Pansharpening Techniques: Optimizing the Loss Function for Convolutional Neural Networks by Rocco Restaino

“…Machine-learning-based algorithms designed for this task require an extensive optimization phase of network parameters, which must be performed using unsupervised learning techniques. …”
Get full text

An Optimized LSTM Model for Diagnosis Prediction of Lower Respiratory Tract Infections Using a Minimalistic Data Set by Lukman Bukenya, Odongo Steven Eyobu, Tonny J. Oyana

“…Compared to conventional models like Bi-LSTM, Random Forest, and XGBoost, our LSTM approach achieves superior training and validation performance, with an F1 score of 90% even without extensive optimization. The study validates our model across both LRTI and non-LRTI cases, underscoring its potential as an efficient, reliable diagnostic tool for resource-limited healthcare environments.…”
Get full text

Interaction with Tactile Paving in a Virtual Reality Environment: Simulation of an Urban Environment for People with Visual Impairments by Nikolaos Tzimos, Iordanis Kyriazidis, George Voutsakelis, Sotirios Kontogiannis, George Kokkonis

“…This paper presents a virtual reality platform designed to support the development of navigation techniques within a safe yet realistic environment, expanding upon existing research in the field. Following extensive optimization, we present a visual representation that accurately simulates various 3D tile textures using graphics replicating real tactile surfaces. …”
Get full text

RAVSim v2.0: Enhanced visualization and comparative analysis for neural network models by Sanaullah, Axel Schneider, Joachim Waßmuth, Ulrich Rückert, Thorsten Jungeblut

“…Furthermore, RAVSim’s code has undergone extensive optimization and debugging, leading to a substantial ∼65% reduction in image classification simulation time compared to the previous RAVSim version. …”
Get full text

SplitAx: A novel method to assess the function of engineered nucleases. by Richard A Axton, Sharmin S Haideri, Martha Lopez-Yrigoyen, Helen A Taylor, Lesley M Forrester

“…Current methods to evaluate the activity of these nucleases are time consuming, require extensive optimization and are hampered by readouts with low signals and high background. …”
Get full text

Exploration of Machine Learning Models for Prediction of Gene Electrotransfer Treatment Outcomes by Alex Otten, Michael Francis, Anna Bulysheva

“…Tissue heterogeneity complicates the delivery process, requiring the extensive optimization of pulsing protocols currently empirically optimized. …”
Get full text

Projecting Forest Fire Probability in South Korea Under Climate Change, Population, and Forest Management Scenarios Using AI & Process-Based Hybrid Model (FLAM-Net) by Hyun-Woo Jo, Myoungsoo Won, Florian Kraxner, Seong Woo Jeon, Yowhan Son, Andrey Krasovskiy, Woo-Kyun Lee

“…Process-based models offer high interpretability through human domain knowledge but require extensive optimization, while machine learning models automatically identify important features but have limited interpretability. …”
Get full text

Understanding and detection of process instabilities in wire arc directed energy deposition additive manufacturing using meltpool imaging and machine learning by André Ramalho, Anis Assad, Benjamin Bevans, Fernando Deschamps, Telmo G. Santos, J.P. Oliveira, Prahalada Rao

“…Humping and humping-induced porosity are leading stochastic causes of poor WA-DED part quality that occur despite extensive optimization of processing conditions. It is therefore essential to understand, detect and control the causal meltpool phenomena linked to these instabilities. …”
Get full text

Chemical and Structural Versatility in the Copper/2,2′-Bipyrimidine/Iodide System: A Regular Alternating Mixed-Valent Cu(II)-Cu(I) Chain Showing Unusually Similar Metal Coordinatio... by Nadia Marino, Francesc Lloret, Miguel Julve, Giovanni De Munno

“…X-ray quality, beautifully shaped, <i>quasi</i>-black prismatic crystals of compound <b>2</b>, namely {[Cu^I(I₃)Cu^II(I)(bpm)₂](I₃)}<i>_n</i>, and brick-reddish parallelepipeds of compound <b>3</b>, namely {[Cu^I₂ (μ-I)₂(bpm)]}<i>_n</i>, were successively obtained through the slow diffusion in H-shaped tubes of aqueous solutions of the three reagents, after extensive optimization of the crystallization conditions. …”
Get full text

Fine structure of the doublet P levels of boron by Saeed Nasiri, Dmitry Tumakov, Monika Stanke, Andrzej Kędziorski, Ludwik Adamowicz, Sergiy Bubin

“…The nonrelativistic wave function of each of the states is generated in an independent variational calculation by expanding it in terms of a large number, 12000–17000, of all-electron explicitly correlated Gaussian (ECG) functions whose nonlinear parameters are extensively optimized with a procedure that employs analytic energy gradient determined with respect to these parameters. …”
Get full text

HRaccoon: A High-performance Configurable SCA Resilient Raccoon Hardware Accelerator by Ziying Ni, Ayesha Khalid, Zhaoyu Zhang, Yijun Cui, Máire O’Neill

“…The proposed FPGA architecture features extensive optimizations in key modules for Raccoon such as the modular reduction, polynomial operations, and sampling. …”
Get full text

A Machine Learning Platform for Isoform-Specific Identification and Profiling of Human Carbonic Anhydrase Inhibitors by Lisa Piazza, Miriana Di Stefano, Clarissa Poles, Giulia Bononi, Giulio Poli, Gioele Renzi, Salvatore Galati, Antonio Giordano, Marco Macchia, Fabrizio Carta, Claudiu T. Supuran, Tiziano Tuccinardi

“…<b>Methods:</b> By integrating four molecular representations with four ML algorithms, we built 64 classification models, each extensively optimized and validated. The best-performing models for each isoform were applied in a virtual screening campaign for ~2 million compounds. …”
Get full text

Study of adsorption potential of cellulose paper for abusable prescription drug analysis: A practical and sustainable approach validated by BAGI and ComplexMoGAPI tools by Torki A. Zughaibi, Ahmed I. Al-Asmari

“…Key parameters, including the number and size of filter papers, elution solvent type and volume, extraction and elution times and speeds, sample pH, and ionic strength, were extensively optimized. Validation according to SWGTOX guidelines demonstrated excellent linearity (0.05–1 µg mL-1, R² > 0.999), high precision (RSD < 11.1 %), and accuracy (85.1–113.6 %). …”
Get full text

Polara-Keras2c: Supporting Vectorized AI Models on RISC-V Edge Devices by Nizar El Zarif, Mohammadhossein Askari Hemmat, Theo Dupuis, Jean-Pierre David, Yvon Savaria

“…Polara-Keras2c enhances compatibility with bare-metal systems, incorporates RISC-V vector extension optimization, and is customized for the Polara architecture. …”
Get full text

Effect of toe box size on basketball-specific movement performance by Jialu Zhang, Jialu Zhang, Zhaowei Chu, Taoping Bai, Taoping Bai, Ming Zhang, Ming Zhang, Weiyan Ren, Zhongyou Li, Zhongyou Li, Zhongyou Li, Zhongyou Li, Wentao Jiang, Wentao Jiang, Wentao Jiang

“…A 2° SCL rotation showed no significant performance improvements (P &gt; 0.05).ConclusionOur findings suggest that shoes with enlarged TB improve both forward and lateral movements. Inward TADL extension optimizes performance by enhancing foot mobility and force transmission, while SCL rotation offers minimal benefits. …”
Get full text

Optimized Machine Learning-Augmented Hybrid Empirical Models for AlGaN/GaN HEMTs: A Comprehensive Analysis by Ahmad Khusro, Saddam Husain, Mohammad Hashmi

“…Thereafter, six extensively optimized ML regression models, namely decision tree (DT), ensemble learning (EL), support vector regression (SVR), kernel approximation regression (KAR), Gaussian process regression (GPR), and neural networks (NN) are employed to simulate the intrinsic behavior of GaN HEMTs. …”
Get full text