Experimental Determination and Comparative Analysis of the PPH030GP, ABS and PLA Polymer Strength Characteristics at Different Strain Rates by M. Yu. Zalohin, V. V. Skliarov, Ja. S. Dovzhenko, D. A. Brega

“…All the samples have been made according to the requirements of GOST 11262–80 and subjected to uniaxial stretching on a tensile machine UIT STM 050/300 at different speeds of clamp expansion. …”
Get full text

Comparison of Deep Transfer Learning Against Contrastive Learning in Industrial Quality Applications for Heavily Unbalanced Data Scenarios When Data Augmentation Is Limited by Amir Farmanesh, Raúl G. Sanchis, Joaquín Ordieres-Meré

“…Computational analysis reveals that DTL requires 40% less training time and 25% fewer parameters while maintaining superior generalization capabilities. …”
Get full text

Low-light image enhancement method for underground mines based on an improved Zero-DCE model by WANG Yiwei, LI Xiaoyu, WENG Zhi, BAI Fengshan

“…Underground coal mine surveillance images suffer from noise, low clarity, missing color, and texture information. Additionally, machine learning-based image enhancement methods face challenges in collecting paired low-light and normal-light image datasets. …”
Get full text

Jidoka-DT simulator programmed by hybridize XGboost-LSTM to evaluate helmets quality produced by Rice-Straw-alumina plastic dough to resist shocks and impenetrable by Ahmed M. Abed, Ahmed Fathy, Radwa A. El Behairy, Tamer S Gaafar

“…The dough has been tested via a Digital Twin (DT) simulator that relies on human dexterity in mapping the helmet surface as a finite element (FEM) that is called Jidoka-DT. The mixture machine is connected to many sensors that track the values of significant parameters, such as temperature, moisture, viscosity, Reynolds number, crack resistance, and compressibility, that affect helmet manufacturing via injecting RSA composition towards mould. …”
Get full text

Ensembling a Learned Volterra Polynomial with a Neural Network for Joint Nonlinear Distortions and Mismatch Errors Calibration of Time-Interleaved Pipelined ADCs by Yan Liu, Mingyu Hao, Hui Xu, Xiang Gao, Haiyong Zheng

“…Limited by prior modeling, conventional digital calibration methods only correct partial errors, while machine learning (ML) approaches achieve comprehensive calibration at a high computational cost. …”
Get full text

Construction and Application of Carbon Emissions Estimation Model for China Based on Gradient Boosting Algorithm by Dongjie Guan, Yitong Shi, Lilei Zhou, Xusen Zhu, Demei Zhao, Guochuan Peng, Xiujuan He

“…Key variables were selected through correlation analysis, missing values were interpolated using K-means clustering, and model parameters were systematically optimized via grid search and cross-validation. …”
Get full text

A comprehensive analysis of model poisoning attacks in federated learning for autonomous vehicles: A benchmark study by Suzan Almutairi, Ahmed Barnawi

“…Due to the increase in data regulations amid rising privacy concerns, the machine learning (ML) community has proposed a novel distributed training paradigm called federated learning (FL). …”
Get full text

Application of Atmospheric Gases and Particulate Matter to the Assessment of Urban Heat Island by Christian Mark Salvador, Pablo Fernandez, Kelsey Carter, Joanna Tannous, David Weston, Christopher DeRolph, Melanie A. Mayes

“…Conclusion This study concludes that VOCs provide more direct and accurate information than typical inorganic gases and PM parameters for characterizing the degree of urbanization. …”
Get full text

Geohazard impact and gas reservoir pressure dynamics in the Zagros Fold-Thrust Belt: An environmental perspective by Mahsa Asghari, Zahra Maleki, Ali Solgi, Mohammad Ali Ganjavian, Pooria Kianoush

“…A novel hybrid model is introduced that integrates geographic information system (GIS) mapping, decision support system (DSS) modeling, and machine learning algorithms. By analyzing a century's worth of seismic data alongside real-time environmental parameters, the model demonstrates a predictive accuracy of 92% using Random Forest algorithms, significantly outperforming traditional methods. …”
Get full text

Modeling seismic hazard and landslide occurrence probabilities in northwestern Yunnan, China: exploring complex fault systems with multi-segment rupturing in a block rotational tec... by J. Cheng, C. Xu, X. Xu, S. Zhang, P. Zhu

“…On average, these values are higher than the PGA given by the China Seismic Ground Motion Parameters Zonation Map. Furthermore, we utilized PGA values with the Bayesian probability method and a machine learning model to predict landslide occurrence probabilities as a function of our PGA distribution map. …”
Get full text

Integrated GBR–NSGA-II Optimization Framework for Sustainable Utilization of Steel Slag in Road Base Layers by Merve Akbas

“…This study proposes an integrated, machine learning-based multi-objective optimization framework to evaluate and optimize the utilization of steel slag in road base layers, simultaneously addressing economic costs and environmental impacts. …”
Get full text

Prediction of Metal Additively Manufactured Bead Geometry Using Deep Neural Network by Min Seop So, Mohammad Mahruf Mahdi, Duck Bong Kim, Jong-Ho Shin

“…This study addresses the challenges of bead geometry prediction by developing a robust predictive framework. Key process parameters, such as the wire travel speed, wire feed rate, and bead dimensions of the previous layer, were monitored using a Coordinate Measuring Machine (CMM) to ensure precision. …”
Get full text

A New Algorithm for the Global-Scale Quantification of Volcanic SO₂ Exploiting the Sentinel-5P TROPOMI and Google Earth Engine by Maddalena Dozzo, Alessandro Aiuppa, Giuseppe Bilotta, Annalisa Cappello, Gaetana Ganci

“…Firstly, we used the Simple Non-Iterative Clustering segmentation method, which is an object-based image analysis approach; secondly, the K-means unsupervised machine learning technique is applied to the segmented images, allowing a further and better clustering to distinguish the SO₂. …”
Get full text

Federated Learning Based on an Internet of Medical Things Framework for a Secure Brain Tumor Diagnostic System: A Capsule Networks Application by Roman Rodriguez-Aguilar, Jose-Antonio Marmolejo-Saucedo, Utku Köse

“…This technique ensures the secure exchange of sensitive patient and institutional data. It enables machine learning or deep learning algorithms to establish a client–server relationship, whereby specific parameters are securely shared between models while maintaining the integrity of the learning tasks being executed. …”
Get full text

Improved breast cancer risk prediction using chromosomal-scale length variation by Yasaman Fatapour, James P. Brody

“…We computed a set of 88 values for each woman in the dataset, representing the chromosomal-scale length variation parameters. These numbers are average log R ratios for four different segments from each of the 22 autosomes. …”
Get full text

Protection of liver sinusoidal endothelial cells using different preservation solutions by Julia H E Houtzager, Anne-Marieke van Stalborch, Charlotte Hofstee, Thomas M van Gulik, Jaap D van Buul

“…Differences in these parameters were analyzed between the different preservation solutions. …”
Get full text

PermQRDroid: Android malware detection with novel attention layered mini-ResNet architecture over effective permission information image by Kazım Kılıç, İbrahim Alper Doğru, Sinan Toklu

“…The proposed architecture has a low number of parameters and memory consumption despite adding the residual layer and the weighting operations in the attention layer. …”
Get full text

A new approach for improving dynamic fault ride through capability of gridctied based wind turbines by Shoaib Ahmed Dayo, Ahsanullah Memon, Zeeshan Anjum Memon, Touqeer Ahmed Jumani, Ghulam Abbas, Salwa Othmen, Amr Yousef, Andika Aji Wijaya

“…The proposed method is validated by comparative analyses with recent studies that showcase its superiority in refining machine dynamics and decreasing overshoots and transients. …”
Get full text

Gaussian Process Regression Total Nitrogen Prediction Based on Data Decomposition Technology and Several Intelligent Algorithms by WANG Yongshun, CUI Dongwen

“…Total nitrogen (TN) is one of the important indicators to reflect the degree of water pollution and measure the eutrophication status of lakes and reservoirs.To improve the accuracy of TN prediction,based on the empirical wavelet transform (EWT) and wavelet packet transform (WPT) decomposition technology,this paper proposes a Gaussian process regression (GPR) prediction model optimized by osprey optimization algorithm (OOA),rime optimization algorithm (ROA),bald eagle search (BES) and black widow optimization algorithm (BWOA) respectively.Firstly,the TN time series is decomposed into several more regular subsequence components by EWT and WPT respectively.Then,the paper briefly introduces the principles of OOA,ROA,BES,and BWOA algorithms and applies OOA,ROA,BES,and BWOA to optimize GPR hyperparameters.Finally,EWT-OOA-GPR,EWT-ROA-GPR,EWT-BES-GPR,EWT-BWOA-GPR,WPT-OOA-GPR,WPT-ROA-GPR,WPT-BES-GPR,WPT-BWOA-GPR models (EWT-OOA-GPR and other eight models for short) are established to predict the components of TN by the optimized super-parameters.The final prediction results are obtained after reconstruction,and WT-OOA-GPR,WT-ROA-GPR,WT-BES-GPR and WT-BWOA-GPR models based on wavelet transform (WT) are built.Eight models,including EWT-OOA-SVM based on support vector machine (SVM),the paper compares the unoptimized EWT-GPR,WPT-GPR models,and the uncomposed OOA-GPR,ROA-GPR,BES-GPR,and BWOA-GPR models.The models were verified by the monitoring TN concentration time series data of Mudihe Reservoir,an important drinking water source in China,from 2008 to 2022.The results are as follows.① The average absolute percentage error of eight models such as EWT-OOA-GPR for TN prediction is between 0.161% and 0.219%,and the coefficient of determination is 0.999 9,which is superior to other comparison models,with higher prediction accuracy and better generalization ability.② EWT takes into account the advantages of WT and EMD.WPT can decompose low-frequency and high-frequency signals at the same time.Both of them can decompose TN time series data into more regular modal components,significantly improving the accuracy of model prediction,and the decomposition effect is better than that of the WT method.③ OOA,ROA,BES,and BWOA can effectively optimize GPR hyperparameters and improve GPR prediction performance.…”
Get full text

Temporal Convolutional Network Approach to Secure Open Charge Point Protocol (OCPP) in Electric Vehicle Charging by Ikram Benfarhat, Vik Tor Goh, Chun Lim Siow, Muhammad Sheraz, Teong Chee Chuah

“…The primary challenge within EVCS architecture lies in defending against various cyberattacks. Several machine learning models, including convolutional neural networks, recurrent neural networks, and long short-term memory, have been employed to enhance EVCS security. …”
Get full text