Feature Enhancement Network for Infrared Small Target Detection in Complex Backgrounds Based on Multi-Scale Attention Mechanism by Sen Zhang, Weilin Du, Yuan Liu, Ni Zhou, Zheng Li

“…By combining the scale and spatial attention mechanisms of the Dynamic Head, our approach adaptively learns the relative importance of different semantic layers. Furthermore, the integration of Normalized Wasserstein–Gaussian Distance (NWD) aims to tackle the convergence issues associated with the increased sensitivity of bounding box regression in identifying minor infrared targets. …”
Get full text

Stem cells in regenerative medicine: Unlocking therapeutic potential through stem cell therapy, 3D bioprinting, gene editing, and drug discovery by Idris Zubairu Sadiq, Fatima Sadiq Abubakar, Babangida Sanusi Katsayal, Bashiru Ibrahim, Auwal Adamu, Mohammed Aliyu Usman, Mukhtar Aliyu, Mukhtar Adeiza Suleiman, Aliyu Muhammad

“…Pluripotent cells, capable of adopting roles from any of the three germ layers, exhibit exceptional versatility and are promising for a wide range of medical conditions. …”
Get full text

Online evaluation method for MMC submodule capacitor aging based on CapAgingNet by Xinlan Deng, Youhan Deng, Liang Qin, Weiwei Yao, Min He, Kaipei Liu

“…Subsequently, the CapAgingNet model is introduced, incorporating key technical modules to enhance performance: the Deep Stem module, which extracts larger receptive fields through multiple convolution layers and mitigates the impact of data sparsity in capacitor aging on feature extraction; the efficient channel attention (ECA) module, utilizing one-dimensional convolution for dynamic weighting to adjust the importance of each channel, thereby enhancing the ability of the model to process high-dimensional features in capacitor aging data; and the multiscale feature fusion (MSF) module, which integrates capacitor aging information across different scales by combining fine-grained and coarse-grained features, thus improving the capacity of the model to capture high-frequency variation characteristics. …”
Get full text

YOLO-UP: A High-Throughput Pest Detection Model for Dense Cotton Crops Utilizing UAV-Captured Visible Light Imagery by Chenglei Sun, Afizan Bin Azman, Zaiyun Wang, Xiaoxiao Gao, Kai Ding

“…Additionally, the model optimizes the neck design to re-duce semantic discrepancies between feature layers, improving small-target detection, and integrates large-kernel separable convolutions to bolster high-level feature processing. …”
Get full text

Surface water mapping from remote sensing in Egypt’s dry season using an improved U-Net model with multi-scale information and attention mechanism by Yong Li, Xiuhui Liu, Vagner Ferreira, Heiko Balzter, Huiyu Zhou, Ying Ge, Meiyun Lai, Simin Chu, Han Ding, Zhenrong Gu

“…The extraction accuracy can be improved by combining convolutional layers for local feature extraction with Vision Transformer using Manhattan self-attention for global context information. …”
Get full text

Dexamethasone intravitreal implant monotherapy in naive patients with macular edema secondary to retinal vein occlusion: long term follow-up retrospective cohort study by Gamze Karataş, Akın Çakır, Tahsin Uzundede, Öznur Aday, Ahmet Melih Özoğuz, Mehmet Egemen Karataş, Aslı Kırmacı Kabakcı

“…METHODS: In this retrospective cohort study, the data about best corrected visual acuity (BCVA), central macular thickness (CMT), serous macular detachment (SMD), hard exudate, hyperreflective foci (HRF), cystoid degeneration, pearl necklace sign, epiretinal membrane (ERM), disorganization of retinal inner layers (DRIL), ellipsoid zone and external limiting membrane (EZ-ELM) integrity, intraocular pressure (IOP) and lens condition were recorded. …”
Get full text

Implementation and comprehensive investigation of gate engineered Si0.1Ge0.9/GaAs charged plasma based JLTFET for improved analog/ RF performance by Pranita Soni, Aditya Jain, Kaushal Kumar, Lokesh Kumar Soni, Ajay Kumar, Neha Gupta, Amit Kumar Goyal, Rakesh Saroha

“…This study introduces the Variable Length Dual Dielectric Material-Gate Spacer Engineering Heterostructure Junction-Less Tunnel Field-Effect Transistor (VLDD-GSE-HJLTFET), a novel device that integrates advanced bandgap engineering, dual-dielectric gate configuration, and heterostructure design using Si0.1Ge0.9/GaAs layers. …”
Get full text

Multi-sphere coupling characteristics and gas-bearing controlling factors of calcareous shale reservoirs in the Yadu-Ziyun-Luodian Aulacogen under Early Carboniferous platform-basi... by Kun Yuan, Kun Yuan, Kun Yuan, Bing Feng, Gangquan Li, Zongan Xue, Zongan Xue, Zongan Xue, Tuo Lin, Tuo Lin, Tuo Lin, Xinxin Fang, Xiangcan Sun, Xiangcan Sun, Xiangcan Sun, Yinbo Xu, Yinbo Xu, Yinbo Xu, Fengzan Zheng

“…A crucial finding is the distinction between low-energy, “thick-bedded” deposits and higher-energy, “thin interbedded” sections characterized by frequent alternations of mudstone and argillaceous limestone (0.5–5 m single layers, mudstone:limestone ratio 1:1–1:2). Significantly, these thin interbedded sections demonstrate superior reservoir quality, exhibiting higher porosity (∼2.9%) and notably higher gas content (∼2.5 m3/t). …”
Get full text

RainHCNet: Hybrid High-Low Frequency and Cross-Scale Network for Precipitation Nowcasting by Lei Wang, Zheng Wang, Wenjun Hu, Cong Bai

“…In addition, a cross-scale supervision module integrates multiscale features from both deep and shallow layers to mitigate information loss. …”
Get full text

Toward a Secure 5G-Enabled Internet of Things: A Survey on Requirements, Privacy, Security, Challenges, and Opportunities by Shams Forruque Ahmed, Md. Sakib Bin Alam, Shaila Afrin, Sabiha Jannat Rafa, Samanta Binte Taher, Maliha Kabir, S. M. Muyeen, Amir H. Gandomi

“…This study investigates the benefits and issues associated with 5G-enabled IoT, including its privacy and security concerns as well as the technology drivers that enable its various layers. By incorporating 5G technology into IoT, several enhancements have been achieved, including enhanced reliability, simplicity, practicability, analysis, efficiency, agility, flexibility, and accessibility. …”
Get full text

Emotion recognition with a Randomized CNN-multihead-attention hybrid model optimized by evolutionary intelligence algorithm by Syed Muhammad Salman Bukhari, Muhammad Hamza Zafar, Syed Kumayl Raza Moosavi, Filippo Sanfilippo

“…The RCNN, characterized by fixed random weights in its convolutional layers, efficiently extracts features from facial landmarks, enabling robust and diverse feature extraction while reducing computational load. …”
Get full text

Spatial and Temporal Dynamics of Photosynthetically Active Radiation in Crops: Effects of Canopy Structure on Yield by Meng Duan, Congying Han, Xiaotao Zhang, Zheng Wei, Zhiguo Wang, Baozhong Zhang

“…Additionally, studies integrating precision agriculture technologies to fine-tune planting density and water management in response to climate change are essential for ensuring sustainable maize production and food security in the future.…”
Get full text

Rare-Earth based magnesium alloys as a potential biomaterial for the future by Abhishek Kumar, Amit Choudhari, Ashish Kumar Gupta, Avinash Kumar

“…Additionally, the transformative potential of integrating rare-earth (RE) elements into Mg alloys is explored. …”
Get full text

Enhancing Anomaly Detection in Attributed Networks Using Proximity Preservation and Advanced Embedding Techniques by Wasim Khan, Mohammad Ishrat, Mohammad Nadeem Ahmed, Shafiqul Abidin, Mohammad Husain, Mohd Izhar, Abu Taha Zamani, Mohammad Rashid Hussain, Arshad Ali

“…A key challenge is maintaining the integrity of both network and node feature structures during the embedding process. …”
Get full text

4D trajectory lightweight prediction algorithm based on knowledge distillation technique by Weizhen Tang, Jie Dai, Zhousheng Huang, Boyang Hao, Weizheng Xie

“…The student network adopts a Temporal Convolutional Network–LSTM (TCN–LSTM) design, integrating dilated causal convolutions and two LSTM layers for efficient temporal modeling. …”
Get full text

Lightweight and robust ship detection method driven by self-attention mechanism by Feng MA, Zihui SHI, Jie SUN, Chen CHEN, Xianbin MAO, Xinping YAN

“…Subsequently, considering the uneven distribution and minor scale variations of ship targets in the dataset, two detection layers are retained to reduce model parameters and further enhance model performance. …”
Get full text

SMEA-YOLOv8n: A Sheep Facial Expression Recognition Method Based on an Improved YOLOv8n Model by Wenbo Yu, Xiang Yang, Yongqi Liu, Chuanzhong Xuan, Ruoya Xie, Chuanjiu Wang

“…Furthermore, the Spatial Pyramid Pooling-Fast (SPPF) module in the backbone network is refined with the addition of two global average pooling layers, strengthening the extraction of sheep facial expression features and bolstering the model’s core feature fusion capacity. …”
Get full text

An Innovative Artificial Intelligence Classification Model for Non-Ischemic Cardiomyopathy Utilizing Cardiac Biomechanics Derived from Magnetic Resonance Imaging by Liqiang Fu, Peifang Zhang, Liuquan Cheng, Peng Zhi, Jiayu Xu, Xiaolei Liu, Yang Zhang, Ziwen Xu, Kunlun He

“…Our dual-path architecture combines a CNN-LSTM encoder for cine CMR analysis and an MLP encoder for IVPG time-series data, followed by feature fusion and dense classification layers. Trained on a multicenter dataset of 1196 patients and externally validated on 137 patients from a distinct institution, the model achieved a superior performance (internal AUC: 0.974; external AUC: 0.962), outperforming ResNet50, VGG16, and radiomics-based SVM. …”
Get full text

YOLOLS: A Lightweight and High-Precision Power Insulator Defect Detection Network for Real-Time Edge Deployment by Qinglong Wang, Zhengyu Hu, Entuo Li, Guyu Wu, Wengang Yang, Yunjian Hu, Wen Peng, Jie Sun

“…Moreover, the C2f module is restructured into a ResNet–RepConv architecture, in which convolution and Batch Normalization layers are fused during inference to reduce model complexity and enhance inference speed. …”
Get full text

Geometry and tectonic history of the Northeastern Cévennes Fault System (Southeast Basin, France) : new insights from deep seismic reflection profiles by Thomasset Camille, Ritz Jean-François, Pouliquen Sylvain, Manchuel Kevin, Le-Roux-Mallouf Romain

“…A few studies performed local modeling of the NCFS structures in three dimensions integrating the rheology of the sedimentary layers within the hypocenter zone. …”
Get full text