Preoperative assessment of tertiary lymphoid structures in stage I lung adenocarcinoma using CT radiomics: a multicenter retrospective cohort study by Xiaojiang Zhao, Yuhang Wang, Mengli Xue, Yun Ding, Han Zhang, Kai Wang, Jie Ren, Xin Li, Meilin Xu, Jun Lv, Zixiao Wang, Daqiang Sun

“…Tumor segmentation was achieved using an automatic virtual adversarial training segmentation algorithm based on a three-dimensional U-shape convolutional neural network (3D U-Net). Radiomic features were extracted from the tumor and peritumoral areas, with extensions of 2 mm, 4 mm, 6 mm, and 8 mm, respectively, and deep learning image features were extracted through a convolutional neural network. …”
Get full text

FAViTNet: An Effective Deep Learning Framework for Non-Invasive Fetal Arrhythmia Diagnosis by Bipin Samuel, Malaya Kumar Hota

“…Channel-wise calibration is utilized to attain more attention to the deep feature maps acquired from the ghost network. The transformer encoder block effectively attains the long-term dependencies from the 1D embedded features with gated linear unit (GLU)-based multi-head self-attention where deep features are learned to discern fetal arrhythmia effectively. …”
Get full text

Self-Supervised Learning Meets Custom Autoencoder Classifier: A Semi-Supervised Approach for Encrypted Traffic Anomaly Detection by A. Ramzi Bahlali, Abdelmalik Bachir, Abdeldjalil Labed

“…In this paper, we propose a semi-supervised learning framework that leverages Self-Supervised Learning (SSL) to learn discriminative representations from unlabeled network traffic. We design a novel pretext task that predicts important masked features, enabling the model to capture meaningful structure in the data. …”
Get full text

Sleep deprivation disturbed regional brain activity in healthy subjects: evidence from a functional magnetic resonance-imaging study by Wang L, Chen Y, Yao Y, Pan Y, Sun Y

“…ALFF was used to assess local brain features. The mean ALFF-signal values of the different brain areas were evaluated to investigate relationships with clinical features and were analyzed with a receiver-operating characteristic curve.Results: Compared with NS subjects, SD subjects showed a lower response-accuracy rate, longer response time, and higher lapse rate. …”
Get full text

GPPK4PCM: pest classification model integrating growth period prior knowledge by Jianhua Zheng, Junde Lu, Yusha Fu, Ruolin Zhao, Jinfang Liu, Zhaoxi Luo, Zhijie Luo

“…The model is composed of three sub-modules where: i) A deep learning network first identifies the growth periods of pests, and this prior knowledge is then used to guide the text encoder of the CLIP pre-trained model in generating period-specific textual features. ii) A parallel deep learning network extracts visual features from pest images. iii) An efficient low-rank multimodal fusion module integrates textual and visual features through parameter-optimized tensor decomposition, significantly improving classification accuracy across pest developmental phases. …”
Get full text

Optical Coherent Tomography-Angiography in the Research of Myopia Complicated by Choroidal Neovascularization by E. A. Drozdova, O. V. Zhiliaeva

“…OCTA identifies the features of the course of myopic CNV depending on the phenotype, allows to evaluate the effectiveness of anti-VEGF therapy and the degree of progression of degenerative changes in the macular region.…”
Get full text

Deep Learning Approach for Estimating Workability of Self-Compacting Concrete from Mixing Image Sequences by Zhongcong Ding, Xuehui An

“…The proposed model integrates features of the convolutional neural network and long short-term memory and is trained to extract features and compute an estimate. …”
Get full text

The glacial paleolandscapes of Southern Africa: the legacy of the Late Paleozoic Ice Age by P. Dietrich, P. Dietrich, P. Dietrich, F. Guillocheau, G. A. Douillet, N. P. Griffis, G. Baby, D. P. Le Héron, L. Barrier, M. Mathian, I. P. Montañez, C. Robin, T. Gyomlai, T. Gyomlai, C. Kettler, A. Hofmann

“…These valleys may have later facilitated ice flow from highlands to lowlands, although the extent and configuration of such features remain speculative.</p> <p>The exhumed pre-LPIA landforms may in some cases be taken for pediments, pediplains, and pedivalleys and interpreted as recording the topographic evolution of Southern Africa after the dislocation of Gondwana during the Mesozoic. …”
Get full text

A dynamic preference recommendation model based on spatiotemporal knowledge graphs by Xinyu Fan, Yinqin Ji, Bei Hui

“…Abstract Recommender systems are of increasing importance owing to the growth of social networks and the complexity of user behavior, and cater to the personalized needs of users. …”
Get full text

An Improved YOLOv8-Based Dense Pedestrian Detection Method with Multi-Scale Fusion and Linear Spatial Attention by Han Gong, Tian Li, Lijuan Wang, Shucheng Huang, Mingxing Li

“…Firstly, to resolve the difficulty of extracting features from small-scale pedestrians in dense environments, a backbone network enhanced with deformable convolution and dynamic convolution is adopted to improve feature extraction capabilities. …”
Get full text

Breast cancer detection based on histological images using fusion of diffusion model outputs by Younes Akbari, Faseela Abdullakutty, Somaya Al Maadeed, Ahmed Bouridane, Rifat Hamoudi

“…These segmented regions, combined with predicted noise from the diffusion model and original images, are processed through an EfficientNet-B0 network to extract enhanced features. A transformer decoder then fuses these features to generate final detection results. …”
Get full text

TLINet: A defects detection method for insulators of overhead transmission lines using partially transformer block. by Xun Li, Yuzhen Zhao, Yang Zhao, Zhun Guo, Yongming Zhang, Xiangke Jiao, Baoxi Yuan

“…Furthermore, considering the multi-scale variations of insulator defects, this paper proposes a Context-Guided Feature Fusion Network (CGFFN). This module enables fine-grained fusion of features at different scales, allowing the model to generate adaptive responses to defects of various sizes. …”
Get full text

A Spatial–Frequency Combined Transformer for Cloud Removal of Optical Remote Sensing Images by Fulian Zhao, Chenlong Ding, Xin Li, Runliang Xia, Caifeng Wu, Xin Lyu

“…In order to further enhance the features extracted by DBSA and FreSA, we design the dual-domain feed-forward network (DDFFN), which effectively improves the detail fidelity of the restored image by multi-scale convolution for local refinement and frequency transformation for global structural optimization. …”
Get full text

An Adaptive Distributed Consumer Trust Model for Social Commerce by Xiumu Weng, Ding Pan, Yun Jin

“…This paper proposes an adaptive distributed trust model. The main features of its algorithm include (1) When calculating product trustworthiness, evaluations from consumers themselves, social networks, and e-commerce platforms are integrated, and the importance of these three sources of trust can change adaptively as consumers learn. (2) When selecting product providers and advisers, the Softmax algorithm is used to deal with the “exploration or exploitation” dilemma in reinforcement learning. (3) Consider the emotional attachment between consumers and advisers. (4) Design a blacklist mechanism to determine alternative product providers. …”
Get full text

An Optimized Dynamic Scene Change Detection Algorithm for H.264/AVC Encoded Video Sequences by Giorgio Rascioni, Susanna Spinsante, Ennio Gambi

“…Scene change detection plays an important role in a number of video applications, including video indexing, semantic features extraction, and, in general, pre- and post-processing operations. …”
Get full text

Securing the CAN bus using deep learning for intrusion detection in vehicles by Ritu Rai, Jyoti Grover, Prinkle Sharma, Ayush Pareek

“…We explore recurrent neural network (RNN) variants, including LSTM, GRU, and VGG-16, to analyze temporal and spatial features in the data. …”
Get full text

A malware classification method based on directed API call relationships. by Cuihua Ma, Zhenwan Li, Haixia Long, Anas Bilal, Xiaowen Liu

“…To effectively capture these features, we introduce First-order and Second-order Graph Convolutional Networks (FSGCN) to approximate the operations of a directed graph convolutional network (DGCN). …”
Get full text

Ovarian Hyperthecosis Presenting as Polycythemia by Gayatri Jaiswal, MD, Fnu Varsha, MD, Patricia Bononi, MD, Christina Dimech, MD, Ashni Dharia, MD

Get full text

SwinLightGAN a study of low-light image enhancement algorithms using depth residuals and transformer techniques by Min He, Rugang Wang, Mingyang Zhang, Feiyang Lv, Yuanyuan Wang, Feng Zhou, Xuesheng Bian

“…The network integrates a generator model based on a Residual Jumping U-shaped Network (U-Net) architecture for precise local detail extraction with an illumination network enhanced by Shifted Window Transformer (Swin Transformer) technology that captures multi-scale spatial features and global contexts. …”
Get full text

Assessment Method for Feeding Intensity of Fish Schools Using MobileViT-CoordAtt by Shikun Liu, Xingguo Liu, Haisheng Zou

“…The method employs a lightweight MobileViT backbone network, integrated with a Coordinate Attention (CoordAtt) mechanism and a multi-scale feature fusion strategy. …”
Get full text