MonoAMP: Adaptive Multi-Order Perceptual Aggregation for Monocular 3D Vehicle Detection by Xiaoxi Hu, Tao Chen, Wentao Zhang, Guangyi Ji, Hongxia Jia

“…However, existing methods face certain limitations in cross-dimensional feature attention mechanisms and multi-order contextual information modeling, which constrain their detection performance in complex scenes. …”
Get full text

Design and predict the potential of imidazole-based organic dyes in dye-sensitized solar cells using fingerprint machine learning and supported by a web application by Mohamed M. Elsenety

“…Among of these, Deep Neural Network models of MLPRegressor algorithm based on the daylight fingerprint shows a significant coefficient of determination combined with the lowest errors. …”
Get full text

Transferring Learned ECG Representations for Deep Neural Network Classification of Atrial Fibrillation with Photoplethysmography by Jayroop Ramesh, Zahra Solatidehkordi, Raafat Aburukba, Assim Sagahyroon, Fadi Aloul

“…This results in the <i>student</i> model yielding average improvements in accuracy, sensitivity, F1 score, and Matthews correlation coefficient of 2.0%, 15.05%, 11.7%, and 9.85%, respectively, across both PPG datasets. …”
Get full text

Analysis of soil salinization and land use change under water conservation retrofit in the Hetao irrigation district by Yi Zhao, Shuya Yang, Haibin Shi, Haoqi Han, Yunlei Dong, Xianyue Li, Jianwen Yan, Yan Yan, Xu Dou, Feng Tian, Qingfeng Miao

“…We establish soil sampling sites in this region, employ Google Earth Engine algorithms to develop models for soil salinity inversion and land use classification, and analyze the change patterns of land salinization and land use types. …”
Get full text

Research on Credit Risk Prevention in Supply Chain Finance Driven by Blockchain by Lin Kejing

“…The article concludes by proposing innovative strategies based on blockchain technology, including constructing a credit information sharing platform, improving the credit assessment model, and establishing a risk early warning and monitoring system, with the aim of improving the efficiency and credit level of supply chain management and further promoting the healthy development of supply chain finance.…”
Get full text

High-accuracy prediction of vessels’ estimated time of arrival in seaports: A hybrid machine learning approach by Sunny Md. Saber, Kya Zaw Thowai, Muhammad Asifur Rahman, Md. Mehedi Hassan, A.B.M. Mainul Bari, Asif Raihan

“…Compared to existing machine learning algorithms, our stacking model exhibits superior prediction performance. …”
Get full text

On the effect of sampling frequency on the electricity theft detection performance by Fatemeh Soleimani Nasab, Foad Ghaderi

“…Experimental results show that the performance of the models decreases with a small slope up to the sampling frequency of one data per week. …”
Get full text

Bayesian Time-Domain Ringing Suppression Approach in Impulse Ultrawideband Synthetic Aperture Radar by Xinhao Xu, Wenjie Li, Haibo Tang, Longyong Chen, Chengwei Zhang, Tao Jiang, Jie Liu, Xingdong Liang

“…This study systematically analyzes the mechanisms of ringing generation, including its physical origins and mathematical modeling in SAR systems. Building on this analysis, we propose a Bayesian ringing suppression algorithm based on sparse optimization. …”
Get full text

Hybrid CFD and Monte Carlo-Driven Optimization Approach for Heat Sink Design by Raquel Busqué, Matias Bossio, Raimon Fabregat, Francesc Bonada, Héctor Maicas, Jordi Pijuan, Albert Brigido

“…The method integrates CFD simulations in Ansys Fluent with a Monte Carlo-driven optimization algorithm, modeling the design of a heat sink domain as a porous medium. …”
Get full text

HybridBranchNetV2: Towards reliable artificial intelligence in image classification using reinforcement learning. by Ebrahim Parcham, Mansoor Fateh, Vahid Abolghasemi

“…In particular, a 14% improvement obtained on the Visual Genome dataset and ImageNet 1K compared to the original HybridBranchNet model. …”
Get full text

Balancing conflicting objectives in pre-salt reservoir development: A robust multi-objective optimization framework by Auref Rostamian, Amir Davari Malekabadi, Marx Vladimir De Souda Miranda, Vinicius Edurado Botechia, Denis José Schiozer

“…The optimization variables are location, type (injection or production), and number of wells, while the non-dominated sorting genetic algorithm II (NSGA-II) is employed for multi-objective optimization. …”
Get full text

XSShield: Defending Against Stored XSS Attacks Using LLM-Based Semantic Understanding by Yuan Zhou, Enze Wang, Wantong Yang, Wenlin Ge, Siyi Yang, Yibo Zhang, Wei Qu, Wei Xie

“…Experimental evaluation shows that XSShield achieves 93% accuracy and an F1 score of 0.9266 on the GPT-4 model, improving accuracy by an average of 88.8% compared to existing solutions. …”
Get full text

A General Framework for CFAR Detection in PolSAR Imagery Based on Quadratic Statistics by Ziyuan Yang, Liguo Liu, Xiaoyang Hou, Yinghui Quan, Xian Zhang, Tao Liu

“…In the field of target detection in polarimetric synthetic aperture Radar (PolSAR) imagery, the constant false alarm rate (CFAR) algorithm is renowned for its operability and high interpretability. …”
Get full text

Optimized Design and Deep Vision-Based Operation Control of a Multi-Functional Robotic Gripper for an Automatic Loading System by Yaohui Wang, Sheng Guo, Jinliang Zhang, Hongbo Ding, Bo Zhang, Ao Cao, Xiaohu Sun, Guangxin Zhang, Shihe Tian, Yongxu Chen, Jixuan Ma, Guangrong Chen

“…A deep vision-based recognition system, enhanced by an improved YOLOv5 algorithm and multi-feature fusion, was employed for real-time object detection and pose estimation. …”
Get full text

Exploring Cosmological Constraints of the Weak Gravitational Lensing and Galaxy Clustering Joint Analysis in the CSST Photometric Survey by Qi Xiong, Yan Gong, Xingchen Zhou, Hengjie Lin, Furen Deng, Ziwei Li, Ayodeji Ibitoye, Xuelei Chen, Zuhui Fan, Qi Guo, Ming Li, Yun Liu, Wenxiang Pei

“…We employ a high-resolution JiuTian-1G simulation to construct a partial-sky light cone to z = 3 covering 100 deg ^2 and obtain the CSST galaxy mock samples based on an improved semianalytical model. We perform a multi-lens-plane algorithm to generate corresponding synthetic weak lensing maps and catalogs. …”
Get full text

Identification of distinct disease activity trajectories in patients with psoriatic arthritis receiving tofacitinib: a post hoc analysis of two phase 3 studies by Laura C Coates, Dafna Gladman, Mikhail Volkov, David Gruben, William Tillett, Stefanie Hahne

“…PASDAS components generally improved to month 6 in all groups, consistent with modelled trajectories. …”
Get full text

Fine-art recognition using convolutional transformers by Yu Liu, Haozhe Bai, Jingchao Wang

“…As part of the most advanced architectures in the deep learning family, transformers are empowered by a multi-head attention mechanism, thus improving learning efficiency. To assess the performance of our model, we compared it with those developed using four pre-trained networks: ResNet50, VGG16, AlexNet, and ViT. …”
Get full text

A novel network-level fused deep learning architecture with shallow neural network classifier for gastrointestinal cancer classification from wireless capsule endoscopy images by Muhammad Attique Khan, Usama Shafiq, Ameer Hamza, Anwar M. Mirza, Jamel Baili, Dina Abdulaziz AlHammadi, Hee-Chan Cho, Byoungchol Chang

“…The proposed framework offers improved accuracy, precision, and computational efficiency compared to state-of-the-art models. …”
Get full text

Multiple imputation integrated to machine learning: predicting post-stroke recovery of ambulation after intensive inpatient rehabilitation by Alice Finocchi, Silvia Campagnini, Andrea Mannini, Stefano Doronzio, Marco Baccini, Bahia Hakiki, Donata Bardi, Antonello Grippo, Claudio Macchi, Jorge Navarro Solano, Michela Baccini, Francesca Cecchi

“…After handling missingness using MImp, ML models were optimised, cross-validated, and tested. …”
Get full text

Artificial intelligence in dentistry—A review by Hao Ding, Jiamin Wu, Wuyuan Zhao, Jukka P. Matinlinna, Jukka P. Matinlinna, Michael F. Burrow, James K. H. Tsoi

“…Owing to the rapid development of three cornerstones of current AI technology—big data (coming through digital devices), computational power, and AI algorithm—in the past two decades, AI applications have started to provide convenience to people's lives. …”
Get full text