DMN-YOLO: A Robust YOLOv11 Model for Detecting Apple Leaf Diseases in Complex Field Conditions by Lijun Gao, Hongwu Cao, Hua Zou, Huanhuan Wu

“…Additionally, a normalized Wasserstein distance (NWD) loss function is introduced to mitigate localization errors, particularly for small or overlapping lesions. …”
Get full text

Milk extracellular vesicles: A burgeoning new presence in nutraceuticals and drug delivery by Spencer R. Marsh, Claire E. Beard, Robert G. Gourdie

“…EVs, including exosomes and small EVs, have demonstrated biological activity in preclinical studies—including reports of enhancement of cognition and neural complexity, promotion of gastrointestinal development, barrier function and microbiome richness, the bolstering of immune response, and facilitation of musculoskeletal maturation in neonates. …”
Get full text

BATF alleviates ox-LDL-induced HCAEC injury by regulating SIRT1 expression in coronary heart disease. by Bei Tian, Jingyu Ji, Can Jin

“…<h4>Conclusion</h4>The research findings suggested a prospective protective function of BATF in HCAEC injury induced by ox-LDL, likely through the mediation of SIRT1 regulation. …”
Get full text

Performance evaluation of ultrathin CdTe-based solar cells with dual absorbers via SCAPS-1D simulation by P. Parathraju, P. Umasankar

“…The efficacy as well as parameter effectiveness of ultrathin CdTe Photovoltaic (PV) cells were simulated in SCAPS-1D simulation software as a function of acceptor concentration and the thickness of the light absorption layer. …”
Get full text

HEE-SegGAN: A holistically-nested edge enhanced GAN for pulmonary nodule segmentation. by Yong Wang, Seri Mastura Mustaza, Mohammad Syuhaimi Ab-Rahman, Siti Salasiah Mokri

“…We also improved the loss function to better capture edge-level details and enhance segmentation precision in edge regions. …”
Get full text

Dilated Convolution and YOLOv8 Feature Extraction Network: An Improved Method for MRI-Based Brain Tumor Detection by Lincy Annet Abraham, Gopinath Palanisamy, Veerapu Goutham

“…Secondly, a dual feature pyramid network (DFPN) is built to provide more discriminative data for dynamic sparse attention mechanism to extract features from the shallow network and top-down routes to direct the following network modules to fuse features. In addition, the DC-YOLOv8FEN uses a position regression loss function and adds Wise-IoU&#x2019;s dynamic non-monotonic focus mechanism to make it even better. …”
Get full text

Fish Body Pattern Style Transfer Based on Wavelet Transformation and Gated Attention by Hongchun Yuan, Yixuan Wang

“…This enhances the perceptual loss function, thereby preventing video flickering and ensuring improved temporal consistency. …”
Get full text

A mmWave JCAS System for Real-Time High-Data Rate Communication and RADAR Sensing by Markus Petri, Nebojsa Maletic

“…For the sensing function, the used hardware-based OFDM baseband processor does not provide a sufficiently precise synchronization of received frames, so a method for the temporal alignment of the received channel impulse responses (CIRs) for different beams is developed and assessed. …”
Get full text

Robust Optical and SAR Image Matching via Attention-Guided Structural Encoding and Confidence-Aware Filtering by Qi Kang, Jixian Zhang, Guoman Huang, Fei Liu

“…Additionally, a match-aware multi-task loss function jointly enforces spatial consistency, affine invariance, and structural coherence for end-to-end optimization. …”
Get full text

AI-powered spatiotemporal imputation and prediction of chlorophyll-a concentration in coastal ecosystems by Fan Zhang, Hiusuet Kung, Fa Zhang, Can Yang, Jianping Gan

“…STIMP reduced the imputation mean absolute error (MAE) by 45.90–81.39% compared with the data interpolating empirical orthogonal function method in geoscience and by 8.92–43.04% against leading AI methods. …”
Get full text

Efficient and secure multi-party computation protocol supporting deep learning by Shancheng Zhang, Gang Qu, Zongyang Zhang, Minzhe Huang, Haochun Jin, Liqun Yang

“…Moreover, we introduce optimized protocols for two crucial deep learning operations: convolution and Softmax function computation. Our convolution protocol leverages the Winograd algorithm to significantly reduce multiplication gate count, yielding over 50% performance improvement. …”
Get full text

Dynamic Bidirectional Feature Enhancement Network for Thin Cloud Removal in Remote Sensing Images by Yu Wang, Hao Chen, Ye Zhang, Guozheng Li

“…First, we design a multidimensional attention module comprising skip-recursive dilated convolution-based spatial attention module and frequency-domain-driven channel attention module. …”
Get full text

Spatial Shape-Aware Network for Elongated Target Detection by Shaowen Xu, Der-Horng Lee

“…The Potential Evaluation Module integrates the potential information of positive samples into the loss function, providing stronger training feedback for high-potential positive samples. …”
Get full text

Effect of Designed Ureteral Stent Instructions on Patient Recovery by Safaa M. Hamed, Rasha F. M. Gaballah

“…It associated with significant morbidity, resulting in a reduction in general health function in another eighty percent of patients. …”
Get full text

State-Space Method-Based Frame Dynamics Analysis of the Six-Rotor Unmanned Aerial Vehicles by Ruijing Liu, Yu Liu, Yi Zhang

“…The Direct Current (DC) gain method is employed to reduce the number of modes, followed by frequency response analysis on the reduced modes to derive the frequency–domain transfer function between the excitation input and response output points. …”
Get full text

Identification of Putative Ortholog Gene Blocks Involved in Gestant and Lactating Mammary Gland Development: A Rodent Cross-Species Microarray Transcriptomics Approach by Maricela Rodríguez-Cruz, Ramón M. Coral-Vázquez, Gabriel Hernández-Stengele, Raúl Sánchez, Emmanuel Salazar, Fausto Sanchez-Muñoz, Sergio Encarnación-Guevara, Jorge Ramírez-Salcedo

“…The mammary gland (MG) undergoes functional and metabolic changes during the transition from pregnancy to lactation, possibly by regulation of conserved genes. …”
Get full text

Design and Implementation of Intelligent Entrance Guard Lock Based on NB-IoT by ZHANG Tianqi;WANG Jin;LI Yuehua

“…The system is mainly composed of peripherals, controllers,NB-IoT modules, information post offices and other modules, which can realize the functions of fingerprint collecting,fingerprint matching, fingerprint deleting, image collecting and transmitting, visit reminding, remote door opening and alarming. …”
Get full text

Bacterial Toxin-Antitoxin Systems and New Strategies for Creating Antibacterial Preparations by B. G. Andryukov, N. N. Besednova, T. S. Zaporozhets, M. P. Bynina

“…Intensive research of bacterial toxin-antitoxin systems (TAS) in recent decades has significantly expanded and deepened knowldge about them. As TAS modules were first discovered in the plasmids and later in the chromosomes of bacteria, and after subsequent study of their specific regulation of activation and functions, their image has changed from simple curious genetic objects to one of the most important tools. …”
Get full text

Immune-related gene characterization and biological mechanisms in major depressive disorder revealed based on transcriptomics and network pharmacology by Shasha Wu, Shasha Wu, Qing Jiang, Jinhui Wang, Jinhui Wang, Daming Wu, Yan Ren

“…Functional enrichment pathway analysis indicated that these differential genes were associated with immune functions. …”
Get full text

A modular click ligand-directed approach to label endogenous dopamine D1 receptors in live cells by Xavier Gómez-Santacana, Marin Boutonnet, Carles Martínez-Juvés, Marta Cimadevila, Juanlo Catena, Enora Moutin, Thomas Roux, Eric Trinquet, Laurent Lamarque, Julie Perroy, Laurent Prézeau, Jurriaan M. Zwier, Jean-Philippe Pin, Amadeu Llebaria

“…Here we report an innovative approach based on the use of molecular modules to build fluorescent ligand-directed probes that can label aminergic GPCRs. …”
Get full text