Engineering Commons^™

Novel Dynamic Batch-Sensitive Adam Optimiser For Vehicular Accident Injury Severity Prediction, Daniel Asare Kyei, Alimatu Saadia-Yussiff, Maame G. Asante-Mensah, Abdul Lateef-Yussiff, Charles Roland Haruna, Derry Emmanuel

Iraqi Journal for Computer Science and Mathematics

The choice of optimiser is important in deep learning, as it strongly influences model efficiency and speed of convergence. However, many commonly used optimisers encounter difficulties when applied to imbalanced and sequential datasets, limiting their ability to capture patterns of minority classes. In this study, we propose Dynamic Batch-Sensitive Adam (DBS-Adam), an optimiser that dynamically scales the learning rate using a batch difficulty score derived from exponential moving averages of gradient norms and batch loss. DBS-Adam improves training stability and accelerates convergence by increasing updates for difficult batches and reducing them for easier ones. We evaluate DBS-Adam by integrating it …

Genpix: A Diverse Dataset For Fake Image Detection, Guessoum Dalila, Benblidia Nadjia, Boumahdi Fatima, Remmide Mohamed Abdelkarim, Nouri Tarek-Amine, Bataouche Azeddine-Lotfi

Iraqi Journal for Computer Science and Mathematics

The rapid advancement of sophisticated generative models has intensified the need for robust fake image detection systems. However, many existing benchmark datasets suffer from limited diversity in content types and generation techniques, constraining the generalization ability of detection models. To address these limitations, we introduce GenPix (Generalized Pixels), a comprehensive dataset encompassing over 80,000 images spanning diverse categories, including faces, objects, and scenes, generated by multiple state-of-the-art models such as Generative Adversarial Networks (GANs) and diffusion-based architectures. The dataset includes samples from different generation methods to ensure broad coverage of fake image characteristics.

GenPix provides a realistic evaluation environment that …

Eyolov8-Msaff: An Enhanced Object Detection Algorithm With Multi-Scale Attention And Feature Fusion For Small And Dense Object Detection In Uav Applications, Mohammed Hasan Mutar, Morteza Valizadeh, Alaa Hussein Abdulaal, Mehdi Chehel Amirani

Iraqi Journal for Computer Science and Mathematics

The proliferation of unmanned aerial vehicles (UAVs) has necessitated the development of sophisticated object detection algorithms capable of handling the unique challenges posed by aerial imagery. Traditional detection methods often struggle with small object sizes, dense distributions, and complex backgrounds characteristic of UAV-captured scenes. This research presents EYOLOv8-MSAFF (Enhanced YOLOv8 with Multi-Scale Attention and Feature Fusion), a novel deep learning architecture specifically engineered for superior performance in UAV-based object detection tasks. The proposed methodology integrates four innovative components: a Hybrid Spatial-Channel Attention Mechanism (HSCAM) that processes attention information in parallel rather than sequentially, an Adaptive Multi-Scale Feature Fusion Module (AMSFFM) …

A Novel Hierarchical Multi-Scale Attention Mechanism For Enhanced Yolov8 Performance In Unmanned Aerial Vehicle-Based Small Object Detection, Mohammed Hasan Mutar, Morteza Valizadeh, Alaa Hussein Abdulaal, Mehdi Chehel Amirani

Iraqi Journal for Computer Science and Mathematics

Object detection in Unmanned Aerial Vehicle (UAV) images presents significant challenges due to the prevalence of small and densely packed objects, as well as variations in scale, orientation, and lighting conditions. This paper introduces a novel object detection algorithm, Hierarchical Multi-Scale Attention YOLO (HMSA-YOLO), which is an improved version of YOLOv8 designed to address these challenges. The proposed method incorporates a novel Hierarchical Multi-Scale Attention (HMSA) module, a Bidirectional Feature Pyramid Network (BiFPN) for enhanced feature fusion, a modified loss function, and an adaptive anchor optimization technique. The HMSA module effectively captures both channel and spatial dependencies at multiple scales, …

Improving The Fpga Radio Design Cycle: Implementing Dvb-S2 Modulation Using Verilator And Gnu Radio, Seth Pellegrino

Dissertations and Theses

In embedded digital radio systems, a central challenge is meeting the real-time throughput required to process the samples--especially for space-bound ultra-wideband SDRs which must handle more than 100 Gbps entirely onboard. An FPGA's programmable logic offers sufficient potential, but realizing a particular radio flow is a project usually fraught with defects and long turnaround times. We simulated Verilog modules in a custom harness that adapted a Verilated model to GNU Radio, which allowed for breaking down a complicated radio flow (here, DVB-S2 modulation) into a series of well-bounded problems each with clear criteria for success. The framework, built on open …

Tinyml-Based Embedded Vision System For Ic Detection In Microcontroller Manufacturing, Mark M. Pallones, King Harold A. Recto, Rynne Daven A. Barrios

Electronics, Computer, and Communications Engineering Faculty Publications

Mixing of microcontroller unit (MCU) integrated circuits (ICs) during the final testing stage of semiconductor manufacturing can lead to material waste, production delays, and customer dissatisfaction. This issue often occurs when standard JEDEC Matrix Trays (JMTs) are reused without confirming that all ICs have been removed after testing, a process typically performed through manual inspection and therefore susceptible to human error due to high test volumes, small IC package sizes, and visual similarity between IC packages and tray surfaces. This study develops an automated IC Detection Test System using embedded vision to determine whether JMT trays are empty prior to …

Rthermal: Gate Level Power And Thermal Simulation For 3d-Stacked Chips, Peter Xiong

Master's Theses

As the number of transistors in modern processors increases, heat dissipation has become a major bottleneck to scalability. The use of 3D stacking further intensifies this problem, as heat from multiple layers can accumulate vertically. These challenges create a growing need for tools that can accurately and efficiently simulate the thermal behavior of 3D chips during design and validation. Several existing tools model thermal behavior for 3D-stacked chips and can simulate average heat over large spatial regions or long time intervals. However, when heat is concentrated in a small area or over a short time window, such models can miss …

Adaptive Task-Driven Lidar Point Cloud Compression For Autonomous Driving, Su Hyun Kim

Master's Theses

Autonomous-driving systems generate large LiDAR point clouds, but compression can damage the sparse object-support structure needed by 3D detectors even when reconstructions appear visually plausible. This thesis asks whether adaptive LiDAR compression can preserve downstream detection better than uniform compression by allocating more fidelity to detector-relevant regions. The main study builds a mask-aware range-image codec with an encoder-decoder bottleneck, an importance head, and an adaptive quantization variant. It compares this adaptive variant package with a confirmed masked uniform baseline under one fixed RangeDet evaluation surface and one fixed KITTI validation subset. Two supporting studies bound the result: a projection-reconstruction PointPillars …

Early Failure Detection In Web Navigation Agents Via Closed Sequential Pattern Mining, Sergio Talavera

Master's Theses

LLM-based web navigation agents fail on the majority of tasks while consuming substantial computational resources before failure becomes apparent. This thesis investigates whether closed sequential pattern mining on the first K steps of agent execution traces can predict task failure early enough to enable meaningful computational savings with interpretable justification. We develop a two-phase system: an offline pipeline that symbolizes agent traces, extracts K-step prefixes, mines closed patterns via BIDE+, and ranks them by failure precision; and an online detector that matches live executions against the resulting pattern library. We evaluate on 1,544 MiniWoB++ traces across three open-weight language models …

Data Augmentation For Vision-Language-Action Models: Bridging Vision And Language, Miaosen Zhou

Master's Theses

This thesis focuses on real-time task execution and object detection for autonomous robots through dataset augmentation. We propose a data augmentation approach to address dataset imbalance in Vision-Language-Action (VLA) models across both image and text modalities during the fine-tuning process. The proposed method takes an image as input and generates a structured textual description using a prompt engineering strategy to augment the textual input. The generated augmented text includes key elements such as the task goal, scene description, reasoning, and execution plan, along with other relevant contextual information. This enriched representation improves the quality of the training data and supports …

Moral: Multimodal Reasoning For Autonomous Language Models With Sensor-Grounded Spatial Bev Rendering, Ambarish Govindarajulu Kaliamurthi

Master's Theses

Autonomous-driving vision-language models describe scenes fluently but reason poorly about metric, safety-critical spatial relationships because they do not read sensor geometry in a grounded way. This thesis presents MoRAL (Multimodal Reasoning for Autonomous Language Models), a two-stage fine-tuning pipeline that teaches a compact 2-billion-parameter VLM to decode a physics-encoded Bird’s Eye View (BEV) representation – LiDAR distance as color, object class as cluster shape, radar Doppler velocity as directional wedges – and then trains it to reason over that representation for driving decisions. Stage 2 then fine-tunes on 57,696 teacher-generated chain-of-thought examples across eight question types, using Cosmos-Reason2-8B as teacher …

The Zeal Instruction Set Architecture, Joseph A. Gerani

Master's Theses

The Instruction Set Architecture of a CPU (Central Processing Unit) determines what type of instructions the CPU is able to understand, how those instructions are encoded, and what it should output upon receiving those instructions as input. There are currently three popular ISAs meant for the consumer market: x86, RISC-V, and ARM, as well as a fourth that mostly now exists in the server market by the name of Power. One of the most important parts of an ISA is for engineers to be able to understand it and make use of it. If an ISA is too complicated, nobody …

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 …