Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2503.06109

Human Mobility Reimagined: Digital Twin Intelligence for Adaptive Campus Course Timetabling

Keshu Wu·Xinyue Ye·Suphanut Jamonnak·Xin Feng
View original source ↗Read source document ↗Export metadata ↓

Abstract

Daily operations in large campuses depend on how efficiently people \emph{move} through space and time. In this sense, course timetables are more than administrative schedules: they act as mobility policies that orchestrate thousands of trajectories, shaping travel burden, congestion, accessibility, and the reliability of back-to-back transitions. Designing timetables that are both feasible and mobility-friendly is challenging because hard constraints including capacity, conflicts, feasibility must be satisfied alongside soft constraints including preferences, satisfaction, coordination, all under dynamic conditions such as real-time disruptions and evolving demand. Traditional static optimization methods often struggle to capture these human mobility impacts and to adapt when campus conditions change. This paper reconceptualizes course timetabling as a recommendation-based task and leverages the Texas A\&M Campus Digital Twin as a dynamic data platform to evaluate mobility consequences at scale. We propose an iterative framework that integrates collaborative and content-based filtering with feedback-driven refinement to generate ranked sets of adaptive timetable recommendations. A mobility-aware composite scoring function combining classroom occupancy, travel distance, travel time, and vertical transitions systematically balances resource efficiency with human-centered movement costs. Extensive experiments using real-world data from Texas A\&M University show that the proposed approach reduces mobility friction and travel inefficiencies, improves classroom utilization, and enhances overall user satisfaction. By coupling recommendation-oriented decision-making with digital twin intelligence, this study provides a robust and scalable blueprint for mobility-centered campus planning and resource allocation, with potential extensions to broader urban systems.

Explore related subjects

cs.CE

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Keshu Wu, Xinyue Ye, Suphanut Jamonnak, Xin Feng. 2025-12-14. Human Mobility Reimagined: Digital Twin Intelligence for Adaptive Campus Course Timetabling. https://arxiv.org/abs/2503.06109

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Dimension Bridging for 3D RANS with Neural Network Accelerated Gaussian Functional Regression

In many computational science and engineering problems, repeatedly solving fully resolved physics-based models to design for a quantity of interest (QoI) can quickly become intractable, requiring the use of low-fidelity models to predict the same QoI but introduce errors where some features are neglected or are otherwise inaccurately resolved. We use Gaussian Functional Regression (GFR) to learn a correction to a 2D Reynolds-Averaged Navier-Stokes (RANS) model to predict the aerodynamic coefficients from a 3D RANS model. This model pair has a disparity in the governing physics from the reduced dimensionality, a previously unexplored application for GFR. Empirically, our results show that with a proper choice of low-dimensional (LD) model, the proposed kernel allows for the use of fewer high-dimensional (HD) evaluations to regress a response surface to the same level of accuracy as standard stationary kernels. Moreover, the new kernel provides more informative uncertainty quantification, which we show is advantageous when used to drive an adaptive sampling algorithm. Finally, we propose a novel neural network accelerated kernel, which we show offers predictions in good agreement while speeding up evaluations by millions of times in wall clock measurements, bringing the computational budget within the real-time regime.

cs.CE↗
arXiv2026

SabreAgent: Language Models at Design Time for Lost-Sales Inventory Control

SabreAgent uses a language model at design time to construct two components for lost-sales inventory control: a product-specific seasonal prior and a validation-selected capped base-stock policy family. During operation, statistical forecasting and inventory optimization use these frozen artifacts to determine orders, with zero language-model calls. We evaluate the approach on the $1{,}320$ instances of InventoryBench. Under the benchmark's cost assumptions, the operations-research core draws on a zero-lead-time optimality result and a projected-inventory rule for positive deterministic lead times. The latter computes replenishment shortfalls by propagating inventory using sales along simulated demand paths. The seasonal prior adds forecast variants alongside the original forecaster, and the selected policy family handles stochastic lead times with order destruction. SabreAgent scores $0.6311$, compared with $0.5380$ for the strongest published baseline, and ranks first in all six benchmark cells. Ablations attribute most of the gain to the OR core. In the paired analysis, the seasonal component adds $1.79\%$ across the three real-data cells, and the search component adds $2.3\%$ across the two stochastic-lead-time cells. These results demonstrate how model-generated priors and policy structure can improve an OR controller through design-time use.

cs.CE↗
arXiv2026

Hierarchical Multi-Task Learning with Liquidity-Aware Signals for Stock Forecasting

Stock price forecasting is a long-standing challenge in computational finance, driven by the inherent randomness of markets and complex temporal patterns. While recent deep-learning models have raised forecasting accuracy by jointly modeling inter-stock and temporal price dynamics, they conflate inter-stock relationships with intra-stock temporal dependencies and focus solely on the univariate objective of price movement. To address these limitations, we propose LiMT, a Hierarchical Multi-Task Learning framework that integrates liquidity-aware signals for stock price forecasting. LiMT employs a Market Regime Encoder (MRE) module that first extracts contemporaneous cross-stock dependencies, then models each stock's temporal dynamics, yielding a unified latent state. Building on this latent state, we introduce a Liquidity-Driven Learning (LDL) module, a mixture-of-experts architecture that features cross-task gating mechanisms to jointly predict price movement, volatility, and trading volume. We further design an Adaptive Portfolio Optimization (APO) mechanism that converts multi-task forecasts into executable portfolio weights under transaction-cost and liquidity constraints. Extensive experiments on the CSI300 and CSI500 benchmarks show that LiMT performs best among strong neural and tree-based baselines across the reported metrics. In realistic CSI300 backtests, APO improves annualized return from 3.99% to 10.01% and Sharpe ratio from 1.22 to 1.86 over equal weighting, showing that the multi-task forecasts translate into deployable portfolio gains.

cs.CE↗