Results 61 to 70 of about 8,962 (250)

Recursive Identification. Estimation and Forecasting of Multivariate Time-series

IFAC Proceedings Volumes, 1988
Abstract The paper describes a new, fully recursive method for identifying, estimat-ing and forecasting multivariate (vector) time-series. Any low frequency (trend) components associated with each of the elements of the vector time-series are first removed by recursive, fixed interval smoothing based on generalised random walk (GRW) models; while the
Ng, CN, Young, PC, Wang, C
openaire   +2 more sources

Disruption of Treg Homeostasis in Rheumatoid Arthritis via Ferroptosis‐Mediated ETC Collapse and TXK‐STAT3/PLCγ1 Activation

Advanced Science, EarlyView.
In rheumatoid arthritis, synovial Tregs accumulate but are functionally impaired due to iron overload‐induced ferroptosis. This triggers mitochondrial dysfunction and TXK tyrosine kinase‐mediated signaling, leading to Treg destabilization and inflammation.
Jingrong Chen, Xiao Guan, Kexu Xiong, Xiaoyi Shi, Luyao Wu, Chuanxin Su, Jun Zhao, Rongzhen Liang, Huimin Wang, Junlong Dang, Ye Chen, Yiding Xiong, Chi Zhou, Futao Zhao, Zhenhang Zhu, Xiaoli Fan, Li Zhou, Nancy Olsen, Yutong Jiang, Song Guo Zheng   +19 more
wiley   +1 more source

Resource Time Series Analysis and Forecasting in Large-Scale Virtual Clusters

Big Data Mining and Analytics
In today’s rapidly evolving internet landscape, prominent companies across various industries face increasingly complex business operations, leading to significant cluster-scale growth.
Yue Lin, Jiamin Wen, Xudong Zhang, Yan Liang, Jianjiang Li   +4 more
doaj   +1 more source

Genome‐Wide In Vivo RNAi Screening Identifies HOXD4 as a Tumor Metastasis Suppressor in Colorectal Cancer

Advanced Science, EarlyView.
Metastasis remains a major challenge in colorectal cancer. Using an in vivo shRNA screening system, this study identifies Homeobox D4 as a key metastasis suppressor. Reduced Homeobox D4 expression is associated with aggressive tumor features. Functional and mechanistic analyses show that it inhibits epithelial‐mesenchymal transition by repressing ...
Zhi‐hua Ye, Wen‐jing Luo, Lu Li, Wen‐di Shuai, Ling Zhou, You‐fa Duan, Xue Chen, Jun‐kai Zhang, Wenlin Huang, Ran‐yi Liu   +9 more
wiley   +1 more source

An Efficient Solution for Multivariate Time Series Forecasting Based on a Stacked Complex Fuzzy Gated Recurrent Neural Network

IEEE Access
Multivariate Time series forecasting finds numerous applications across various fields, including society, industry, market, etc. Recently, gated recurrent unit neural networks (GRU) have shown high efficiency in processing sequential time series data in
Nguyen van Quyet, Nguyen Tho Thong, Nguyen Long Giang, Luong Thi Hong Lan   +3 more
doaj   +1 more source

Cuproptosis and Mitophagy Mediated by the THUMPD1/IGF2R‐Dependent Suppression of AKT and Activation of AMPK Signaling Suppress Lung Adenocarcinoma Progression

Advanced Science, EarlyView.
THUMPD1 drives a tumor‐suppressive signaling cascade in lung adenocarcinoma by promoting IGF2R expression. IGF2R associates with PPP2R1A to suppress AKT and activate AMPK, leading to SLC31A1 upregulation and copper accumulation. Elevated copper disrupts mitochondrial metabolism and induces excessive mitophagy, thereby restraining tumor growth and ...
Kai Wu, Bo Qin, Zhuoyu Gu, Weizheng Ding, Xiaoming Chen, Kaishang Zhang, Yujin Qiao, Shuang Yuan, Song Zhao, Xiangnan Li, Peng Zhang   +10 more
wiley   +1 more source

TFEformer: Temporal Feature Enhanced Transformer for Multivariate Time Series Forecasting

IEEE Access
Transformer-based models have traditionally been the primary focus of research for addressing time series forecasting challenges. However, the emergence of recently introduced high-performance linear models has cast doubt upon the effectiveness of ...
Chenhao Ying, Jiangang Lu
doaj   +1 more source

Revisiting Attention for Multivariate Time Series Forecasting

Proceedings of the AAAI Conference on Artificial Intelligence
Current Transformer methods for Multivariate Time-Series Forecasting (MTSF) are all based on the conventional attention mechanism. They involve sequence embedding and performing a linear projection for Q, K, and V, and then computing attention within this latent space.
openaire   +2 more sources

ML Workflows for Screening Degradation‐Relevant Properties of Forever Chemicals

Advanced Science, EarlyView.
The environmental persistence of per‐ and polyfluoroalkyl substances (PFAS) necessitates efficient remediation strategies. This study presents physics‐informed machine learning workflows that accurately predict critical degradation properties, including bond dissociation energies and polarizability.
Pranoy Ray, Andrew R. Castillo, Manoj Kolel‐Veetil, Surya R. Kalidindi   +3 more
wiley   +1 more source

Cotton Recruits Soil‐Derived Delftia tsuruhatensis to Suppress Aphid Detoxification Via Salicylic Acid‐Mediated Defense

Advanced Science, EarlyView.
This study systematically reveals a complex interactive network involving plants, microbes, and insects, elucidating the ecological and molecular mechanisms by which cotton enhances its resistance to aphids through the active recruitment of the beneficial soil bacterium Delftia tsuruhatensis.
Hui Xue, Fengchao Diao, Qiqing Yu, Xiangzhen Zhu, Tingfang Zhong, Li Wang, Kaixin Zhang, Dongyang Li, Jichao Ji, Junyu Luo, Jinjie Cui, Xueke Gao   +11 more
wiley   +1 more source