Diagnosis of non-puerperal mastitis based on “whole tongue” features: non-invasive biomarker mining and diagnostic model construction by Siyuan Tu, Yulian Yin, Lina Ma, Hongfeng Chen, Meina Ye

“…The microbiota composition was assessed using 16S rRNA gene sequencing (V3–V4 region) and bioinformatic pipelines (QIIME2, DADA2). Based on clinical, imaging, and microbial features, three machine learning models—logistic regression (LR), support vector machine (SVM), and gradient boosting decision tree (GBDT)—were trained to distinguish NPM.ResultsThe GBDT model achieved a superior diagnostic performance (AUROC = 0.98, accuracy = 0.95, and specificity = 0.95), outperforming the LR (AUROC = 0.98, accuracy = 0.95, and specificity = 0.90) and SVM models (AUROC = 0.87, accuracy = 0.80, and specificity = 0.75). …”
Get full text

Predictions of Multilevel Linguistic Features to Readability of Hong Kong Primary School Textbooks: A Machine Learning Based Exploration by Zhengye Xu, Yixun Li, Duo Liu

Get full text

Visualization Analysis of Integrating College Sports Training and Psychology into Basketball Physical Education Teaching System Based on Image Recognition Algorithm by Junzhang Cheng, Lingtao Wen, Baolei Zhang

“…On this basis, a basketball movement model based on ORB (Oriented FAST and Rotated BRIEF) local feature extraction has been proposed, and a basketball teaching visualization analysis system has been constructed. …”
Get full text

Bridge Damage Identification Using Time-Varying Filtering-Based Empirical Mode Decomposition and Pre-Trained Convolutional Neural Networks by Shenghuan Zeng, Jian Cui, Ding Luo, Naiwei Lu

“…This study presents a bridge damage identification framework integrating time-varying filtering-based empirical mode decomposition (TVFEMD) with pre-trained convolutional neural networks (CNNs). …”
Get full text

A Remaining Useful Life Prediction Method for Rolling Bearings Based on Hierarchical Clustering and Transformer–GRU by Wenping Lei, Xing Dong, Fuyuan Cui, Guangzhong Huang

“…However, existing RUL prediction methods face two main challenges: (1) feature construction methods based on predefined indicators often ignore the correlation among features; and (2) single models typically yield limited prediction accuracy. …”
Get full text

An ECG-Based Model for Left Ventricular Hypertrophy Detection: A Machine Learning Approach by Marion Taconne, Valentina D.A. Corino, Luca Mainardi

“…We propose an automatic LVH detection method based on ECG-extracted features and machine learning. …”
Get full text

Fault Prediction of Hydropower Station Based on CNN-LSTM-GAN with Biased Data by Bei Liu, Xiao Wang, Zhaoxin Zhang, Zhenjie Zhao, Xiaoming Wang, Ting Liu

“…Finally, a dynamic multi-task training algorithm is proposed to ensure the convergence and training efficiency of the deep models. …”
Get full text

Research on bolt loosening recognition based on sound signal and GA-SVM–RFE by Li-Ye Hou, De-Bing Zhuo

“…Abstract In response to the difficulties faced in detecting bolt connection damage in steel truss structures, this paper proposes a bolt loosening identification method based on sound signal analysis, a Genetic Algorithm-Optimized Support Vector Machine (GA-SVM), and Recursive Feature Elimination (RFE). …”
Get full text

Toward an Accurate Liver Disease Prediction Based on Two-Level Ensemble Stacking Model by Marghany Hassan Mohamed, Botheina Hussein Ali, Ahmed Ibrahim Taloba, Ahmad O. Aseeri, Mohamed Abd Elaziz, Shaker El-Sappagah, Nora Mahmoud El-Rashidy

“…Also, a two-level ensemble stacking model is applied based on several meta-ensemble classifiers and the feature selection technique to optimize the accuracy of the ensemble classifiers. …”
Get full text

Real-Time Recognition and Localization of Kiwifruit Based on Improved YOLOv5s Algorithm by Jin-Sui Dai, Zhi-Qin He

“…First, data enhancement is implemented in the training strategy to ensure the model’s efficient learning and generalization ability in complex environments; then the Coordinate Attention mechanism is introduced to highlight the key features of the image and improve detail detection; Secondly, the Bidirectional Feature Pyramid Network structure is used to optimize the feature fusion and strengthen the information exchange between different layers through bidirectional connectivity; then, the loss function is optimized to improve the bounding box localization accuracy; and finally, the combined with the binocular vision stereo matching algorithm Semi-Global Block Matching to obtain the spatial location information of Kiwifruit. …”
Get full text

Broad learning system based on attention mechanism and tracking differentiator by LIAO Lüchao, ZOU Weidong, YANG Jialong, LU Huihuang, XIA Yuanqing, GAO Jianlei

“…In terms of model structure, A-TD-BLS introduced self-attention mechanism to the original BLS, and further fused and transformed the extracted features through attention weighting to improve the feature learning ability.In terms of model training methods, a weight optimization algorithm based on tracking differentiator was designed.This method effectively alleviates the overfitting phenomenon of the original BLS by limiting the size of the weight values, significantly reduces the influence of the number of hidden layer nodes on model performance and makes the generalization performance more stable.Moreover, the training algorithm was extended to the BLS incremental learning framework, so that the model can improve performance by dynamically adding hidden layer nodes.Multiple experiments conducted on some benchmark datasets show that compared to the original BLS, the classification accuracy of A-TD-BLS is increased by 1.27% on average on classification datasets and the root mean square error of A-TD-BLS is reduced by 0.53 on average on regression datasets.Besides, A-TD-BLS is less affected by the number of hidden layer nodes and has more stable generalization performance. …”
Get full text

Partial Discharge Pattern Recognition of Switchgear Based on Residual Convolutional Neural Network by Xueyou HUANG, Jun XIONG, Yu ZHANG, Hui LIU, Lu CHEN, Xianglin MENG, Xiuchen JIANG

“…The experimental results show that the recognition correct rate of the proposed method reaches 96.06%, at least 20.22% higher than that of the traditional recognition methods, and the recognition rate can be improved more with the increase of the number of samples in the training set. Through integrated use of the feature layer fusion module and residual module, the proposed model is significantly improved in the generalization performance and is more suitable for practical engineering.…”
Get full text

Silent speech recognition using visual cascading fusion of tongue-lip movements based on pre-trained and fine-tuned model by Chongchong Yu, Xuening Wang, Zhaopeng Qian

“…Besides, the pre-trained and fine-tuned frameworks based on Visual-HuBERT using masked technology are used to address the overfitting problems of model due to a lack of training data. …”
Get full text

Accurate detection of critical LLFs and LGFs in PV arrays based on deep reinforcement learning using proximal policy optimization (PPO) by Sherko Salehpour, Aref Eskandari, Amir Nedaei, Mohammad Gholami, Mohammadreza Aghaei

“…Additionally, to carry out the dataset dimensionality reduction, thus simplifying the training process, a two-stage feature engineering process has been implemented, including a feature importance finding stage using the permutation technique and a feature selection stage. …”
Get full text

CDIO IDEOLOGY IN MATH TRAINING by Yuliya V. Vainshtein, Viktoriya A. Shershneva, Konstantin V. Safonov

Get full text

Research on early warning model of coal spontaneous combustion based on interpretability by Huimin Zhao, Xu Zhou, Jingjing Han, Yixuan Liu, Zhe Liu, Shishuo Wang

“…XGBoost, SVR, RF, LightGBM and BP models were selected as base models to establish an early warning model for CSC based on the stacking integration architecture. …”
Get full text

Research on Aerospace Text Classification Based on BERT-LSTM Model by AN Rui, CHEN Hailong, AI Siyu, CUI Xinying

“…Due to the problems of other existing models, such as the inability to extract the weights of the key parts of the text, the model classification is inaccurate, and it is difficult to adapt to the heavy work environment in the space text classification work. Therefore, based on the fusion of the BERT pre-training model and the LSTM neural network model, we combine the multi-feature embedding and multi-network fusion methods to construct the BERT-LSTM model, using the BERT model to convert the input text into word vectors. …”
Get full text

A Pilot Study: Sleep and Activity Monitoring of Newborn Infants by GRU-Stack-Based Model Using Video Actigraphy and Pulse Rate Variability Features by Ádám Nagy, Zita Lilla Róka, Imre Jánoki, Máté Siket, Péter Földesy, Judit Varga, Miklós Szabó, Ákos Zarándy

“…In this work, we provide a Gated Recurrent Unit (GRU)-stack-based solution that works on a dynamic feature set generated by computer vision methods from the cameras’ video feed and patient monitor to classify the activity phases of infants adapted from the NIDCAP (Newborn Individualized Developmental Care Program) scale. …”
Get full text

KNEE OSTEOARTHRITIS STAGE CLASSIFICATION BASED ON HYBRID FUSION DEEP LEARNING FRAMEWORK by Delveen Luqman Abd Alnabi, Shereen Sh Ahmed, Nisreen Luqman Abd Alnabi

“…The feature-level, decision-level, score-level, and meta-based fusion technologies were also performed on the outputs of the best three trained models to minimize the individual models’ errors. …”
Get full text

Alignment-Based Pseudo-Label Generation With Collaborative Filtering Mechanism for Enhanced Cross-Domain Aspect-Based Sentiment Analysis by Yadi Xu, Noor Farizah Ibrahim

“…This method effectively reduces style feature differences between domains and solves adversarial training limitations in terms of convergence and stability, thus improving the quality of pseudo-tag generation. …”
Get full text