A cutting-edge neural network approach for predicting the thermoelectric efficiency of defective gamma-graphyne nanoribbons.

This study predicts the thermoelectric figure of merit (ZT) for defective gamma-graphyne nanoribbons (γ-GYNRs) using binary coding, convolutional neural networks (CNN), long short-term memory networks (LSTM), and multi-scale feature fusion. The approach accurately predicts ZT values with only 500 initial structures (3% of 16,512 candidates), achieving an R above 0.91 and a mean absolute error (MAE) of 0.

Structural Characterization and Antioxidant Activity of β-Glucans from Highland Barley Obtained with Ultrasonic-Microwave-Assisted Extraction.

In order to efficiently extract β-glucan from highland barley (HBG) and study its structural characterization and antioxidant activity, ultrasonic-microwave-assisted extraction (UME) was optimized by the response surface method (RSM). Under the optimal extraction conditions of 25.05 mL/g liquid-solid ratio, 20 min ultrasonic time, and 480 W microwave intensity, the DPPH radical scavenging activity of HBG reached 25.

Elastic Net Constraint-Based Tensor Model for High-Order Graph Matching.

The procedure of establishing the correspondence between two sets of feature points is important in computer vision applications. In this article, an elastic net constraint-based tensor model is proposed for high-order graph matching. To control the tradeoff between the sparsity and the accuracy of the matching results, an elastic net constraint is introduced into the tensor-based graph matching model.

DrPOCS: Drug Repositioning Based on Projection Onto Convex Sets.

Drug repositioning, i.e., identifying new indications for known drugs, has attracted a lot of attentions recently and is becoming an effective strategy in drug development.