Intelligent library shelf management system for open-access environments: A CNN-based approach with enhanced image recognition and disorder detection by Xueqi Zhang

Get full text

GNSS time series analysis of the crustal movement network of China: Detecting the optimal order of the polynomial term and its effect on the deterministic model by Shuguang Wu, Hua Ouyang, Houpu Li, Zhao Li, Haiyang Li, Yuefan He

“…The latter contains some stochastic noises, which can be affected by detecting the former parameters. If there are not enough parameters assumed, modeling errors will occur and adversely affect the analysis results. …”
Get full text

Wheel flat detection using long short-term memory and transformer models with a 1:10 scale railway test rig by Yong Cui, Euiyoul Kim, Shizhe Yan, Qing Yu

“…The findings indicate that the Transformer model significantly outperforms the Long Short-Term Memory model, especially when feature-level sensor fusion is employed, achieving an average error as low as 0.0069 mm with percentage of error at 5.30%, minimizing the maximum error to 0.0985 mm. …”
Get full text

Mitigating Container Damage and Enhancing Operational Efficiency in Global Containerisation by Sergej Jakovlev, Tomas Eglynas, Mindaugas Jusis, Valdas Jankunas, Miroslav Voznak

“…To address these concerns, we present the Impact Detection Methodology (IDM), a system designed to monitor and detect impacts in real time, enhancing operational precision and safety. …”
Get full text

SegPhase: development of arrival time picking models for Japan’s seismic network using the hierarchical vision transformer by Shinya Katoh, Yoshihisa Iio, Hiromichi Nagao, Hiroshi Katao, Masayo Sawada, Kazuhide Tomisaka

“…By lowering the threshold to 0.1, we observed an increase in the number of detected events without noticeable changes in the hypocenter location error and observed–calculated discrepancies. …”
Get full text

An Integrated UAV and Deep Learning Framework With HSB-Based Segmentation for Automated Slope Anomaly Detection in Mountainous Soil and Water Conservation Sites by Nai-Hsin Pan, Bo-Yuan Chang

“…The study further employed the hue, saturation, and brightness (HSB) color space for anomalous area estimation, achieving precise segmentation with a mean error rate of approximately 7.1%, as verified against 3D model-based ground truth. …”
Get full text

An Application of Deep Learning Models for the Detection of Cocoa Pods at Different Ripening Stages: An Approach with Faster R-CNN and Mask R-CNN by Juan Felipe Restrepo-Arias, María José Montoya-Castaño, María Fernanda Moreno-De La Espriella, John W. Branch-Bedoya

“…Furthermore, a qualitative evaluation using confidence heatmaps and error analysis revealed that R-CNN architectures occasionally missed small or partially occluded pods. …”
Get full text

From Simulation to Field Validation: A Digital Twin-Driven Sim2real Transfer Approach for Strawberry Fruit Detection and Sizing by Omeed Mirbod, Daeun Choi, John K. Schueller

“…Two separate trials with field images resulted in F1-scores of 0.92 and 0.81 for detection and a sizing error of 1.4 mm (R² = 0.92) when comparing image-derived diameters against caliper measurements. …”
Get full text

Detection Accuracy of High-Resolution Infrared Satellite Precipitation Estimates Over Mainland China: A Multiperspective Assessment of Fengyun-4A by Da Qian, Yi Lyu, Zhehui Shen, Hao Wu, Ruochen Huang, Bin Yong, Hongjun Su

“…Despite integrated into operational systems such as hydrologic forecasting, their error characteristics and correction potentials remain unexplored. …”
Get full text

Correlation of Calibration Parameters for HPGe Detector Efficiency Based on Monte Carlo Simulation by LI Yan1, SHAN Chenyu2, GU Weiguo1, WANG Dezhong1

“…Upon comparing the simulated detection efficiencies across various conditions with those obtained using the correction coefficients, the relative error is found to be within 5.5%, indicating high accuracy. …”
Get full text

3D-CNN detection of systemic symptoms induced by different Potexvirus infections in four Nicotiana benthamiana genotypes using leaf hyperspectral imaging by Rizos-Theodoros Chadoulis, Ioannis Livieratos, Ioannis Manakos, Theodore Spanos, Zeinab Marouni, Christos Kalogeropoulos, Constantine Kotropoulos

“…The timing of disease detection was also assessed, finding that accuracies approached 0.8 as early as $$6$$ 6 – $$8$$ 8  DPI depending on the virus. …”
Get full text

Precise Performance Analysis of Dual-Hop Mixed RF/Unified-FSO DF Relaying With Heterodyne Detection and Two IM-DD Channel Models by Omer Mahmoud Salih Al-Ebraheemy, Anas M. Salhab, Anas Chaaban, Salam A. Zummo, Mohamed-Slim Alouini

“…This paper provides precise performance analysis of the dual-hop mixed radio frequency (RF)/unified free space optical (FSO) decode-and-forward (DF) relaying system, in which the heterodyne detection and the intensity modulation-direct detection (IM-DD) are taken into account for FSO detection. …”
Get full text

Integrated Lower Limb Robotic Orthosis with Embedded Highly Oriented Electrospinning Sensors by Fuzzy Logic-Based Gait Phase Detection and Motion Control by Ming-Chan Lee, Cheng-Tang Pan, Jhih-Syuan Huang, Zheng-Yu Hoe, Yeong-Maw Hwang

“…Results demonstrate that the exoskeleton accurately detects gait phases, achieving a maximum tracking error of 4.23% in an 8-s gait cycle under no-load conditions and 4.34% when tested with a 68 kg user. …”
Get full text

Fine-tuned YOLO-based deep learning model for detecting malaria parasites and leukocytes in thick smear images: A Tanzanian case study by Beston Lufyagila, Bonny Mgawe, Anael Sam

“…However, manual identification is labor-intensive, time-consuming, and prone to diagnostic errors—particularly in resource-limited settings. …”
Get full text

Mango (Mangifera indica) tree detection and counting in mango orchard with satellite images using deep learning model YOLO: A comparative analysis by LALIT BIRLA, ANSHU BHARADWAJ, RAJNI JAIN, CHANDAN KUMAR DEB, VINAY KUMAR SEHGAL, RAMASUBRAMANIAN V

“…However, traditional methods often rely on manual efforts or expensive feature engineering, leading to errors, inefficiencies, and limited scalability. Recent advancements in deep learning-based approaches have demonstrated state-of-the-art performance in automated tree counting, offering improved accuracy, robustness, and computational efficiency. …”
Get full text

Model updating method for detect and localize structural damage using generalized flexibility matrix and improved grey wolf optimizer algorithm (I-GWO) by Sina Sadraei, Majid Gholhaki, Omid Rezaifar

“…The accuracy of this method in locating the 15-story shear frame, the 25-member two-dimensional truss bridge, and the 23-member two-dimensional frame, as well as in identifying all damages, is demonstrated by the fact that the error between the simulated and estimated results in an average of twenty runs and each damage scenario was less than 3 percent. …”
Get full text

A Hybrid Deep Learning Model for Enhanced Structural Damage Detection: Integrating ResNet50, GoogLeNet, and Attention Mechanisms by Vikash Singh, Anuj Baral, Roshan Kumar, Sudhakar Tummala, Mohammad Noori, Swati Varun Yadav, Shuai Kang, Wei Zhao

“…Traditional methods of damage assessment, which rely on manual inspections, can be labor-intensive and subject to human error. This paper introduces a hybrid deep learning model that combines the capabilities of ResNet50 and GoogLeNet, further enhanced by a convolutional block attention module (CBAM), proposed to improve both the accuracy and performance in detecting structural damage. …”
Get full text

Research on Change Point Detection during Periods of Sharp Fluctuations in Stock Prices–Based on Bayes Method <i>β</i>-ARCH Models by Fenglin Tian, Yong Wang, Qi Qin, Boping Tian

“…By detecting the change points of the price of eight stocks with a high number of limit up and limit down changes occurring in the observation period, the following conclusions are obtained: (1) Change point detection using the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>β</mi></semantics></math></inline-formula>-ARCH model based on the Bayes method is effective. (2) For different values of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>β</mi></semantics></math></inline-formula>, this research study finds that based on the classical ARCH model (i.e., <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>β</mi><mo>=</mo><mn>1</mn></mrow></semantics></math></inline-formula>) of the change point parameter, the results are relatively optimal. (3) The accuracy of change point detection can be improved by correcting stock short-term effects by using the Kalman filtering method.…”
Get full text

Respiratory Rate Estimation from Thermal Video Data Using Spatio-Temporal Deep Learning by Mohsen Mozafari, Andrew J. Law, Rafik A. Goubran, James R. Green

“…This paper introduces an end-to-end deep learning approach to RR measurement using thermal video data. A detection transformer (DeTr) first finds the subject’s facial region of interest in each thermal frame. …”
Get full text

Automated Coronary Artery Identification in CT Angiography: A Deep Learning Approach Using Bounding Boxes by Marin Sakamoto, Takaaki Yoshimura, Hiroyuki Sugimori

“…The evaluation metrics included Average Precision (AP), Intersection over Union (IoU), Dice Similarity Coefficient (DSC), and Mean Absolute Error (MAE) to achieve both detection accuracy and spatial localization precision. …”
Get full text