Artificial neural networks

Development of Machine Learning and Deep Learning Models for Predicting Groundwater Levels in South Korea

Research conducted at Duy Tan University in Da Nang, Vietnam, has led to the development of machine learning and deep learning models to predict groundwater levels in South Korea. The study utilized four machine learning and two deep learning algorithms to forecast groundwater levels in Bongseong well on Jeju Island,

Advances in Civil Structural Health Monitoring: A Novel Methodology for Buried Water Pipelines

A new study from researchers at Dalian University of Technology has proposed a novel methodology for the joint identification of foundation voids and structural deformations in buried water pipelines. The method uses physics-informed neural networks (PINNs) to analyze distributed strain data and accurately identify void characteristics, including location and length.

Artificial neural networks

Adaptive Beamforming Using Neural Networks for Conformal Antenna Arrays

Researchers at the University of Tunis El Manar have developed a novel approach to adaptive beamforming for conformal antenna arrays using neural networks. This breakthrough offers significant improvements in size, 3D scanning capability, and performance compared to existing configurations. By electronically steering the main radiating beam in both azimuth and

Artificial neural networks

Dual Neural Network Method for Elliptic Partial Differential Equations and Systems

Researchers at Purdue University have developed a new method for solving elliptic partial differential equations and systems, using a deep neural network function and a dual formulation. The Dual Neural Network (DuNN) method is designed to provide accurate solutions to complex problems in a wide range of fields, including physics

Artificial neural networks

Diverse and Flexible Behavioral Strategies Arise in Recurrent Neural Networks Trained on Multisensory Decision Making

Researchers at Loughborough University have made a groundbreaking discovery in the field of neural networks, revealing that behavior variability across individuals leads to substantial performance differences during cognitive tasks. The investigation, supported by the Nederlandse Organisatie voor Wetenschappelijk Onderzoek, employed recurrent neural networks trained on a multisensory decision-making task to

Artificial neural networks

Machine Learning Accelerates Design of Multispectral Compatible Camouflage Metamaterials

Researchers from Wuhan University in China have employed a feedforward neural network and a direct inversion algorithm to accelerate the design of an optically transparent metamaterial absorber with infrared-microwave compatible camouflage properties. The designed metamaterial exhibits excellent performance in both infrared and microwave ranges, with an infrared emissivity of approximately

Artificial neural networks

Efficient Fully Parallel Convolutional Neural Network Architecture Reduces Power Consumption and Chip Area

A groundbreaking study from Babol Noshirvani University of Technology in Iran proposes a novel fully parallel convolutional neural network (FP-CNN) architecture that leverages single-memristor crossbar arrays to optimize area and power efficiency. This innovative design enables the computation of multiple feature maps in one processing cycle, leading to significant reductions

Artificial neural networks

Advances in Electronics: Prototype-Based Networks Show Promise

Researchers from the Polytechnic University of Madrid have made significant findings in the field of electronics, specifically in the development of prototype-based networks (PBNs). These neural networks are designed to be inherently interpretable, allowing for a deeper understanding of model outputs by analyzing the activation of specific neurons, known as

Artificial neural networks

Neural Network Improves Solar Image Quality Assessment

Research conducted at the National Solar Observatory has developed a convolutional classification neural network to assess the quality of solar images in near real-time. The network has been shown to improve the quality of science data products in an automated data reduction pipeline without human intervention. This breakthrough has significant

Artificial neural networks

Dissipativity Analysis and Bumpless Transfer Control for Synchronization of Switched Delayed Neural Networks: A New Approach

Researchers from Northeastern University have made a breakthrough in the field of networks by developing a new method for dissipativity analysis and bumpless transfer control for synchronization of switched delayed neural networks (SDNNs). The study, funded by the National Natural Science Foundation of China, China Postdoctoral Science Foundation, and Open

Artificial neural networks

Novel Fuzzy Neural Network Framework Enhances Multiple Attribute Decision-making in Uncertain Environments

Research conducted at the University of Faisalabad in Faisalabad, Pakistan has proposed a novel fuzzy neural network (FNN) framework that operates under complex Fermatean fuzzy sets to enhance multiple attribute decision-making (MADM) in uncertain environments. The model integrates Schweizer-Sklar-based aggregation operators within the FNN's computational layers to process

Artificial neural networks

Equivariant Neural Networks for Physics and Chemistry

Researchers from the University of Chicago have developed a new class of artificial neural networks called equivariant neural nets, which can efficiently incorporate symmetries into the network structure. This innovation has significant implications for applications in physics and chemistry, where symmetries play a crucial role in understanding complex phenomena. The

See all