AI-Assisted Cotton Grading: Active and Semi-Supervised Learning to Reduce the Image-Labelling Burden.

The assessment of food and industrial crops during harvesting is important to determine the quality and downstream processing requirements, which in turn affect their market value. While machine learning models have been developed for this purpose, their deployment is hindered by the high cost of labelling the crop images to provide data for model training. This study examines the capabilities of semi-supervised and active learning to minimise effort when labelling cotton lint samples while maintaining high classification accuracy. Random forest classification models were developed using supervised learning, semi-supervised learning, and active learning to determine Egyptian cotton grade. Compared to supervised learning (80.20-82.66%) and semi-supervised learning (81.39-85.26%), active learning models were able to achieve higher accuracy (82.85-85.33%) with up to 46.4% reduction in the volume of labelled data required. The primary obstacle when using machine learning for Egyptian cotton grading is the time required for labelling cotton lint samples. However, by applying active learning, this study successfully decreased the time needed from 422.5 to 177.5 min. The findings of this study demonstrate that active learning is a promising approach for developing accurate and efficient machine learning models for grading food and industrial crops.

Recycling rice straw ash to produce low thermal conductivity and moisture-resistant geopolymer adobe bricks.

Rice straw ash (RSA) geopolymer adobe bricks were produced using the geopolymerization reaction among the RSA, soil, and alkaline activator at the Biosystem Engineering Department, Faculty of Agriculture, Alexandria University, Egypt, to optimize adobe brick advantages. The bulk density, water absorption, compressive strength, and thermal conductivity of the new composite were measured at RSA contents of 0%, 5%, 10%, and 20% and sodium hydroxide contents of 2.5%, 5%, 7.5%, and 10% after curing the composite for 28 days. Results indicated that increasing RSA from 0% to 20% increased the compressive strength and decreased the bulk density, water absorption, and thermal conductivity. Further, increasing sodium hydroxide from 2.5% to 10% increased the bulk density and compressive strength and decreased the water absorption. Significant effects of RSA and sodium hydroxide percentages and their interaction on all the studied characters were reported. The best conditions to minimize bulk density, water absorption, thermal conductivity, and optimize compressive strength of the composite were at 10% sodium hydroxide and 20% RSA. The minimum bulk density, water absorption, and thermal conductivity were 1.463 g/cm3, 8.3%, and 0.46 W/(m·K), respectively, while the maximum CS was 2.1 MPa after 28 days. Using RSA geopolymer adobe bricks on building interior walls is recommended to decrease bricks' thermal conductivity, water absorption, and weight.