Benthos-DETR: a high-precision efficient network for benthic organisms detection by Weibo Rao, Gang Chen, Yifei Zhang, Jue Cang, Shusen Chen, Chenyang Wang

“…In the neck, the original concatenation module is replaced with the Fusion Focus Module, effectively aggregating feature layer information from different stages of the backbone to achieve cross-scale feature fusion. …”
Get full text

Multi-label Classification Based on Label-Aware Variational Autoencoder by SUN Hongjian, XU Pengyu, LIU Bing, JING Liping, YU Jian

“…For label relevance learning, the multi-layer self-attention mechanism in the shared decoder is used to fully fuse the similarity information of multiple labels, and through the co-occurring interactions between different labels, the label higher-order relevance representations are learnt and used for cross-aware feature embedding. …”
Get full text

Changes in retinal and choroidal thickness after carotid endarterectomy: a systematic review by Ana Cibrão-Pedroso, João Rocha-Neves, Rafael Vieira, João Barbosa Breda, André Ferreira

“…Retinal measurements were less consistently assessed; among the three studies that evaluated retinal nerve fibre layer and ganglion cell complex thickness, no consistent postoperative changes were observed. …”
Get full text

Beam steerable MIMO antenna based on conformal passive reflective metasurface for 5G millimeter wave applications by Bilal Tariq Malik, Shahid Khan, Slawomir Koziel

“…This novel conformal metasurface antenna design has the advantages of higher gain, lower cost, a simpler feeding source, and a lower profile when compared to traditional reflective metasurfaces using bulky horn antennas and phased arrays with complex feeding networks and phase shifters for beam steering. …”
Get full text

Cloud Survivability Scenarios Under Attacks With and Without Countermeasures by Rachid Beghdad, Faiza Benmenzer, Alaa Eddine Khalfoune

“…While current countermeasures offer initial mitigation, they are insufficient against complex and combined threats. Thus, future research should focus on developing robust, multi-layered defence mechanisms and providing data centre duplication to ensure service availability.…”
Get full text

BCDnet: Parallel heterogeneous eight-class classification model of breast pathology. by Qingfang He, Guang Cheng, Huimin Ju

“…Breast pathological tissue images have complex and diverse characteristics, and the medical data set of breast pathological tissue images is small, which makes it difficult to automatically classify breast pathological tissues. …”
Get full text

Sustainable ethyl lactate synthesis over MgAl-LDHs: impact of Mg/Al ratio and structural tuning by Anis Usmani, Kanogwan Tohdee, Piyasan Praserthdam, Bunjerd Jongsomjit

“…Herein, the study aims to explore the effects of composited acid–base catalysts in esterification to ethyl lactate. Magnesium aluminum-layered-double hydroxide (MgAl-LDHs), as a bifunctional catalyst with a complex structure, was prepared via co-precipitation, and consequently evaluated in an esterification. …”
Get full text

Simrec: a similarity measure recommendation system for mixed data clustering algorithms by Abdoulaye Diop, Nabil El-Malki, Max Chevalier, André Péninou, Geoffrey Roman-Jimenez, Olivier Teste

“…Commonly, two similarity measures are combined, one for numerical attributes and one for categorical attributes. This adds a layer of complexity to the problem since it requires the selection of two similarity measures instead of just one. …”
Get full text

Knife and bulldozer bottom blade interaction with soil at the beginning of a pass by V. A. Nikolayev

“…Interaction with the soil of the knife and the blade of the bulldozer is accompanied by a complex of interrelated processes. These processes complicate the theoretical analysis of the interaction of the knife and the bottom part of the blade of bulldozer equipment with the soil. …”
Get full text

Clinical Performance of Bulk-Fill Versus Incremental Composite Restorations in Primary Teeth: A Systematic Review of In Vivo Evidence by Maria Sarapultseva, Desheng Hu, Alexey Sarapultsev

“…Marginal integrity was generally equivalent, though incremental techniques showed modest advantages in complex cavities. Secondary outcomes were inconsistently reported, with no significant group differences. …”
Get full text

U-Pb (LA-ICP-MS) age of detrital zircons and the sources of terrigenous sediments of the Ipsit suite, Karagass series (Sayan segment of the Sayan-Baikal-Patom belt) by Z. L. Motova, T. V. Donskaya, D. P. Gladkochub, V. B. Khubanov

“…Such ages correlate with the age of the granitoids of the Sayan complex and the felsic volcanites from the Maltsev layer of the Elash series (Biryusa block). …”
Get full text

Self-Supervised Spatio-Temporal Representation Learning of Satellite Image Time Series by Iris Dumeur, Silvia Valero, Jordi Inglada

“…In this article, a new self-supervised strategy for learning meaningful representations of complex optical satellite image time series (SITS) is presented. …”
Get full text

Toward an Ab Initio Theory of High-Temperature Superconductors: A Study of Multilayer Cuprates by Benjamin Bacq-Labreuil, Benjamin Lacasse, A.-M. S. Tremblay, David Sénéchal, Kristjan Haule

“…Nevertheless, material-specific predictions, while essential for constructing a comprehensive theory, remain challenging due to the complex relationship between real materials and the parameters of the effective models. …”
Get full text

PGTransNet: a physics-guided transformer network for 3D ocean temperature and salinity predicting in tropical Pacific by Song Wu, Senliang Bao, Wei Dong, Senzhang Wang, Xiaojiang Zhang, Chengcheng Shao, Junxing Zhu, Xiaoyong Li

“…Numerical models are the most prevalent of the traditional approaches, which are often too complex and lack of generality. Recently, with the rise of AI, many data-driven methods are proposed. …”
Get full text

EEG-SymNet: multi-channel EEG signal-based schizophrenia diagnosis using channel recalibration and symmetric spatial temporal transformer network by Naif Alsharabi, Rakesh Kumar Mahendran, Gharbi Alshammari

“…Next, the Multi-Channel Frequency Recalibration Module (CRFM) refines the model’s ability to interpret complex inter-channel relationships, enhancing inter-channel communication. …”
Get full text

Gas Generation in Lithium-Ion Batteries: Mechanisms, Failure Pathways, and Thermal Safety Implications by Tianyu Gong, Xuzhi Duan, Yan Shan, Lang Huang

“…Gas evolution in lithium-ion batteries represents a pivotal yet underaddressed concern, significantly compromising long-term cyclability and safety through complex interfacial dynamics and material degradation across both normal operation and extreme thermal scenarios. …”
Get full text

DMF-YOLO: Dynamic Multi-Scale Feature Fusion Network-Driven Small Target Detection in UAV Aerial Images by Xiaojia Yan, Shiyan Sun, Huimin Zhu, Qingping Hu, Wenjian Ying, Yinglei Li

“…The method exhibits superior robustness in dense scenarios, complex backgrounds, and long-range target detection. …”
Get full text

Mechanical performance of 3D printed functionally graded PETG: An experimental investigation by Sheikh Aadil Hussain, M.S. Charoo, Mir Irfan Ul Haq

“…In contrast, samples with the octahedral pattern exhibited larger voids, poor layer adhesion, and delamination, likely contributing to their reduced strength. …”
Get full text

The Analysis of 3D Printing Thermoplastic Materials by Using FDM Technique by Shoukat Ali noonari, Amna Hafeez rajout, Hamza Shaikh Shaikh, Jabir Ali Ali, Aftab Ahmed Khuhro Khuhro, Faheem Ahmed Solangi Solangi

“… The size of the production run and the geometric complexity of the component are the primary factors limiting the use of standard manufacturing methods; thus, we are often compelled to employ procedures and equipment that raise the element's final cost. …”
Get full text

Img2Neuro: brain-trained neural activity encoders for enhanced object recognition by Mona A Aboelnaga, Mohamed W El-Kharashi, Seif Eldawlatly

“…For decades, the brain’s visual pathway has inspired machine and deep learning models, yet these models oversimplify the brain’s complex visual processing. This is manifested in the significant superiority of the brain in comparison to the developed models in terms of the accuracy and the amount of data needed for training. …”
Get full text