A knowledge‐based materials descriptor for compositional dependence of phase transformation in NiTi shape memory alloys DOI Creative Commons
Cheng Li,

Qingkai Liang,

Yumei Zhou

et al.

Materials Genome Engineering Advances, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 11, 2024

Abstract This study presents ∆τ, a novel descriptor that captures the compositional dependence of phase transformation temperature (Ap) in NiTi‐based shape memory alloys (SMAs). Designed to address complexity multicomponent SMAs, ∆τ was integrated into symbolic regression (SR) and kernel ridge (KRR) models, yielding substantial improvements predicting key functional properties: temperature, enthalpy, thermal hysteresis. Using KRR model with we explored NiTiHfZrCu space, identifying six promising high Ap (>250°C), large enthalpy (>27 J/g), low Experimental validation confirmed model's accuracy showing high‐temperature behavior hysteresis, suitable for high‐performance applications aerospace nuclear industries. These findings underscore power domain‐informed descriptors like enhancing machine learning‐driven materials design.

Language: Английский

Cotton Area Extraction Based on High-Resolution Sentinel-2 Satellite Images DOI Creative Commons
Xihuizi Liang,

Haiyan Tian,

Wen Wang

et al.

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Journal Year: 2025, Volume and Issue: 18, P. 10924 - 10936

Published: Jan. 1, 2025

Language: Английский

Citations

0
Optimizing foreign fiber segmentation performance with DeepLab V3+ and GAN in industrial IoE environments DOI Creative Commons
Shuo Yang, Jingbin Li, Yang Li

et al.

Digital Communications and Networks, Journal Year: 2025, Volume and Issue: unknown

Published: March 1, 2025

Language: Английский

Citations

0
Integrating Large Language Models with Cross-modal Data Fusion for Advanced Intelligent Transportation Systems in Sustainable Cities Development DOI
Jiachen Jiang, Yang Li, Jing Nie

et al.

Applied Soft Computing, Journal Year: 2025, Volume and Issue: unknown, P. 113278 - 113278

Published: May 1, 2025

Language: Английский

Citations

0
Machine-learning models for diagnosis of rotator cuff tears in osteoporosis patients based on anteroposterior X-rays of the shoulder joint DOI Creative Commons
Yu Zhao, Jingjing Qiu, Yang Li

et al.

SLAS TECHNOLOGY, Journal Year: 2024, Volume and Issue: 29(4), P. 100149 - 100149

Published: May 23, 2024

This study aims to diagnose Rotator Cuff Tears (RCT) and classify the severity of RCT in patients with Osteoporosis (OP) through analysis shoulder joint anteroposterior (AP) X-ray-based localized proximal humeral bone mineral density (BMD) measurements clinical information based on machine learning (ML) models.

Language: Английский

Citations

2
Detection of Ginkgo biloba seed defects based on feature adaptive learning and nuclear magnetic resonance technology DOI

Shuaishuai Zhao,

Maocheng Zhao,

Liang Qi

et al.

Journal of Plant Diseases and Protection, Journal Year: 2024, Volume and Issue: 131(6), P. 2111 - 2124

Published: Oct. 12, 2024

Language: Английский

Citations

1
Few-shot learning in intelligent agriculture: A review of methods and applications DOI
Jing Nie, Yichen Yuan, Yang Li

et al.

Tarım Bilimleri Dergisi, Journal Year: 2023, Volume and Issue: unknown

Published: Dec. 7, 2023

Due to the high cost of data acquisition in many specific fields, such as intelligent agriculture, available is insufficient for typical deep learning paradigm show its superior performance. As an important complement learning, few-shot focuses on pattern recognition tasks under constraint limited data, which can be used solve practical problems application fields with scarcity. This survey summarizes research status, main models and representative achievements from four aspects: model fine-tuning, meta-learning, metric enhancement, especially introduces learning-driven applications agriculture. Finally, current challenges development trends agriculture are prospected.

Language: Английский

Citations

1
The flow field simulation and suction structure optimal design of the dual-airway pneumatic fallen jujube fruit pickup device​ DOI Open Access

HUIZHE DING,

Jingbin Li, Huting Wang

et al.

TURKISH JOURNAL OF AGRICULTURE AND FORESTRY, Journal Year: 2024, Volume and Issue: 48(1), P. 26 - 42

Published: Feb. 1, 2024

In order to explore the characteristics of flow field in cavity dual-airway pneumatic fallen jujube fruit pickup device key components under action negative pressure air and optimize structural parameters device, a numerical simulation model body mouth was constructed based on computational fluid dynamics. First all, influence center partition suction analyzed. Secondly, taking velocity unevenness coefficient as response index, single factor test carried out structure obtain optimal value interval each factor, then through orthogonal surface analysis composite optimization method, parameter combination determined follows: The falloff angle is 91.37°, opening width 50mm, flanging radius 6.45mm, relative height 20mm. this case, 5.89%. Finally, validation tests are out. results show that 6.22%, 6.60% 6.45%, respectively. maximum deviation from predicted 0.71% error 12.05%. This study not only great significance research complex design equipment, but also provides reference for development mechanized equipment.

Language: Английский

Citations

0
Detection of Heart Disease Using ANN DOI

Pooja Dehankar,

Susanta Das

Advances in medical diagnosis, treatment, and care (AMDTC) book series, Journal Year: 2024, Volume and Issue: unknown, P. 182 - 196

Published: May 30, 2024

Heart disease remains one of the leading causes mortality worldwide. Early detection and accurate diagnosis are crucial for effective treatment prevention cardiac complications. Artificial neural networks (ANNs) have emerged as powerful tools heart detection, leveraging their ability to learn complex patterns from data. This chapter comprehensively reviews recent studies developments in application ANNs highlighting strengths, challenges, future directions. The also explores opportunities field, imagining use federated learning collaborative model development, integration AI-driven decision support systems into standard clinical workflows, explainable AI techniques improve interpretability. It investigates a number methods, such multimodal data sources, convolutional (CNNs) image-based diagnosis, risk prediction models, ECG analysis.

Language: Английский

Citations

0
A performance-driven framework with a system-of-systems approach for augmented asset management of railway system DOI Creative Commons
Jaya Kumari, Ramin Karim, Pierre Dersin

et al.

International Journal of Systems Assurance Engineering and Management, Journal Year: 2024, Volume and Issue: 15(8), P. 3988 - 4002

Published: July 20, 2024

Abstract The railway system is a complex technical system-of-systems (SoS). To address the complexity of system, holistic approach needed that facilitates development an appropriate asset management regime. A systems-of-systems (SoS) considers nature comprising interconnected subsystems like rolling stock and infrastructure. Neglecting these interdependencies risks sub-optimization overall performance. Asset utilising SoS ensures focus on requirements. efficiency effectiveness based aspects such as availability, reliability, safety enhance aspects, monitoring, improvement key performance indicators (KPIs) emphasizing increased capacity reduced operational costs essential. KPIs offer quantifiable parameters for optimization. Augmenting through data-driven technologies can improve management. However, challenges persist in implementation solutions due to system’s lack perspective. systematic performance-driven framework with augmented provides handrail utilisation requirements at centre while developing proposed aims establish clear relationship between KPIs, sub-systems components aiding organizations design implementation. This paper explains important demonstrates application maintenance planning high value fleet stock. Adoption expected are aligned support decision making.

Language: Английский

Citations

0
A Joint Network of Super-Resolution and Active Learning for Agricultural Land Classification DOI Creative Commons
Jiachen Yang, Zechen Wang, Desheng Chen

et al.

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Journal Year: 2024, Volume and Issue: 17, P. 13669 - 13677

Published: Jan. 1, 2024

Remote sensing image analysis plays a vital role in achieving intelligent agricultural monitoring. However, the acquisition of high-resolution remote data can be resource-intensive, resulting an imbalance between training samples and artificial intelligence model parameters. In order to achieve accurate land recognition limited-resolution images, this article proposes joint network super-resolution active learning (AL). The introduces pretrained optimizes for classification tasks. It effectively detects detailed features completes reconstruction. Based on reconstructed data, AL algorithm is proposed with DBSS. balances contributions interclass boundary samples. Furthermore, we propose semisupervisory assistance strategy based consistency, it fully utilizes predictive power deep models aiming reduce labeling costs. This framework proved effective by experiments dataset, reduces cost annotation improves efficiency low-resolution sensing.

Language: Английский

Citations

0