Physically-constrained evapotranspiration models with machine learning parameterization outperform pure machine learning: Critical role of domain knowledge. by Yeonuk Kim, Monica Garcia, T Andrew Black, Mark S Johnson

“…We found a strong correlation (r = 0.93) between the sensitivity of ET estimates to machine-learned parameters and model error (root-mean-square error; RMSE), indicating that reduced sensitivity minimizes error propagation and improves performance. …”
Get full text

Development and Practice of Cloud Collaborative Platform for Downhole Measurement Tools by Che Yang, Yuan Guangjie, Qian Hongyu, Du Weiqiang, Wang Chenlong, Ding Jiping

“…The measurement tools are mainly single machine version， which is difficult to meet the current requirements for improving drilling quality and efficiency. In the paper， based on the remote operation requirements of coreless magnetic steering tool， a platform architecture of five modules， including simulation rehearsal， virtual training， remote operation， smart tool and intelligent decision， was designed in detail， achieving a whole process digitization from predrilling risk assessment and in-drilling acquisition and processing to post-drilling feedback and optimization， and a visual interface was developed. …”
Get full text

Centralized Measurement Level Fusion of GNSS and Inertial Sensors for Robust Positioning and Navigation by Mohamed F. Elkhalea, Hossam Hendy, Ahmed Kamel, Ashraf Abosekeen, Aboelmagd Noureldin

“…The experimental results clearly illustrate the considerable improvements achieved by the recommended tightly coupled (TC) algorithm when integrated with MDDA, in contrast to the loosely coupled (LC) algorithm. …”
Get full text

Generalizability of machine learning models for diabetes detection a study with nordic islet transplant and PIMA datasets by Dinesh Chellappan, Harikumar Rajaguru

“…Researchers utilizing a hybrid feature extraction method such as Artificial Bee Colony (ABC) and Particle Swarm Optimization (PSO) followed by metaheuristic feature selection algorithms as Harmonic Search (HS), Dragonfly Algorithm (DFA), Elephant Herding Algorithm (EHA). …”
Get full text

Masks-to-Skeleton: Multi-View Mask-Based Tree Skeleton Extraction with 3D Gaussian Splatting by Xinpeng Liu, Kanyu Xu, Risa Shinoda, Hiroaki Santo, Fumio Okura

“…Furthermore, we use a minimum spanning tree (MST) algorithm during the optimization loop to regularize the graph to a tree structure. …”
Get full text

A single-snapshot inverse solver for two-species graph model of tau pathology spreading in human Alzheimer’s disease by Zheyu Wen, Ali Ghafouri, George Biros, the Alzheimer’s Disease Neuroimaging Initiative (ADNI)

“…This optimization problem is solved with a projection-based quasi-Newton algorithm. …”
Get full text

Distributed and efficient identity authentication based on consortium blockchain by Yao Ying, Yan Yong, Guo Shaoyong, Xiong Ao, Zhang Wang

Get full text

Development of a machine learning-based surrogate model for friction prediction in textured journal bearings by Yujun Wang, Georg Jacobs, Shuo Zhang, Benjamin Klinghart, Florian König

“…This enhancement is achieved through an architecture design based on cross-validation and further optimization utilizing the genetic algorithm. Eventually, the average prediction accuracy is improved to 98.81% from 95.89%, with the maximum error reduced to 3.25% from 13.17%. …”
Get full text

Transmission scheme for collaborative‐RIS‐aided NOMA system with multiple channels by Heyi Li, Hong Wang, Peiqi Li, Peiyu Wang

Get full text

Joint source–channel rate allocation with unequal error protection for space image transmission by Dan Dong, Shaohua Wu, Dongqing Li, Jian Jiao, Chanjuan Ding, Qinyu Zhang

“…This separate design, although simple to be implemented, cannot explore the transmission performance to the most. In this article, we propose a joint source–channel rate allocation framework to improve the space image transmission performance. …”
Get full text

Adaptive DBP System with Long-Term Memory for Low-Complexity and High-Robustness Fiber Nonlinearity Mitigation by Mingqing Zuo, Huitong Yang, Yi Liu, Zhengyang Xie, Dong Wang, Shan Cao, Zheng Zheng, Han Li

“…In this paper, an improved A-DBP algorithm with long-term memory (LTM) is proposed, employing root mean square propagation (RMSProp) to achieve low-complexity and high-robustness compensation performances. …”
Get full text

Methods to Quantitatively Evaluate the Effect of Shale Gas Fracturing Stimulation Based on Least Squares by DENG Cai, SUN Kexin, WEN Huan, HU Chaolang

“…This method identified the precise number of active perforations and calculated their average diameter after erosion during the fracturing process. Advanced optimization algorithms were employed to efficiently address both the fitting and calculation tasks. …”
Get full text

Rethinking Exploration and Experience Exploitation in Value-Based Multi-Agent Reinforcement Learning by Anatolii Borzilov, Alexey Skrynnik, Aleksandr Panov

“…We aim to optimize a deep MARL algorithm with minimal modifications to the well-known QMIX approach. …”
Get full text

Predictive modeling of hydrogen production and methane conversion from biomass-derived methane using machine learning and optimisation techniques by Adegboyega Bolu Ehinmowo, Bright Ikechukwu Nwaneri, Joseph Oluwatobi Olaide

“…In this study, the integration of various machine learning algorithms with Bayesian optimisation, firefly algorithm, Levenberg-Marquardt, and differential evolution techniques were investigated for hydrogen production via thermocatalytic methane decomposition. …”
Get full text

A PSO-XGBoost Model for Predicting the Compressive Strength of Cement–Soil Mixing Pile Considering Field Environment Simulation by Jiagui Xiong, Yangqing Gong, Xianghua Liu, Yan Li, Liangjie Chen, Cheng Liao, Chaochao Zhang

“…A cement–soil preparation system considering actual immersion conditions was established, based on controlling the initial water content state of the foundation soil before pile formation and applying submerged conditions post-formation. Utilizing data mining on 84 sets of experimental data with various preparation parameter combinations, a prediction model for the as-formed strength of CSM Pile was developed based on the Particle Swarm Optimization-Extreme Gradient Boosting (PSO-XGBoost) algorithm. …”
Get full text

MultS-ORB: Multistage Oriented FAST and Rotated BRIEF by Shaojie Zhang, Yinghui Wang, Jiaxing Ma, Jinlong Yang, Liangyi Huang, Xiaojuan Ning

“…Experimental results demonstrate that for blurred images affected by illumination changes, the proposed method improves matching accuracy by an average of 75%, reduces average error by 33.06%, and decreases RMSE (Root Mean Square Error) by 35.86% compared to the traditional ORB algorithm.…”
Get full text

An adaptive continuous threshold wavelet denoising method for LiDAR echo signal by Dezhi Zheng, Tianchi Qu, Chun Hu, Shijia Lu, Zhongxiang Li, Guanyu Yang, Xiaojun Yang

“…The adaptive threshold is dynamically adjusted according to the wavelet decomposition level, and the continuous threshold function ensures continuity with lower constant error, thus optimizing the denoising process. Simulation results show that the proposed algorithm has excellent performance in improving SNR and reducing root mean square error (RMSE) compared with other algorithms. …”
Get full text

Two-Step Screening for Depression and Anxiety in Patients with Cancer: A Retrospective Validation Study Using Real-World Data by Bryan Gascon, Joel Elman, Alyssa Macedo, Yvonne Leung, Gary Rodin, Madeline Li

“…<b>Conclusions:</b> The present study is among the first to demonstrate that a two-step screening algorithm for depression may improve depression screening in cancer using real-world data. …”
Get full text

IoT intrusion detection method for unbalanced samples by ANTONG P, Wen CHEN, Lifa WU

Get full text

Predicting hydrocarbon reservoir quality in deepwater sedimentary systems using sequential deep learning techniques by Xiao Hu, Jun Xie, Xiwei Li, Junzheng Han, Zhengquan Zhao, Hamzeh Ghorbani

“…Three sequential deep learning models—Recurrent Neural Network and Gated Recurrent Unit—were developed and optimized using the Adam algorithm. The Adam-LSTM model outperformed the others, achieving a Root Mean Square Error of 0.009 and a correlation coefficient (R2) of 0.9995, indicating excellent predictive performance. …”
Get full text