Threshold Successive Cancellation Flip Decoding Algorithm for Polar Codes: Design and Performance by Zhicheng Liu, Liuquan Yao, Shuai Yuan, Guiying Yan, Zhiming Ma, Yuting Liu

“…Theoretical analysis reveals that Th-SCF asymptotically delays the first error position (FEP, the first part where the SC decoder fails) with probability 1, ensuring high decoding performance. …”
Get full text

Adaptive period decomposition network with muti-scale temporal variation learning for water level prediction by Hui Wang, LiPing Wang, QiCang Qiu, Yuyan Gao, WenJuan Li, QiuShun Wang

“…New hydrologic insights for the region:: Compared to ten other advanced prediction models, DLGNet achieved an average reduction in mean square error (MSE) by 94. 82%, 93. 35%, and 83. 13% for short-term, mid-term, and long-term predictions, respectively. …”
Get full text

NetCodeAIoT: Enhancing Augmented Intelligence of Things for Vehicle Systems in 5G Networks by Okuwudili Mathew Ugochukwu, Renata Lopes Rosa, Muhammad Saadi, Demostenes Z. Rodriguez, Frederico G. Guimaraes

“…NetCodeAIoT dynamically adjusts the sparsity level of the decoding matrix, implements unequal error protection network coding, and enables instantaneous decoding of data. …”
Get full text

An Adaptive Three-Dimensional Self-Masking Strategy for the Micro-Fabrication of Quartz-MEMS with Out-of-Plane Vibration Units by Yide Dong, Chunyan Yin, Guangbin Dou, Litao Sun

“…The unit exhibited a repeatability error below 1.13%, confirming the precision and reliability of the proposed fabrication strategy.…”
Get full text

Effect of Key Parameters on Ploughing Force Performance of Planing-Type Anti-Climbers by Zhuyao Li, Jiyou Fei, Dongxue Song, Hong He, Chang Liu, Chong Zhang

“…The results demonstrate that the model achieves ≤15% relative error compared with the simulation data and ≤5% deviation from the experimental measurements, confirming its engineering applicability. …”
Get full text

A hybrid reinforcement learning and knowledge graph framework for financial risk optimization in healthcare systems by Md Shahab Uddin, Ahsan Ahmed, Md Aktarujjaman, Mohammad Moniruzzaman, Mumtahina Ahmed, M. F. Mridha, Md. Jakir Hossen

“…Experimental results on real and synthetic healthcare datasets demonstrate that the proposed model outperforms traditional regressors, deep neural networks, and standalone RL agents across multiple evaluation metrics, including cost prediction error, diagnostic classification accuracy, cumulative reward, and average billing reduction. …”
Get full text

BDNet: Bengali Handwritten Numeral Digit Recognition based on Densely connected Convolutional Neural Networks by Abu Sufian, Anirudha Ghosh, Avijit Naskar, Farhana Sultana, Jaya Sil, M.M. Hafizur Rahman

“…So, the BDNet model gives 47.62% error reduction compared to previous state-of-the-art models. …”
Get full text

Hardware Implementation for Triaxial Contact-Force Estimation from Stress Tactile Sensor Arrays: An Efficient Design Approach by María-Luisa Pinto-Salamanca, Wilson-Javier Pérez-Holguín, José A. Hidalgo-López

“…The calculation of force vectors on the proposed hardware required an average time of 58.68 ms, with an estimation error of 12.6% for normal forces and 7.7% for tangential forces on a 10 × 10 taxel tactile sensor array. …”
Get full text

Optimized design of a permanent magnet brushless DC motor for solar water-pumping applications by Aryadip Sen, Bhim Singh, Kumar Mahtani, Arash Moradzadeh, S.M. Muyeen

“…The proposed design minimizes the volume of the PM, achieving a 20 % reduction in material usage and lowering the overall cost of the motor without compromising performance. …”
Get full text

Design and Application of an Energy Management System Based on Artificial Intelligence Technology by Hongye Lin, Xuanying Bai, Chun Li, Shenghan Xu, Haibin Xu, Zne-Jung Lee, Yun Lin, Qunshan Zhou, Jingxun Cai

“…In response to the increasingly severe energy consumption problem and to promote energy saving and emission reduction, this study aims to design and apply an energy management system platform based on artificial intelligence (AI) technology. …”
Get full text

Mechanistic Impacts of a Scale‐Aware Convection Scheme on Typhoon Intensity: Diagnostics From Minimum Sea‐Level Pressure by Yanjie Liu, Xiaocong Wang, Yimin Liu, Hao Miao, Xuesong Zhu, Wei Huang, Yaxin Zhao, Kai Wang

“…The results of four typhoon cases show the scale‐aware CPS generally reduces the track error by about 15 km and the intensity error by about 10% compared to the default CPS. …”
Get full text

Smart Agile Prioritization and Clustering: An AI-Driven Approach for Requirements Prioritization by Aya M. Radwan, Manal A. Abdel-Fattah, Wael Mohamed

“…Various machine learning algorithms are tested, with KNN and Random Forest demonstrating the highest accuracy and lowest Mean Squared Error (MSE), outperforming traditional prioritization techniques. …”
Get full text

Accelerating Disease Model Parameter Extraction: An LLM-Based Ranking Approach to Select Initial Studies for Literature Review Automation by Masood Sujau, Masako Wada, Emilie Vallée, Natalie Hillis, Teo Sušnjak

“…The effectiveness of the approach across multiple diseases demonstrates the potential for broad application in systematic literature reviews. The substantial reduction in screening effort, along with the provision of explainable AI rationales, marks an important step toward automated parameter extraction from the scientific literature.…”
Get full text

Dynamic Modeling and Parameter Optimization of Potato Harvester Under Multi-Source Excitation by Jianguo Meng, Zhipeng Li, Zheng Li, Yanzhou Li, Wenxia Xie

“…The comparison between actual and simulated signals shows that the RMS error of acceleration is only 2.42%, indicating that introducing two degrees of freedom in pitch and roll directions to the potato harvester can accurately describe its vibration characteristics. …”
Get full text

Cosmology with Topological Deep Learning by Jun-Young Lee, Francisco Villaescusa-Navarro

“…When applied to the Quijote suite, our TNNs achieve a significant reduction in the mean squared error. Compared to our GNNs, which lack higher-order message-passing, ClusterTNNs show improvements of up to 22% in Ω _m and 34% in σ _8 jointly, while the best FullTNN achieves an improvement of up to 60% in σ _8 . …”
Get full text

UAV-based inspection of wind turbine blade surface defects detection technology by TAN Xingguo, ZHANG Gaoming

“…The feature information of defect is separated and extracted through image foreground segmentation and threshold processing, and the connected domain is framed to realize the detection of blade surface. The accuracy and error rate of defect images is calculated and tested by introducing performance evaluation index MIoU. …”
Get full text

Prediction of pressure drop in heavy oil water ring based on modified two fluid model by Jiqiang Fu, Mingjun Du, Jiaqiang Jing, Huichao Liu, Jie Sun, Weicong Chen, Yongjiu Chen

“…Abstract Accurate prediction of pressure drop of the heavy oil-water ring flow in pipeline is of great significance for establishing an optimal drag reduction model and ensuring safe production. The effects of different factors on the flow pattern and pressure drop of heavy oil-water annular two-phase flow were systematically analyzed, and a standard two-fluid pressure drop prediction model for annular flow was established. …”
Get full text

Speech Intelligibility Prediction Using Binaural Processing for Hearing Loss by Xiajie Zhou, Candy Olivia Mawalim, Masashi Unoki

“…Experimental results show that, compared to the baseline system of the second Clarity Prediction Challenge (CPC2) dataset, the proposed method achieves an 8.3% reduction in root mean squared error (RMSE). Notably, the proposed method reduces RMSE by 12.8% when predicting inconsistent hearing loss compared to listeners with consistent hearing levels, confirming the potential of combining hearing loss modeling with binaural processing.…”
Get full text

Spot Image Segmentation of Lifting Container Vibration Based on Improved Threshold Method and Mathematical Morphology by Tian-Bing Ma, Qiang Wu, Fei Du, Wei-Kang Hu, Yong-Jing Ding

“…The novelty of this method lies in the accurate threshold segmentation and noise reduction processing of the laser speck vibration image under various interference environments in the operation of the mine hoisting system and the accurate acquisition of vibration signals. …”
Get full text

Improving Localization in Wireless Sensor Networks for the Internet of Things Using Data Replication-Based Deep Neural Networks by Jehan Esheh, Sofiene Affes

“…By combining the modified datasets with the original training data, we significantly increase the dataset size, which leads to a substantial reduction in normalized root mean square error (NRMSE). …”
Get full text