MULTI-MODEL STACK ENSEMBLE DEEP LEARNING APPROACH FOR MULTI-DISEASE PREDICTION IN HEALTHCARE APPLICATION by Bhaskar Adepu, T. Archana

“…A robust stacked deep ensemble model is proposed combining the InceptionResNetV2, EfficientNetV2L, and Xception architectures. …”
Get full text

Automatic plant disease detection using computationally efficient convolutional neural network by Muhammad Rizwan, Samina Bibi, Sana Ul Haq, Muhammad Asif, Tariqullah Jan, Mohammad Haseeb Zafar

“…The manual approach, where plant pathologists inspect fields, is costly, error‐prone, and time‐consuming. Alternatively, automatic approaches utilize 2D plant images processed through machine learning. …”
Get full text

An End-to-End Deep Learning System for Automated Fashion Tagging: Segmentation, Classification, and Hierarchical Labeling by Basak Esin Kokturk-Guzel

“…Following segmentation, the system classifies these items into primary categories, reaching a top-level classification accuracy of 96% with the InceptionV3 model, and determines their dominant color with an RGB-based color-matching algorithm. …”
Get full text

Moving Towards the Reliability-oriented Design of Hairpin Winding for EV Traction Machines Driven by SiC Inverter by Xiaowei Ju, Yue Zhang, Zhiwei Xue, Yuan Cheng, Shumei Cui

“…Subsequently, a high-frequency equivalent circuit model of the HW TM prototype is developed. The error of simulation and experiment is only 5.7 %, which proves the accuracy of the model. …”
Get full text

Lower extremity functional performance tests and their measurement properties in athletes: a systematic review and narrative synthesis by Alison Rushton, Nicola R Heneghan, Lee Herrington, James Martin, Rosalyn Cooke, Andy Soundy

“…Side hop, functional movement screen and landing error scoring system showed moderate certainty for one measurement property. …”
Get full text

Real-time Sorting of Broiler Chicken Meat with Robotic arm: XAI-enhanced Deep Learning and LIME Framework for Freshness Detection by Mahamudul Hasan, Nishat Vasker, M. Saddam Hossain Khan

“…Traditional methods for sorting chicken meat based on freshness are often manual and prone to error, necessitating the development of an automated, accurate sorting system. …”
Get full text

Hybrid transfer learning and self-attention framework for robust MRI-based brain tumor classification by Soumyarashmi Panigrahi, Dibya Ranjan Das Adhikary, Binod Kumar Pattanayak

“…Magnetic Resonance Imaging (MRI) is crucial for diagnosis, but manual analysis is resource-intensive and error-prone, highlighting the need for robust Computer-Aided Diagnosis (CAD) systems. …”
Get full text

Collaborative AI Dysarthric Speech Recognition System With Data Augmentation Using Generative Adversarial Neural Network by Yibo He, Kah Phooi Seng, Li-Minn Ang

“…Experiments conducted on the UASpeech corpus demonstrate a significant reduction in the word error rate (WER) compared to the baseline approach. …”
Get full text

The impostor phenomenon among surgeons and surgeons in training: a scoping review by Chunlan Jin, Jian Ling, Zuhuan Xu, Tao Lin, Weiqin Chen

“…Abstract Background The impostor phenomenon (IP), is a condition in which people think they are incapable of success and tend to attribute their success to external causes such as luck, error, or knowing the appropriate individuals. It has been confirmed as a contributor to burnout for practicing physicians, residents, and medical students. …”
Get full text

Statistical Modeling to Improve Time Series Forecasting Using Machine Learning, Time Series, and Hybrid Models: A Case Study of Bitcoin Price Forecasting by Moiz Qureshi, Hasnain Iftikhar, Paulo Canas Rodrigues, Mohd Ziaur Rehman, S. A. Atif Salar

“…Bitcoin (BTC-USD) is a virtual currency that has grown in popularity after its inception in 2008. BTC-USD is an internet communication network that makes using digital money, including digital payments, easy. …”
Get full text

IoT-Enhanced Smart Parking Management With IncepDenseMobileNet for Improved Classification by Xiaoxia Zheng, Wenxi Feng, Ning Wang, Huhemandula

“…The model demonstrated a log loss of 0.18 and outstanding performance on new metrics, including Weighted Error Impact Score (WEIS), Dynamic Class Stability Index (DCSI), and Harmonized Classification Risk (HCR), signifying its effectiveness. …”
Get full text

Prognostic assessment of sarcopenia in patients with fractures: a systematic review and meta-analysis by Hejie Zheng, Tianhong Wang, Zhuoyang Li, Huimin Lu

“…Methods A systematic search was carried out in PubMed, Embase, Cochrane Library, and Web of Science using the keywords “sarcopenia” and “fracture” from the inception of each database to January 14, 2025. The logarithm and its standard error of the odds ratio (OR) were calculated to assess the effect size. …”
Get full text

Estimation of Fractal Dimension and Detection of Fake Finger-Vein Images for Finger-Vein Recognition by Seung Gu Kim, Jin Seong Hong, Jung Soo Kim, Kang Ryoung Park

“…Furthermore, experiments conducted with the proposed spoof detector yielded average classification error rates of 0.4% and 0.12% on the two aforementioned open databases, respectively, outperforming existing SOTA methods for spoof detection.…”
Get full text

Size Increment During Surveillance in Papillary Thyroid Cancer: Evidence Synthesis and Dose–Response Meta‐Analysis by Mohamed Badie Ahmed, Emad Naem, Harman Saman, Abeer Alsherawi, Asma Syed, Noora Al‐Abdulla, Latifa Alkaabi, Mahmoud A. Zirie, Suhail A. Doi

“…Methods A dose–response meta‐analysis was conducted using the robust error meta‐regression method, using time as the “dose” and cumulative progression (%) was assessed. …”
Get full text

A fully automated U-net based ROIs localization and bone age assessment method by Yuzhong Zhao, Yihao Wang, Haolei Yuan, Weiwei Xie, Qiaoqiao Ding, Xiaoqun Zhang

“…Numerical experiments demonstrate that the method achieves a mean absolute error (MAE) of 0.38 years for males and 0.45 years for females on the public RSNA dataset, and 0.41 years for males and 0.44 years for females on an in-house dataset, validating the accuracy of both localization and prediction.…”
Get full text

Associations between biomarkers and skeletal muscle function in individuals with osteoarthritis: a systematic review and meta-analysis by Stephanie L. Smith, Lorna Paul, Martijn P. M. Steultjens, Rebecca L. Jones

“…Muscle strength and vitamin D reported a significant association (Hedge’s g: 0.58 (Standard Error (SE): 0.27; P = 0.03), k = 3 studies). Walking speed and high-sensitivity C-reactive protein reported no significant associations (Hedge’s g: -0.02 (SE: 0.05; P = 0.73), k = 3 studies). …”
Get full text

Edge-optimized multimodal cross-fusion architecture for efficient crop disease detection by Thomas Kinyanjui Njoroge, Kelvin Mugoye Shindu, Rachael Kibuku

“…Traditional diagnostic methods, such as manual inspections, are often inefficient and error-prone. Existing deep learning models (e.g., ResNet50, Inception V3) struggle with computational inefficiency and poor generalizability in real-world farming contexts. …”
Get full text

Novel Neural Networks for Camera Calibration in Underwater Environments by Cristian H. Sanchez-Saquin, Leonardo Barriga-Rodriguez, Leonardo A. Baldenegro-Perez, Guillermo Ronquillo-Lomeli, Noe A. Rodriguez-Olivares

“…The process began with the training of the InceptionResNetV2 neural network from scratch, followed by the adjustment of the dense layers for regression and calibration matrix estimation. …”
Get full text

Improved image reconstruction from brain activity through automatic image captioning by Fatemeh Kalantari, Karim Faez, Hamidreza Amindavar, Soheila Nazari

“…Image optimization is performed iteratively to minimize the error between features decoded from brain data and features extracted from the generated image. …”
Get full text

Red blood cell transfusion strategy in traumatic brain injury patients: a systematic review and meta-analysis by Jing Wang, Xiang-Hui Li, Jiang-Quan Yu, Rui-Qiang Zheng

“…Conclusions In critically ill patients with TBI, a liberal RBCT strategy appears to improve functional outcomes but carries the risk of false positive errors. In addition, this strategy does not seem to improve survival and may increase the risk of TARDS. …”
Get full text