Construction and evaluation of an AI system for tracking cricket behavior under conditions of bright and dark lighting
In: Journal of Insects as Food and FeedSearch for other papers by T. Kaewplik in
Current site
Google Scholar
Search for other papers by D. Akiyama in
Current site
Google Scholar
Search for other papers by Y. Sasaki in
Current site
Google Scholar
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.
Purchase
Buy instant access (PDF download and unlimited online access):
Institutional Login
Log in with Open Athens, Shibboleth, or your institutional credentials
Personal login
Log in with your brill.com account
-
Akiyama, D. and Sasaki, Y., 2022. Construction of cricket ecology grasp AI system for smart mass production. Agricultural Information Research 31: 59-64.https://doi.org/10.3173/air.31.59
-
Alori, J., Descoins, A., Berneche, J., Yuhara, K., Lezama, F., Castro, A., David, Linares, R.C., Fernández, D., Kurucz, F., Akyon F.C., Ríos, B., shafu.eth, Nar, K. and Huh, D., 2022. tryolabs/norfair: v2.1.0. Zenodo.https://doi.org/10.5281/ZENODO.7226359
-
Anonymous, 2022. Insect protein market size, share & COVID-19 impact analysis, by product type (Coleoptera, Lepidoptera, Hymenoptera, Orthopetra, and others), application (food & beverages, animal feed, and pharmaceuticals & cosmetics), and regional forecast, 2022-2029. Available at:https://www.fortunebusinessinsights.com/industry-reports/insect-based-protein-market-100780.
-
Bochkovskiy, A., Wang, C.-Y. and Liao, H.-Y.M., 2020. YOLOv4: optimal speed and accuracy of object detection. arXivhttps://doi.org/10.48550/arXiv.2004.10934
-
Botha, L.M., Jones, T.M. and Hopkins, G.R., 2017. Effects of lifetime exposure to artificial light at night on cricket (Teleogryllus commodus) courtship and mating behaviour. Animal Behaviour 129: 181-188.https://doi.org/10.1016/j.anbehav.2017.05.020
-
Dobermann, D., Swift, J.A. and Field, L.M., 2017. Opportunities and hurdles of edible insects for food and feed. Nutrition Bulletin 42(4): 293-308.https://doi.org/10.1111/nbu.12291
-
Food and Agriculture Organization of the United Nations (FAO), 2013. Edible insects. Future prospects for food and feed security. Food and Agriculture Organization of the United Nations, Rome, Italy. Available at:https://www.fao.org/3/i3253e/i3253e.pdf.
-
Fukumura, K. and Nagata, S., 2017. Behavioral tracing demonstrates dietary nutrient discrimination in two-spotted cricketsGryllus bimaculatus. Bioscience, Biotechnology and Biochemistry 81: 1-4.https://doi.org/10.1080/09168451.2017.1343119
-
Funato, T., Nara, M., Kurabayashi, D., Ashikaga, M. and Aonuma, H., 2011. A model for group-size-dependent behaviour decisions in insects using an oscillator network. Journal of Experimental Biology 214: 2426-2434.https://doi.org/10.1242/jeb.057356
-
Ge, Z., Liu, S., Wang, F., Li, Z. and Sun, J., 2021. YOLOX: Exceeding YOLO Series in 2021 V100 batch 1 Latency (ms) YOLOX-L YOLOv5-L YOLOX-DarkNet53 YOLOv5-Darknet53 EfficientDet5 COCO AP (%) Number of parameters (M) Figure 1: speed-accuracy trade-off of accurate models (top) and Size-accuracy curve of lite models on mobile devices (bottom) for YOLOX and other state-of-the-art object detectors. arXiv 5: 12.https://doi.org/10.48550/arXiv.2107.08430
-
Hanboonsong, Y., Jamjanya, T. and Durst, P.B., 2013. Six-legged livestock: edible insect farming, collection and marketing in Thailand. Food and Agriculture Organization of the United Nations, Regional Office for Asia and the Pacific, Bangkok, Thailand. Available at:http://www.fao.org/docrep/017/i3246e/i3246e.pdf.
-
Hansen, M.F., Oparaeke, A., Gallagher, R., Karimi, A., Tariq, F. and Smith, M.L., 2022. Towards machine vision for insect welfare monitoring and behavioural insights. Frontiers in Veterinary Science 9: 835529.https://doi.org/10.3389/fvets.2022.835529
-
Jocher, G., Chaurasia, A., Stoken, A., Borovec, J., Vong, C., Kwon, Y., Michael, K., TaoXie, Fang, J., Matt, J., Changyu, L., Yifu, Z., Wong, C., V, A., Montes, D., Wang, Z., Fati, C., Nadar, J., Laughing, UnglvKitDe, Sonck, V., tkianai, yxNONG, Skalski, P., Hogan, A., Nair, D., Strobel, M. and Jain, M., 2022. ultralytics/yolov5: v7.0 – YOLOv5 SOTA realtime instance segmentation. Zenodo.https://doi.org/10.5281/zenodo.7347926
-
Levy, K., Wegrzyn, Y., Efronny, R., Barnea, A. and Ayali, A., 2021. Lifelong exposure to artificial light at night impacts stridulation and locomotion activity patterns in the cricketGryllus bimaculatus. Proceedings of the Royal Society B: Biological Sciences 288: 20211626.https://doi.org/10.1098/rspb.2021.1626
-
Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, W., Li, Y., Zhang, B., Liang, Y., Zhou, L., Xu, X., Chu, X., Wei, X. and Wei, X., 2022. YOLOv6: a single-stage object detection framework for industrial applications. arXivhttps://doi.org/10.48550/ARXIV.2209.02976
-
Nepal, U. and Eslamiat, H., 2022. Comparing YOLOv3, YOLOv4 and YOLOv5 for autonomous landing spot detection in faulty UAVs. Sensors 22: 464.https://doi.org/10.3390/s22020464
-
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., Kopf, A., Yang, E., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Steiner, B., Fang, L., Bai, J. and Chintala, S., 2019. PyTorch: an imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., d’Alché-Buc, F., Fox, E. and Garnett, R. (eds.) Advances in neural information processing systems 32. pp. 8024-8035. Available at:http://papers.neurips.cc/paper/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf.
-
Redmon, J. and Farhadi, A., 2018. YOLOv3: an incremental improvement. arXivhttps://doi.org/10.48550/arXiv.1804.02767
-
Roark, E., Albotros, N., Keck, K., Murphy, J. and Musiime, T.B., 2018. The effect of light conditions on the resting metabolic rate of house crickets,Acheta domesticus. Journal of Introductory Biology Investigations 8: 91488203. Available at:https://undergradsciencejournals.okstate.edu/index.php/jibi/article/view/6859.
-
Skalski, P., 2019. Make sense. Available at:https://www.makesense.ai/.
-
Tan, L., Huangfu, T. and Wu, L., 2021. Comparison of YOLO v3, faster R-CNN, and SSD for real-time pill identification. arXivhttps://doi.org/10.21203/rs.3.rs-668895/v1
-
Timothy, C.A. and Emmanuel, O., 2020. Phototactic response of two spotted cricket (Gryllus bimaculatus De Geer) to electric bulb light colours and types. International Journal of Sustainable Agricultural Research 7: 66-72.https://doi.org/10.18488/journal.70.2020.72.66.72
-
Vaga, M., Gustafsson, E. and Jansson, A., 2018. Evaluation of reusable hiding units for rearing house crickets (Acheta domesticus). In: Scientific Committee (ed.) Book of Abstracts of the 69th Annual Meeting of the European Federation of Animal Science. Wageningen Academic Publishers, Wageningen, the Netherlands, p. 470.https://doi.org/10.3920/978-90-8686-871-1
-
Vossen, L.E., Nilsson, E., Jansson, A. and Roman, E., 2023. Open field behavior in the house cricket (Acheta domesticus): effect of illumination, sex differences and individual consistency. Journal of Insects as Food and Feed 9(3) 317-324.https://doi.org/10.3920/JIFF2022.0063
-
Wang, C.-Y., Bochkovskiy, A. and Liao, H.-Y.M., 2022. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXivhttps://doi.org/10.48550/arXiv.2207.02696
-
Wenning, M.J., Piotrowski, T., Janzen, J., Nieβing, B. and Schmitt, R.H., 2022. Towards monitoring of a cricket production using instance segmentation. Journal of Insects as Food and Feed 8: 763-772.https://doi.org/10.3920/JIFF2021.0165
| All Time | Past 365 days | Past 30 Days | |
|---|---|---|---|
| Abstract Views | 331 | 205 | 28 |
| Full Text Views | 34 | 4 | 1 |
| PDF Views & Downloads | 57 | 5 | 0 |
Construction and evaluation of an AI system for tracking cricket behavior under conditions of bright and dark lighting
In: Journal of Insects as Food and FeedSearch for other papers by T. Kaewplik in
Current site
Google Scholar
PubMed
Search for other papers by D. Akiyama in
Current site
Google Scholar
PubMed
Search for other papers by Y. Sasaki in
Current site
Google Scholar
PubMed
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.
| All Time | Past 365 days | Past 30 Days | |
|---|---|---|---|
| Abstract Views | 331 | 205 | 28 |
| Full Text Views | 34 | 4 | 1 |
| PDF Views & Downloads | 57 | 5 | 0 |
