Seasonally Adaptive VMD-SSA-LSTM: A Hybrid Deep Learning Framework for High-Accuracy District Heating Load Forecasting by Yu Zhang, Keyong Hu, Lei Lu, Qingqing Yang, Min Fang

“…Notably, the MAPE values are reduced to 1.3824%, 0.9549%, 6.4018%, and 1.3272%, with average error reductions of 9.4873%, 3.8451%, 6.6545%, and 6.5712% compared to alternative models. …”
Get full text

Mapping the most effective measures to optimize carrot slice tray drying using physics-based and Monte Carlo simulations by Jörg Schemminger, Sharvari Raut, Barbara Sturm, Thijs Defraeye

“…The results of this study support the identification of the ideal case-specific optimization strategies and thus help to avoid costly trial-and-error approaches in the future.…”
Get full text

Increased virtual resolution for sub-pixel displacement algorithm optimization in digital image correlation for AISI 1020 steel by Silmara M. Cardoso, Maurício M. Ribeiro, Douglas S. Silva, Raí Felipe P. Junio, Sergio N. Monteiro, Jean da S. Rodrigues

“…The results showed a reduction in the error observed in synthetic images with increased magnification and good agreement with the deformation data obtained using the conventional extensometry technique.…”
Get full text

Research on multi-scenario adaptive acoustic encoders based on neural architecture search by Yiliang Wu, Yiliang Wu, Xuliang Luo, Xuliang Luo, Fengchan Guo, Tinghui Lu, Tinghui Lu, Cuimei Liu

“…The SAAE method achieves an average error rate reduction of more than 5% compared with existing acoustic encoders, highlighting its capability to deeply analyze speech features in specific scenarios and design high-performance acoustic encoders in a targeted manner.…”
Get full text

Dyadic Probabilistic Shaping of PAM-4 and PAM-8 for Cost-Effective VCSEL-MMF Optical Interconnection by Lin Sun, Chang Wang, Jiangbing Du, Chenyu Liang, Wenjia Zhang, Ke Xu, Fan Zhang, Zuyuan He

“…Energy efficient signaling can be achieved with up to 46% theoretical power reduction by PS. Experimentally, we obtained 16% reduction of optical power for the VCSEL-MMF optical link. …”
Get full text

Denoising Autoencoder and Contrast Enhancement for RGB and GS Images with Gaussian Noise by Armando Adrián Miranda-González, Alberto Jorge Rosales-Silva, Dante Mújica-Vargas, Edwards Ernesto Sánchez-Ramírez, Juan Pablo Francisco Posadas-Durán, Dilan Uriostegui-Hernandez, Erick Velázquez-Lozada, Francisco Javier Gallegos-Funes

“…However, external factors, such as adverse environmental conditions or errors in data transmission, can alter the captured image, leading to information loss. …”
Get full text

A Near-Infrared Imaging System for Robotic Venous Blood Collection by Zhikang Yang, Mao Shi, Yassine Gharbi, Qian Qi, Huan Shen, Gaojian Tao, Wu Xu, Wenqi Lyu, Aihong Ji

“…The average error of the optimized AD-Census stereo matching algorithm is reduced by 25.69%, and the improvement of the image stereo matching performance is more obvious. …”
Get full text

A neural network-based synthetic diagnostic of laser-accelerated proton energy spectra by Christopher J. G. McQueen, Robbie Wilson, Timothy P. Frazer, Martin King, Matthew Alderton, Ewan F. J. Bacon, Ewan J. Dolier, Thomas Dzelzainis, Jesel K. Patel, Maia P. Peat, Ben C. Torrance, Ross J. Gray, Paul McKenna

“…Trained on data from fewer than 700 laser-plasma interactions, the model achieves an error level of 13.5%, and improves with more data. …”
Get full text

The Influence of Variable Operating Conditions and Components on the Performance of Centrifugal Compressors in Natural Gas Storage Reservoirs by Hua Chen, Gang Li, Shengping Wang, Ning Wang, Lifeng Zhou, Hao Zhou, Yukang Sun, Lijun Liu

“…Verification results show that the conversion error of this method is within 2%. Based on the proposed performance prediction method for non-similar operating conditions, the effects of varying inlet temperatures, pressures, and natural gas compositions on compressor performance are investigated. …”
Get full text

A Reduced-Order Algorithm for a Digital Twin Model of Ultra-High-Voltage Valve-Side Bushing Considering Spatio-Temporal Non-Uniformity by Yongsheng He, Yongfu Li, Xiangcheng Li, Yanan Yuan, Fan Yang, Zongxiang Lu

“…This proposed method reduces the calculation time to 10% of the full-order simulation model while controlling the error range of the key research area less than 0.1%. …”
Get full text

The Impact of Rain on Image Quality From Sensors on Connected and Autonomous Vehicles by Tim Brophy, Darragh Mullins, Robert Cormican, Enda Ward, Martin Glavin, Edward Jones, Brian Deegan

“…The results show a 45% reduction in SNR at 40 m and 38 mm/h, a 70% maximum decrease in Weber contrast at 30 m and 38 mm/h, and a 42% increase in color error as a result of rain in the environment. …”
Get full text

DCT-DiffPose: A Lightweight Diffusion Model With Multi-Hypothesis for 3D Human Pose Estimation by Linzhan Zhong, Fangni Chen, Bolun Zheng, Rui Feng, Lei Zhang, Jian Wan

“…Our method achieves a 19% lower Mean Per Joint Position Error (MPJPE) and a 55% reduction in FLOPs compared to D3DP. …”
Get full text

Service-Life Study of Polycarbonate Outdoors Using Python with Incomplete Data by Jiangfeng An, Duncheng Peng, Xuejie Zhou, Jun Wu, Penghua Zheng

“…The results indicated that (1) the degradation of PC tensile properties is mainly affected by the experimental period (76.37%), whilst the effect of the environmental or pollutant factors on the degradation is less pronounced (23.63%); (2) the classification accuracy of the trained model on the training set is 91% (91/100), and on the testing set is 72.13% (44/61); and lastly, (3) it is inferred from the error analysis of the classification results that the performance change of polycarbonate in Qionghai and Wuhan is characterized by an initial reduction followed by a slight improvement. …”
Get full text

A deep neural network framework for estimating coastal salinity from SMAP brightness temperature data by Yidi Wei, Qing Xu, Qing Xu, Xiaobin Yin, Xiaobin Yin, Yan Li, Yan Li, Kaiguo Fan

“…The framework leverages machine learning interpretability tools (Shapley Additive Explanations, SHAP) to optimize input feature selection and employs a grid search strategy for hyperparameter tuning.Results and discussionSystematic validation against independent in-situ measurements demonstrates that the baseline DNN model constructed for the entire region and time period outperforms conventional algorithms including K-Nearest Neighbors, Random Forest, and XGBoost and the standard SMAP SSS product, achieving a reduction of 36.0%, 33.4%, 40.1%, and 23.2%, respectively in root mean square error (RMSE). …”
Get full text

Mine cable partial discharge denoising method based on multivariate variational mode decomposition and improved wavelet threshold by Jiyuan CAO, Yanwen WANG, Peng CHEN, Xuan ZHOU, Weixiong ZHU, Yihe ZHANG, Le WANG

“…The partial discharge characteristic signal is classified as gross error by 3σ criteria, and the Gaussian white noise and narrow-band interference signal in the noise dominant component are inversely suppressed. …”
Get full text

Research on obstacle avoidance for aerial work vehicle booms with light arrays based on an improved gradient projection method by Yi HUANG, Lei DENG, Kangyi DENG, Qin SHU, Guangan REN, Zhihong ZHOU

“…At the same time, the end position error reduction algorithm is added to reduce the end velocity and improve the trajectory tracking accuracy. …”
Get full text

Synchronization and demodulation of LoRa null port data by Lei Fang, Chen Bo, Lv Jingzhao, Li Pingan, Du Haitao, Li Su

“…The code rate is 4/5 with the best effect error correction, and the noise resistance performance improves by about 1 dB.…”
Get full text

Significant Influence on Residual Bending Strength by Cracks Generation During Grinding of Ceramics by Jinshuo Zhang, Tianyi Sui, Bin Lin, Bingrui Lv, Jingming Li, Jingguo Zhou

“…Lastly, a model is developed to delineate the relationship between processing parameters and the residual bending strength of the product, with the model exhibiting an error margin of less than 11%. This model clearly reveals the effect of crack generation under different process parameters on residual flexural strength.…”
Get full text

Application of Non-Linear System Model Updating Using Feature Extraction and Parameter Effects Analysis by John F. Schultze, François M. Hemez, Scott W. Doebling, Hoon Sohn

“…This is an extension of the familiar linear updating paradigm of utilizing the eigen-parameters or frequency response functions (FRFs) to include such devices as peak acceleration, time of arrival or standard deviation of model error. The next expansion of the updating process is the inclusion of statistical based parameter analysis to quantify the effects of uncertain or significant effect parameters in the construction of a meta-model. …”
Get full text

NSGT: A Plasma Position Prediction Method for the HL-2A Tokamak Device Based on Transformer by Ling Zhou, Bin Yang, Xiangcheng Lin, Kaihao Zhu, Ziran Lan, Xiangwen Li

“…The experimental results show that the NSGT model has a significant reduction in the root - mean - square error of prediction compared with the LSTM method, effectively supporting the real - time adjustment of the closed - loop control system. …”
Get full text