A refined lion optimizer for deep learning by Jian Rong, Chenhao Ma, Qinghui Zhang, Yong Cao, Weili Kou

“…Compared to the AdamW and Lion optimizer, the loss and accuracy present the RLion can promote the classification validation accuracy about $$0 \sim +20\%$$ higher than AdamW on many models even the learning rate is as high as AdamW. …”
Get full text

Efficient Multi-Stage Self-Supervised Learning for Pathology Image Analysis via Masking by Ming Feng, Weiquan Huang, Liang Hu

“…We evaluated RHP’s performance on four downstream tasks, including patch classification, nucleus segmentation, gland segmentation, and whole slide image classification across eight public datasets. …”
Get full text

Application of Solutions of Uncorrected Tasksʼ Theory for Managing of Production Processesʼ Robustness by P. S. Serenkov, V. M. Romanchak, I. E. Pesliak

“…We have  proposed  a  classification  of  situations  of  robustness  losses  in  production  processes in accordance with the classification of the signs of incorrect tasks by J. …”
Get full text

Prediction of 123I-FP-CIT SPECT Results from First Acquired Projections Using Artificial Intelligence by Wadi’ Othmani, Arthur Coste, Dimitri Papathanassiou, David Morland

“…It could be particularly useful in patients with compliance issues. Confirmation with images from other centers will be necessary.…”
Get full text

An Integrated Framework for Ergonomic Performance Assessment in Food Manufacturing: A Case Study Using Ergo-VSM, AHP, and TLS by Tyas Yuli Rosiani, Meng-Hua Li, Dewi Rahmasari

“…Based on a three-tier classification system low (<60%), moderate (60–90%), and high (>90%) this score falls within the moderate category, indicating several areas require improvement. …”
Get full text

Evaluation of predictive maintenance efficiency with the comparison of machine learning models in machining production process in brake industry by Can Aydın, Burak Evrentuğ

“…Comprehensive examination and analysis of data were conducted to understand the symptoms and relationships of machine failures. ML classification methods were employed in the relevant study. …”
Get full text

Multimodal Fusion Multi-Task Learning Network Based on Federated Averaging for SDB Severity Diagnosis by Songlu Lin, Renzheng Tang, Yuzhe Wang, Zhihong Wang

“…However, real-world polysomnography (PSG) data often suffer from modality heterogeneity, label scarcity, and non-independent and identically distributed (non-IID) characteristics across institutions, posing significant challenges for model generalization and clinical deployment. To address these issues, we propose a federated multi-task learning (FMTL) framework that simultaneously performs sleep staging and SDB severity classification from seven multimodal physiological signals, including EEG, ECG, respiration, etc. …”
Get full text

A Systematic Review of Using Deep Learning Technology in the Steady-State Visually Evoked Potential-Based Brain-Computer Interface Applications: Current Trends and Future Trust Met... by A. S. Albahri, Z. T. Al-qaysi, Laith Alzubaidi, Alhamzah Alnoor, O. S. Albahri, A. H. Alamoodi, Anizah Abu Bakar

“…The literature’s findings in terms of the main aspects identified in existing applications of deep learning pattern recognition techniques in SSVEP-based BCI, such as feature extraction, classification, activation functions, validation methods, and achieved classification accuracies, are examined. …”
Get full text

The Enigmatic Odontogenic Keratocyst: A Cross-sectional Study of Odontogenic Cysts and Tumors Using Ki-67 by Pretty Prince Panakkal, Pramod Philip Matthews, Soma Susan, Nivia Mahadoon, Pinky Varghese, Afshan Pallikkalakathu

Get full text

YOLOv10-CBRC: A high-precision document image layout analysis model by Zhenjie Wu, Weilan Wang, Hongrui Li

“…However, two significant issues persist: (1) the inadequacy of Tibetan document datasets;(2) insufficient utilization of layout information by existing models. …”
Get full text

Securing the economic management and service infrastructure of banks via the use of artificial intelligence (MO-ILSTM) by Xintong Wu

“…The ILSTM approach is extended from binary data classification to various classifications, addressing the inability of economic management or service infrastructure to efficiently handle complex data processing needs and ensure prompt decision-making. …”
Get full text

RESEARCH OF THE MAIN ASPECTS OF INNOVATIVE POLICY OF THE ENTERPRISE IN THE DOMESTIC INDUSTRY by T. Barsova, O. Orlova, L. Putyatina

“…The article is devoted to topical issues related to improving the innovative activity in the industry. …”
Get full text

Elderly-onset rheumatoid arthritis: an outlook from a practicing rheumatologist by Ch. Baimukhamedov

“…All current challenges and concerns associated with rheumatoid arthritis (RA) in the elderly are analyzed from the point of view of a practicing rheumatologist, including issues of terminology and diagnostics, the need to develop classification criteria for RA presenting at old age. …”
Get full text

Using social media for environmental insight: a multi-model deep learning framework approach by Minglu Che, Chengyao Wang, Yanyun Nian, Pinqi Rao

“…Monitoring ecological conditions and detecting environmental issues are critical for safeguarding human health and sustainable development. …”
Get full text

Mapping urban functional zones with remote sensing and geospatial big data: a systematic review by Shouhang Du, Xiuyuan Zhang, Yichen Lei, Xin Huang, Wei Tu, Bo Liu, Qingyan Meng, Shihong Du

“…Meanwhile, future opportunities to these issues and the expansion of functions from 2D to 3D are discussed, in order to formulate an enhanced UFZ mapping framework.…”
Get full text

IRRITABLE BOWEL SYNDROME IN CHILDREN: DIAGNOSTICS AND MODERN APPROACHES TO THERAPY by S.Yu. Tereshchenko

“…In the article modern data on prevalence, diagnostic criteria and approaches to the treatment of irritable bowel in children are presented. The issues of the terminology and classification of recurrent abdominal pains in children are clarified, the basic pathophysiological mechanisms of the disease are indicated. …”
Get full text

Epidemiological Analysis of the COVID-19 Clusters in the Early Stages of the Epidemic in Shanghai, China: Pandemic-to-Epidemic Response Shift by Dechuan Kong, Qiwen Fang, Jian Chen, Linjie Hu, Yihan Lu, Yaxu Zheng, Yiyi Zhu, Bihong Jin, Wenjia Xiao, Shenghua Mao, Chenyan Jiang, Xiaohuan Gong, Sheng Lin, Ruobing Han, Xiao Yu, Qi Qiu, Xiaodong Sun, Hao Pan, Huanyu Wu

“…By enhancing household hygiene and developing a case classification and management system based on transmissibility, it is possible to better prevent and control regional COVID-19 outbreaks.…”
Get full text

Performance validation of deep-learning-based approach in stool examination by Kristal Dale Felimon Corpuz, Teera Kusolsuk, Benjamaporn Wongphan, Putza Chonsawat, Kaung Myat Naing, Siridech Boonsang, Veerayuth Kittichai, Chia-Kwung Fan, Santhad Chuwongin, Dorn Watthanakulpanich

“…Abstract Background Human intestinal parasitic infections (IPI) pose a significant global health issue caused by parasitic helminths and protozoa, affecting around 3.5 billion people worldwide, with more than 200,000 deaths annually. …”
Get full text

OptiNeoCare: optimisation of routine care in the management of severe perinatal asphyxia in full-term or near-term newborns – study protocol for analysis of suboptimal care by conf... by Pierre-Yves Ancel, Thierry Debillon, Gilles Cambonie, Geraldine Favrais, Gilles Kayem, Hendy Abdoul, Ayoub Mitha, Isabelle Guellec, Gauthier Loron, Charles Garabedian, Thomas Desplanches, Pierre Delorme, Eric Verspyck, Cyril Huissoud, Marie Delnaud, Blanche Graesslin, Pierre Tourneux, Maliha Badr, Sophie Chapeliere, Marie Brasseur-Daudruy, Max Gonzalez Estevez, Agnes Rigouzzo

“…Introduction Severe perinatal asphyxia at term or near term remains a critical public health issue, associated with high risks of neonatal death and hypoxic-ischaemic encephalopathy (HIE). …”
Get full text

Kinematic Adaptive Frame Recognition (KAFR): A Novel Framework for Video Segmentation via Frame Similarity and Surgical Tool Tracking by Huu Phong Nguyen, Shekhar Madhav Khairnar, Sofia Garces Palacios, Amr Al-Abbas, Melissa E. Hogg, Amer H. Zureikat, Patricio M. Polanco, Herbert J. Zeh, Ganesh Sankaranarayanan

“…Our approach follows these steps:1) Tracking phase: a YOLOv8 model is utilized to detect tools presented in the scene, 2) Similarity phase: Similarities between consecutive frames are computed by estimating variation in the spatial positions and velocities of the tools, 3) Classification phase: An X3D CNN is trained to classify segmentation. …”
Get full text