VTechWorks
VTechWorks provides global access to Virginia Tech scholarship, including journal articles, books, theses, dissertations, conference papers, slide presentations, technical reports, working papers, administrative documents, videos, images, and more by faculty, students, and staff. Faculty can deposit items to VTechWorks from Elements, including journal articles covered by the University open access policy. Email vtechworks@vt.edu for help.
Open Access Policy
Virginia Tech's open access policy enables researchers to deposit the accepted version of scholarly articles with no embargo.
Theses and Dissertations
Virginia Tech was first in the world to require ETDs in 1997, and continues to add scans of older theses and dissertations.
Open Textbooks
More than 50 freely available and openly licensed textbooks are among our most downloaded items.
Communities in VTechWorks
Select a community to browse its collections.
Recent Submissions
Heteroskedastic Gaussian processes for ecological forecasting
Patil, Parul Vijay (Virginia Tech, 2026-10-09)
Modern stochastic simulators and ecological time series share a common challenge: they exhibit input dependent noise. In such situations, accurate predictions into the future along with principled uncertainty are essential. Heteroskedastic Gaussian processes (hetGPs) are a flexible and nonparametric modeling technique wherein, two processes are inferred simul- taneously – the mean response and the latent noise levels corresponding to input locations.
In this dissertation, I show how hetGPs are versatile and can be used in both small and large scale regimes. First, I show how hetGPs outperform other models in data-driven forecasting of sparse and irregularly sampled tick densities across several different locations. Then, I develop a Bayesian and scalable hetGP (bhetGP) to handle the scale of modern stochastic simulation campaigns without undercutting UQ. Next, I use this novel bhetGP for cali- bration of a computer model designed to forecast lake temperatures. Finally, I provide an extension to hetGPs where the noise can only be modeled for a subset of dimensions re- ducing computational cost and complexity. An open-source implementation for the bhetGP method and the extension is provided as the bhetGP R package on CRAN. Together these contributions establish hetGPs as a principled, scalable, and broadly applicable framework for ecological forecasting – one where uncertainty is a core deliverable.
Evaluating Brewery and Ethanol Industry Byproducts as Functional Ingredients in Aquaculture Diets
Pough II, Jason D.'wayne (Virginia Tech, 2026-10-09)
From Detection to Reliability: Supervised Contrastive Learning and Perception Evaluation in Dynamic Conditions for Autonomous Driving
Jiang, Boyu (Virginia Tech, 2026-10-08)
Safe autonomous driving requires both reliably detecting rare safety-critical events (SCEs) — crashes and near-crashes — and understanding when the perception systems responsible for detection can be trusted. This dissertation addresses this progression from detection to reliability.
On the detection side, this work develops representation learning frameworks grounded in Supervised Contrastive Learning (SCL). Applied to the Second Strategic Highway Research Program (SHRP 2) Naturalistic Driving Study (NDS) video data, SCL enhances intra-class cohesion and inter-class separation in the learned representation space, improving crash/near-crash/baseline classification over supervised and self-supervised contrastive benchmarks. Extending this principle to vehicle kinematics, the proposed supervised contrastive variational autoencoder (scVAE) uses a dual-encoder architecture to disentangle a label-regulated salient latent space from shared driving patterns, achieving state-of-the-art clustering and enabling scenario generation, denoising, and event prediction.
On the reliability side, this dissertation introduces Perception Characteristics Distance (PCD), a metric that quantifies the maximum distance at which a perception system remains reliable under a given decision rule. PCD models the mean and variance of perception performance as a function of distance via spline regression and variance change-point detection. Evaluated on the newly introduced SensorRainFall dataset across weather and lighting conditions, PCD reveals distance-dependent reliability characteristics that conventional static metrics overlook.
Together, these contributions provide a unified statistical paradigm for both detecting SCEs and assessing perception reliability in dynamic conditions, supporting the development and validation of safe automated driving systems.
Failure Analysis and Re-Design of an Electromagnetic Energy Harvesting Railroad Tie
Jadhav, Advait Vishal (Virginia Tech, 2026-10-08)
Advanced Rail Technologies call for intelligent and autonomous trackside monitoring, signalling and communication equipment. This equipment must be powered where it is installed, and across much of the rail network no power supply exists. The Energy Harvesting Tie developed at the Center for Vehicle Systems and Safety at Virginia Tech captures the vertical deflection of the rail under passing wheels within the enclosure of a standard composite crosstie, converting it through a ball screw and bevel gear stage into unidirectional generator rotation by half-wave mechanical motion rectification. Following instrumented laboratory and revenue-service campaigns, the first-generation prototype was left in track to expose degradation mechanisms inaccessible to short-term testing. At nine months of continuous service, it ceased to produce voltage on any generator phase, abruptly and with no preceding decline.
This thesis establishes the cause and develops a second-generation design. Teardown of the recovered unit and a failure modes and effects analysis identify degradation of the one-way clutch cage and sprags as the dominant risk driver, and reconstruct a causal chain of lost sprag positioning, lubrication loss and internally generated debris, axial migration against a compliant polymer locating member, and diversion of transmitted torque into a parasitic frictional path at the gearhead adapter joint. Eight design requirements follow, each traceable to a specific teardown observation.
Design loads are derived from the revenue-service displacement record at the electrical operating point imposing the greatest mechanical duty. A nodal torque-propagation model retaining every rotating inertia gives a peak clutch torque of 23.02 N·m at zero stress ratio, an indexing rate of 0.7-1.5 Hz, and a ball-screw axial reaction reaching 11.58 kN and shows that the conventional reduction of freewheeling inertance to the generator rotor and gearhead alone understates it significantly.
The redesign mitigates issues concerning race concentricity, axial location and gearhead torque reaction by consolidating the components, using a complete sealed clutch unit located by co-rotating metallic shoulders and a two-point supported eight-fastener generator mount in place of a cantilevered four-fastener arrangement. Every load-bearing member is verified analytically. Testing of the assembled unit over 131 compression events confirms half-wave rectification on consecutive events, validates the drivetrain kinematic chain, and recovers the machine constant in situ, with performance holding up to expectation. Instrumented revenue-service redeployment remains the necessary next step.
Computing with Spikes: Legendre-based SNNs and Deep Local Learning toward Neuromorphic Intelligence
Gaurav, Ramashish (Virginia Tech, 2026-10-08)
The pursuit of Green AI has brought Neuromorphic Computing with Spiking Neural Networks (SNNs) to the forefront as an energy-efficient alternative to conventional Artificial Neural Networks (ANNs). This dissertation advances Neuromorphic Computing along four interconnected directions: the algorithmic design of reservoir-based SNNs, their deployment on Intel's Loihi-2 neuromorphic chip, a biologically-inspired local-learning method to train deep SNNs, and real-world neuromorphic applications spanning wireless domain and event-based vision. We begin by proposing a family of Legendre Delay Network (LDN) based SNNs for Time Series Classification (TSC): the Spiking Reservoir Computing (SRC) model, the Legendre-SNN (LSNN), and the Deep Legendre-SNN (DeepLSNN). These models use the LDN as a static reservoir to extract temporal features, followed by a trainable spiking network. Herein, we present the first spiking-TSC benchmark by evaluating the DeepLSNN on 102 TSC datasets. We then address the non-trivial challenge of deploying these heterogeneous models entirely on Loihi-2 - by implementing the quantized LDN on the chip's embedded Lakemont (LMT) cores and the spiking network on its Neuro-Cores; thus, this work contributes scarce technical documentation to program the LMT cores. We next propose "DALTON" – a Three-Factor-Rule-based local-learning method that effectively leverages the depth of Convolutional SNNs. Finally, we present two real-world neuromorphic applications on Loihi-2: 5G jamming detection and drone-recognition using our newly introduced related datasets. Across our works, we find that our neuromorphic methods are not only highly energy-efficient and low-latency, but also help close the performance gap between SNNs and ANNs, thereby paving the future of neuromorphic intelligence.