Cue prompt adapting model for relation extraction by Kai Wang, Yanping Chen, Kunjian Wen, Chao Wei, Bo Dong, Qinghua Zheng, Yongbin Qin

“…The performance achieves an impressive improvement, outperforming existing state-of-the-art models. …”
Get full text

Transformer-Based Motion Predictor for Multi-Dancer Tracking in Non-Linear Movements of Dancesport Performance by Zhiling Wang

“…Traditional Multi-Object Tracking (MOT) frameworks predominantly rely on appearance-based features and Kalman Filter-based motion models, which struggle with complex, non-linear motion patterns exhibited in dance performances. …”
Get full text

Recycling Performance of the Tire Remanufacturing with Production Capacity Constraints considering Carbon Tax and Technology Subsidy by Ruiqi Hu

“…After considering the manufacturer’s production capacity constraints and market preference, this paper presents a closed-loop supply chain of automotive tires which consists of a remanufacturer, a retailer, and a recycler, where used tires are collected and reused. Based on the features of the closed-loop tire remanufacturing supply chain, four Stackelberg models are developed to investigate the influences of the carbon tax and the technology subsidy on recycling performance. …”
Get full text

Calculation models of slabs with one-way connections by A. K. Yusupov, Kh. M. Muselemov, R. I. Vishtalov

“…The paper considers issues that allow constructing calculation models of slabs on discrete supports and solid arrays with one-sided connections, and provides algorithms that allow analyzing the performance of plate structures (two-dimensional structures in plan).Method. …”
Get full text

Explainable data mining model for hyperinsulinemia diagnostics by Nevena Rankovic, Dragica Rankovic, Mirjana Ivanovic, Igor Lukic

“…Medical datasets are often highly imbalanced and may contain irrelevant features that hinder predictive performance. To address these challenges in the medical data analysis, we propose a model employing Functional Principal Component Analysis (FPCA), which also accounts for outliers that could otherwise lead to the inclusion of irrelevant features. …”
Get full text

Comparative Analysis of Performance Metrics for Machine Learning Classifiers with a Focus on Alzheimer's Disease Data by Sivakani Rajayyan, Syed Masood Mohamed Mustafa

“…The ADNI database is used for the implementation process. To compare the performance of the proposed model, the OASIS dataset is applied to the model with the same algorithms and the accuracy of the algorithms is 98%, 99%, 99% and 100% respectively. …”
Get full text

Predictive model for necrotising fasciitis (NF) outcome by Sushmitha Kalakeri, Utsav Balar, Gehad Abdelkhalek

“…Clinical, laboratory and radiological parameters were assessed to identify key predictors of NF outcomes (Fig 1). Feature selection was performed using five machine learning models. …”
Get full text

Prediction of Highway Tunnel Pavement Performance Based on Digital Twin and Multiple Time Series Stacking by Gang Yu, Shuang Zhang, Min Hu, Y. Ken Wang

“…This paper (1) establishes an MTSS prediction model with heterogeneous stacking of eXtreme gradient boosting (XGBoost), the artificial neural network (ANN), random forest (RF), ridge regression, and support vector regression (SVR) component learners after exploratory data analysis (EDA); (2) proposes a method based on multiple time series feature extraction to accurately predict the pavement performance change trend, using the highway segment as the minimum computing unit and considering multiple factors; (3) uses grid search with the k-fold cross validation method to optimize hyperparameters to ensure the robustness, stability, and generalization ability of the prediction model; and (4) constructs a digital twin for pavement performance prediction to realize the real-time dynamic evolution of prediction. …”
Get full text

Automated grading of rectocele with an MRI radiomics model by Weiwei Lai, Shuang Wang, Jiannan Li, Rui Qi, Zeyun Zhao, Min Wang

“…The radiomics features were reduced in dimension, and a machine learning model was developed using a Support Vector Machine (SVM). …”
Get full text

High performance adaptive step size fractional numerical scheme for solving fractional differential equations by Mudassir Shams, Ahmad Alalyani

“…These equations provide a powerful framework for describing phenomena with memory effects and hereditary features that standard integer-order models cannot account for. …”
Get full text

Textual similarity for legal precedents discovery: Assessing the performance of machine learning techniques in an administrative court by Hugo Mentzingen, Nuno António, Fernando Bacao, Marcio Cunha

“…Our findings reveal that models focusing on granular text representations perform optimally, especially when extracting concepts and relations. …”
Get full text

Early Prediction of Students’ Performance Through Deep Learning: A Systematic and Bibliometric Literature Review by İhsan Hakan Selvi, Tuğba Yıldız, Orhan Torkul, Ahmet Kala

“…The review addresses five key research questions, including the distribution of studies by publication year, type, and education level; the datasets and features used; DL models and techniques; the timing of early predictions; and the challenges, limitations, and opportunities encountered. …”
Get full text

A Novel High Performance Object Identification Approach in Care Homes Using Gaussian Preprocessing by Sara Auweiler, Melina Mueller, Diana Puhla, Pascal Penava, Ricardo Buettner

“…Building on this, we use Gaussian blurring as an innovative preprocessing technique to improve model accuracy by reducing high-frequency noise and enhancing feature extraction. …”
Get full text

Rough-and-Refine Model for Scene Graph Generation by Li Junliang, Lv Shirong, Li Wei

“…Visualization experiments conducted in various scenarios validate the model's exceptional capability for scene graph generation and illustrate the performance enhancement of the Refine model over the Rough model.…”
Get full text

Numerical Study on the Wave Attenuation Performance of a Novel Partial T Special-Type Floating Breakwater by Xuanqi Ruan, Hongliang Qian, Jingxuan Dai, Feng Fan, Shuang Niu

“…First, the User-Defined Function (UDF) feature in ANSYS Fluent was employed to compile the six degrees of freedom (6-DOF) motion model. …”
Get full text

Prestressed ultra-high performance concrete (UHPC) beams for reusable structural systems: design and testing by Dario Redaelli, Jonathan Moix, Alex Muresan, Jan Brütting, Corentin Fivet

“…In the first part of this contribution, the main features of the new structural system and preliminary design assumptions for UHPC modules are briefly outlined. …”
Get full text

Kinematic performance analysis of a 2RPU-RPUR parallel mechanism without parasitic motion by CHE Linxian, HUANG Xin, PENG Siyang, WANG Yuanze, LAN Jun

Get full text

Identification of rice leaf disease based on DepMulti-Net by Kui Hu, Kui Hu, Xinying Zheng, Xinying Zheng, Xinyao Su, Lei Wu, Yongmin Liu, Yongmin Liu, Zhenhua Deng

“…This research presents DepMulti-Net, a novel rice disease and pest identification model, designed to overcome the challenges of complex background interference, difficult disease feature extraction, and large model parameter volume in rice leaf disease identification. …”
Get full text

STSG: A Short Text Semantic Graph Model for Similarity Computing Based on Dependency Parsing and Pre-trained Language Models by Hai Liao, Yan Liang, Song Chen, Lingyun Xiang, Zhimin Chang, Yun Xiao

“…A text semantic graph layer based on the graph attention network (GAT) is also realized, which regards word vectors as node features and word dependency as edge features. The attention mechanism of GAT can identify the importance of different word correlations and solve the word dependency modeling effectively. …”
Get full text

Green Supply Chains: Feature Analysis and Key Node Identification in Multi-Layer Supply Chain Networks Based on Fused Multi-Scale Metric by Shanshan Wang, Ruoxuan AI, Shoukat Iqbal Khattak, Sadia Tariq

“…Still, supply chain experts have paid little attention to how inter-layer information, intrinsic features of real-world networks, and ESG performance affect the significance of node identification. …”
Get full text