The dataset contains data used in the thesis "Hierarchical Fish Species Detection in Real-Time Video Using YOLO". It consists of the weights of the models that was used for the different experiments, some framework configurations, and the object detection dataset. The detector runs on the Darknet framework.
The object detection dataset is a collection of 1879 images of underwater fish taken from a stationary camera in Lindesnes, Norway. Each image has a corresponding annotation file that defines a bounding box and class for each fish. The images are annotated with hierarchical classification and biological taxonomy in mind. The hierarchy is defined in fish_taxonomy.xml. This means that if the species cannot be discerned, a higher class in the hierarchy will be used. There is 7721 annotated fish in the dataset.
Contributors:Adolf Krige, Jakub Haluska, Paul Christakopoulos, Ulrika Rova
Abstract: Due to the high cost of bioprinters they are not feasible for proof of concept experiments or educational purposes. Furthermore, the more affordable DIY methods all disable the plastic printing capability of the original printer. Here we present an affordable bio-printing modification that is easy to install and maintains the original capabilities of the printer. The modification used mostly 3D printed parts and is based on the popular, open-source Prusa i3 3D printer. The modifications are kept as simple as possible and uses standard slicing software, allowing for installation by less experienced builders. By using disposable syringes and easily sterilizable parts, an aseptic bioprinting setup can be achieved, depending on the environment. It also allows for 2 component printing as well as UV curing.
1H, 13C NMR (FID and processed spectra) and HR-MS spectroscopic data of amino-phenol chelating ligands, their derivatives with B-galactose, N,O-ligands and HR-MS spectra of Fe iron(III) complexes as bioresponsive, smart, enzyme sensitive systems