AEMS: Adaptive Ensemble GNNs for Multibehavior Stream Recommendation by Ritchie Natuan Caibigan, Punyaphol Horata, Pusadee Seresangtakul

“…The AEMS synergizes long-term preference patterns (derived from historical interactions) with real-time user intents and item attributes (captured through multibehavior signals), integrating them via an adaptive ensemble neural gating mechanism. …”
Get full text

Deep learning driven prediction and comparative study of surrounding rock deformation in high speed railway tunnels by Zeping Yang, Zhikai Cheng, Da Wu

“…The methodology incorporates quadratic exponential smoothing for outlier mitigation, followed by sequential feature extraction using convolutional neural networks (CNNs) and bidirectional gated recurrent units (GRUs). Comparative experiments demonstrate the model’s superiority over conventional architectures including RNN, LSTM, GRU, and CNN-GRU. …”
Get full text

Forecasting Sales in Live-Streaming Cross-Border E-Commerce in the UK Using the Temporal Fusion Transformer Model by Qi Zhang, Xue Li, Pengbin Gao

“…Our multimodal approach integrates diverse time series data, including historical sales, key opinion leader (KOL) influence, and seasonal patterns. The Temporal Fusion Transformer (TFT) model demonstrated consistently lower Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Squared Error (MSE) across all forecasting horizons compared to other machine learning approaches, including Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), and Gated Recurrent Unit(GPU)-accelerated architectures. …”
Get full text

A clustering-based federated deep learning approach for enhancing diabetes management with privacy-preserving edge artificial intelligence by Xinyi Yang, Juan Li

“…We develop tailored models that enhance prediction accuracy by clustering patients based on carbohydrate (CHO) intake patterns. Utilizing Simple Recurrent Neural Network (SimpleRNN) and Gated Recurrent Unit (GRU) methods, the study evaluates the performance of local patients who contribute to training the cluster and global (non-cluster) models. …”
Get full text

Anomaly Detection in Network Traffic via Cross-Domain Federated Graph Representation Learning by Yanli Zhao, Zongduo Liu, Junjie Pang

“…Traditional detection approaches typically rely on statistical features while overlooking the interaction patterns and structural dependencies among traffic flows. …”
Get full text

fNIRS evidence of abnormal frontotemporal cortex activation and functional connectivity in depressed patients after stroke: neuromodulatory mechanisms from mild to moderate depress... by Shanshan Zhou, Xiaodie Liu, Mengyuan Chen, Wenyi Chen, Yawen Pan, Yinghao Zhi

“…In contrast, the mild-PSD group displayed no notable connectivity differences between the two groups.ConclusionThis study presents distinct patterns of frontotemporal cortex activation and functional connectivity alterations associated with varying severity levels of PSD. …”
Get full text

Evolution of the Unified State Exam and its Effect on Students’ Mathematical Preparation by A. S. Kotyurgina, E. I. Fedorova, V. B. Nikolaev, Yu. B. Nikitin

“…However, due to the non-linear rating scale, it is not necessary to do these tasks, as well as some other tasks involving a detailed solution. …”
Get full text

A Cross-Sectional Analysis of Oil Pulling on YouTube Shorts by Jun Yaung, Sun Ha Park, Shahed Al Khalifah

“…., dentist, hygienist, influencer), engagement metrics, stated benefits, oil type and regimen, the use of disclaimers or citations, and stance toward oil pulling rated on a 5-point Likert scale. Speaker background and nationality were determined through publicly available channel descriptions or linked websites, with user identities anonymized and ethical approval deemed unnecessary due to the use of publicly available content. …”
Get full text

Customer-related quality of perspective potato hybrids (Solanum tuberosum L.) by Н. С. Кожушко, М. М. Сахошко, С. І. Бердін, М. Г. Баштовий, Д. В. Смілик

“…In terms of culinary and consumer type of food (table) potatoes, eight hybrids were rated as type B, five and five hybrids belonged to types A and C respectively, and three hybrids belonged to type D. …”
Get full text

Prevalence and association between eating disorders, depression, and obesity among Palestinian adolescent refugees by Basma Damiri, Ahmad Hanani

“…The interviews included the Birleson Depression Self-Rating Scale and the Eating Attitudes Test-26 (EAT-26), a screening tool used to detect individuals at risk for disordered eating behaviors but who are not diagnosed with specific eating disorders. …”
Get full text

Functional Identification Reveals That TaTGA16-2D Promotes Drought and Heat Tolerance by Jingna Ru, Jiamin Hao, Xiaoqian Ji, Bingqing Hao, Jiale Yang, Hongtao Wang, Baoquan Quan, Pengyan Guo, Jiping Zhao, Chao Wang, Huawei Shi, Zhaoshi Xu

“…Under heat stress, the survival rates of transgenic lines exceeded 34%, compared to less than 18% in wild-type plants. …”
Get full text

Assessing patient-reported outcomes (PROs) in paediatric oncology research: Which PRO would a pro pick, if a pro was picking PROs? by Ameeta Retzer, Sarah Al-Jilaihawi, Shivani Bailey, Vickie Buenger, Sarah Damery, Anne-Sophie Darlington, Manuel Diezi, John Devin Peipert, Jessica Roydhouse, Bryce B. Reeve

“…The choice of PRO depends on the intended application and associated research questions, and structuring a rationale for the use of PRO data is key to deciding upon a PRO strategy. Rates of PRO use in paediatric oncology research remain low though the general use of PROs in clinical trials has been gradually increasing. …”
Get full text

The Ethical Significance of Brain-Computer Interfaces as Enablers of Communication by Toma Gruica

“…Intracortical BCIs, by contrast, can restore communicative capacity by directly decoding neural signals associated with intended speech or movement.[5] One landmark study documented an amyotrophic lateral sclerosis (ALS) patient who, after entering CLIS, learned to use an implanted BCI speller to construct sentences at a rate of approximately one character per minute. The patient’s communications ranged from the mundane, such as requesting music, to expressions of existential significance involving care preferences.[6] Importantly, when researchers were asked how they would respond if the patient spelled “unplug my ventilator,” they emphatically stated that BCI output would not determine decisions regarding life support withdrawal. …”
Get full text

Deep Temporal and Structural Embeddings for Robust Unsupervised Anomaly Detection in Dynamic Graphs by Samir Abdaljalil, Hasan Kurban, Rachad Atat, Erchin Serpedin, Khalid Qaraqe

“…Our method successfully captures temporal patterns, making it robust against subtle anomalies and structural changes. …”
Get full text

CRYPTOCURRENCY TIME SERIES FORECASTING MODEL USING GRU ALGORITHM BASED ON MACHINE LEARNING by Melina Melina, Sukono Sukono, Herlina Napitupulu, Norizan Mohamed, Yulison Herry Chrisnanto, Asep ID Hadiana, Valentina Adimurti Kusumaningtyas

“…The high fluctuation and volatility of cryptocurrency prices and the complexity of non-linear relationships in data patterns attract investors and researchers who want to develop accurate cryptocurrency price forecasting models. …”
Get full text

D4Care: A Deep Dynamic Memory-Driven Cross-Modal Feature Representation Network for Clinical Outcome Prediction by Binyue Chen, Guohua Liu

“…In addition, we also introduce a memory-aware constrained layer normalization to alleviate the challenges of multi-modal feature heterogeneity. Besides, we use gating mechanisms and dynamic memory components to enable the model to learn feature information of different historical-current patterns, further improving the model’s performance. …”
Get full text

Predicting hydrocarbon reservoir quality in deepwater sedimentary systems using sequential deep learning techniques by Xiao Hu, Jun Xie, Xiwei Li, Junzheng Han, Zhengquan Zhao, Hamzeh Ghorbani

“…Three sequential deep learning models—Recurrent Neural Network and Gated Recurrent Unit—were developed and optimized using the Adam algorithm. …”
Get full text

Air-for-water substitution in characterizing lake heatwaves in the middle and lower reaches of the Yangtze River Basin by Zihan Zhu, Wei Wang, Heng Lyu, Bo Wang, Zhiwen Wen, Qiuxiang Jin

“…But the difference in long-term change rates between two heatwaves exhibits no discernible spatial pattern. …”
Get full text

MSA-GCN: Exploiting Multi-Scale Temporal Dynamics With Adaptive Graph Convolution for Skeleton-Based Action Recognition by Kowovi Comivi Alowonou, Ji-Hyeong Han

“…On the other hand, the TMST module integrates a Gated Multi-stage Temporal Convolution (GMSTC) with a Temporal Multi-Head Self-Attention (TMHSA) to capture global temporal features and accommodate both long-term and short-term dependencies within action sequences. …”
Get full text

GT-SRR: A Structured Method for Social Relation Recognition with GGNN-Based Transformer by Dejiao Huang, Menglei Xia, Ruyi Chang, Xiaohan Kong, Shuai Guo

“…In order to overcome these restrictions, this essay suggests a SRR model that integrates Gated Graph Neural Network (GGNN) and Transformer. …”
Get full text