Hanoi University of Science and Technology

This paper introduces a pioneering, end-to-end system designed for the accurate estimation of PM2.5 concentrations, which uniquely integrates custom-designed hardware with advanced computational algorithms. A central innovation of this work is the development of a seamless data pipeline that connects real-time vehicle tracking with sophisticated air quality prediction, offering a novel and comprehensive solution for urban environmental monitoring. The system employs a cost-effective, custom-built sensor package, including PMS7003 and BME280 sensors alongside a 5MP camera, with a bespoke hardware design specifically engineered to enhance operational stability. For the estimation component, a rigorous comparative analysis was conducted, demonstrating that the Cubist regression model significantly outperforms other contemporary machine learning and traditional mathematical models; this success is attributed to its superior ability to model the complex, nonlinear relationship between observed traffic density and ambient PM2.5 levels. Furthermore, a streamlined vehicle counting algorithm, leveraging a fine-tuned YOLOv7 model, ensures robust and accurate traffic detection performance across various lighting and environmental conditions. This research successfully establishes an optimal PM2.5 estimation pipeline based on real-world vehicle counts, presenting an integrated framework for dynamic urban air quality analysis. Received: 30 August 2024 | Revised: 30 September 2025 | Accepted: 14 January 2026 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available in GitHub at https://github.com/comrang-altf4/PM2.5. Author Contribution Statement Chuong Dinh Le: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Data curation, Writing – original draft, Writing – review & editing, Visualization. Hoang Viet Pham: Conceptualization, Methodology, Software, Investigation, Data curation, Writing – original draft, Visualization. Thinh Gia Tran: Conceptualization, Methodology, Software, Validation, Investigation, Writing – original draft, Visualization. An Dinh Le: Conceptualization, Methodology, Resources, Writing – review & editing, Supervision, Project administration. Anh-Duy Pham: Conceptualization, Methodology, Resources, Supervision, Project administration. Dat Thanh Vo: Software, Writing – original draft, Visualization. Hien Bich Vo: Resources, Supervision. Dzung Huy Han: Supervision.

Reliable extraction of the cartridge case after firing is essential to the proper functioning of a gas-operated gun. This study presents a predictive model for the extraction force of a 7.62×39 mm steel cartridge case, based on the maximum chamber pressure and the contact friction coefficient (between the cartridge case and the chamber). A Central Composite Design (CCD) with two factors was used to generate the simulation data from finite element models developed in ANSYS. A reduced quadratic regression model was constructed and statistically validated, showing a high predictive capability (R2 = 0.969, adjusted R2 = 0.953). The model reveals that friction has a stronger influence on the extraction force than the maximum pressure, and that their interaction is non-linear. Experimental validation at the design centre, using a custom-built extraction test rig, yielded an average measured force of 39.10 N, closely matching the predicted value of 38.90 N (error = 0.51 %). The proposed model is a fast and reliable tool for the design and optimisation of ammunition and extractor mechanisms in small arms.

Knowledge distillation (KD) is widely recognized as an effective approach for compressing large language models (LLMs). However, standard KD methods often falter when confronted with architectural or tokenization heterogeneity between teacher and student models, which creates a mismatch in their representations. While Optimal Transport (OT) provides a promising solution to align these representations, most OT-based methods rely on a single cost function, which isn’t enough to capture the multifaceted discrepancies between models with distinct designs. To address this limitation, we introduce Multi-Cost Wasserstein Knowledge Distillation (MCW-KD), a novel framework that enhances KD by simultaneously optimizing several cost functions within a unified OT formulation. MCW-KD employs specific cost matrices to effectively align both the final hidden states and the output distributions of the models. We also provide a rigorous theoretical foundation for the proposed Multi-Cost Wasserstein Distance, ensuring both mathematical validity and computational ability. Extensive experiments on instruction-following datasets demonstrate that MCW-KD significantly improves student model performance compared to state-of-the-art KD baselines, especially when teacher and student models have different tokenizers.

Continuum robots, characterized by their hyper-redundant and flexible structures, have gained significant attention in fields such as minimally invasive surgery, remote inspection, and soft manipulation. Their complex design and highly nonlinear kinematic behavior present substantial modeling and control challenges. This paper presents a complete framework encompassing the design, modeling, and inverse kinematics solution for a novel two-segment, tendon-driven continuum robot utilizing an elastic spring backbone for enhanced compliance and structural simplicity. A constant curvature forward kinematic model is presented. Subsequently, an efficient numerical approach for solving the challenging inverse kinematics problem is introduced by adapting the Jacobian-based Newton-Raphson method and incorporating the Moore-Penrose Pseudoinverse. This strategy effectively manages the robot's redundancy, ensuring smooth and reliable trajectory generation. Experimental verification confirms the robot's feasibility, demonstrating that the system successfully navigates along the trajectories computed by the inverse kinematics, thus validating the reasonableness of the kinematic model and ensuring seamless and smooth operation. These findings provide a robust foundation for improving motion planning of simple continuum robot platforms in practical applications.