Engineering Commons^™

Delay-Doppler Integrated Sensing And Communications (Dd-Isac) With Predictive Beamforming, Mohammad Abdul Mobin, Yanjun Pan, Jingxian Wu

Electrical Engineering and Computer Science Faculty Publications and Presentations

A new delay-Doppler (DD) integrated sensing and communications (ISAC) framework is proposed for unmanned aerial vehicle (UAV) systems. In the DD-ISAC framework, both sensing and communications are performed by using the orthogonal delay Doppler division multiplexing (ODDM) waveforms, which unify sensing and communication designs through the unique ODDM waveform properties, such as local DD-domain bi-orthogonality and dual-resolution. Specifically, the dual-resolution property enables the generation of a range-Doppler map for accurate and low complexity sensing, and the bi-orthogonality minimizes interference for both sensing and communications. The ODDM waveforms are used in combination with the phase comparison monopulse technique and a scaled …

Cats 2.0: Leveraging Large Language Models And Graph Databases For Robust Arabic Sms E-Commerce Systems, M. Samir Abou El-Seoud, Daoud M. Daoud 2

Computer Science

Arabic SMS-based e-commerce platforms pose unique challenges due to the spontaneous and noisy nature of user-generated text (e.g., abbreviations, dialectal Arabic, or “Arabizi” transliterations). In this paper, we present Classified Ads Text Service (CATS) 2.0, an improved classified ads system that combines probabilistic large language models (LLMs) with deterministic graph-based knowledge representations to achieve robust understanding and matching of Arabic SMS content. Building on earlier work that emphasized the importance of integrating sublanguage analysis with content-oriented methods, our approach uses a hybrid pipeline: an LLM interprets free-text messages and extracts structured information, which is then inserted into a Neo4j graph …

Machine-Learning- And Iot-Based Approach For Predicting Water Quality Using Data Classification And Explainable Ai Technique, M. Samir Abou El-Seoud, Omar H. Karam 2, Hosam El-Sofany 3

Computer Science

Maintaining water quality is crucial for both public health and environmental sustainability. This study proposes a machine-learning- (ML-) and Internet-of-Things- (IoT-) based approach to water quality prediction that utilizes explainable artificial intelligence (XAI) and data classification techniques. The proposed approach integrates IoT devices to enhance real-time data collection, facilitating continuous monitoring and early anomaly detection. Ten different ML classifiers—Decision Trees, K-Nearest Neighbors, XGBoost, Naïve Bayes, Logistic Regression, AdaBoost, Random Forests, Support Vector Machines, Voting, and Multi-Layer Perceptron—were evaluated to find out which one works best for predicting water quality. We used three distinct approaches for feature selection: analysis of variance …

Eeg And Imu Gait Signal Processing: A Comparative Assessment Of The "Reza" Exponential Filter And Classic Filters, Reza Pousti, Daniel M. Russell, Derek C. Monroe, Christopher K. Rhea

Rehabilitation Sciences Faculty Publications

Noise degrades both EEG and gait signals, and classical IIR filters (Butterworth, Chebyshev, elliptic) involve trade-offs between passband flatness, ripple, and roll-off. This study compared a novel exponential "Reza" filter with these designs for neural and locomotor data. We analyzed an open-source mobile brain-body imaging dataset with EEG and gait data from 49 healthy adults (EEG: 256-channel, 512 Hz; IMUs: six APDM Opals, 128 Hz). EEG channels were grand-averaged and band-pass filtered at 0.5-50 Hz, while IMU axes were averaged and band-pass filtered at 0.5-5 Hz. The outcomes were signal-to-noise ratio SNR (dB) and band-integrated Welch PSD (EEG:0.5-50 Hz; IMU:0.5-5 …

Multisystem Predictors Of Dynamic Gait Stability Across Fall Risk In Older Adults, Ashwini Kulkarni, Neda Moghim, Ross Gore, Soumya Banerjee, Christopher K. Rhea, Brittany Samulski

Rehabilitation Sciences Faculty Publications

Gait stability arises from interactions between physiological, cognitive, and psychological systems, yet these domains are often assessed in isolation. This study examined multisystem predictors of anteroposterior margin of stability during walking (MoSAP) in community-dwelling older adults. Of 340 participants, 143 were retained after data quality screening (105 females; age: 70.8 ± 7.8 years). Participants completed the Physiological Profile Assessment (PPA), cognitive testing using Montreal Cognitive Assessment (MoCA), fear-of-falling evaluations using Modified Falls Efficacy Scale (MFES) and a biomechanical gait assessment during preferred and fast speeds. Participants were stratified into four PPA-based fall-risk groups: low, mild, moderate, and high risk. MoSAP …

Engineering Plga Nanoparticle Size To Modulate Immune Responses After Spinal Cord Injury, Daniel J. Kolpek

University of Kentucky Doctoral Dissertations

Spinal cord injury is a severe and debilitating condition that often results in lifelong complications, including paralysis. Many of these chronic outcomes are driven by a sustained inflammatory response at the injury site, which limits tissue regeneration and functional recovery. As a result, therapeutic strategies that modulate this immune response have gained significant interest. Polymer based nanoparticle therapies have emerged as a promising approach due to their ability to interact with and influence immune cell behavior. Importantly, the physicochemical properties of nanoparticles can be precisely tuned to optimize these effects. Among these properties, size has been shown to influence key …

Adaptive Boundary-Aware Fact-Checker Placement For Misinformation Suppression In Social Networks, Mostafa Taghizade Firouzjaee, Ghazal Naderi, Ross Gore, Neda Moghim

School of Cybersecurity Faculty Publications

The spread of fake news on online social networks is driven by imitation-based user behavior and network topology, often leading to persistent misinformation clusters and echo chambers. In this study, we develop a spatial evolutionary game-theoretic framework in which agents update their latent opinions through payoff-biased imitation, while external fact-checkers act as non-imitative intervention nodes. Building on this formulation, we propose an adaptive, boundary-aware intervention mechanism that dynamically regulates both the density and spatial allocation of fact-checkers according to real-time system conditions. Competing information clusters are identified through local neighborhood composition, enabling boundary nodes, i.e., interfaces between fake-news and non-fake-news …

Toward Secure And Practical Machine Learning-Based Access Control: A Framework With Real-World Constraints And Adversarial Analysis, Olusesi Balogun, Mohammad Ghasemigol, Zhipeng Cai, Daniel Takabi

School of Cybersecurity Faculty Publications

Attribute-Based Access Control (ABAC) frameworks coordinate access requests based on subject, object, and environment attributes, as well as policy rules, and are widely used in corporate security systems. Recently, machine learning has been applied to ABAC to address policy-generation imbalances, misassigned privileges, and attribute leakages. However, existing MLBAC techniques do not consider the structural constraints and attribute interdependencies present in traditional ABAC systems. Moreover, these frameworks have not been extensively evaluated under black-box attack scenarios. To address these gaps, we propose extensions to MLBAC that integrate structural constraints, attribute dynamism, and attribute weighting into the MLBAC objective function. Additionally, we …

A Hybrid Cnn-Lstm Surrogate Model For Hyper-Resolution Spatiotemporal Flood Forecasting In Norfolk, Virginia, Yidi Wang, Jonathan L. Goodall, Chetan Kumar, Diana Mcspadden, Sergio A. Barbosa, Binata Roy, Ali Shahabi, Navid Tahvildari

Data Science Faculty Publications

Study region

Norfolk, Virginia, United States

Study focus

Accurate and timely flood forecasting is essential for enhancing resilience in coastal urban areas in the context of increasing frequency and intensity of rainfall, sea level rise and urbanization. This study presents a hybrid deep learning-based surrogate model that integrates Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks to enable real-time spatiotemporal flood forecasting. The model leverages CNN to capture spatial features from inputs such as elevation and Topographic Wetness Index (TWI), while LSTM processes time-series inputs of rainfall and tide data to capture temporal features.

New hydrologic insights for …

Injectable Hydrogels For Bone Regeneration: Mechanical Reinforcement Strategies Using Nanoparticles And Nanofibers: Review Paper, Fariba Ganji, Morteza Mirzagoli, Lobat Tayebi

Electrical & Computer Engineering Faculty Publications

Background and Purpose: The growing demand for bone regeneration following severe injuries highlights the importance of scaffolds in bone tissue engineering (BTE). Injectable hydrogels have emerged as promising candidates because their properties closely mimic the native extracellular matrix (ECM). However, their limited mechanical strength and structural instability restrict their practical application. Approach: This review summarizes recent strategies for reinforcing in situ-forming injectable hydrogels to improve their mechanical performance for bone regeneration. Particular emphasis is placed on nanomaterial-based strategies, including the incorporation of nanoparticles and nanofibers, and their ability to enhance the physical properties of polymeric networks. Key Results: Evidence from …

Generative Imaging For Computational Pathology, Md Jillur Rahman Saurav

Computer Science and Engineering Dissertations

Hematoxylin and eosin (H&E) staining remains central to cancer diagnosis, providing morphological information essential for pathological assessment. Immunohistochemistry (IHC) and newer multiplexed imaging technologies complement H&E by revealing molecular information critical for accurate tumor subtyping and treatment decisions. In practice, however, H&E and IHC are obtained from different consecutive sections that are not spatially aligned, comprehensive multiplexed panels are expensive and tissue-consumptive, and not all stains are available at every clinical site, limiting comprehensive molecular profiling and the full diagnostic potential of these technologies in clinical practice. This dissertation addresses these gaps through three complementary generative deep learning studies in …

Co-Encapsulation Of Microalgae Haematococcus Pluvialis And Lactic Acid Bacteria Lacticaseibacillus Casei Via Filamentous Fungi Scaffolds Improved Probiotic Viability In Simulated Gastro-Intestinal Conditions, Suvro Talukdar, Tyler J. Barzee

Biosystems and Agricultural Engineering Faculty Publications

Fungal-assisted cell immobilization has emerged as a promising approach for food, energy and environmental applications, utilizing the hyphal network of filamentous fungi to encapsulate microorganisms. Co-encapsulation of multiple microorganisms within fungal pellets enables the development of food delivery systems that combine complementary functional and nutritional properties, including enhanced probiotic protection and delivery of bioactive compounds. This study used edible filamentous fungus Aspergillus awamori to encapsulate Haematococcus pluvialis microalgae and Lacticaseibacillus casei lactic acid bacteria (LAB) for probiotic delivery. Both active and heat-deactivated pellets successfully co-encapsulated microalgae and LAB, although low shear conditions were required for inactive fungal states. Under in-vitro …

Exploring Relational Farming Futures For Responsible Innovation In Precision Agriculture Through Q-Method And Speculative Design, Bhavna Joshi, Maaz Gardezi, Edward Prutzer, Awais Hameed Khan, Asim Zia, Benjamin E. K. Ryan, Ali Dadkhah, Donna M. Rizzo, John T. Mcmaine, David Clay

Biosystems and Agricultural Engineering Faculty Publications

This article draws on concepts of speculative design and responsible innovation to examine the possible impacts of data-driven precision agriculture on farmers and farm work. We use an innovative mixed-method approach to research design. Using artistic depiction of futures of precision agriculture in design workshop and in-depth semistructured interviews conducted with the farmers in Vermont and South Dakota, we explain how farmers perceive different futures of precision agriculture. Specifically, in our design workshop, we combined visual arts and social science methods, namely Q-method, to explore existing and new relationships between humans, technologies, and environment in the design, deployment, and use …

Charge‐Governed Mechanistic Evaluation Of Aav2 Clarification Via Functionalized Flat Sheet And Hollow Fiber Deconstructed Depth Filters, Mara Baughman‐Leach, Mattie Brock, Malgorzata Chwatko, Dibakar Bhattacharyya

Chemical and Materials Engineering Faculty Publications

The expansion of adeno-associated virus (AAV)-based therapeutics has increased the demand for efficient clarification. In this study, a functionalized deconstructed depth filtration platform was developed to dissect how membrane–virus charge, modulated by pH, influences separation. Three charge regimes, positive (pH 4), neutral (pH 6), and negative (pH 8) between the membranes and AAVs, were examined. The flat-sheet system, composed of sequential 1.2, 0.8, 0.45, and 0.1 µm membranes, enabled the first layer-by-layer analysis of depth filtration behavior. This revealed that Stage 1 and Stage 4 dominate clarification. Remarkably, substantial DNA capture (> 75%) was observed even in the largest-pore stage, …

Creep-Recovery Behavior Of Copper Springs At Low Stresses, Ming-Yen Tsai, Shou-Yi Chang, Yi-Chia Chou, Jyun-Lin Hu, Yulin Zhang, Fuqian Yang, Sanboh Lee

Chemical and Materials Engineering Faculty Publications

Copper springs, unlike conventional wires, endure complex stress states such as torsion and bending under sustained thermal and mechanical loads. This study examines the time-dependent creep-recovery behavior of copper springs under low tensile forces at temperatures ranging from 523 K to 623 K, focusing on springs with spring indexes (ratio of mean spring diameter to wire diameter) of 6.4, 8.5, and 9.6. The non-linear Burgers model with a Kelvin solid effectively captures the deformation response and mirrors dislocation nucleation and annihilation kinetics. SEM and TEM imaging reveal that low-angle grain boundaries (LAGBs) act as both dislocation sources and sinks. The …

Dino-Lg: Enhancing Vision Transformers With Label Guidance For Coronary Artery Calcium Detection, Mahmut Selman Gokmen, Caner Ozcan, Moneera N. Haque, Steve W. Leung, Seth Parker, Brent Seales, Cody Bumgardner

Biomedical Engineering Faculty Publications

Coronary artery disease (CAD), one of the leading causes of mortality worldwide, necessitates effective risk assessment strategies, with coronary artery calcium (CAC) scoring via computed tomography (CT) being a key method for prevention. Traditional methods, primarily based on UNET architectures implemented on pre-built models, face challenges like the scarcity of annotated CT scans containing CAC and imbalanced datasets, leading to reduced performance in segmentation and scoring tasks. In this study, we address these limitations by introducing DINO-LG, a novel label-guided extension of DINO (self-distillation with no labels) that incorporates targeted augmentation on annotated calcified regions during self-supervised pre-training. Our three-stage …

Validity And Reliability Of Force Insoles To Measure Center Of Pressure During Return-To-Sport Testing, Delaney Mcneese, Charles Eisner, Rachel Todd, Brian W. Noehren, Meredith K. Owen

Biomedical Engineering Faculty Publications

Center of pressure is a valuable biomechanical variable, predicting joint loading contributions during movement and giving insight into compensatory patterns. The purpose of this study was to assess the validity and reliability of force insoles in calculating vertical ground reaction force and center of pressure during return-to-sport jump testing. Ten healthy individuals performed double- and single-leg vertical and horizontal jumps on an instrumented treadmill while wearing instrumented force insoles. Vertical ground reaction force and anterior–posterior and medial–lateral center of pressure were collected at peak vertical ground reaction force from both devices. Repeat testing occurred 7 ± 5 days following the …

Non-Contact Optical Spectroscopy For Metabolic And Vascular Characterizations Of Orthotopic Tongue Cancer Models In Vivo, Md Zahid Hasan, Jing Yan, Sumit Sarker, Pranto Soumik Saha, Caigang Zhu

Biomedical Engineering Faculty Publications

Most tissue optical spectroscopy platforms use a fiber probe for light delivery and collection, while the inconsistent probe-sample contact could induce significant distortions in the measured optical signals, which consequently bring analysis errors. Moreover, it will be practically difficult to use a fiber probe for measurements in some cases such as oral cancer investigations using small animal models. To address the critical challenge, we report a portable, lens-based, optical spectroscopy device capable of quantifying key vascular and metabolic parameters in vivo without probe-sample contact. We combined lenses based diffuse reflectance and fluorescence spectroscopy into one portable platform to enable multi-parametric …

Combined Autofluorescence And Diffuse Reflectance Spectroscopy For Rapid Metabolic And Vascular Characterizations Of Orthotopic Tongue Tumors In Vivo, Pranto Soumik Saha, Jing Yan, Sumit Sarker, Zahid Hasan, Caigang Zhu

Biomedical Engineering Faculty Publications

Precise label-free quantification of tissue metabolic and vascular dynamics in vivo represents a critical challenge for cancer therapy prediction and longitudinal treatment assessment. In this study, we demonstrated a portable autofluorescence and diffuse reflectance spectroscopy device along with novel spectroscopic algorithms to quantify tissue vascular and metabolic parameters of orthotopic head and neck cancer models in vivo. Tissue-mimicking phantom studies were used to verify the dual-modal optical spectroscopy and easy-to-use spectroscopic algorithms for rapid and accurate estimation of tissue oxygen saturation, total hemoglobin contents, and intrinsic optical redox ratio. Animal studies were conducted to demonstrate the feasibility of our …

Noninvasive Diffuse Optical Monitoring Of Cerebral Blood Flow And Oxygenation Responses To Intermittent Hypoxia In Neonatal Rats, Pegah Safavi, Mehrana Mohtasebi, Chowdhury Azimul Haque, Faezeh Akbari, Xuhui Liu, Yiqi Yuan, Li Chen, Lei Chen, Guoqiang Yu

Biomedical Engineering Faculty Publications

Significance: Intermittent hypoxia (IH) is common in preterm neonates and can cause hypoxic–ischemic brain injury. Simultaneous monitoring of cerebral blood flow (CBF) and oxygenation is essential to detect oxygen delivery-extraction mismatches and guide intervention.

Aim: We aimed to adapt and test an innovative diffuse speckle contrast flow oximetry (DSCFO) system for continuous monitoring of cerebral hemodynamics during IH in neonatal rats, a model approximating human neonates.

Approach: Two compact laser diodes and a miniature CMOS camera were integrated into a fiber-free probe for continuous monitoring of changes in relative CBF (rCBF) and oxy- and deoxy-hemoglobin concentrations (Δ[HbO₂] and …

Simulation And Characterization Of Fuel Cell System Incorporated Internet Of Things, Ahmad N. Alhjouj

Mechanical Engineering Theses

Small air-cooled proton exchange membrane fuel cell (PEMFC) systems are increasingly relevant for portable and distributed applications, yet practical modeling and monitoring methods remain limited: high-fidelity physics-based models are too costly for real-time use, while purely data-driven models discard physical interpretability. This thesis develops an experimentally grounded gray-box framework for the characterization, reduced-order modeling, and IoT-enabled monitoring of a small hydrogen PEMFC system. A low-order nonlinear state-space model couples an electrochemical voltage layer to a lumped thermal layer, with parameters identified in stages using self-adaptive differential evolution. Identifiability analysis shows that static loss parameters are well constrained, while dynamic parameters …

Dielectric And Thermal Ageing Characteristics Of Al₂O₃ Nanofluid-Impregnated Cellulose For Power Transformer Applications, Shaymaa A. Qenawy, Basma Eltlhawy, Hussein M. Waly

Mansoura Engineering Journal

As nanotechnology progresses, nanofluids have emerged as promising candidates for transformer insulation due to their enhanced dielectric and thermal properties. This study evaluates the degradation behavior of a mineral oil-cellulose system compared to an alumina (Al₂O₃) nanofluid-cellulose system. Accelerated thermal ageing tests were conducted at 120°C for a 20-day duration, simulating approximately 20 years of field service. Key findings reveal that the nanofluid-impregnated paper exhibited superior mechanical longevity, characterized by a 3% reduction in the tensile strength deterioration rate relative to mineral oil samples. Initially, the AC breakdown voltage (BDV) of the nanofluid was 10.85% higher …

A Multiobjective Framework For Joint Coverage And Motion Planning In Uav Inspection Tasks, Luis Fernando Escobar Carvajal

Graduate Theses, Dissertations, and Problem Reports (ETD)

Unmanned Aerial Vehicles (UAVs) have become essential for data acquisition in complex 3D environments. However, traditional Coverage Path Planning (CPP) methodologies often rely on a sequential pipeline that isolates viewpoint generation from flight path routing. This decoupling fails to account for the interdependence between viewpoint distribution and minimum flight paths, effectively restricting the search space and preventing the identification of a global optimum. This dissertation proposes a unified multi-objective framework for joint coverage and motion planning. The primary contribution of this work is the transition from isolated, sequential steps to a simultaneous optimization of the number and position of viewpoints …

A Digital Calibration Source For 21 Cm Cosmology Telescopes, Kalyani Balkrishna Bhopi

Graduate Theses, Dissertations, and Problem Reports (ETD)

Precise calibration of radio telescope beams and gains is a central requirement for 21 cm intensity mapping experiments, which aim to measure large scale cosmological structure through the redshifted emission line of neutral hydrogen. Bright astrophysical foregrounds dominate the sky at these frequencies, and separating them from the cosmological signal demands precise control over instrumental systematics, particularly the telescope beam and its frequency-dependent response. Existing aerial calibration sources are incoherent broadband emitters, detectable only as total power. They provide no direct phase information and suffer from poor sensitivity in low signal-to-noise regimes.

We present the Precision Emitter for 21cm Array …

Non-Invasive Digital Restoration Of Damaged Photographic Film Negatives, Ankan Bhattacharyya

University of Kentucky Doctoral Dissertations

Physical restoration of damaged photographic film causes more damage. Also, existing non-invasive digital restoration of film negatives does not produce print-quality optical images. Instead, they produce X-ray projections, which are not the same as optical projections. This thesis addresses these problems and establishes a framework that can digitally restore old, damaged films without the need to open them physically. Virtual Unwrapping is an existing pipeline that has proven itself over the last couple of decades to work on unopenable papyrus scrolls, like the Herculaneum Scrolls. This thesis utilizes the concept of virtual unwrapping to restore damaged photographic film negatives. Due …

Radial And Carotid Arterial Pulse Signals For Assessing Cardiovascular Function At Rest And During Post-Exercise Recovery In A Heart Transplant Patient: A Case Study, Md Mahfuzur Rahman, Mamun Hasan, Jennifer F. May, John M. Herre, Leryn Reynolds, Zhili Hao

Mechanical & Aerospace Engineering Faculty Publications

Aim: This study investigates the feasibility of using radial and carotid arterial pulse signals to assess cardiovascular (CV) function at rest and during post-exercise recovery in a heart transplant (HTx) patient. Method: Two micro-fabricated tactile sensors were used to simultaneously acquire arterial pulse signals at the radial artery (RA) and carotid artery (CA). Measurements were taken at rest and at multiple time points post-exercise on three subjects: an HTx patient, a percutaneous coronary intervention (PCI; coronary stent) patient and a healthy control. An SDOF-TF-based time-frequency analysis algorithm was applied to extract a comprehensive set of CV parameters, including heart rate …

Computational Study Of Rotating Detonation Combustors, Aditya Balasubramaniam

Mechanical and Aerospace Engineering Theses

Rotating detonation combustors (RDCs) are pressure-gain combustion devices that sustain one or more continuously rotating detonation waves, offering potential thermodynamic and performance advantages over conventional deflagration-based systems. Their behavior depends strongly on combustor geometry and operating conditions. Understanding these effects is therefore essential for the design and optimization of practical RDCs. Accordingly, this thesis numerically investigates annular RDCs with two primary objectives: (1) to evaluate the effects of propellant mass flux and (2) to assess the influence of annular width on detonation-wave dynamics and combustor performance.

A finite-volume framework is used to solve the compressible reactive Euler equations with hydrogen–air …

Scalable Quantum Network Routing Through Reinforcement Learning And Resource Optimization, Tasdiqul Islam

Computer Science and Engineering Dissertations

Long-distance quantum communication depends on distributing high-delity entanglement across quantum repeaters. Entangled states are fragile: they decohere in memory, are consumed when used, and lose delity after each swap. Quantum routing therefore diers from classical routing: an algorithm must decide not only the path, but when to generate, store, swap, and consume entanglement before they lose their usefulness. This dissertation studies scalable resource allocation and routing for quantum networks under delity, memory, and concurrency constraints. It rst addresses re- peater deployment with heuristics that nd near-optimal locations while cutting com- putation from days to seconds versus integer linear programming (ILP). …

Early Detection And Objective Assessment Of Neonatal Hypoxic-Ischemic Encephalopathy Severity, Soheila Norasteh

Bioengineering Dissertations

Hypoxic–ischemic encephalopathy (HIE) is a neonatal brain injury caused by reduced oxygen and blood flow to the brain around the time of birth. It remains a major cause of neonatal mortality and long-term neurodevelopmental impairment worldwide. Therapeutic hypothermia is the standard treatment for moderate-to severe HIE and improves outcomes when initiated within the first six hours of life. Therefore, accurate assessment of injury severity during this period is essential. Cur rently, HIE severity is determined primarily through neurological examination and classified as mild, moderate, or severe. However, these examinations are subjective, cannot provide continuous monitoring of brain function, and may …

Standardization Of Neuromuscular Reflex Analysis—Role Of Fine-Tuned Vision-Language Model Consortium And Openai Gpt-Oss Reasoning Llm-Enabled Decision Support System, Eranga Bandara, Ross Gore, Sachin Shetty, Ravi Mukkamala, Christopher K. Rhea, Brittany S. Samulski, Amin Hass, Atmaram Yarlagadda, Shaifali Kaushik, Malith De Silva, Andriy Maznychenko, Inna Sokolowska, Kasun De Zoysa

VMASC Publications

Background/Objectives: Accurate assessment of neuromuscular reflexes, such as the Hoffmann reflex (H-reflex), plays a critical role in sports science, rehabilitation, and clinical neurology. Conventional interpretation of H-reflex electromyography (EMG) waveforms is subject to inter-rater variability and interpretive bias, limiting reliability and standardization. This study aims to develop an automated, interpretable, and robust agentic AI–driven framework for H-reflex waveform analysis. Methods: We propose a fine-tuned Vision–Language Model (VLM) consortium combined with a reasoning Large Language Model (LLM)–enabled decision support system for automated H-reflex interpretation. Multiple VLMs were fine-tuned on curated datasets of H-reflex EMG waveform images annotated with expert clinical observations, …