Drilling Condition Identification Method for Imbalanced Datasets by Yibing Yu, Huilin Yang, Fengjia Peng, Xi Wang

“…Secondly, a sliding-window-based Synthetic Minority Oversampling Technique (SMOTE) algorithm is developed, which generates new minority-class samples while preserving temporal dependencies, achieving balanced data distribution among classes. …”
Get full text

Designing a Sustainable Supply Chain Network for Perishable Products Integrating Internet of Things and Mixed Fleets by Lihong Pan, Xialian Li, Miyuan Shan

“…The model is solved using the Non-Dominated Sorting Genetic Algorithm II (NSGA-II). A case study based on real-world data demonstrates the model’s effectiveness. …”
Get full text

Stochastic Demand-Side Management for Residential Off-Grid PV Systems Considering Battery, Fuel Cell, and PEM Electrolyzer Degradation by Mohamed A. Hendy, Mohamed A. Nayel, Mohamed Abdelrahem

“…The optimization problem was solved using a genetic algorithm (GA), which efficiently explores the solution space to determine the optimal operating schedules and reduce degradation costs. …”
Get full text

YOLO-MES: An Effective Lightweight Underwater Garbage Detection Scheme for Marine Ecosystems by Chengxu Huang, Wenyuan Zhang, Beitian Zheng, Jiahao Li, Bochen Xie, Ruisi Nan, Zongming Tan, Baohua Tan, Neal N. Xiong

“…To address this issue, this paper introduces YOLO-MES, an innovative underwater debris detection algorithm that integrates a lightweight design and a feature enhancement mechanism to enable efficient model deployment while preserving high accuracy. …”
Get full text

Application of the Lagrange Equation for Intelligent Sensor Vibration Control for Power Network Monitoring by Xiaojing Cheng

“…The TMD natural frequency is 14.179 rad/s and the damping ratio is 0.0432 by the DH optimization method, while the TMD natural frequency is 14.1812 rad/s, and the damping ratio is 0.0436 by the augmented Lagrangian optimization algorithm. …”
Get full text

Earthquake Design of Reinforced Concrete Buildings Using NSGA-II by Herian A. Leyva, Edén Bojórquez, Juan Bojórquez, Alfredo Reyes-Salazar, José H. Castorena, Eduardo Fernández, Manuel A. Barraza

“…For this purpose, genetic algorithms (GAs) are used through the technique NSGA-II (Nondominated Sorting Genetic Algorithm), thus a multiobjective procedure with two objective functions is established. …”
Get full text

Noise-Aware UAV Path Planning in Urban Environment with Reinforcement Learning by Shahin Sarhan, Marco Rinaldi, Stefano Primatesta, Giorgio Guglieri

“…The Deep Deterministic Policy Gradient (DDPG) algorithm optimizes flight paths, minimizing the noise impact, and balancing both the path length and the population density located under the UAV path. …”
Get full text

GARMT: Grouping-Based Association Rule Mining to Predict Future Tables in Database Queries by Peixiong He, Libo Sun, Xian Gao, Yi Zhou, Xiao Qin

“…However, data sparsity—where most fields in large table sets remain unused by most queries—leads to inefficiencies in access optimization. We propose a grouping-based approach (GARMT) that partitions SQL queries into fixed-size groups and applies a modified FP-Growth algorithm (GFP-Growth) to identify frequent table access patterns. …”
Get full text

Characterizing Satellite Soil Moisture Drydown: A Bivariate Filtering Approach by Jhilam Sinha, Ashish Sharma, Lucy Marshall, Seokhyeon Kim

“…Abstract Drying of soil impacts land energy and water balance, influences the sustainability of vegetation growth, and modulates hydrological extremes including floods. While satellite soil moisture data are widely used for a range of environmental applications, systematic differences from regional in‐situ data prevent their optimal use as key physical signatures (such as soil moisture recession, also termed drydown) are represented differently. …”
Get full text

A framework to organize public transport-based crowdshipping by Meijing Zhang, Lynette Cheah

“…This approach allows transit passengers to serve as crowdshippers, ensuring that parcel delivery demand aligns with crowdshipper availability, while considering locker capacity constraints. The framework involves formulating and solving parcel assignment and vehicle routing problems, incorporating matching for parcels and lockers, and using an iterative heuristic algorithm for optimal locker selection. …”
Get full text

Slax: a composable JAX library for rapid and flexible prototyping of spiking neural networks by Thomas M Summe, Siddharth Joshi

“…To address this, we introduce Slax, a JAX-based library designed to accelerate SNN algorithm design and evaluation. Slax is compatible with the broader JAX and Flax ecosystem and provides optimized implementations of diverse training algorithms, enabling direct performance comparisons. …”
Get full text

The Footropter: A Passive Prosthetic Prescription Tool With Adjustable Forefoot and Hindfoot Stiffness by Harrison L. Bartlett, Brittany M. Moores, Brian E. Lawson, Max K. Shepherd

“…The Footropter, when paired with a preference optimization algorithm, can enable CPs to integrate patients’ experiential input into the clinical prescription process.…”
Get full text

UAV Spiral Maneuvering Trajectory Intelligent Generation Method Based on Virtual Trajectory by Tao Chen, Shaopeng Li, Yong Xian, Leliang Ren, Zhenyu Liu

“…A deep reinforcement learning (DRL) approach, employing the proximal policy optimization (PPO) algorithm, is implemented to train a policy network capable of end-to-end virtual trajectory generation. …”
Get full text

ISAC Receiver Design: Joint DoA and Data Estimation in the Presence of Incomplete Signal Observations by Iman Valiulahi, Christos Masouros, Mahmoud Alaaeldin, Emad Alsusa

“…We propose a convex optimization based on the dual of atomic norm minimization (ANM). …”
Get full text

Machine learning analysis of thermo-bioconvection in a micropolar hybrid nanofluid-filled square cavity with oxytactic microorganisms by Ahlawat Anil, Chaudhary Shilpa, Karuppusamy Loganathan, Mohammed Salman Arafath, Kandasamy Thirumalaisamy, Thameem Basha Hayath

“…In addition, a machine learning approach was employed to accurately predict fluid transport properties using a multilayer artificial neural network structured with a feed-forward backpropagation model and optimized using the Levenberg–Marquardt algorithm. …”
Get full text

Coordinated Jamming and Poisoning Attack Detection and Mitigation in Wireless Federated Learning Networks by Sofia Barkatsa, Maria Diamanti, Panagiotis Charatsaris, Stefanos Voikos, Eirini Eleni Tsiropoulou, Symeon Papavassiliou

Get full text

Efficient RANSAC in 4D Plane Space for Point Cloud Registration by Chang Liu, Chao Liu, Yuming Zhang, Zhongqi Wu, Jianwei Guo

“…3D registration methods based on point-level information struggle in situations with noise, density variation, large-scale points, and small overlaps, while existing primitive-based methods are usually sensitive to tiny errors in the primitive extraction process. …”
Get full text

A Machine Learning Approach for Predicting Particle Spatial, Velocity, and Temperature Distributions in Cold Spray Additive Manufacturing by Lurui Wang, Mehdi Jadidi, Ali Dolatabadi

“…To bypass the high cost of purely CFD-driven optimization, we construct a two-stage machine learning (ML) framework trained on 48 high-fidelity CFD simulations. …”
Get full text

Lightcone bounds for quantum circuit mapping via uncomplexity by Matthew Steinberg, Medina Bandić, Sacha Szkudlarek, Carmen G. Almudever, Aritra Sarkar, Sebastian Feld

“…We also develop an initial placement algorithm based on graph similarity search, aiding us in optimally placing circuit qubits onto a device. 600 realistic benchmarks using the IBM Qiskit compiler and a brute-force method are then tested against the lightcone bound, with results unambiguously verifying the veracity of the bound, while permitting trustworthy estimations of minimal overhead in near-term realizations of quantum algorithms. …”
Get full text

Enhancing the effectiveness of wireless sensor networks through consensus estimation and universal coverage by Hua Tian

“…The method divides the network environment into distinct regions, activating only one node per region based on its residual energy and centrality, while other nodes enter a low-energy sleep mode to conserve power. …”
Get full text