This study presents an advanced computational framework that integrates a finite-difference Navier--Stokes solver, a SIMP-based topology optimization engine, and a Lagrangian particle advection module into a unified, iteratively coupled pipeline for physics-driven geometric design. The framework autonomously evolves the internal material distribution of a 2D microchannel by minimizing an objective function that directly quantifies particle mis-sorting, eliminating reliance on manual heuristic design and external actuation forces. Applied to the problem of passive microfluidic particle separation, the computational approach generated manufacturable, binary-material topologies across five opti... More >

As a classical convex optimization problem in geometry, computing the maximum inscribed ball (MaxIB) in ultra-high-dimensional polytopes is critical for enabling real-time IoT applications, such as optimal deployment of sensor networks, where polytopes model physical constraints arising from obstacles or coverage boundaries. However, existing methods suffer from the curse of dimensionality, leading to prohibitive computational costs. This paper develops a more efficient approach for computing the (1-\(\epsilon\))-approximate MaxIB in high-dimensional polytopes. To address these challenges, the problem is reformulated with adaptive penalty parameters to enforce strong convexity, enabling line... More >

Simulation-driven optimization of complex engineering systems increasingly demands intelligent frameworks capable of replacing exhaustive parameter sweeps with rapid, learned predictions. This paper presents a general surrogate optimization framework that couples high-fidelity simulation with a machine learning regression model to predict system performance and select optimal configurations without exhaustive re-simulation. Fiber-optic dispersion compensation is adopted as a representative benchmark: selecting the optimal placement strategy for dispersion-compensating fiber (DCF)-pre-, post-, or symmetrical-across varying system parameters is computationally expensive, making it an ideal t... More >

The Internet of Things (IoT) continues to expand rapidly, resulting in increasingly heterogeneous and complex wireless sensor networks (WSNs). Traditional anomaly detection approaches cannot cope with dynamic traffic patterns, high data volumes, and strict resource constraints. This study presents a hybrid XGBoost-CNN model that integrates XGBoost-based feature selection with a lightweight Convolutional Neural Network optimized for IoT environments. The proposed model was evaluated using real-world IoT traffic data and benchmarked against XGBoost, KNN, and SVM. Experimental results show that the hybrid approach improves detection accuracy by up to 2.29%, increases throughput by 8-48%, and re... More >

Accurate state estimation for dynamic targets is essential in fields such as target tracking, navigation, and autonomous driving. However, traditional estimation models struggle to handle the nonlinear motion patterns and sensor noise prevalent in real-world environments. To address these challenges, this paper proposes a novel end-to-end estimation model named Variational Neural Network with Planar Flow (VNNPF). The model integrates a Bayesian Gated Recurrent Unit (BGRU) as the process model, a planar flow-based variational autoencoder (PFVAE) as the measurement model, and a Bayesian hyperparameter optimization module inspired by Kalman filtering. The BGRU captures nonlinear temporal depend... More >

This literature review examines the state of Text-to-SQL technology, which translates natural language queries into SQL. It analyzes rule-based, neural, and hybrid approaches, assessing their strengths and weaknesses, and surveys commonly used datasets, benchmarks, and evaluation metrics. The study identifies research gaps concerning generalization, scalability, and interpretability, and suggests integrating user feedback and domain knowledge. To better understand the implementation and potential improvements of machine learning in this domain, we conducted a systematic literature review (SLR) of publications from 2015 to 2023. From 439 gathered papers, 23 were identified as highly relevant.... More >

This paper examines the vulnerability of Small and Medium-sized Enterprises (SMEs) exposed to evolving climate changes in Pakistan, specifically the impacts of extreme weather events, including floods and drought. The earlier literature illustrates that SMEs are affected by climate-related risks, but the current study takes the discussion further by implementing machine learning algorithms to measure the vulnerabilities of SMEs more objectively. A mixed-methods design was used to combine surveys with machine-learning techniques. PyCaret was employed to tune instruments such as Logistic Regression (LR), Random Forest (RF), ordered logistic regression, LightGBM, ADA Boost, SVM, KNN, GBC, and N... More >

The rapid accumulation of large-scale, long-term meteorological data presents unprecedented opportunities for data-driven weather modeling and high-resolution atmospheric prediction. While various deep learning techniques-such as Long Short-Term Memory (LSTM), Recurrent Neural Networks (RNNs), and Graph Neural Networks (GNNs)-have been explored for weather forecasting, the complex spatial dependencies within historical meteorological data, particularly dynamic spatial correlations among distributed observation stations, remain insufficiently addressed. To tackle this challenge, we propose a Dynamic Spatio-Temporal Fusion Graph Network (DSTFGN), a novel framework that integrates multivariate... More >