Scientific methods are used to monitor fish growth and behavior and reduce the loss caused by stress and other circumstances. Conventional techniques are time-consuming, labor-intensive, and prone to accidents. Deep learning (DL) technology is rapidly gaining popularity in various fields, including aquaculture. Moving towards smart fish farming necessitates the precise and accurate identification of fish biodiversity. Observing fish behavior in real time is imperative to make better feeding decisions. The proposed study consists of an efficient end-to-end convolutional neural network (CNN) classifying fish behavior into the normal and starvation categories. The performance of the CNN is evaluated by varying the number of fully connected (FC) layers with or without applying max-pooling operation. The accuracy of the detection algorithm is increased by 10% by incorporating three FC layers and max pooling operation. The results demonstrated that the shallow architecture of the CNN model, which employs a max-pooling function with more FC layers, exhibits promising performance and achieves 98% accuracy. The presented system is a novel step in laying the foundation for an automated behavior identification system in modern fish farming. Full article

Germplasm repositories can benefit sustainable aquaculture by supporting genetic improvement, assisted reproduction, and management of valuable genetic resources. Lack of reliable quality management tools has impeded repository development in the past several decades. Microfabricated open-hardware devices have emerged as a new approach to assist repository development by providing standardized quality assessment capabilities to enable routine quality control. However, prototyping of microfabricated devices (microdevices) traditionally relies on photolithography techniques that are costly, time intensive, and accessible only through specialized engineering laboratories. Although resin 3-D printing has been introduced into the microfabrication domain, existing publications focus on customized or high-cost (>thousands of USD) printers. The goal of this report was to identify and call attention to the emerging opportunities to support innovation in microfabrication by use of low-cost (<USD 350) resin 3-D printing for rapid prototyping. We demonstrate that low-cost mask-based stereolithography (MSLA) 3-D printers with straightforward modifications can provide fabrication quality that approaches traditional photolithography techniques. For example, reliable feature sizes of 20 µm with dimensional discrepancy of <4% for lateral dimensions and <5% for vertical dimensions were fabricated with a consumer-level MSLA printers. In addition, alterations made to pre-processing, post-processing, and printer configuration steps improved print quality as demonstrated in objects with sharper edges and smoother surfaces. The prototyping time and cost of resin 3-D printing (3 h with USD 0.5/prototype) were considerably lower than those of traditional photolithography (5 d with USD 80/prototype). With the rapid advance of consumer-grade printers, resin 3-D printing can revolutionize rapid prototyping approaches for microdevices in the near future, facilitating participation in interdisciplinary development of innovative hardware to support germplasm repository development for aquatic species. Full article