Study on the Relationship Between Porosity and Mechanical Properties Based on Rock Pore Structure Reconstruction Model by Nan Xiao, Jun-Qing Chen, Xiang Qiu, Fu Huang, Tong-Hua Ling

“…The research workflow incorporated advanced image processing techniques, including adaptive total variation denoising algorithms for CT image enhancement and deep learning-based threshold segmentation for feature extraction. …”
Get full text

Explainable Multi-Scale CAM Attention for Interpretable Cloud Segmentation in Astro-Meteorological Applications by Qing Xu, Zichen Zhang, Guanfang Wang, Yunjie Chen

“…However, traditional threshold- and texture-based methods suffer from limited accuracy (65–80%) under complex conditions such as thin cirrus or twilight transitions. …”
Get full text

Detection of Critical Parts of River Crab Based on Lightweight YOLOv7-SPSD by Guoai Fang, Yu Zhao

“…In this paper, we propose a lightweight deep learning model called YOLOv7-SPSD for detecting river crab tails. …”
Get full text

Wasserstein GAN for moving differential privacy protection by Enze Liu, Zhiguang Chu, Xing Zhang

“…Abstract Training machine learning models often requires large datasets, but using sensitive data for training poses risks of privacy leakage. …”
Get full text

InCrowd-VI: A Realistic Visual–Inertial Dataset for Evaluating Simultaneous Localization and Mapping in Indoor Pedestrian-Rich Spaces for Human Navigation by Marziyeh Bamdad, Hans-Peter Hutter, Alireza Darvishy

“…Under challenging conditions, systems exceeded the required localization accuracy of 0.5 m and the 1% drift threshold, with classical methods showing drift up to 5–10%. …”
Get full text

Electrochemical–Thermal Modeling of Lithium-Ion Batteries: An Analysis of Thermal Runaway with Observation on Aging Effects by Milad Tulabi, Roberto Bubbico

“…Additionally, a machine learning algorithm (logistic regression) is employed to identify an internal resistance threshold, beyond which thermal runaway (TR) becomes highly probable, and to predict TR probability based on key battery parameters. …”
Get full text

A study on the detection of conductor quantity in cable cores based on YOLO-cable by Xiaoguang Xu, Jiale Ding, Qi’an Ding, Qikai Wang, Yi Xun

“…This study provides new insights and technical support for the application of deep learning in industrial inspections.…”
Get full text

Neural representation of consciously seen and unseen information by Pablo Rodríguez-San Esteban, Jose A. Gonzalez-Lopez, Ana B. Chica

“…Abstract Machine learning (ML) techniques have steadily gained popularity in Neuroscience research, particularly when applied to the analysis of neuroimaging data. …”
Get full text

A human pose estimation network based on YOLOv8 framework with efficient multi-scale receptive field and expanded feature pyramid network by Shaobin Cai, Han Xu, Wanchen Cai, Yuchang Mo, Liansuo Wei

“…Compared to YOLOv8-Pose, EE-YOLOv8 achieves an AP of 89.0% at an IoU threshold of 0.5 (an improvement of 3.3%) and an AP of 65.6% over the IoU range of 0.5–0.95 (an improvement of 5.8%). …”
Get full text

Breast Cancer Classification With Enhanced Interpretability: DALAResNet50 and DT Grad-CAM by Suxing Liu, Galib Muhammad Shahriar Himel, Jiahao Wang

“…Furthermore, the proposed Dynamic Threshold Grad-CAM (DT Grad-CAM) method provides clearer and more focused visualizations, enhancing interpretability and assisting medical experts in identifying key features.…”
Get full text

Diagnosis of knee meniscal injuries using artificial intelligence: A systematic review and meta-analysis of diagnostic performance. by Soheil Mohammadi, Ali Jahanshahi, Mohammad Shahrabi Farahani, Mohammad Amin Salehi, Negin Frounchi, Ali Guermazi

“…Also, a meta-analysis was done using contingency tables to estimate diagnostic performance metrics (sensitivity and specificity), and a meta-regression analysis was performed to investigate the effect of the following variables on the main outcome: imaging view, data augmentation and transfer learning usage, and presence of meniscal tear in the injury, with a corresponding 95% confidence interval (CI) and a P-value of 0.05 as a threshold for significance.…”
Get full text

RS-DETR: An Improved Remote Sensing Object Detection Model Based on RT-DETR by Hao Zhang, Zheng Ma, Xiang Li

“…Object detection is a fundamental task in computer vision. Recently, deep-learning-based object detection has made significant progress. …”
Get full text

LV-FeatEx: Large Viewpoint-Image Feature Extraction by Yukai Wang, Yinghui Wang, Wenzhuo Li, Yanxing Liang, Liangyi Huang, Xiaojuan Ning

“…Firstly, the method uses a dual-threshold approach based on image grayscale histograms and Kapur’s maximum entropy to constrain the AGAST (Adaptive and Generic Accelerated Segment Test) feature detector. …”
Get full text

Technical variability and safety of sleeve gastrectomy: a nationwide survey of bariatric centers in Poland by Przemysław Sroczyński, Piotr Major, Michał R. Janik

“…The centers were stratified by annual SG volume using a 50-procedure threshold, corresponding to the suggested learning curve. …”
Get full text

Optimizing Classroom Lighting for Enhanced Visual Comfort and Reduced Energy Consumption by Samaneh Aghajari, Cheng-Chen Chen

“…Glare can lead to discomfort and eye fatigue, adversely affecting learning performance. To measure and assess this phenomenon, the “Unified Glare Rating (UGR)” metric is employed, which helps designers accurately evaluate the level of glare caused by lighting. …”
Get full text

Exploring Process Heterogeneity in Environmental Statistics: Examples and Methodological Advances by Gregor Laaha, Johannes Laimighofer, Nur Banu Özcelik, Svenja Fischer

“…A mixture model combining peak-over-threshold distributions of flood types can handle this heterogeneity, especially regarding tail heaviness, making it relevant for flood design. …”
Get full text

Rethinking model prototyping through the MedMNIST+ dataset collection by Sebastian Doerrich, Francesco Di Salvo, Julius Brockmann, Christian Ledig

“…Abstract The integration of deep learning based systems in clinical practice is often impeded by challenges rooted in limited and heterogeneous medical datasets. …”
Get full text

Breaking language barriers with image detection and natural language processing model for English to Spanish translation by Bakhita Salman, Andres Lopez, Nathanielle Delapena

“…Fine-tuning the transformer model parameters, including learning rate scheduling and gradient clipping, further optimized system performance. …”
Get full text

A Hybrid Fault Detection Method of Independent Component Analysis and Auto-Associative Kernel Regression for Process Monitoring in Power Plant by Seunghwan Jung, Jonggeun Kim, Sungshin Kim

“…However, DCSs not only have the advantages of collecting large amounts of operational history data, but they also have the shortcoming of limited monitoring capabilities, such as early detection, due to their reliance on generating fault alarms based on simple threshold values. To improve the stability and reliability of industrial processes, it is essential to operate DCS in conjunction with data-driven process monitoring technologies. …”
Get full text

Bilateral Symmetry-Based Abnormality Detection in Breast Thermograms Using Textural Features of Hot Regions by Ankita Dey, Ebrahim Ali, Sreeraman Rajan

“…Thermography is known for its potential to detect breast abnormalities at an early stage. A novel threshold-based non-machine learning asymmetry analysis using textural features is proposed for breast abnormality detection. …”
Get full text