eLife

Human EEG and artificial neural networks reveal disentangled representations and processing timelines of object real-world size and depth in natural images

Neural and computational evidence reveals that real-world size is a temporally late, semantically grounded, and hierarchically stable dimension of object representation in both human brains and ...
IEEE

Dynamic Spatial-Temporal Graph Convolutional Neural Networks Approach for Active Mode Traffic Prediction

Abstract: Accurate short-term predictions of active mode traffic are crucial for effective urban traffic control and management, helping to reduce delays, stops, and improve travel time reliability, ...
Nanowerk

Twisted graphene unlocks thermal sensing with built-in logic

Twisted graphene heterostructures detect temperature with 99% accuracy, reduce thermal image errors by 46%, and execute logic ...
Modern Engineering Marvels on MSN

How a dropout mastered PhD-level AI with ChatGPT

For Gabriel Petersson, the path to becoming a research scientist at OpenAI didn’t start in a lecture hall but began with a ...

Hyderabadi cracks decades-old global biological puzzle at 25 years of age

Using the AI, a young scientist Mohan Vamsi Nallapareddy and his team developed an AI tool, which can predict protein-production failures at the molecular level and such predictions could ...
EurekAlert!

Metallic glass discovery using AI-guided graph learning from Wikipedia data

A research team from the Songshan Lake Materials Laboratory has developed an AI-guided "Recommendation System" to discover ...
IEEE

Multigranularity Deep Graph Convolutional Neural Network Node Clustering Leveraging Spatial Information

Abstract: In the era of information explosion, clustering analysis of graph-structured data and empty graph-structured data is of great significance for extracting the intrinsic value of data. From ...
Scientific Research Publishing

Phan, A.V., Nguyen, M.L., Nguyen, Y.L.H. and Bui, L.T. (2018) DGCNN: A Convolutional Neural Network over Large-Scale Labeled Graphs. Neural Networks, 108, 533-543.

ABSTRACT: Point cloud-based 3D object detection is a key technology in autonomous driving and mobile robot perception systems. However, the sparsity and irregularity of point cloud data result in poor ...