By combining ionic nonvolatile memories and transistors, this work proposes a compact synaptic unit to enable low‐precision neural network training. The design supports in situ weight quantization without extra programming and achieves accuracy comparable to ideal methods. This work obtains energy consumption advantage of 25.51× (ECRAM) and 4.84× (RRAM)
Zhen Yang +9 more
wiley +1 more source
Technical Note: 3D localization of lung tumors on cone beam CT projections via a convolutional recurrent neural network. [PDF]
Wang C +9 more
europepmc +1 more source
Tatum-Level Drum Transcription Based on a Convolutional Recurrent Neural Network with Language Model-Based Regularized Training [PDF]
Ryoto Ishizuka +3 more
openalex +1 more source
Leveraging Artificial Intelligence and Large Language Models for Cancer Immunotherapy
Cancer immunotherapy faces challenges in predicting treatment responses and understanding resistance mechanisms. Artificial intelligence (AI) and machine learning (ML) offer powerful solutions for cancer immunotherapy in patient stratification, biomarker discovery, treatment strategy optimization, and foundation model development.
Xinchao Wu +4 more
wiley +1 more source
SST-CRAM: spatial-spectral-temporal based convolutional recurrent neural network with lightweight attention mechanism for EEG emotion recognition. [PDF]
Qiao Y, Zhao Q.
europepmc +1 more source
This manuscript presents the WDMS platform, an AI‐assisted, self‐powered wearable dual‐mode sensor for tele‐neurology. It integrates a contact–separation TENG insole with stretchable polyurethane optical‐fiber strain sensors to synchronously track plantar pressure and lower‐limb muscle deformation.
Tianliang Li +12 more
wiley +1 more source
A Hybrid Model for Soybean Yield Prediction Integrating Convolutional Neural Networks, Recurrent Neural Networks, and Graph Convolutional Networks [PDF]
Vikram S. Ingole +5 more
openalex +1 more source
Physics‐Embedded Neural Network: A Novel Approach to Design Polymeric Materials
Traditional black‐box models for polymer mechanics rely solely on data and lack physical interpretability. This work presents a physics‐embedded neural network (PENN) that integrates constitutive equations into machine learning. The approach ensures reliable stress predictions, provides interpretable parameters, and enables performance‐driven, inverse ...
Siqi Zhan +8 more
wiley +1 more source
Smart Optogenetics for Real‐Time Automated Control of Cardiac Electrical Activity
We are able to stop dangerous heart‐rhythm spirals before they fully form. Within about 100 ms, it pinpoints the spiral's tiny central tip (≈0.9 mm) using light‐based sensing and machine learning, then shines targeted light to shut it down. This fast, precise, closed‐loop approach detects, targets, and terminates arrhythmias in real time.
Shanliang Deng +15 more
wiley +1 more source
Multimodal Wearable Biosensing Meets Multidomain AI: A Pathway to Decentralized Healthcare
Multimodal biosensing meets multidomain AI. Wearable biosensors capture complementary biochemical and physiological signals, while cross‐device, population‐aware learning aligns noisy, heterogeneous streams. This Review distills key sensing modalities, fusion and calibration strategies, and privacy‐preserving deployment pathways that transform ...
Chenshu Liu +10 more
wiley +1 more source

