Explainable deep learning-based meta-classifier approach for multi-label classification of retinal diseases by Md. Moniruzzaman Hemal, Suman Saha

“…The two best-performing models were selected based on the validation results and were used as base models, which are subsequently combined using a meta-classifier. …”
Get full text

Faster-PPENet: Advancing Logistic Intelligence for PPE Recognition at Construction Sites by Jasim Alnahas

“…We have presented a robust feature extractor base by altering the conventional ResNet model. …”
Get full text

A nomogram involving immune‐inflammation index for predicting distant metastasis‐free survival of major salivary gland carcinoma following postoperative radiotherapy by Wenbin Yan, Xiaomin Ou, Chunying Shen, Chaosu Hu

“…Further external validation of the model is warranted for clinical utility.…”
Get full text

BiMER: Design and Implementation of a Bimodal Emotion Recognition System Enhanced by Data Augmentation Techniques by Emrah Dikbiyik, Onder Demir, Buket Dogan

“…Using datasets that were balanced by applying data augmentation, single-mode emotion recognition experiments were performed with models developed for Speech Emotion Recognition (SER) and Textual Emotion Recognition (TER). …”
Get full text

Estimation of econometric indicators on the basis of the regression analysis (on the example of food consumption by the population of the Arkhangelsk region) by S. A. Kochkin

“…For calculation of these indicators the nonlinear one-factorial regression model describing interrelation of the income and food expenditures of the population of the Arkhangelsk region was offered. …”
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

“…Specifically, the three-stage data enhancement process achieves a reduction in the WER for the fine-tuned Wav2Vec2-XLSR and Whisper-Tiny models by 9.81% and 6.56%, respectively, with an average WER of 13.58% for the best performing system. …”
Get full text

Experimental Study on Hysteresis During Cyclic Injection in Hierarchical Porous Media by Shuo Yang, Si Suo, Yixiang Gan, Shervin Bagheri, Lei Wang, Johan Revstedt

“…Finally, the upward trend of relative permeability with saturation was fitted by the van Genuchten model. The model parameter in the hierarchical structure is higher than that in the uniform structure, which is caused by extra pore space in 2nd‐order structure. …”
Get full text

Neutronics Analysis on High-Temperature Gas-Cooled Pebble Bed Reactors by Coupling Monte Carlo Method and Discrete Element Method by Kashminder S. Mehta, Braden Goddard, Zeyun Wu

“…Computational approaches are developed to perform high-fidelity neutronics analysis by coupling the superior modelling capacities of the Monte Carlo Method (MCM) and Discrete Element Method (DEM). …”
Get full text

ELNet: An Efficient and Lightweight Network for Small Object Detection in UAV Imagery by Hui Li, Jianbo Ma, Jianlin Zhang

“…Real-time object detection is critical for unmanned aerial vehicles (UAVs) performing various tasks. However, efficiently deploying detection models on UAV platforms with limited storage and computational resources remains a significant challenge. …”
Get full text

Mapping County-Level Rice Planting Areas by Joint Use of High-Resolution Optical and Time Series SAR Imagery by Jia Xu, Haojie Wang, Lin Qiu, Hui Wang, Yang Mu

“…Subsequently, the long short-term memory (LSTM)-based temporal classification model was utilized to acquire rice cultivation information at parcel scale using time-series Sentinel-1 SAR data. …”
Get full text

Association of real life postural transitions kinematics with fatigue in neurodegenerative and immune diseases by Robbin Romijnders, Arash Atrsaei, Rana Zia Ur Rehman, Lea Strehlow, Jèrôme Massoud, Chloe Hinchliffe, Victoria Macrae, Kirsten Emmert, Ralf Reilmann, C. Janneke van der Woude, Geert Van Gassen, Frédéric Baribaud, Teemu Ahmaniemi, Meenakshi Chatterjee, Bruno Kusznir Vitturi, Clémence Pinaud, Jérôme Kalifa, Stefan Avey, Wan-Fai Ng, Clint Hansen, Nikolay V. Manyakov, Walter Maetzler

“…Over 4 weeks, participants wore an IMU and reported fatigue levels four times daily. Using mixed-effects models, associations were identified between fatigue and specific kinematic features, such as 5th and 95th percentiles of sit-to-stand performance, suggesting that fatigue alters the control and effort of movement. …”
Get full text

Semi-Supervised Object Detection for Remote Sensing Images Using Consistent Dense Pseudo-Labels by Tong Zhao, Yujun Zeng, Qiang Fang, Xin Xu, Haibin Xie

“…Semi-supervised learning aims to improve the generalization performance of a model by exploiting the large quantity of unlabeled data together with limited labeled data during training. …”
Get full text

Hybrid machine learning-based 3-dimensional UAV node localization for UAV-assisted wireless networks by Workeneh Geleta Negassa, Demissie J. Gelmecha, Ram Sewak Singh, Davinder Singh Rathee

“…The model adapts to varying link densities, maintaining stable performance even in high-density scenarios. …”
Get full text

A New Incremental Learning Method Based on Rainbow Memory for Fault Diagnosis of AUV by Ying Li, Yuxing Ye, Zhiwei Zhang, Long Wen

“…Third, the RM is combined with the enhanced KAN network, and the stored samples are then combined with new task training data and fed into a multi-branch feature fusion neural network. The proposed RM-MFKAN model was conducted on the “Haizhe” dataset, and the experimental results have demonstrated that the proposed model achieves superior performance in fault diagnosis for AUVs.…”
Get full text

Indoor Wi-Fi fingerprint localization method based on CSI tensor decomposition by Mu ZHOU, Yuexin LONG, Qiaolin PU, Yong WANG, Wei HE

“…Aiming at the problem that as the scale of the fingerprint database increases, the training cost and processing complexity of CSI fingerprints will also greatly increase, an indoor Wi-Fi fingerprint localization method based on CSI tensor decomposition was proposed.Firstly, the tensor decomposition algorithm based on the PARAFAC (parallel factor) analysis model and the ALS (alternate least squares) iterative algorithm were combined to reduce the interference of the environment.Then, the tensor wavelet decomposition algorithm was used to extract the feature and obtain the CSI fingerprint.Finally, a localization model was established based on the PLSR (partial least squares regression) algorithm to realize the location estimation.Experimental results show that the confidence probability of the proposed method is 94.88% within 4 m localization error, which verifies that the proposed method has good localization performance while fitting the relationship between CSI location fingerprints and location coordinates.…”
Get full text

Fault Diagnosis Method of Plunger Pump Based on Meta-Learning and Improved Multi-Channel Convolutional Neural Network Under Small Sample Condition by Xiwang Yang, Jiancheng Ma, Hongjun Hu, Jinying Huang, Licheng Jing

“…The improved squeeze and excitation networks (ISENets) have been enhanced to concurrently enhance the network’s adaptive perception of the significance of each channel feature. On this basis, a meta-learning strategy is introduced, the learning process of model initialization parameters is improved, the network is optimized by a multi-task learning mechanism, and the initial parameters of the diagnosis model are adaptively adjusted, so that the model can quickly adapt to new fault diagnosis tasks on limited datasets. …”
Get full text

PPLA-Transformer: An Efficient Transformer for Defect Detection with Linear Attention Based on Pyramid Pooling by Xiaona Song, Yubo Tian, Haichao Liu, Lijun Wang, Jinxing Niu

“…Our model demonstrates satisfactory performance with minimal computational cost. …”
Get full text

Tennis ball detection based on YOLOv5 with tensorrt by Xiulei Zhang, Bin Li

“…First, YOLOv5 is used for target detection to achieve efficient tennis feature extraction. Second, TensorRT is introduced for inference acceleration to improve the real-time performance of the model through layer fusion and memory optimization. …”
Get full text

Incremental predictive value of liver fat fraction based on spectral detector CT for major adverse cardiovascular events in T2DM patients with suspected coronary artery disease by Min Wang, Tanglin Wei, Li Sun, Yanhua Zhen, Ruobing Bai, Xiaomei Lu, Yue Ma, Yang Hou

“…Moreover, compared with the traditional FRS model, the model that included LFF, CACS, and FRS showed stable clinical net benefit and demonstrated better predictive performance, with a C-index of 0.725, a net reclassification improvement (NRI) of 0.397 (95% CI 0.187–0.528, P < 0.01), and an integrated discrimination improvement (IDI) of 0.100 (95% CI 0.043–0.190, P < 0.01). …”
Get full text

Exploring the prognostic impact of triglyceride-glucose index in critically ill patients with first-ever stroke: insights from traditional methods and machine learning-based mortal... by Yang Chen, Zhenkun Yang, Yang Liu, Yuanjie Li, Ziyi Zhong, Garry McDowell, Coleen Ditchfield, Taipu Guo, Mingjuan Yang, Rui Zhang, Bi Huang, Ying Gue, Gregory Y. H. Lip

“…TyG was also correlated with ICU length of stay (r = 0.077), hospital length of stay (r = 0.042), and Glasgow Coma Score (r = -0.132). TyG and other six features were used to construct ML models. The random forest model performed best in internal validation with AUC (0.900) and G-mean (0.443), and in external validation with AUC (0.776) and G-mean (0.399). …”
Get full text