. This study proposes a novel approach for constructing and evaluating a specialized knowledge graph, termed the cognitive neuroscience knowledge graph (CNKG), from scientific …

Robust Variable-Gain Backstepping Control For Nonlinear Systems With Real-Time Application To Induction Motor, Fadi Alyoussef, İbrahi̇m Kaya, Ahmad Akrad, Rabia Sehab, Cristina Morel

Turkish Journal of Electrical Engineering and Computer Sciences

This study proposes a novel variable-gain mechanism with a minimal number of tuning parameters to enhance the performance of conventional backstepping controllers for nonlinear systems while avoiding singularity and peaking phenomena. The proposed approach is simple, computationally efficient, and well suited for real-time implementation without imposing a significant computational burden. Its effectiveness is validated through real-time experiments conducted using a dSPACE DS1104 controller board and a 7.5-kW induction motor (IM). Simulation results demonstrate that the proposed controller outperforms the conventional backstepping controller. Robustness analyses under variations in stator resistance, load inertia, and viscous friction coefficient reveal substantial reductions in the …

Swindeitvit: A Soft Voting Vision Transformer Ensemble For Accurate And Explainable Solar Panel Fault Detection, Mahe Zabin

Turkish Journal of Electrical Engineering and Computer Sciences

Solar panels are becoming very essential in providing sustainable energy but they are usually affected by defects on the surface like dust, snow, bird droppings, physical damages and electrical faults which interfere with their performance. These faults must be identified accurately and in a timely manner to enhance energy efficiency, lower the maintenance cost, and supplement the traditional manual methods of inspection which are labor-intensive, time-consuming and subject to human errors in judgment. The most common methods, such as traditional CNNs and hybrid architectures tend to be less accurate, less explainable and cannot be properly evaluated to be deployed in …

Enhancement Of Nested Hexagonal Fractal Antenna Performance For Multiband Wireless Applications, Abdelbasset Azzouz, Rachid Bouhmidi, Mohammed Chetioui, Redouane Berber, Ahmed Jamal Abdullah Al-Gburi

Turkish Journal of Electrical Engineering and Computer Sciences

This work focuses on developing a compact multiband antenna to meet the growing demand for versatile and efficient radiating structures in modern wireless communication systems. A hexagonal fractal antenna is proposed and analyzed for applications such as mobile communications, WLAN, industrial, scientific and medical (ISM) bands, Wi-Fi, satellite links, radar systems, and military communications. By iteratively modifying the antenna geometry with larger hexagonal elements, the design enhances multiband behavior and improves key performance parameters including gain, S11, voltage standing wave ratio (VSWR), and radiation characteristics. The antenna is modeled using high-frequency structure simulator (HFSS)® and fabricated on a low-cost 0.8 …

Parameter Optimization Of Dual-Qsg Based Pll For Real-Time Control Of Grid-Connected Ev Chargers, Gaurav Yadav, Sudhanshu Mittal, Vineet Kumar, Sombir Kundu, Praveen Bansal

Turkish Journal of Electrical Engineering and Computer Sciences

Dual-Quadrature Signal Generator (D-QSG) based Phase lock loop (PLL) has been recently proposed to handle the nonideal grid voltage conditions. However, selecting the parameter for D-QSG based controller has been a great challenge, especially for higher-order systems. Inappropriate parameter selection tends to increase settling time both in terms of amplitude as well as harmonics attenuation. Hence, in the proposed work, the main focus is on parameter selection to achieve a faster response. Here, a fourth-order Quasi-Synchronous Generator has been realized by cascading the two nonidentical second order generalized integrators (NISOGIs). Furthermore, the parameters of both the NISOGIs are selected in …

Erratum To “Sgsc-Kko-Lstm: A Deeplearning Classifier Model For Smart Grid” [Turkish Journal Of Electrical Engineering & Computer Sciences 34 (2) 2026 185-213], Samaniba Imchen, Dushmanta Kumar Das

Turkish Journal of Electrical Engineering and Computer Sciences

The first and second authors were incorrectly ordered in the article PDF due to a typesetting error. To rectify this oversight and ensure the accuracy of the published work, the author order have been corrected as follows: 1. Samaniba Imchen – First Author 2. Dushmanta Kumar Das – Second Author

A link to the original article can be found at: https://doi.org/10.55730/1300-0632.4170

Cybersecurity Governance Of Industrial Iot In Sub-Saharan Africa: Policy Gaps, Threat Landscape, And Lessons From Comparative African Contexts, Faztudo Languisse Eng.

Journal of Cybersecurity Education, Research and Practice

The rapid deployment of Industrial Internet of Things (IIoT) systems across Sub-Saharan Africa's extractive, energy, logistics, and agro-industrial sectors has introduced a cybersecurity challenge of growing urgency: industrial networks that were designed for operational efficiency are increasingly exposed to cyber threats for which neither the organizations nor the regulatory frameworks are adequately prepared. This article examines the cybersecurity governance of IIoT systems in a developing African economy, using Mozambique as a primary case study and drawing comparative lessons from South Africa, Rwanda, and Kenya. Through an integrative literature review and documentary analysis of national digital, cybersecurity, and industrial policies, the …

Assessing Computer Vision Based Conflict Detection In Uas Traffic Monitoring Under Secure Communication Constraints, Fadjimata Issoufou Anaroua

Doctoral Dissertations and Master's Theses

The rapid growth of Unmanned Aircraft Systems (UAS) and Advanced Air Mobility (AAM) is creating a new low-altitude airspace ecosystem where drones, air taxis, service suppliers, communication networks, sensors, and ground-based monitoring systems must work together safely. Within this ecosystem, UAS Traffic Management (UTM) is expected to provide a digital framework for coordinating operations beyond traditional air traffic control. However, reliable integration also requires resilient monitoring methods that can detect non-cooperative aircraft, protect communication links, and maintain timely situational awareness under real-world constraints.

This dissertation examines how computer vision can support cooperative monitoring systems such as Remote ID and ADS-B …

Enhanced Intrusion Detection Using Recurrent Neural Networks With Amino Acid Codon Features, Omar Fitian Rashid, Mohammed Ahmed Subhi, Safa Ahmed Abdulsahib, Mohammed Khaleel Hussein, Marwan Ali Albahar

Iraqi Journal for Computer Science and Mathematics

Intrusion Detection Systems (IDS) is the main defense mechanism deployed by the current networks to prevent cyber threats. Recurrent Neural Network (RNN) are also a novel IDS structure that replaces the conventional training and testing mechanism. The strategy encodes network traffic data as biological sequences using amino acid codons in such a fashion that the RNN is capable of effectively analyzing temporal and sequence data patterns. RNN architecture design adopts embedding layers to handle codon representations and Long Short-Term Memory (LSTM) layers to perform sequential data learning, which is followed by a fully connected network to perform classification functions, which …