Results 81 to 90 of about 8,962 (250)

Beyond d‐Band Catalysis: A Critical Review and Descriptor Framework for Rare‐Earth Engineering in Lithium–Sulfur Batteries

Advanced Science, EarlyView.
Rare‐earth catalysts regulate lithium–sulfur battery chemistry through f‐orbital–mediated interactions, enabling simultaneous polysulfide adsorption and catalytic conversion on conductive carbon hosts. This synergistic control suppresses the shuttle effect, accelerates redox kinetics, and guides stable Li2S nucleation, providing a mechanistic framework
Fan Wang, Shihzad Shakil, Guozhi Wu, Jiarui Huang, Hanhui Lei, Terence Xiaoteng Liu   +5 more
wiley   +1 more source

T2T Genome Assembly and Multi‐Omics Data Reveal Terrestrial Adaptation and Mucus Biosynthesis in Tropical Leatherleaf Slug (Laevicaulis alte)

Advanced Science, EarlyView.
A gap‐free genome assembly and multi‐omics comparison of the terrestrial slug Laevichaulis alte with an aquatic relative reveal that expansion of the VEGF family orchestrates mucus production, lipid metabolism, and immune defense—highlighting key molecular innovations for conquering life on land.
Gang Wang, Shaofang He, Zhongkai Wang, Aobo Pang, Xiaoli Sun, Rongchen Liu, Fang Wang, Sisi Chen, Zhijuan Bian, Dongcheng Wei, Liuhan Wu, Siyao Zhao, Qiuting Ji, Yiqi Sun, Niying Sun, Yushinta Fujaya, Boping Tang, Kianann Tan, Daizhen Zhang, Lianfu Chen   +19 more
wiley   +1 more source

Trend-Error Decomposition for Self-Supervised Time Series Learning in Multivariate Forecasting Task

IEEE Access
Self-Supervised Learning (SSL) has become a powerful paradigm in Artificial Intelligence, enabling the training of machine learning models using unlabeled data.
Sara Pederzoli, Francesco del Buono, Maurizio Vincini, Francesco Guerra   +3 more
doaj   +1 more source

Neuron‐Derived MIF Engages VCAM1 to Fuel a Self‐Amplifying CXCL8 Loop That Drives Perineural Invasion and Metastasis in Gastric Cancer

Advanced Science, EarlyView.
Neuron‐derived MIF binds VCAM1 on gastric cancer cells and activates ERK/STAT3 signaling, leading to CXCL8 transcription and secretion. Tumor‐derived CXCL8 subsequently stimulates neuronal CXCR2 to enhance MIF production, establishing a self‐amplifying MIF–VCAM1–CXCL8 positive‐feedback loop that promotes perineural invasion, tumor progression, and ...
Xunjun Li, Zhongya Zhai, Haiyi Yu, Renjie Qiu, Fengyu Li, Luxi Xiao, Boxi Huang, Huiying Liu, Jiayong He, Bowen Cai, Jiawen Chen, Jiang Yu, Guoxin Li, Tao Chen   +13 more
wiley   +1 more source

Causal‐Guided Ultra‐Long‐Term Time Series Forecasting Via Anticipated Covariates

Advanced Science, EarlyView.
Often treated as unknown, information from the future remains underutilized.We demonstrate that in a coupled dynamical system, providing the future state of the effect enables accurate forecasting of the cause for a long timesteps. A time series forecasting paradigm that introduces anticipated covariates to represent such known future states is ...
Jintong Zhao, Yufei Liu, Ruixi Huang, Zhongxue Gan, Siyang Leng   +4 more
wiley   +1 more source

A Machine Vision‐Guided Microphysiological Platform With Automated Microfluidics Enables Longitudinal Biomarker Monitoring and Emulation of Translationally Relevant Exposure Scenarios

Advanced Science, EarlyView.
A pneumatically actuated multi‐tissue microphysiological system is integrated with AI‐based machine vision and automatic sampling and replenishment systems. The platform allows for the emulation of translationally relevant long‐term pharmacokinetic exposure scenarios for multiple weeks while enabling longitudinal monitoring of response biomarkers ...
Jibbe Keulen, Yi Zhong, Laura Dangel, Sonia Youhanna, Reza Zandi Shafagh, Jinhye Ryu, Domnica‐Gabriela Gurau, Mathias Haag, Thomas E. Mürdter, Yingxin Liang, Iro Beligiani, Nicole Ziegler, Sabine Willems, Nayere Taebnia, Wouter van der Wijngaart, Volker M. Lauschke   +15 more
wiley   +1 more source

MFDR++: Robust and Efficient Multivariate Time Series Forecasting With Deep Reconstruction

IEEE Access
Recent advances in deep learning–based multivariate time series (MTS) forecasting indicate that increasing model complexity does not necessarily yield better accuracy, largely due to improper inductive biases in modeling intra- and interseries ...
Zhenyang Zhang, Mingqiang Yuan, Xiong Ge, Donghui Wang, Ruoxuan Luan, Zhiqi Song, Wei Li   +6 more
doaj   +1 more source

DiffTST: Diff Transformer for Multivariate Time Series Forecast

IEEE Access
Deep learning models employing the Transformer architecture have demonstrated exceptional performance in the field of multivariate time series forecasting research. However, these models often incorporate irrelevant or weakly relevant information during the processing of time series, leading to noise.
Song Yang, Wenyong Han, Yaping Wan, Tao Zhu 0001, Zhiming Liu, Shuangjian Li   +5 more
openaire   +2 more sources

From Materials to Systems: Challenges and Solutions for Fast‐Charge/Discharge Na‐Ion Batteries

Advanced Energy Materials, EarlyView.
This review systematically analyzes the key characteristics limiting the fast‐charge/discharge capability of Na‐ion batteries (SIBs) from a multi‐scale perspective encompassing electrode materials, the electrode‐electrolyte interface, and the system. Furthermore, it presents practical solution strategies for the fundamental issues arising at each scale,
Bonyoung Ku, Sangbin Park, Sunha Hwang, Sunghyun Lim, Won‐Sub Yoon, Jongsoon Kim   +5 more
wiley   +1 more source

Conformal multistep-ahead multivariate time-series forecasting

Machine Learning
Abstract Time-series forecasts underpin decision-making processes in a wide range of application domains. Recently it has been shown that these processes can be strengthened by conformal prediction, a framework that allows adding prediction intervals to point forecasts.
Filip Schlembach, Evgueni N. Smirnov, Irena Koprinska, Mark H. M. Winands   +3 more
openaire   +2 more sources