Machine learning
Researchers from the Harbin Institute of Technology have proposed a new framework, RefineCatDiff, for high-quality medical image segmentation. According to the study, existing convolutional neural network-based or vision transformer-based segmentation models often struggle to produce accurate masks when dealing with complex images. However, diffusion models are particularly effective at capturing
Artificial intelligence
The integration of artificial neural networks (ANN) and decision tree analysis (DTA) into project management practices has led to significant improvements in project efficiency, cost estimation, and time management. According to a recent study, these AI tools possess superior predictive accuracy, decision support, and adaptability capabilities compared to conventional tools
Artificial intelligence
Researchers from Pacific National University, in collaboration with other institutions, have successfully developed an autoregressive neural network model for predicting road accidents in the Khabarovsk Territory. The study, published in Intellekt. Innovacii. Investicii, aimed to improve road safety by leveraging machine learning techniques to analyze historical accident data and forecast
Artificial intelligence
Researchers from the University of Information Technology and Communications have conducted a study comparing the predictive abilities of multiple linear regression (MLR) and artificial neural networks (ANN) in estimating wheat production in Iraq. The study found that ANN outperformed MLR, producing more accurate estimates with lower error levels. This breakthrough
Artificial intelligence
Recent research by Dengpan Ye and colleagues from Wuhan University has proposed a novel recurrent neural network (RNN) adversarial attack model called Temporal Adversarial Examples Attack Model (TEAM). According to the study, the development of artificial intelligence has made neural networks crucial for network intrusion detection systems (NIDS). However, these
Artificial intelligence
Research findings on Networks discuss the integration of domain knowledge into the artificial intelligence learning process, with a focus on decentralized settings. The University of Calabria researchers propose the Physics-Informed DFL (PIDFL) architecture to integrate domain knowledge expressed as differential equations. The proposed framework achieves on average over 40% lower
Machine learning
Researchers at the Chengdu University of Technology have successfully developed an artificial neural network that can accurately predict drilling performance in the petroleum industry. The team, led by Xiong Xiuli, used a back-propagation artificial neural network (BP-ANN) to train a drilling performance prediction function based on field data from a
Technical institutes
A team of researchers from the Xi'an University of Technology has developed a deep learning model that can accurately predict atmospheric ozone concentrations. The model combines an attention mechanism with a convolutional neural network (CNN) and long short-term memory (LSTM) network to address the nonlinear nature of multivariate
Machine learning
Researchers from Chengdu Technological University have made significant strides in cloud computing, developing advanced machine learning models for intrusion detection in cloud environments. According to the study, the team focused on Transformer-based Spatio-Temporal Graph Neural Networks (ST-GNN), CNN, LSTM, Isolation Forest, and conventional GNNs, evaluating their performance on three distinct
Machine learning
Researchers from Fudan University have developed an artificial neural network (ANN) model to predict the depth, width, and volume of ablation thermal lesions during radiofrequency cardiac ablation (RFCA). According to the study, the two-branch ANN model was able to predict thermal lesion size with errors of 0.1986 mm, 0.
Machine learning
Researchers at Ateneo de Manila University have developed a Machine Vision System (MVS) that can automate the inspection of microcontroller units (MCU) and detect empty trays, addressing a serious issue in the manufacturing environment. The MVS uses a Convolutional Neural Network (CNN) deployed in OpenMV H7 Plus, a low-power, memory-constrained
Machine learning
Research conducted by the Defence Institute of Advanced Technology has found that a novel approach using Artificial Neural Networks (ANNs) can optimize the decolorization of Rhodamine B dye from effluents. The ANNs were used to model the adsorption capacity of sodium hydroxide-functionalized sugarcane bagasse biochar (NaOH-SBB), which demonstrated a strong
