Graph2Mat: universal graph to matrix conversion for electron density prediction by Pol Febrer, Peter Bjørn Jørgensen, Miguel Pruneda, Alberto García, Pablo Ordejón, Arghya Bhowmik

“…The novel prediction model also allows for two new and promising measures of uncertainty (total charge error and self-consistency error) that will facilitate its practical usage, e.g. within active learning workflows. …”
Get full text

Implementing FFE-MLSD With Improved BER and Reduced Complexity for Long-Reach PAM4 Wireline Receivers by Hanseok Kim, Sihyun Lee, Piljun Jeong, Jaeha Kim, Woo-Seok Choi

“…This paper proposes a PAM4 receiver DSP architecture based on Feed-Forward Equalizer (FFE) and Maximum Likelihood Sequence Detector (MLSD), targeting improved bit-error-rate (BER) performance and reduced hardware complexity. …”
Get full text

Voice Spoofing Detection Through Residual Network, Max Feature Map, and Depthwise Separable Convolution by Il-Youp Kwak, Sungsu Kwag, Junhee Lee, Youngbae Jeon, Jeonghwan Hwang, Hyo-Jung Choi, Jong-Hoon Yang, So-Yul Han, Jun Ho Huh, Choong-Hoon Lee, Ji Won Yoon

“…We experimented using depthwise separable convolutions (from MobileNet) to reduce model sizes; this resulted in an 84.3 percent reduction in parameter count (from 286K to 45K), while maintaining similar performance (EER of 0.36%). …”
Get full text

Inverse estimation of the release rate of the heated pollutant source with strong convection and its application to the exhaust system design by Lei Cao, Yi Wang, Yanqiu Huang, Shengnan Guo, Junwei Guo, Yingke Zheng

“…It is also concluded that the strong convection and the measurement error both have the negative impact on the accuracy of the IESR. …”
Get full text

Deep learning-based thermal modeling of slipping velocity in oblique magnetohydrodynamic non-Newtonian nanofluid flows by Nek Muhammad Katbar, Hina Zahir, Kamel Guedri, Basim M. Makhdoum, Siti Suzilliana Putri Mohamed Isa, Syed M. Hussain, Abbas Khan

“…Statistical comparisons confirm the accuracy of ANN with a mean square error below 10^-5. The results reveal that an increase in the homogeneous reaction parameter enhances nanoparticle dispersion, thereby increasing the nanofluid temperature by approximately 18.6 % for the shear-thinning case and 22.3 % for the shear-thickening case. …”
Get full text

Cosmology with One Galaxy: Autoencoding the Galaxy Properties Manifold by Amanda Lue, Shy Genel, Marc Huertas-Company, Francisco Villaescusa-Navarro, Matthew Ho

“…In contrast, variations in other parameters such as σ _8 cause negligible error changes, suggesting galaxies shift along the manifold. …”
Get full text

Digital Code-Division Multiplexing Channel Aggregation for Mobile Fronthaul Architecture With Low Complexity by Haibo Li, Qi Yang, Songnian Fu, Ming Luo, Xiang Li, Zhixue He, Peng Jiang, Yongpiao Liu, Shaohua Yu

“…After transmission over 5 km SSMF, CWs can be error-free recovered while the LTE signals are recovered with an EVM of ∼3.6%.…”
Get full text

Forecasting tuberculosis in Ethiopia using deep learning: progress toward sustainable development goal evidence from global burden of disease 1990–2021 by Zinabu Bekele Tadese, Fetlework Gubena Arage, Tigist Kifle Tsegaw, Eyob Akalewold Alemu, Tsegasilassie Gebremariam Abate, Eliyas Addisu Taye

“…Model performance was evaluated using Root Mean Squared Error, Mean Absolute Error, Mean Absolute Percentage Error, and Symmetric Mean Absolute Percentage Error. …”
Get full text

Research on the evolution and prediction of the heights of water-conducting fracture zones in overlying rocks during layered mining of extremely thick coal seams by MENG Hailun, CHENG Xianggang, QIAO Wei

“…As the working face continued to advance, the horizontal fractures within the overlying rock layers were compacted by the layer above, the fracture aperture decreased, and the fractal dimension gradually reduced. ③ During layered mining, the fractal dimension of fractures generally exhibited four stages: ascending dimension stage, dimension reduction stage, stationary stage, and fluctuating stage. ④ The PSO-SVR model was evaluated using indicators including mean absolute error (MAE), mean bias error (MBE), and correlation index R2. …”
Get full text

Machine Learning Framework for Early Detection of Chronic Kidney Disease Stages Using Optimized Estimated Glomerular Filtration Rate by Samit Kumar Ghosh, Namareq Widatalla, Ahsan H. Khandoker

“…The application of GWO for hyperparameter tuning has resulted in a 37.3% reduction in root mean square error (RMSE), a 37.4% drop in mean absolute percentage error (MAPE), and a 2.06% improvement in <inline-formula> <tex-math notation="LaTeX">$\text {R}^{2}$ </tex-math></inline-formula> to improve the precision of prediction. …”
Get full text

D-Band 4.6 km 2 × 2 MIMO Photonic-Assisted Terahertz Wireless Communication Utilizing Iterative Pruning Deep Neural Network-Based Nonlinear Equalization by Jingwen Lin, Sicong Xu, Qihang Wang, Jie Zhang, Jingtao Ge, Siqi Wang, Zhihang Ou, Yuan Ma, Wen Zhou, Jianjun Yu

“…Additionally, the pruning process contributed to a decrease in network complexity, with a maximum reduction of 85.9% for 10 GBaud signals and 63.0% for 30 GBaud signals. …”
Get full text

Experimental study on rock fracture toughness under temperature and confining pressure coupling condition by Bo Cai, Nailing Xiu, Dongxu Li, Haifeng Fu, Xiaodong Dai, Dawei Deng, Hexiang Zhao, Xueyuan Han, Songyang Yuan, Liangang Deng

“…Key findings reveal a temperature-dependent degradation of fracture toughness (40% reduction from 25°C to 200°C at zero confining pressure) and a confining pressure-driven enhancement (76% increase from 0 to 100 MPa at ambient temperature). …”
Get full text

Surface circulation characterization along the middle southern coastal region of Vietnam from high-frequency radar and numerical modeling by T. H. Tran, T. H. Tran, A. Sentchev, T. To Duy, M. Herrmann, S. Ouillon, S. Ouillon, K. C. Nguyen

“…Both methods achieved a significant reduction (<span class="inline-formula">∼</span> 36 %–40 %) in the error of the surface current velocity fields compared to the measured data. …”
Get full text

Control of multi-level quadratic DC-DC boost converter for photovoltaic systems using type-2 fuzzy logic technique-based MPPT approaches by Souheyb Mohammed Belhadj, Bouziane Meliani, Habib Benbouhenni, Sarra Zaidi, Z.M.S. Elbarbary, Mohammed M. Alammer

“…By incorporating type-reduction and interval type-2 fuzzy logic principles, the T2FLC enhances robustness, precision, and adaptability to rapidly changing irradiance and temperature levels. …”
Get full text

Analysis of Three-Dimensional Micro-Contact Morphology of Contact Groups Based on Superpixel AMR Morphological Features and Fractal Theory by Jiahang Shen, Defeng Cui, Wenhua Li, Peidong Zhao, Xianchun Meng, Jiyuan Cai, Zheng Han, Haitao Wang

“…The model demonstrates a 15% improvement in contact area prediction accuracy and a 20% reduction in contact resistance estimation error compared to existing models. …”
Get full text

Improving Electrical Stimulation Effectiveness and Versatility for Non-Invasive Transdermal Monitoring Applications via an Innovative Mixed-Signal Electronic Interface by Alessandro Zompanti, Davide Ciarrocchi, Simone Grasso, Riccardo Olivieri, Giuseppe Ferri, Marco Santonico, Giorgio Pennazza

“…Electrical stimulation can be used in several applications such as fatigue reduction, muscle rehabilitation, neurorehabilitation, neuro-prosthesis and pain relief. …”
Get full text

Experiment and Finite Element Research on Mechanical Performance of Thin-Walled Steel–Wood Composite Columns Under Eccentric Compression by Yangfa Zhu, Jianhua Shao, Anxiang Feng, Xianglan Li, Zhanguang Wang, Hongxuan Xu, Jiajun Gao, Boshi Ma

“…Through a meticulous comparison between the test and finite element analysis results, the error was ascertained to be in the range of 4.9–11.1%. …”
Get full text

Experimental modal identification of a pedestrian bridge through drive-by monitoring integrated with shared-mobility vehicles by Kun Feng, David Hester, Su Taylor, Connor O'Higgins, Alan Ferguson, Zuo Zhu, Guang Zou, Myra Lydon, Juliana Early

“…The research presented in this paper explores the feasibility of combining two routes: (1) fleet emissions reduction and (2) transport resilience enhancement, through drive-by monitoring integrated with shared mobility, including electric mobility scooter and bicycle. …”
Get full text

AI-driven demand forecasting for enhanced energy management in renewable microgrids: A hybrid LSTM-CNN approach by Bashiru olalekan ariyo, mutalub adesina lambe, olalekan ogunbiyi, musa abdulwaheed, bilkisu jimada ojuolape, monsurat omolara balogun

“…Results: The hybrid LSTM-CNN model demonstrated superior performance, achieving an R2 value of 0.87, a Mean Absolute Error (MAE) of 1.45 MWh, and a Root Mean Squared Error (RMSE) of 2.12 MWh. …”
Get full text

Pharmacokinetic Model‐Informed Precision Dosing of Natalizumab in Multiple Sclerosis by Stefan P. H. van denBerg, Alyssa A. Toorop, Femke Hooijberg, Gertjan Wolbink, Nivea M. F. Voelkner, Liza M. Y. Gelissen, Joep Killestein, Zoé L. E. vanKempen, Thomas P. C. Dorlo, Theo Rispens

“…Corresponding precision (root mean square error) was 2.3 versus 4.0, and 1.5 versus 5 μg/mL. …”
Get full text