An artificial intelligence model to predict mortality among hemodialysis patients: A retrospective validated cohort study by Zhong Peng, Shuzhu Zhong, Xinyun Li, Fengyi Yu, Zixu Tang, Chunyuan Ma, Zihao Liao, Song Zhao, Yuan Xia, Haojun Fu, Wei Long, Mingxing Lei, Zhangxiu He

“…The machine learning algorithms used to develop the models for the training group included logistic regression (LR), decision tree (DT), extreme gradient boosting machine (eXGBM), neural network (NN), and support vector machine (SVM). The predictive performances of all the models were evaluated using discrimination and calibration. …”
Get full text

Exploratory multi-cohort, multi-reader study on the clinical utility of a deep learning model for transforming cryosectioned to formalin-fixed, paraffin-embedded (FFPE) images in b... by Xue Chao, Yu Wu, Xi Cai, Jiehua He, Chengyou Zheng, Mei Li, Rongzhen Luo, Lijuan Song, Xiaoqin Li, Wentai Feng, Shuoyu Xu, Peng Sun

“…The model employs a modified generative adversarial network (GAN) enhanced with an attention mechanism to correct artifacts and a self-regularization constraint to preserve clinically significant features. …”
Get full text

Fault Prediction and Reconfiguration Optimization in Smart Grids: AI-Driven Approach by David Carrascal, Paula Bartolomé, Elisa Rojas, Diego Lopez-Pajares, Nicolas Manso, Javier Diaz-Fuentes

“…The study applies models based on Machine Learning (ML) and Deep Learning (DL) techniques, specifically evaluating Random Forest (RF) and Support Vector Machine (SVM) as ML methods, and Artificial Neural Network (ANN) as a DL method, evaluating each for accuracy, precision, and recall. …”
Get full text

Constitutive model of metal rubber material considering plastic accumulation behavior by FENG Zhipeng, YANG Fang, FU Hailong, AI Shigang, WANG Yue, YUAN Liangyang

“…Fabricated from metallic wires such as 304 stainless steel and nickel-titanium shape memory alloys through sophisticated manufacturing processes including spiral winding, planar weaving, and cold compression molding, this advanced material features an intricate three-dimensional porous network architecture composed of numerous interlaced metallic coils. …”
Get full text

DeepOmicsSurv: a deep learning-based model for survival prediction of oral cancer by Deepali, Neelam Goel, Padmavati Khandnor

“…The model's performance was evaluated against DeepSurv, DeepHit, Cox Proportional Hazards (CoxPH), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN). …”
Get full text

Detection and mapping of Antarctic lichen using drones, multispectral cameras, and supervised deep learning by Narmilan Amarasingam, Juan Sandino, Ashray Doshi, Diana King, Elka Blackman, Johan Barthelemy, Barbara Bollard, Sharon A. Robinson, Felipe Gonzalez

“…Two DL methods were evaluated to classify and map Usnea spp., Umbilicaria and Pseudephebe species (black lichen), moss and non-vegetation: method (1) standalone DL model fitting, namely fully convolutional network (FCN), U-Net, and Deeplabv3+, with semi-automatic labelling thresholding using VIs; and method (2) ensemble stacking by using eXtreme gradient boosting (XGBoost) as the input model, whose predictions are used as features for training a U-Net model. …”
Get full text

Research on Reservoir Hydrocarbon-Bearing Property Identification Method Based on Logging Data and Machine Learning by Chunyong Yu, Kaixuan Qu, Li Peng

“…Subsequently, seven model inputs were formed by combining these three types of well-logging data, and their performance was evaluated in combination with three machine learning techniques: K-nearest neighbor, random forest, and artificial neural networks. …”
Get full text

Development and Validation of a Brain Aging Biomarker in Middle-Aged and Older Adults: Deep Learning Approach by Zihan Li, Jun Li, Jiahui Li, Mengying Wang, Andi Xu, Yushu Huang, Qi Yu, Lingzhi Zhang, Yingjun Li, Zilin Li, Xifeng Wu, Jiajun Bu, Wenyuan Li

“…We proposed a novel brain vision graph neural network (BVGN), incorporating neurobiologically informed feature extraction modules and global association mechanisms to provide a sensitive deep learning–based imaging biomarker. …”
Get full text

Preparation of future teachers for innovative activities in pedagogical and technological educational environment by N. I. Naumkin, N. N. Shekshaeva, V. F. Kupryashkin, E. V. Zabrodina

“…The environment includes conceptually-targeted, infrastructural, content-based, psychological-didactic, methodological-technological and relaxation-diagnostic components, its features are the following: 1) focus on innovative training of technology teachers as directly related to the material objects of the innovative economy of the country; 2) universality in the form of the possibility of using it to solve other educational tasks; 3) graphical visualisation of the environment model with an indication of the hierarchy and interrelation of components, its scale, combinatoricity and functional sufficiency; 4) compliance of the environment with all the requirements of regulatory documents on educational activities at the university; 5) possibility of full-scale implementation of modern approaches to learning (innovative, personalised, environmental, project, etc.); 6) possibility of constant monitoring and control of the implementation of the environment within its relaxation and diagnostic component; 7) use of modern educational technologies, including digital; 8) possibility of obtaining specialised knowledge and studying other disciplines within the framework of using network learning; 9) innovativeness of the environment, determined by the novelty of the approach to teaching the teachers innovation technology and its effectiveness.To teach innovation activity in this environment, a model of a methodological system for the formation of competence in innovation activity among future technology teachers has been created, combining conceptually-targeted, meaningful, instrumental-activity and reflexive-evaluative components. …”
Get full text

Study of the earthquakes source parameters, site response, and path attenuation using P and S-waves spectral inversion, Aswan region, south Egypt by Saadalla Hamada, Qaysi Saleh, Hayashida Takumi, Hamada Mona

“…Aswan broadband seismic network with highly sensitive sensors and good station coverage gave the opportunity to study the seismicity distribution, focal depth, the fault plane solution, the attenuation of seismic wave, the station sites response, and the source spectra of Aswan earthquakes with magnitude (ML)\left({M}_{{\rm{L}}}) between 0.8 and 4.2 recorded from 2010 to 2023 comprehensively. …”
Get full text

Building Damage Detection with UNet-Backbone Fusion in High-Resolution Satellite Imagery: 2023 Morocco Earthquake by S. Holail, T. Saleh, T. Saleh, X. Xiao, A. H. Ali, D. Li

“…The network leverages multi-scale feature differentiation to model spatial and temporal semantic relationships, addressing the issue of intra-class semantic variation. …”
Get full text

Gut microbiota maturation and early behavioral and cognitive development by Ziliang Zhu, Yue Yang, Tinu M. Samuel, Tengfei Li, Weiyan Yin, Brittany R. Howell, Seoyoon Cho, Heather C. Hazlett, Jed T. Elison, Hongtu Zhu, Norbert Sprenger, Weili Lin

“…Specifically, we extracted gut microbiota characteristics at three scale levels: diversity measures, microbial networks, and subject-wise longitudinal trajectory features, shedding light on how associations between cognition/temperament and gut microbiota may differ at global (diversity), ecological (microbial networks) and subject-wise levels. …”
Get full text

QoS-Based Resource Allocation in Multicarrier NOMA-IBFD Cellular System With Sectorization by Ananda Kumar Karem, A. Krishna Chaitanya, Satya Kumar Vankayala, Seungil Yoon, Ganesh Chandrasekaran, Karthik Muralidhar

“…Subsequently, we extend our investigation at sector level to obtain a comprehensive understanding of network dynamics within a more confined coverage area. …”
Get full text

Hydra-Mask-RCNN: An Adaptive HydraNet Architecture for Autonomous Aerial Vehicle Object Detection by Sara Naseri Golestani, Mahdi SadeghiBakhi, King Fai Ma, Henry Leung

“…By integrating an adaptive branching network (ABN) with HydraNet, HMRCNN improves feature extraction and object detection capabilities. …”
Get full text

Estimation of the water content of needles under stress by Erannis jacobsoni Djak. via Sentinel-2 satellite remote sensing by Jiaze Guo, Xiaojun Huang, Xiaojun Huang, Xiaojun Huang, Debao Zhou, Junsheng Zhang, Gang Bao, Gang Bao, Siqin Tong, Siqin Tong, Yuhai Bao, Yuhai Bao, Dashzebeg Ganbat, Dorjsuren Altanchimeg, Davaadorj Enkhnasan, Mungunkhuyag Ariunaa

“…Multiple vegetation indices are screened via recursive feature elimination cross validation (RFECV), and then support vector regression (SVR) and back-propagation neural network (BP) models are used to predict the leaf weight content fresh (LWCF) and leaf weight content dry (LWCD) of needles over a large area. …”
Get full text

Bicontinuous Nanophasic Conetworks of Polystyrene with Poly(dimethylsiloxane) and Divinylbenzene: From Macrocrosslinked to Hypercrosslinked Double-Hydrophobic Conetworks and Their... by Anna Petróczy, István Szanka, András Wacha, Zoltán Varga, Yi Thomann, Ralf Thomann, Rolf Mülhaupt, Laura Bereczki, Nóra Hegyesi, Béla Iván

“…The Korsmeyer–Peppas type evaluation of the swelling data indicates hindered Fickian diffusion of both solvents in the conetwork organogels. …”
Get full text

SympCoughNet: symptom assisted audio-based COVID-19 detection by Yuhao Lin, Xiu Weng, Bolun Zheng, Weiwei Zhang, Zhanjun Bu, Yu Zhou

“…To address this limitation, we propose SympCoughNet, a deep learning-based COVID-19 audio classification network that integrates cough sounds with clinical symptom data. …”
Get full text

High resolution weld semantic defect detection algorithm based on integrated double U structure by Xiaoyan Li, Yi Wei, Zhigang Lv, Peng Wang, Liangliang Li, Mengyu Sun, Chu Wang

“…In terms of model architecture, by improving U2Netp and UNet networks, MC-SPP module (multi-connection spatial pyramid pooling), RMAG module (residual multi-add gating recurrent unit), HDC-CBAM module (hybrid dilated convolution-convolutional block attention) and CCM module (cross-layer connection fusion) were integrated to form a cascade network with multi-level feature fusion capability. …”
Get full text

Comparison and Interpretability Analysis of Deep Learning Models for Classifying the Manufacturing Process of Pigments Used in Cultural Heritage Conservation by Inhee Go, Yu Fu, Xi Ma, Hong Guo

“…Conversely, CNNs provided more detailed interpretations, offering valuable insights into the learned feature maps and hierarchical data processing. Despite its interpretability challenges, the ViT outperformed the CNNs across all evaluation metrics. …”
Get full text

IRGL-RRI: interpretable graph representation learning for plant RNA–RNA interaction discovery by Qingquan Liao, Xuchong Liu, Wei Zhao, Yu Tong, Fangzheng Xu, Xinxin Liu, Yifan Chen

“…A graph representation based on a masking strategy and regularization enhances RNA feature extraction. Furthermore, an RRI modeling approach combining Kolmogorov-Arnold Networks (KAN) and multi-scale fusion is proposed to deeply resolve the complex dynamic interaction mechanisms of RRIs and improve model interpretability. …”
Get full text