Digital Commons Network^™

Enhancing Stem Education With Modeling, Simulation, And Ai Technologies: From Virtual Laboratories To Intelligent Teaching Assistants, Yiyang Li

Electrical & Computer Engineering Theses & Dissertations

Rapid advancements in modeling and simulation (M&S) and artificial intelligence (AI) present new opportunities to enhance various aspects of STEM education, from virtual laboratories that simulate physical lab environments in software to intelligent teaching assistants that provide on-demand, curriculum-aligned instructional support. Virtual laboratories offer a potential solution to the access and scalability challenges of laboratory courses by allowing students to conduct experiments without physical equipment or geographical constraints. AI-powered teaching assistants, particularly those grounded in course-specific materials, can help mitigate the instructional support gap that arises when students work independently in digital learning environments. This dissertation presents three-phase research into …

Development Of Dynamic Proof-Mass Configurations For Broadband Piezoelectric Energy Harvesting, Nico E. Galarza

Electrical and Computer Engineering ETDs

The purpose of this thesis is to investigate and develop dynamic proof-mass configurations for broadband piezoelectric energy harvesting. Conventional piezoelectric energy harvesters are typically limited by narrow operating bandwidths, restricting their performance under variable-frequency excitation. This research presents the design, fabrication, and experimental evaluation of multiple proof-mass concepts intended to increase the usable frequency range of cantilever-based piezoelectric energy harvesters. Several dynamic mass configurations were developed using additive manufacturing techniques and integrated with commercially available piezoelectric cantilevers. Experimental testing was conducted under controlled vibration conditions to characterize voltage response, resonant behavior, and bandwidth performance. The results demonstrate that dynamic proof-masses …

Dynamic Reconstruction Engineering Of Anti-Corrosion Ni-Based Anodes For Alkaline Seawater Electrolysis, Yi-Gang Zhang, Wen-Wen Xu, Tian-Yu Zhang, Zhi-Yi Lu

Journal of Electrochemistry

Green hydrogen production via alkaline seawater electrolysis offers an environmentally sustainable and potentially cost-effective route to address both energy and climate challenges. Achieving long-term anode stability under complex ionic environments and industrial current densities remains a central bottleneck. Specifically, Ni-based anodes exhibit intense surface reconstruction during the oxygen evolution reaction, necessitating dynamic anti-corrosion strategies. This mini review systematically summarizes reconstruction engineering approaches to develop anti-corrosion Ni-based anodes of alkaline seawater electrolysis across increasingly complex ionic environments from simulated seawater to real seawater: (i) Cl^– dominated; (ii) Cl^– with co-existing oxyanions, and (iii) Cl^–  with co-existing Br^{– …}

Preparation And Performance Study Of In-Situ Self-Assembled Biphasic Smmn2O5-Nimn2O4 Composite Cathode, Neng-Chu Xia, Yu Zhou, Qin Wang, Jia-You Zhang, Chun Yu, Yang Zhang, Wan-Bing Guan, Jian-Xin Wang

Journal of Electrochemistry

Mullite-structured oxides exhibit excellent oxygen reduction reaction activity, possess a low thermal expansion coefficient due to their unique crystal structure, and can eliminate the need for a barrier layer and simplify the preparation process as they contain no alkaline earth elements. Thus, they hold great promise as novel cathode materials for solid oxide fuel cells. In this work, a mullite-spinel-structured SmMn₂O₅-NiMn₂O₄ (SMO-NMO) composite cathode was one-step synthesized via a solid-liquid composite route, and its in-situ self-assembly enabled good compatibility with the electrolyte without any barrier layer. Characterization results showed that the SMO:NMO = …

Multi-Robot Cooperative System For Complex Aerospace Manipulation Tasks: Theory And Application, Longsen Gao

Electrical and Computer Engineering ETDs

Multi-robot systems can extend manipulation capabilities beyond the limits of a single robot, particularly for tasks involving large, flexible, delicate, or free-floating payloads. Reliable cooperative manipulation, however, remains difficult when payload dynamics, contact geometry, compliance properties, deformation-induced forces, and external disturbances are only partially known, and when safety constraints must be enforced during physical interaction. This dissertation develops a two-layer control framework for resilient multi-robot manipulation under uncertainty, with emphasis on space servicing, satellite stabilization, aerial transportation, and cooperative manipulation of free-floating structures.

Enhanced Computational Modeling Of Photoionization And Streamer Formation, Anahita Alibalazadeh

Electrical and Computer Engineering ETDs

Photoionization is a key mechanism governing the formation and propagation of streamer discharges in air by generating electron-ion pairs ahead of the streamer front. Accurate and computationally efficient modeling of this non-local process is essential for reliable plasma simulations. However, the widely used Zheleznyak photoionization model relies on empirical assumptions and requires computationally expensive domain-wide integration.

This dissertation advances photoionization modeling in three ways. First, the classical integral model is enhanced by incorporating experimentally measured vacuum ultraviolet (VUV) emission spectra together with photoabsorption and photoionization cross-section data, enabling direct calculation of the photoionization source term as a function of pressure …

Developing A Dispersion Interferometer For Characterizing Power Flow Plasma Formation And Transport Studies, Nathan R. Hines

Electrical and Computer Engineering ETDs

Sandia's refurbished $Z$-pinch machine experiences persistent current loss in its post-hole convolute and inner magnetically insulated transmission line regions, widely attributed to low-density electrode plasmas whose formation and transport remain poorly constrained by existing diagnostics. This dissertation develops and validates a fiber-coupled, continuous-wave, second-harmonic orthogonally polarized dispersion interferometer for time-resolved measurements of electron areal density in millimeter-scale gaps. The diagnostic employs single-laser second-harmonic generation, non-steering differential phase control, and polarization-based phase retrieval to achieve sub-$10^{15}$~cm$^{-2}$ sensitivity, multi-hundred-megahertz bandwidth, and sub-$200$~$\mu$m effective cross-gap spatial resolution. Performance is benchmarked against a $94$~GHz interferometer on the UNM Helicon-Cathode plasma device and then fielded …

3d Electromagnetic Simulations Of A 1.6 Cell S-Band Photoinjector: Emittance Studies For Electron Microscopy, Trudy Bolin

Electrical and Computer Engineering ETDs

Modern beam-based materials research demands electron sources with increasingly precise time resolution, high brightness, and stability. For example, there are various instruments across the U.S. dedicated to ultrafast electron diffraction (UED), but fewer are dedicated to ultrafast electron microscopy (UEM), which demands beam stability. Modeling femtosecond electron bunches with ultra-low emittance < 50 nm-rad inside a 1.6-cell S-band (2856 MHz) rf photoinjector with full 3D electromagnetic simulations can require high-performance computing (HPC) environments due to the scale disparity between the macroscopic cavity geometry and the femtosecond-scale bunch kinematics. To enable optimization in a desktop computing environment, this work presents a streamlined 3D electromagnetic Particle-in-Cell (PIC) simulation framework optimized for 400-femtosecond bunch regimes. The covariance method was employed to study emittance properties for electron bunch counts ranging from thousands to millions and has successfully resolved highly transient, pure rf phase-space rotations, such as a localized energy-spread minimum occurring at the gun exit iris. To overcome the computational cost of these simulations, a machine-learning-based Bayesian optimization approach was deployed to construct multi-objective Pareto fronts from sparse datasets. Because the simulation software is scalable from desktop to HPC facilities, the framework is ready for experiments at the National Energy Research Scientific Computing Center (NERSC) at Lawrence Berkeley National Laboratory (LBNL).

Real-Time Waveform Synthesis For Rfsoc-Based Quantum Control Systems, Tiamike I. Dudley

Electrical and Computer Engineering ETDs

RFSoCs are gaining adoption in many labs for quantum control systems thanks to their compactness and affordability. Making full use of the many components on an RFSoC evaluation board is a challenging engineering problem that must be solved to realize scalable control systems. In this dissertation, I evaluate the performance of various RFSoC components in the context of quantum information science. I present two custom FPGA engines that accelerate and parallelize arbitrary waveform generation. The first engine can be instantiated many times to power low-speed DACs for ion-shuttling trap electrodes. The second engine synthesizes CPMG-XY8n dynamical decoupling pulse sequences on …

Simulations Of Atmospheric Pressure Streamer Discharges: Mechanisms Of Streamer Propagation And Related Physics, Dejan Nikic

Electrical and Computer Engineering ETDs

Gas discharge simulations are performed with particular focus on photoionization process in a positive streamer discharge. The effects of this process are investigated by isolating the change in photoionization mean free path (MFP) and keeping the additional processes constant. Furthermore, comparison are made between various effects of simulation parameters, such as initial conditions, geometry extent, simula- tion particle count etc. All of these simulations are performed using a modern Direct Simulation Monte Carlo Particle-in-Cell (DSMC-PIC) code developed by Sandia Na- tional Laboratories. Large scale simulations including 1 cm and 5 cm electrode gaps are performed under standard atmospheric condition air. …

Load Balancing Algorithms For Cloud Computing Systems, Mark Rakesh Christian

Electronic Theses and Dissertations 2020 - Present

Cloud computing depends on load balancing to allocate user requests among virtual machines (VMs), affecting response time, utilization, and scalability. Round Robin, Equally Spread Current Execution, and standard Throttled scheduling are widely used; however, standard Throttled selects among eligible VMs using an implementation-dependent order with no explicit preference. This thesis proposes the Weighted Throttled Load Balancing (WTLB) algorithm, which introduces an explicit, deterministic selection priority among eligible VMs, implemented by modifying the Throttled scheduler within CloudAnalyst.

Evaluated under an identical six-region, multi-data-center configuration against Round Robin, ESCE, and standard Throttled, WTLB preserves the aggregate response-time, processing-time, and cost profile of …

Synergizing Crowd Collaboration: Enhancing Crowdsourcing Matching Via Integration Of Matching Theory And Coalition Games, Rowan Aengus Kinney

Electrical and Computer Engineering ETDs

This paper tackles the challenges inherent in crowdsourcing dynamics by introducing the CROWDMATCH mechanism. Aimed at enabling crowdworkers to strategically select suitable crowdsourcers while contributing information to crowdsourcing tasks, CROWDMATCH considers incentives, information availability and cost, and the decisions of fellow crowdworkers to model the utility functions for both the crowdworkers and the crowdsourcers. Specifically, the paper presents an initial Approximate CROWDMATCH mechanism grounded in matching theory principles, eliminating externalities from crowdworkers’ decisions and enabling each entity to maximize its utility. Subsequently, the Accurate CROWDMATCH mechanism is introduced, being initiated by the outcome of the Approximate CROWDMATCH mechanism, and employing …

Modeling For You: A Personalized Approach To Residential Energy Simulation And Distributional Reinforcement Learning, Nestor Gabriel Pereira

Electrical and Computer Engineering ETDs

The growing complexity and uncertainty of residential energy use, driven by electric

vehicles and renewable technologies, demand more intelligent and robust

management systems. Traditional methods often fail when faced with unpredictable

electricity prices and user behavior. This dissertation addresses this gap by presenting

a novel personalized framework combining detailed household energy modeling with

a risk-aware reinforcement learning agent for appliance scheduling.

The first contribution is a probabilistic, bottom-up simulation model that captures

the interdependent behaviors of occupants, appliances, and electric vehicles to

generate realistic, high-fidelity load profiles. The second contribution is a lightweight,

tabular Distributional Q-Learning (D-QL) algorithm that schedules …

Application Of Palmprint Data For Prediction Of Diabetes, Ramasamy K Mr

Theses and Dissertations

Type 2 diabetes is one among the diabetes mellitus which has strong relation with lifestyle, genetics and metabolic dysfunction. The increasing global prevalence, rising healthcare costs, and high percentage of undiagnosed individuals leads to the need of noninvasive, cost-effective early detection methods. In conventional diagnostic methods, laboratory investigations and periodic clinical visits are needed, which may not be feasible for working and middle-aged populations. To overcome this, the research work proposes an automatic, non-invasive and early prediction of Type 2 diabetes using palmprint image analysis integrated with clinical data for identifying diabetic and non-diabetic individuals. The first proposed method aims …

Evaluating The Suitability Of Commercial Off-The-Shelf Software Radio Peripheral Front-Ends For High-Fidelity Satnav Monitoring Applications, Mark J. Carroll, Sanjeev Gunawardena, Timothy I. Machin, Christine M. Schubert Kabban, Joseph J. Rushanan

Faculty Publications

Signal quality monitoring is an essential portion of the Global Positioning System (GPS) enterprise. Through monitoring, accuracy and normality are achieved for each satellite and signal. GPS users rely on this information from monitoring stations to ensure safe and successful operation. Traditional monitoring has been performed with hardware receivers or custom radio frequency front-ends. These receivers have known and measured impacts on the distortions of the received signal. This research aims to elucidate and quantify the amount of distortion introduced by the front-ends of general-purpose commercial off-the-shelf software-defined radio (SDR) peripherals. Monitoring stations outfitted with SDRs are more flexible and …

Sustainable Consumer Behavior Modeling: A Complex-Systems Approach To Neuromarketing, Preethi Nanjundan, Nupoor Sanjay Bhute, Ragini Topre, Lijo Thomas

Northeast Journal of Complex Systems (NEJCS)

This study examines the application of complex-systems modeling to neuromarketing data for gaining deeper insights into the mechanisms underlying sustainable consumer behavior. It investigates how neural and biometric responses, interpreted through a systems-based perspective, can uncover dynamic interactions, feedback mechanisms, and emergent behavioral patterns influencing sustainable purchase decisions. The research explores the impact of sustainability-oriented marketing stimuli on long-term behavioral intentions by emphasizing the interconnected roles of cognitive processing, emotional engagement, implicit associations, and collective consumer dynamics. Through simulation-based modeling and structural analysis, the study demonstrates how subconscious neural responses and affective mechanisms mediate the relationship between marketing interventions, consumer …

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 …

Policy Reflections On Promoting Strategic Oriented Basic Research In China: Insights From The U. S. Department Of Energy’S Basic Research Funding System, You Yu, Yun Liu, Wenneng Zhou

Bulletin of Chinese Academy of Sciences (Chinese Version)

Strategy-oriented basic research is a key pathway to driving major original breakthroughs at the frontiers of science, serving national strategic needs, and securing a leading position in global science and technology. It is also a vital pillar for achieving high-level self-reliance and self-strengthening in science and technology and enhancing the capacity for original innovation. Faced with the urgent need to build a science and technology powerhouse and achieve breakthroughs in key core technologies, China has gradually improved its organizational framework for advancing strategy-oriented basic research and has established a solid foundation for policy support and resource allocation. Nevertheless, when measured …

Provocable Forgiveness In Noisy Brand--Consumer Systems:An Agent-Based Study Of Repeated Interaction, Tahere Ahmadiyan, Hamidreza Navidi, Behbod Keshavarzi

Northeast Journal of Complex Systems (NEJCS)

Repeated brand--consumer exchange is often treated as a managerial problem of loyalty, recovery, and trust. It can also be read as a small complex system: many local decisions about cooperation, retaliation, and forgiveness accumulate into market-level selection. This study uses that perspective to examine which relational rules survive when communication is imperfect. Eight canonical Iterated Prisoner's Dilemma strategies are translated into marketing archetypes and evaluated through round-robin tournaments, a six-level noise sweep, proportional-fitness ecological dynamics, and finite-population Moran invasion tests. The tournament leaderboard is calculated without same-strategy self-play, so that reported payoffs reflect inter-archetype competition rather than homogeneous self-coordination. At …

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 …

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 …

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 …

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 …

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.

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 …

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

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 …

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 …