arXiv subjects

Katayoun Eshkofti

Publications and source records attributed to Katayoun Eshkofti.

4 recordsLinked to original sources

arXiv2026

Generalizability of Learning-based Occupancy Detection in Residential Buildings (extended version)

This paper investigates non-intrusive occupancy detection methods for residential buildings using environmental sensor data from the KTH Live-In Lab in Stockholm, Sweden. Three machine learning approaches, namely, logistic regression (LR), support vector machines (SVM), and long short-term memory (LSTM) network enhanced with an attention mechanism, are evaluated in terms of predictive performance and computational complexity. The analysis considers the trade-off between sensor availability (investment cost) and prediction accuracy in real applications, as well as the models' cross-apartment generalizability. Hyperparameters for both the SVM and LSTM models are optimized using Bayesian optimization. All three models are evaluated on data collected from apartments not used during training, and on data generated from a calibrated digital model of the testbed. Results show that all models achieve comparable performance on the same-apartment test data (accuracy of approximately 0.83, F1 score of approximately 0.86). When assessed on cross-apartment data, the LSTM model demonstrates the strongest generalization capability (accuracy of 0.84, F1 score of 0.85), while LR provides a competitive, low-complexity alternative for applications that do not require cross-apartment generalization.

eess.SY↗

arXiv2026

Curriculum-Learned Vanishing Stacked Residual PINNs for Hyperbolic PDE State Reconstruction

Modeling distributed dynamical systems governed by hyperbolic partial differential equations (PDEs) remains challenging due to discontinuities and shocks that hinder the convergence of traditional physics-informed neural networks (PINNs). The recently proposed vanishing stacked residual PINN (VSR-PINN) embeds a vanishing-viscosity mechanism within stacked residual refinements to enable a smooth transition from the parabolic to hyperbolic regime. This paper integrates three curriculum-learning methods as primal-dual (PD) optimization, causality progression, and adaptive sampling into the VSR-PINN. The PD strategy balances physics and data losses, the causality scheme unlocks deeper stacks by respecting temporal and gradient evolution, and adaptive sampling targets high residuals. Numerical experiments on traffic reconstruction confirm that enforcing causality systematically reduces the median point-wise MSE and its variability across runs, yielding improvements of nearly one order of magnitude over non-causal training in both the baseline and PD variants.

cs.NE↗

arXiv2025

Modeling and Physics-Enhanced Fault Detection in Wastewater Pump Stations

Monitoring wastewater pump stations is essential because they are critical infrastructure. However, monitoring is still often performed manually due to the lack of suitable algorithmic methods and data. This paper introduces a high-fidelity, physics-enhanced simulator of a three-pump wastewater station that captures transient hydro-mechanical dynamics at a one-second resolution. The simulator is fully parameter-driven, adaptable to other wastewater stations, and capable of generating datasets for data-driven analytics. It can also generate balanced faulty datasets when real failures are scarce or confidential. A comparison with high-frequency SCADA data from a municipal station shows strong agreement across key operational metrics. Furthermore, the paper proposes robust statistical and mathematical frameworks for fault detection and isolation, including a nested-model F-test to detect pump degradation or system faults, and a tangent residual approach to distinguish pump faults from system faults using operating-point kinematics. This framework enables what-if studies, facilitates early fault diagnosis based on flow rate and head, and provides actionable insights for condition-based maintenance in wastewater pumping infrastructure.

eess.SY↗

arXiv2025

Vanishing Stacked-Residual PINN for State Reconstruction of Hyperbolic Systems

In a more connected world, modeling multi-agent systems with hyperbolic partial differential equations (PDEs) offers a compact, physics-consistent description of collective dynamics. However, classical control tools need adaptation for these complex systems. Physics-informed neural networks (PINNs) provide a powerful framework to fix this issue by inferring solutions to PDEs by embedding governing equations into the neural network. A major limitation of original PINNs is their inability to capture steep gradients and discontinuities in hyperbolic PDEs. To tackle this problem, we propose a stacked residual PINN method enhanced with a vanishing viscosity mechanism. Initially, a basic PINN with a small viscosity coefficient provides a stable, low-fidelity solution. Residual correction blocks with learnable scaling parameters then iteratively refine this solution, progressively decreasing the viscosity coefficient to transition from parabolic to hyperbolic PDEs. Applying this method to traffic state reconstruction improved results by an order of magnitude in relative $\mathcal{L}^2$ error, demonstrating its potential to accurately estimate solutions where original PINNs struggle with instability and low fidelity.

eess.SY↗