Convolutional Neural Networks Using Enhanced Radiographs for Real-Time Detection of Sitophilus zeamais in Maize Grain.

The application of artificial intelligence (AI) such as deep learning in the quality control of grains has the potential to assist analysts in decision making and improving procedures. Advanced technologies based on X-ray imaging provide markedly easier ways to control insect infestation of stored products, regardless of whether the quality features are visible on the surface of the grains. Here, we applied contrast enhancement algorithms based on peripheral equalization and calcification emphasis on X-ray images to improve the detection of Sitophilus zeamais in maize grains. In addition, we proposed an approach based on convolutional neural networks (CNNs) to identity non-infested and infested classes using three different architectures; (i) Inception-ResNet-v2, (ii) Xception and (iii) MobileNetV2. In general, the prediction models developed based on the MobileNetV2 and Xception architectures achieved higher accuracy (≥0.88) in identifying non-infested grains and grains infested by maize weevil, with a correct classification from 0.78 to 1.00 for validation and test sets. Hence, the proposed approach using enhanced radiographs has the potential to provide precise control of Sitophilus zeamais for safe human consumption of maize grains. The proposed method can automatically recognize food contaminated with hidden storage pests without manual features, which makes it more reliable for grain inspection.

Cafeteria-Type Feeding of Chickens Indicates a Preference for Insect (Tenebrio molitor) Larvae Meal.

This study aimed to determine whether broiler chickens display a preference for Tenebrio molitor larvae (TM) meal by evaluating ingredient acceptability and birds' performance. Sixty 14-day-old male chickens were assigned into two treatment groups (5 birds/pen, n = 6) in a cafeteria-type study: the control (C) group, and the TM group. Each pen was equipped with one bell drinker and four through feeders allocated side by side; all feeders of the C group contained a complete standard diet whereas each feeder of the TM group contained one of the following ingredients: ground corn, extruded semi-whole soybean, vitamin-mineral supplement mixture, and TM meal. Feed intake was recorded daily and growth was monitored periodically up to day 32. Chickens which had access to individual feed components showed a delay to display preference for TM, but consumed, overall, up to 50% of the total intake as TM meal. Feed intake and growth performance were lower in all periods for TM group (p < 0.02), whereas feed conversion ratio was improved on days 22-28 and days 29-32 of age (p < 0.01). Data from bivariate and multidimensional analysis indicate that birds started to reach a balance of ingredient intake at 25 days of age, showing a high correlation between consumption of each ingredient and the day of the experiment. Chickens exhibited a preference for T. molitor meal, resulting in improved feed efficiency, which allows us to conclude that it can be a suitable feed alternative for poultry.