Teachers are expected to respond quickly and accurately to any diabetes incident that may occur to children in the school setting. Access to diabetes information is crucial for student safety, health, academic achievement, and social competence. This paper describes a technique to provide Web-based diabetes information using computer audio and video to enrich a text-based training experience. Two groups of teachers were presented with diabetes training material via either paper or a Web-based computer system. Both groups were then evaluated for diabetes knowledge and satisfaction. Subjects using the Web-based system had significantly (t = 2.22; p < 0.033) higher knowledge scores (72.5% versus 66.4% correct) and were significantly (t = 3.9; p < 0.001) more satisfied with the training session (4.2 versus 3.1 on a five-point scale) than subjects who used paper documents traditionally used for teacher training. With the advantages in learning and the reduced cost of a Web-based system, diabetes distance education is a viable and desirable alternative to paper-based diabetes education.

Fish species recognition is crucial to identifying the abundance of fish species in a specific area, controlling production management, and monitoring the ecosystem, especially identifying the endangered species, which makes accurate fish species recognition essential. In this work, the fish species recognition problem is formulated as an object detection model to handle multiple fish in a single image, which is challenging to classify using a simple classification network. The proposed model consists of MobileNetv3-large and VGG16 backbone networks and an SSD detection head. Moreover, a class-aware loss function is proposed to solve the class imbalance problem of our dataset. The class-aware loss takes the number of instances in each species into account and gives more weight to those species with a smaller number of instances. This loss function can be applied to any classification or object detection task with an imbalanced dataset. The experimental result on the large-scale reef fish dataset, SEAMAPD21, shows that the class-aware loss improves the model over the original loss by up to 79.7%. The experimental result on the Pascal VOC dataset also shows the model outperforms the original SSD object detection model.

No abstract

No abstract

No abstract