arXiv subjects

Mohammad Shirazi

Publications and source records attributed to Mohammad Shirazi.

7 recordsLinked to original sources

arXiv2026

Unsupervised Pattern Analysis in Japanese Veterinary Toxicology: A Regulatory-Compliant Framework for Cross-Species Risk Assessment

Veterinary pharmacovigilance systems are essential for monitoring adverse drug events (ADEs), yet existing approaches often fail to capture region-specific toxicity patterns shaped by local biological and regulatory contexts. In Japan, these challenges are amplified by species-specific metabolic differences and reporting practices defined by the Ministry of Agriculture, Forestry, and Fisheries (MAFF). Most prior work relies on prediction-oriented models, limiting mechanistic interpretability. This study proposes a regulatory-integrated unsupervised framework for pattern discovery using the National Veterinary Assay Laboratory (NVAL) database. ADEs are encoded into organ system-aligned representations and adjusted for species-specific reporting biases, enabling cross-species comparison. Similarity-based clustering and dimensionality reduction are applied to identify latent toxicity structures. Analysis of 4,120 high-confidence ADE reports (9,080 drug-ADE combinations) identified three significant species clusters (p < 0.01), including hepatic-dominant patterns in companion animals (0.42 $\pm$ 0.06), renal toxicity in ruminants (0.39 $\pm$ 0.07), and dermatological sensitivity in sheep (0.35 $\pm$ 0.07). Drug-level clustering achieved 83% alignment with pharmacological classes, while cosine similarity outperformed alternative metrics (silhouette score: 0.48; cluster precision: 87%). Regulatory validation showed strong agreement with established classifications. These findings demonstrate that regulation-aligned unsupervised analysis can uncover biologically meaningful, region-specific toxicity patterns, providing an interpretable and scalable framework for veterinary drug safety assessment.

cs.AI↗

arXiv2023

Radial limits of solutions to elliptic partial differential equations

For certain elliptic differential operators $L,$ we study the behaviour of solutions to $Lu=0,$ as we tend to the boundary along radii in strictly starlike domains in $\R^n, n\ge 3.$ Analogous results are obtained in other special domains. Our approach involves introducing harmonic line bundles as instances of Brelot harmonic spaces and approximating continuous functions by harmonic functions on appropriate subsets. These approximation theorems on harmonic spaces yield interesting examples for approximation by solutions of $Lu=0$ on some domains in $\R^n.$

math.AP↗

arXiv2023

Investigating Deep Neural Network Architecture and Feature Extraction Designs for Sensor-based Human Activity Recognition

The extensive ubiquitous availability of sensors in smart devices and the Internet of Things (IoT) has opened up the possibilities for implementing sensor-based activity recognition. As opposed to traditional sensor time-series processing and hand-engineered feature extraction, in light of deep learning's proven effectiveness across various domains, numerous deep methods have been explored to tackle the challenges in activity recognition, outperforming the traditional signal processing and traditional machine learning approaches. In this work, by performing extensive experimental studies on two human activity recognition datasets, we investigate the performance of common deep learning and machine learning approaches as well as different training mechanisms (such as contrastive learning), and various feature representations extracted from the sensor time-series data and measure their effectiveness for the human activity recognition task.

eess.SP↗

arXiv2023

Machine Learning and Hamilton-Jacobi-Bellman Equation for Optimal Decumulation: a Comparison Study

We propose a novel data-driven neural network (NN) optimization framework for solving an optimal stochastic control problem under stochastic constraints. Customized activation functions for the output layers of the NN are applied, which permits training via standard unconstrained optimization. The optimal solution yields a multi-period asset allocation and decumulation strategy for a holder of a defined contribution (DC) pension plan. The objective function of the optimal control problem is based on expected wealth withdrawn (EW) and expected shortfall (ES) that directly targets left-tail risk. The stochastic bound constraints enforce a guaranteed minimum withdrawal each year. We demonstrate that the data-driven approach is capable of learning a near-optimal solution by benchmarking it against the numerical results from a Hamilton-Jacobi-Bellman (HJB) Partial Differential Equation (PDE) computational framework.

math.OC↗

arXiv2023

Faber series for $L^2$ holomorphic one-forms on Riemann surfaces with boundary

Consider a compact surface $\mathscr{R}$ with distinguished points $z_1,\ldots,z_n$ and conformal maps $f_k$ from the unit disk into non-overlapping quasidisks on $\mathscr{R}$ taking $0$ to $z_k$. Let $Σ$ be the Riemann surface obtained by removing the closures of the images of $f_k$ from $\mathscr{R}$. We define forms which are meromorphic on $\mathscr{R}$ with poles only at $z_1,\ldots,z_n$, which we call Faber-Tietz forms. These are analogous to Faber polynomials in the sphere. We show that any $L^2$ holomorphic one-form on $Σ$ is uniquely expressible as a series of Faber-Tietz forms. This series converges both in $L^2(Σ)$ and uniformly on compact subsets of $Σ$.

math.CV↗

arXiv2021

Asymptotic first boundary value problem for holomorphic functions of several complex variables

In 1955, Lehto showed that, for every measurable function $ψ$ on the unit circle $\mathbb T,$ there is function $f$ holomorphic in the unit disc $\mathbb D,$ having $ψ$ as radial limit a.e. on $\mathbb T.$ We consider an analogous boundary value problem, where the unit disc is replaced by a Stein domain on a complex manifold and radial approach to a boundary point $p$ is replaced by (asymptotically) total approach to $p.$

math.CV↗

arXiv2019

Schiffer comparison operators and approximations on Riemann surfaces bordered by quasicircles

We consider a compact Riemann surface $R$ of arbitrary genus, with a finite number of non-overlapping quasicircles, which separate $R$ into two subsets: a connected Riemann surface $Σ$, and the union $\mathcal{O}$ of a finite collection of simply-connected regions. We prove that the Schiffer integral operator mapping the Bergman space of anti-holomorphic one-forms on $\mathcal{O}$ to the Bergman space of holomorphic forms on $Σ$ is an isomorphism. We then apply this to prove versions of the Plemelj-Sokhotski isomorphism and jump decomposition for such a configuration. Finally we obtain some approximation theorems for the Bergman space of one-forms and Dirichlet space of holomorphic functions on $Σ$ by elements of Bergman space and Dirichlet space on fixed regions in $R$ containing $Σ$.

math.CV↗