Results 41 to 50 of about 1,727,853 (256)

Graph convolution networks based on adaptive spatiotemporal attention for traffic flow forecasting

open access: yesScientific Reports
Traffic flow is the most direct indicator of traffic conditions, and accurate prediction of traffic flow is a key challenge for scholars in the field of intelligent transportation. However, traffic flow displays significant nonlinearity, dynamic changes,
Hongbo Xiao, Beiji Zou, Jianhua Xiao
doaj   +1 more source

Reversible Tuning of Multiple Molecular Kinking for Stem Cell Regulation In Vivo

open access: yesAdvanced Functional Materials, EarlyView.
In this work, we introduce the novel concept of background component‐free “multiple kinks” material platform composed solely of liganded multiple kink‐bearing molecules as a strategy for dynamic biomaterial design. Tri‐kink molecules enable effective near‐infrared light‐triggered ligand masking and visible light‐triggered ligand exposure, thereby ...
Kanghyeon Kim   +28 more
wiley   +1 more source

Partial Convolutional LSTM for Spatiotemporal Prediction of Incomplete Data

open access: yesIEEE Access, 2020
Advanced data analysis techniques facilitate data-driven spatiotemporal prediction in various fields. However, in real-world data, missing values are inevitable, which causes the data incomplete and makes predictions more challenging.
Hyesook Son, Yun Jang
doaj   +1 more source

2D Skeletal Muscle Thin Film Actuators Enhance Efficiency of Biohybrid Robots

open access: yesAdvanced Functional Materials, EarlyView.
2D skeletal muscle thin film actuators generate millinewton‐scale forces and millimeter‐scale strokes while remaining functional for over 30 days. Their force density is 20‐fold higher than 3D skeletal muscle actuators, enabling multi‐fin robots with tunable speed and multidirectional steering.
Maheera Bawa   +5 more
wiley   +1 more source

Spatiotemporal Deep-Learning-Based Algal Bloom Prediction for Lake Okeechobee Using Multisource Data Fusion

open access: yesIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022
This study focuses on predicting harmful algal bloom (HAB) events in Lake Okeechobee, a shallow lake in Florida. A spatiotemporal deep learning model is employed to predict the levels of cyanobacteria Microcystis aeruginosa present in the lake for a ...
Yufei Tang   +6 more
doaj   +1 more source

An Integrated Oxygen‐Supplying Device and Predictive Multiphysics Model for Extended Ambient Transport of Insulin‐Producing Cells

open access: yesAdvanced Functional Materials, EarlyView.
Cell therapies typically rely on cold‐chain logistics and cryopreservation, limiting access and compromising cell quality. Here, a dual‐chamber device separates an oxygen‐supplying chamber from a hyaluronic acid cargo chamber, sustaining oxygen delivery for over 70 h and enabling ambient‐temperature shipment.
Daniel A. Domingo‐Lopez   +9 more
wiley   +1 more source

Improving the Estimation of PM2.5 Concentration in the North China Area by Introducing an Attention Mechanism into Random Forest

open access: yesAtmosphere
Fine particulate matter with an aerodynamic diameter less than 2.5 µm (PM2.5) profoundly affects environmental systems, human health and economic structures.
Luo Zhang   +6 more
doaj   +1 more source

Bioinspired Hydrogels with Broadly Programmable Mechanics for Soft‐Tissue Interfaces

open access: yesAdvanced Functional Materials, EarlyView.
Sea cucumber‐inspired gelatin hydrogels are formed by directional freezing and mechanically programmed through subsequent ionic treatment. Multiscale characterization and modeling link ion‐regulated chain interactions to directional load transfer within the aligned hierarchical architecture.
Youchao Teng   +20 more
wiley   +1 more source

Study on mining wind information for identifying potential offshore wind farms using deep learning

open access: yesFrontiers in Energy Research
The global energy demand is increasing due to climate changes and carbon usages. Accumulating evidences showed energy sources using offshore wind from the sea can be added to increase our consumption capacity in long term.
Jiahui Zhang   +4 more
doaj   +1 more source

A Novel Deep Learning-Based Spatiotemporal Fusion Method for Combining Satellite Images with Different Resolutions Using a Two-Stream Convolutional Neural Network

open access: yesRemote Sensing, 2020
Spatiotemporal fusion is considered a feasible and cost-effective way to solve the trade-off between the spatial and temporal resolution of satellite sensors.
Duo Jia   +5 more
doaj   +1 more source

Home - About - Disclaimer - Privacy