Since 2013, the Food and Agriculture Organization of the United Nations published a publication that embraced the opportunity to use insect for food and feed, to raise the profile of insects and further promoting diversity of diet, sustainable practices, and food security, insect production has attracted attention as a potential food source, and advanced methods have been developed. Among insects, crickets are of particular interest because they are omnivorous and easy to mass produce. Ultimately, we aim to build a system in Japan that can mass-produce crickets using food waste. For this purpose, a cricket feeding system that utilises food loss is needed to support the development and commercialisation of new insect foods along with renewable energy and smart production methods to reduce labour requirements. To improve productivity and develop smart production, we should understand the ecology of crickets (focusing on their behaviour in terms of diet and water consumption) with the premise of mass production. However, relatively few studies have considered these factors in detail. We consider that this information could enable considerable improvement in the productivity of cricket production systems. Therefore, in this study, we constructed an Artificial Intelligent system designed to capture ecological information on crickets using a You Only Look Once version 5 model for mass production. The proposed system is relatively inexpensive, has high recognition accuracy and real-time performance, can be configured for different lighting conditions, and can recognise crickets even under dark conditions. The results show that this system can be implemented on prototype smart cricket farms and can be integrated with mass production systems. It is robust to bright and dark conditions with high accuracy and real-time framerates, with mAP values of 0.903 and 0.921 and framerates of 20.20 and 20.96 frames, respectively.

Abstract

Crickets are being reevaluated as food and livestock feed due to their high nutritional value and low environmental impact during production, as food waste can be used as feed. On the other hand, current cricket production uses feed used in aquaculture and poultry farming, and these feeds contain animal proteins such as fish meal and chicken meal. This is simply converting other animal proteins into insect proteins. Therefore, this study aimed to test whether two-spotted cricket powder can be used as a substitute for fishmeal in diets for Gryllus bimaculatus production. Cricket weight, feed efficiency, and number of crickets were evaluated by feeding rice bran: cricket powder = 85:15 and rice bran: fish meal = 85:15, respectively, referring to the feed mix ratio used by cricket producers. Results showed no statistically significant differences between the two experiments in cricket weight and feed conversion ratio. When data were obtained separately for each growth phase, cricket weight was found to be highest in the fourth post-hatching week for the diet with cricket powder and then decreased (initial input: 1 g; 28 days: 89.45 ± 22.19 g; 35 days: 49.47 ± 14.11 g). Feed conversion efficiency was found to be higher in the second half of growth (1-7 days: 0.48; 23-28 days: 0.80). The use of insect powder as bait for crickets is a new proposal. In cricket production, adults with low reproductive capacity are packaged and sold as food or livestock feed, but by using insect powder as feed during cricket production, it is possible to reduce animal protein in the feed. In the future, we plan to investigate the usefulness of mass-produced insect powder as feed for crickets.

Abstract

In this study, a self-selected feed design was conducted for Japanese food wastes, considering the macronutrients (protein, lipid, carbohydrate) and six feed options and three options for vegetable wastes, and performance was compared with commercial diet to determine the usefulness of the feed design method and the possibility of using food waste in Japan were examined by comparing the performance of the feed design method with commercial diet. Data on self-selection diet design for crickets at different growth stages were obtained to determine the differences in feed consumption rates and nutrient requirements among stages. The results showed that it is possible to achieve cricket weight and feed conversion efficiencies (0.5-0.8) comparable to those of commercial diets using food residues when macro-nutrients are considered, and abundant options are provided. On the other hand, the use of only vegetable wastes resulted in lower cricket weight and higher feed conversion efficiency (0.8-1.4). Based on feed consumption rates, bread bran, rice bran, and fish meal were found to be suitable feeds among Japanese food waste for production in all growth stages, while bean curd and sake less were found to be suitable for production in some growth stages. Data obtained from self-selections separated by growth stage revealed that the percentage of feed consumption varied greatly among growth stages, being about 50-68% in the late growth stage. Percentages of macronutrients and micronutrients were also found to vary by growth stage. Protein percentages were found to be higher in the second week after hatching. Lipids were highest in the first week and decreased thereafter. Crude fiber was lowest in the fourth week. Ash content did not change significantly at all stages. This research is the first attempt at self-selection of crickets in different growth stages, and the data obtained can contribute to feed design.