arXiv subjects

Vu Thi Hanh Thu

Publications and source records attributed to Vu Thi Hanh Thu.

5 recordsLinked to original sources

arXiv2026

Hybrid Machine Learning-Assisted Raman Spectroscopy with Generative Feature Augmentation for Pharmaceutical Identification

Rapid and reliable identification of pharmaceutical residues is important for safeguarding public health, ensuring food safety, and enabling practical Raman-based screening. In this study, we propose HyMLRaman, a hybrid Raman spectroscopy framework that combines deep spectral feature extraction, generative models, and classical machine-learning classifiers to identify six pharmaceutical compounds, including amoxicillin, chloramphenicol, ciprofloxacin, tetracycline, ibuprofen, and paracetamol. Raman spectra are converted into spectral images and encoded with several deep neural-network backbones, among which EfficientNet-B3 yields the most effective representation. The resulting 1536-dimensional embeddings are then used to train downstream classifiers, including SVM, KNN, logistic regression, random forest, XGBoost, and ANN, using stratified 10-fold cross-validation. The hybrid EfficientNet-B3--SVM configuration achieves the strongest baseline performance, reaching 96.31% accuracy and a macro-F1 score of 96.36%, outperforming the standalone CNN baseline. To address limited-data conditions, a generative model, a DDPM-based feature augmentation, is introduced in a PCA-reduced EfficientNet-B3 latent space. The low-data ablation results show that DDPM augmentation provides selective benefits, particularly for KNN with reduced training fractions, and that its effect remains classifier-dependent. Finally, an application-level Raman Pharmaceutical Analyzer demonstrates the feasibility of embedding the trained model into an interactive Raman analysis workflow. These results suggest that HyMLRaman provides a practical and interpretable route for rapid Raman-based pharmaceutical screening.

cs.LG↗

arXiv2026

Anharmonic Phonon Renormalization and Defect Tolerance of the Thermoelectric Power Factor in Monolayer SnSe

Monolayer tin selenide (SnSe) exhibits phase-dependent anharmonic lattice dynamics, yet their consequences for the thermoelectric power factor (PF) and point-defect tolerance remain unresolved. We combine density functional theory, the stochastic self-consistent harmonic approximation (SSCHA), and Boltzmann transport calculations including electron-phonon and electron-defect scattering to investigate monolayer $α$-SnSe (Pnma) and $β$-SnSe (Cmcm). In dynamically stable $α$-SnSe, SSCHA renormalizes the finite-temperature phonons without changing the qualitative n-type transport picture. In $β$-SnSe, SSCHA removes the harmonic soft-mode instability of the Cmcm phase at 800-1000 K, and thereby enables high-temperature transport calculations; LO/TO-2 is the principal electron-scattering channel. In the lower-density window near $10^{12}$ cm$^{-2}$, the n-type PF reaches 15-19 $μ\mathrm{W}/(\mathrm{K}^{2}\cdot\mathrm{cm})$ at 800-900 K and exceeds the p-type PF primarily because of the higher electrical conductivity. Se vacancies ($V_{\mathrm{Se}}$) produce weaker electron-defect scattering than Sn vacancies ($V_{\mathrm{Sn}}$), and p-type transport is less defect tolerant than n-type transport in both phases. We define an operational critical defect concentration, $C_{\mathrm{crit}}$, at which the PF decreases by 15% relative to the corresponding defect-free value. The lowest $C_{\mathrm{crit}}$ is $8.841\times10^{-5}$ (approximately 88 ppm) for p-type $α$-SnSe with $V_{\mathrm{Sn}}$; for n-type $β$-SnSe with $V_{\mathrm{Se}}$, the 15% threshold is not reached up to $5\times10^{-3}$ (5000 ppm). These results distinguish finite-temperature phonon renormalization in stable $α$-SnSe from anharmonic stabilization in $β$-SnSe and provide defect-concentration limits for preserving the PF.

cond-mat.mtrl-sci↗

arXiv2025

Rapid Machine Learning-Driven Detection of Pesticides and Dyes Using Raman Spectroscopy

The extensive use of pesticides and synthetic dyes poses critical threats to food safety, human health, and environmental sustainability, necessitating rapid and reliable detection methods. Raman spectroscopy offers molecularly specific fingerprints but suffers from spectral noise, fluorescence background, and band overlap, limiting its real-world applicability. Here, we propose a deep learning framework based on ResNet-18 feature extraction, combined with advanced classifiers, including XGBoost, SVM, and their hybrid integration, to detect pesticides and dyes from Raman spectroscopy, called MLRaman. The MLRaman with the CNN-XGBoost model achieved a predictive accuracy of 97.4% and a perfect AUC of 1.0, while it with the CNN-SVM model provided competitive results with robust class-wise discrimination. Dimensionality reduction analyses (PCA, t-SNE, UMAP) confirmed the separability of Raman embeddings across 10 analytes, including 7 pesticides and 3 dyes. Finally, we developed a user-friendly Streamlit application for real-time prediction, which successfully identified unseen Raman spectra from our independent experiments and also literature sources, underscoring strong generalization capacity. This study establishes a scalable, practical MLRaman model for multi-residue contaminant monitoring, with significant potential for deployment in food safety and environmental surveillance.

cond-mat.mtrl-sci↗

arXiv2025

Point Defects Limited Carrier Mobility in Janus MoSSe monolayer

Point defects, often formed during the growth of Janus MoSSe, act as built-in scatterers and affect carrier transport in electronic devices based on Janus MoSSe. In this study, we employ first-principles calculations to investigate the impact of common defects, such as sulfur vacancies, selenium vacancies, and chalcogen substitutions, on electron transport, and compare their influence with that of mobility limited by phonons. Here, we define the saturation defect concentration ($C_{\mathrm{sat}}$) as the highest defect density that still allows the total mobility to remain within 90\% of the phonon-limited value, providing a direct measure of how many defects a device can tolerate. Based on $C_{\mathrm{sat}}$, we find a clear ranking of defect impact: selenium substituting for sulfur is relatively tolerant, with $C_{\mathrm{sat}}\approx2.07\times10^{-4}$, while selenium vacancies are the most sensitive, with $C_{\mathrm{sat}}\approx3.65\times10^{-5}$. Our $C_{\mathrm{sat}}$ benchmarks and defect hierarchy provide quantitative, materials-specific design rules that can guide the fabrication of high-mobility field-effect transistors, electronic devices, and sensors based on Janus MoSSe.

cond-mat.mtrl-sci↗

arXiv2025

Rational Design Heterobilayers Photocatalysts for Efficient Water Splitting Based on 2D Transition-Metal Dichalcogenide and Their Janus

Direct Z-scheme heterobilayers with enhanced redox potential are viewed as promising for solar-driven water splitting, arising from the synergy between intrinsic dipoles in Janus materials and interfacial electric fields across the layers. This study explores 20 two-dimensional Janus transition-metal dichalcogenide (TMDC) heterobilayers for efficient water splitting. Using density-functional theory (DFT) calculations, we screen them based on band gaps and intrinsic electric fields to identify promising candidates, then further assess carrier mobility and surface chemistry to fully evaluate their overall performance. By examining the alignment of synthetic and internal electric fields, we distinguish between Type-I, Type-II, and Z-scheme configurations, enabling the targeted design of optimal photocatalytic materials. Furthermore, we employ the Fröhlich interaction model to quantify the mobility contributions from the longitudinal optical phonon mode, providing detailed insights into how carrier mobility, influenced by phonon scattering, affects photocatalytic performance. Our findings demonstrate the potential of Janus-based Z-scheme systems to overcome existing limitations in photocatalytic water splitting by optimizing the electronic and structural properties of 2D materials, highlighting a viable pathway for advancing clean energy generation through enhanced photocatalytic processes.

cond-mat.mtrl-sci↗