Multi-Modal Fused-Attention Network for Depression Level Recognition Based on Enhanced Audiovisual Cues by Yihan Zhou, Xiaokang Yu, Zixi Huang, Feierdun Palati, Zeyu Zhao, Zihan He, Yuan Feng, Yuxi Luo

“…The FIE block utilizes ResNet-18 to enhance the feature representation of video frames and integrates two types of attention mechanisms to capture spatial-temporal patterns. Meanwhile, the VIE block processes the Mel spectrogram of the audio signal, followed by an optimized Swin transformer block to extract auditory features. …”
Get full text

Global biome changes over the last 21 000 years inferred from model–data comparisons by C. Li, C. Li, A. Dallmeyer, J. Ni, M. Chevalier, M. Willeit, A. A. Andreev, X. Cao, L. Schild, L. Schild, B. Heim, M. Wieczorek, U. Herzschuh, U. Herzschuh, U. Herzschuh

“…</p> <p>Overall, our reconstruction, with its relatively high temporal and spatial resolution, serves as a robust dataset for evaluating ESM-based paleo-megabiome simulations and provides potential clues for improving systematic model biases.…”
Get full text

Extreme gradient and boosting algorithm for improved bias-correction and downscaling of CMIP6 GCM data across indian river basin by Chandni Thakur, Venkatesh Budamala, KS Kasiviswanathan, Claudia Teutschbein, Bankaru-Swamy Soundharajan

“…Additionally, uncertainty estimates using the p-factor indicated that the extreme gradient boosting model exhibited lower uncertainty in reproducing the observed spatio-temporal patterns of climate variables. Overall, the proposed framework enhances the reliability of global climate model simulations, supporting robust regional-scale hydrological modeling and climate change impact assessments.…”
Get full text

A Comprehensive Review on the Application of 3D Convolutional Neural Networks in Medical Imaging by Satyam Tiwari, Goutam Jain, Dasharathraj K. Shetty, Manu Sudhi, Jayaraj Mymbilly Balakrishnan, Shreepathy Ranga Bhatta

“…CNNs use specific filters to find spatial and temporal relationships in images, making understanding and interpreting them easier. …”
Get full text

Deep Learning Architectures for Single-Label and Multi-Label Surgical Tool Classification in Minimally Invasive Surgeries by Hisham ElMoaqet, Hamzeh Qaddoura, Mutaz Ryalat, Natheer Almtireen, Tamer Abdulbaki Alshirbaji, Nour Aldeen Jalal, Thomas Neumuth, Knut Moeller

“…This study proposes a novel deep learning approach for surgical tool classification based on combining convolutional neural networks (CNNs), Feature Fusion Modules (FFMs), Squeeze-and-Excitation (SE) networks, and Bidirectional long-short term memory (BiLSTM) networks to capture both spatial and temporal features in laparoscopic surgical videos. …”
Get full text

SmartTrust: a hybrid deep learning framework for real-time threat detection in cloud environments using Zero-Trust Architecture by Umesh Kumar Lilhore, Sarita Simaiya, Roobaea Alroobaea, Abdullah M. Baqasah, Majed Alsafyani, Afnan Alhazmi, Md Monish Khan

“…SmartTrust integrates CNN, LSTM, and Transformer models to analyze spatial and temporal patterns in network traffic and user behaviours. …”
Get full text

Explainable AI-driven assessment of hydro climatic interactions shaping river discharge dynamics in a monsoonal basin by Prashant Parasar, Akhouri Pramod Krishna

“…The main findings of this study are (1) KAN demonstrated high predictive performance with root mean squared error (RMSE) values ranging from 42.7 to 58.3 m3/s, Nash–Sutcliffe efficiency (NSE) between 0.80 and 0.87, mean absolute error (MAE) between 28.9 to 52.7 and R2 values between 0.84 and 0.90 across stations. (2) SHAP based feature contribution analysis identified Relative humidity (hurs), specific humidity (huss), and temperature (tas) as key predictors, while (pr) showed limited contribution due to spatial inherent inconsistencies in GCM precipitation data. (3) The bootstrapped SHAP distributions highlighted substantial variability in feature importance, particularly for humidity variables, revealing station specific uncertainty patterns in model interpretation. (4) The KAN framework results indicate strong temporal alignment and physical realism, confirming KAN’s robustness in capturing seasonal discharge dynamics and extreme flow events under monsoon influence environments. (5) In this study KAN with SHAP (SHapley additive exPlanations) is implemented for hydrological modeling under monsoon-influenced and data-limited regions such as SRB, offering improved accuracy, functional precision and efficiency compared to traditional models. …”
Get full text

Acoustic cues for person identification using cough sounds by Van-Thuan Tran, Ting-Hao You, Wei-Ho Tsai

“…The proposed architecture, CoughCueNet, is a convolutional recurrent neural network designed to capture both spatial and temporal patterns in cough sounds. The training process incorporates a hybrid loss function that combines supervised contrastive (SC) learning and cross-entropy (CE) loss to enhance feature discrimination. …”
Get full text

In vivo imaging and pharmacokinetics of percutaneously injected ultrasound and X-ray imageable thermosensitive hydrogel loaded with doxorubicin versus free drug in swine. by Jose F Delgado, Ayele H Negussie, Nicole A Varble, Andrew S Mikhail, Antonio Arrichiello, Tabea Borde, Laetitia Saccenti, Ivane Bakhutashvili, Joshua W Owen, Robert Morhard, John W Karanian, William F Pritchard, Bradford J Wood

“…Dual modality POL imaging enabled analysis of patterns of gel distribution and morphology, alongside of pharmacokinetics of local delivery. …”
Get full text

HTSA-LSTM: Leveraging Driving Habits for Enhanced Long-Term Urban Traffic Trajectory Prediction by Yiying Wei, Xiangyu Zeng, Xirui Chen, Hui Zhang, Zhengan Yang, Zhicheng Li

“…This paper proposes a Habit-based Temporal–Spatial Attention Long Short-Term Memory (HTSA-LSTM) network, a novel framework that integrates a dual spatiotemporal attention mechanism to capture dynamic dependencies across time and space, coupled with a driving style analysis module. …”
Get full text

Advanced Deep Learning Approaches for Forecasting High-Resolution Fire Weather Index (FWI) over CONUS: Integration of GNN-LSTM, GNN-TCNN, and GNN-DeepAR by Shihab Ahmad Shahriar, Yunsoo Choi, Rashik Islam

“…The models were evaluated using the Index of Agreement (IOA) and root mean squared error (RMSE). …”
Get full text

Driving factors and management strategies for water quality improvement in Fuxian Lake, China: A case study on ecological restoration and sustainable management of plateau lakes by Huimei Wang, Nuruol Syuhadaa Mohd

“…By using a mixed-methods approach that integrates 34-year monitoring data (1990–2024) with principal component analysis (PCA), Statistical trend analyses (Mann-Kendall test with Sen’s slope), combined with geospatial visualization (GIS, kriging interpolation), Correlation networks (Pearson) and constrained ordination (Redundancy Analysis, RDA), we quantified the temporal-spatial dynamics of water quality parameters (TN, TP, COD), pinpointed dominant pollution pathways, and evaluated the cumulative efficacy of policy interventions versus climatic drivers. …”
Get full text

Global, regional, and national burden of heart failure and its underlying causes, 1990–2021: results from the global burden of disease study 2021 by Jun Ran, Ping Zhou, Jinxi Wang, Xuemei Zhao, Yan Huang, Qiong Zhou, Mei Zhai, Yuhui Zhang

“…This study aims to systematically analyze the global HF disease burden from 1990 to 2021 across temporal, spatial, and demographic dimensions to provide evidence for targeted prevention and control strategies. …”
Get full text

A novel multi-modal rehabilitation monitoring over human motion intention recognition by Saleha Kamal, Saleha Kamal, Mohammed Alshehri, Yahya AlQahtani, Abdulmonem Alshahrani, Nouf Abdullah Almujally, Ahmad Jalal, Ahmad Jalal, Hui Liu, Hui Liu, Hui Liu

“…This paper presents a novel multi-modal framework that integrates RGB and depth data to extract high-resolution spatial-temporal and anatomical features for accurate HMIR. …”
Get full text

Water Use Efficiency Spatiotemporal Change and Its Driving Analysis on the Mongolian Plateau by Gesi Tang, Yulong Bao, Changqing Sun, Mei Yong, Byambakhuu Gantumur, Rentsenduger Boldbayar, Yuhai Bao

“…Thus, it is important to evaluate temporal and spatial changes in WUE over a prolonged period. …”
Get full text

Enhancing security in 6G-enabled wireless sensor networks for smart cities: a multi-deep learning intrusion detection approach by Waqar Khan, Muhammad Usama, Muhammad Shahbaz Khan, Oumaima Saidani, Hussam Al Hamadi, Noha Alnazzawi, Mohammed S. Alshehri, Jawad Ahmad

“…This hybrid approach captures spatial, temporal, and contextual patterns in network traffic, improving detection accuracy against botnets, denial-of-service (DoS) attacks, and reconnaissance threats.Results and discussionTo validate the proposed framework, we employ the Kitsune and 5G-NIDD datasets, which provide intrusion detection scenarios relevant to IoT-based and non-IP traffic environments. …”
Get full text

Relationships between vegetation indices and surface reflectance: Implications for detecting and monitoring sandification in arid regions by Yifan Yue, Wenzhi Zhao, Rentao Liu

“…Temporally, sandification intensity has greatly declined, with the area of extremely severe sandification shrinking from 2282 to 377 km2; spatially, sandification has occurred along a pronounced northeast–southwest gradient. …”
Get full text

Explainable AI Meets Synthetic Data: A Deep Learning Framework for Detecting Network Intrusion in NextG Network Infrastructure by Md Junayed Hossain, Khorshed Alam, Md Fahad Monir, Md Mozammal Hoque, Tarem Ahmed

“…The CNN and LSTM models, applied independently, leverage their respective strengths to extract spatial and temporal features from network traffic, achieving robust classification accuracy. …”
Get full text

Differential Transcript Profiles of MHC Class Ib(Qa-1, Qa-2, and Qa-10) and Aire Genes during the Ontogeny of Thymus and Other Tissues by Breno Luiz Melo-Lima, Adriane Feijó Evangelista, Danielle Aparecida Rosa de Magalhães, Geraldo Aleixo Passos, Philippe Moreau, Eduardo Antonio Donadi

“…Aiming to characterize the transcriptional profiles of nonclassical MHC class I genes in spatial-temporal association with the Aire expression, we evaluated the gene expression of H2-Q7(Qa-2), H2-T23(Qa-1), H2-Q10(Qa-10), and Aire during fetal and postnatal development of thymus and other tissues. …”
Get full text

The Interannual Variability of Global Burned Area Is Mostly Explained by Climatic Drivers by Andrina Gincheva, Juli G. Pausas, Miguel Ángel Torres‐Vázquez, Joaquín Bedia, Sergio M. Vicente‐Serrano, John T. Abatzoglou, Josep A. Sánchez‐Espigares, Emilio Chuvieco, Sonia Jerez, Antonello Provenzale, Ricardo M. Trigo, Marco Turco

“…Our results reveal complex spatial patterns in the dependence of BA variability on antecedent and concurrent weather conditions, highlighting where BA is mostly influenced by either FWI or SPEI and where the combined effect of both indicators must be considered. …”
Get full text