Scalable reinforcement learning for large-scale coordination of electric vehicles using graph neural networks by Stavros Orfanoudakis, Valentin Robu, E. Mauricio Salazar, Peter Palensky, Pedro P. Vergara

“…We prove that EV-GNN enhances classic Reinforcement Learning (RL) algorithms’ scalability and sample efficiency by combining an end-to-end Graph Neural Network (GNN) architecture with RL and employing a branch pruning technique. …”
Get full text

Local differential privacy-based frequent sequence mining by Teng Wang, Zhi Hu

“…Besides, PrivFSM leverages a threshold-based pruning strategy to prune fake nodes, which reduces perturbations and computation costs. …”
Get full text

Effects of Hybridizing the U-Net Neural Network in Traffic Lane Detection Process by Aron Csato, Florin Mariasiu

“…A vision-based lane detection system is difficult to implement in vehicles due to the unique characteristics of algorithms, neural network architectures, limitations, and strict hardware/software requirements. …”
Get full text

A redundant weight removal method inspired by specific immunotherapy for boosting transfer learning security by Qing Huang, Hongli Deng, Junxiang Wang, Tao Yang, Bochuan Zheng

“…Currently, redundant weights are removed mainly through pruning algorithms designed by correlating student data with teacher model nodes. …”
Get full text

Design, Fabrication, and Application of Large-Area Flexible Pressure and Strain Sensor Arrays: A Review by Xikuan Zhang, Jin Chai, Yongfu Zhan, Danfeng Cui, Xin Wang, Libo Gao

“…Fabrication techniques include 3D printing, screen printing, laser etching, magnetron sputtering, and molding, each influencing sensor performance in different ways. …”
Get full text

Defect Detection and 3D Reconstruction of Complex Urban Underground Pipeline Scenes for Sewer Robots by Ruihao Liu, Zhongxi Shao, Qiang Sun, Zhenzhong Yu

“…The Sewer-YOLO-Slim model achieves reductions of 60.2%, 60.0%, and 65.9% in model size, parameters, and floating-point operations (FLOPs), respectively, while improving the mean average precision (mAP) by 1.5%, reaching 93.5%. Notably, the pruned model is only 4.9 MB in size. Comprehensive comparisons and analyses are conducted with 12 mainstream detection algorithms to validate the superiority of the proposed model. …”
Get full text

Optimizing Beam Stiffness and Beam Modal Response with Variable Spacing and Extrusion (VaSE) by Patrick N. Murphy, Richard A. Vittum, Bashir Khoda

“…This paper presents a novel algorithm, Variable Spacing and Extrusion (VaSE), designed to optimize the infill pattern of material extrusion (ME) 3D-printed parts for specified mechanical performance while ensuring manufacturability. …”
Get full text

A Bicriteria Approach Identifying Nondominated Portfolios by Javier Pereira, Broderick Crawford, Fernando Paredes, Ricardo Soto

“…Next, a sorting process is applied on the input data or information matrix, which is intended to prune nonfeasible solutions early in the constructive algorithm. …”
Get full text

Ensemble Transformer–Based Detection of Fake and AI–Generated News by Md. Ishraquzzaman, Mohammed Ashraful Islam Chowdhury, Shahreen Rahman, Riasat Khan

“…This work leverages advanced natural language processing, machine learning, and deep learning algorithms to effectively detect fake and AI–generated content. …”
Get full text

EPO Extension of Dispatching Rules to Minimize Effects of Time Uncertainty in Production Scheduling by Radosław Puka, Iwona Skalna, Jerzy Duda, Tomasz Derlecki

“…., it has no negative impact on their most important advantage over other production scheduling algorithms. The results obtained from the real data of a large international offset printing company with various machine and job heterogeneities confirm the effectiveness of the proposed EPO extension in producing schedules that are indeed robust to changes in production time.…”
Get full text

TOPOLOGICAL IMAGE PROCESSING FOR COMPREHENSIVE DEFECT AND DEVIATION ANALYSIS USING ADAPTIVE BINARISATION by Igor Badanyuk, Igor Nevliudov, Dmytro Nikitin

“…The aim of the work is to improve the method of adaptive binarisation for images obtained by technical vision systems by developing an automatic algorithm for detecting the required value of the image binarisation window. …”
Get full text

Advanced Methods for Identifying Counterfeit Currency: Using Deep Learning and Machine Learning by Nama'a Hamed, Fadwa Al Azzo

“…Using machine learning algorithms like Random Forest, Decision Tree Classifier, XGBoost, CatBoost, and Support Vector Machine (SVM) in addition to deep learning techniques like Convolutional Neural Networks (CNNs), VGG16, MobileNetV2, and InceptionV3, we examine the security characteristics of Iraqi dinar banknotes and build robust models. …”
Get full text

A Review of Generative Design Using Machine Learning for Additive Manufacturing by Parankush Koul

“…Generative design uses complex algorithms to automate the process of designing best-fit designs, mass customization, and customization to suit specific customer requirements with high efficiency and quality. …”
Get full text

Recording dan Pencarian Silsilah Kambing Perah Menggunakan Algoritme Depth First Search by Rizki Wahyudi, Muhammad Iqbal, Lussy Dwi Oktaviana

“…To solve the problem, a Recording system is built for website-based livestock data logging and for genealogical search will use the Depth first search algorithm. In order for the research to be directed, this research uses waterfall method with stage requirement analysis, design, implementation, testing, and maintenance. …”
Get full text

UNIVERSAL INFORMATION BLOCKS AS PART OF THE DATABASE MANAGEMENT SYSTEM OF THE OPERATIONAL DUTY SHIFT OF THE СONTROL СENTER IN CRISIS SITUATIONS by A. L. Popov

“…Interfaces of information blocks are included in the composition of each workstation and provide for the processes of: entering, changing, searching and filtering data; Previewing, printing and saving documents. In the development of algorithms, original software solutions were applied: combining data prepared by several specialists, generating document details, transferring information between different workstations, monitoring the availability of documents, accessing the necessary reference information.Conclusion. …”
Get full text

Optimized AI and IoT-Driven Framework for Intelligent Water Resource Management by Mahmoud Badee Rokaya Mahmoud, Dalia Ismaeil Ibrahim Hemdan, Samah Hazzaa Alajmani, Raneem Yousif Alyami, Ghada Elmarhomy, Hassan Hashim, El-Sayed Atlam

“…The architecture combines the ensemble-learning algorithms (XGBoost, LightGBM), hybrid AIs (XGBoost + Autoencoder), and metaheuristic feature selection (GA, PSO, SA) for making intelligent decisions. …”
Get full text

Optimal in silico target gene deletion through nonlinear programming for genetic engineering. by Chung-Chien Hong, Mingzhou Song

“…In the second result, a heuristic algorithm, called GKONP, is designed to approximate the optimal solution, involving an approach to prune insignificant terms in the objective function, and the parallel differential evolution algorithm. …”
Get full text

The use of a three-dimensional mesh in plastic surgery by Rodrigo de Faria Valle Dornelles, Nivaldo Alonso, Luiz Alexandre Lorico Tissiani, Anderson Rodrigo Souza, Lúcia Nocchi Cardim

“…INTRODUCTION: Image recording as we know it today has evolved considerably from the beginning of photography by means of light printing directly onto a photosensitive material, up to the mathematical algorithms that constitute three-dimensional (3-D) meshes in stereophotogrammetry. …”
Get full text

Features of training 3d computer modeling and visualization of future teachers of informatics by O. G. Rylova

“…Questions on three-dimensional computer modeling and visualization will pass through the content line through the content of six academic disciplines («Computer graphics and multimedia», «Computational methods and computer modeling», «Programming Technologies and Algorithmization Methods», «Information Technologies in Education», «Methods teaching informatics» and «Architecture and software of computer systems»). …”
Get full text

Unsupervised learning of part similarity for goal-guided accelerated experiment design in metal additive manufacturing by Rui Liu, Sen Liu, Xiaoli Zhang

“…In this work, a similarity-based acceleration (S-acceleration) method for design of experiments is developed using K-means clustering and Gaussian Mixture Model (GMM) unsupervised learning algorithms to reduce the time and costs associated with unveiling process-property (porosity defects) relationships during manufacturing. …”
Get full text