A novel hybrid system for automatic detection of fish quality from eye and gill color characteristics using transfer learning technique.

Fish remains popular among the body's most essential nutrients, as it contains protein and polyunsaturated fatty acids. It is extremely important to choose the fish consumption according to the season and the freshness of the fish to be purchased. It is very difficult to distinguish between non-fresh fish and fresh fish mixed in the fish stalls. In addition to traditional methods used to determine meat freshness, significant success has been achieved in studies on fresh fish detection with artificial intelligence techniques. In this study, two different types of fish (anchovy and horse mackerel) used to determine fish freshness with convolutional neural networks, one of the artificial intelligence techniques. The images of fresh fish were taken, images of non-fresh fish were taken and two new datasets (Dataset1: Anchovy, Dataset2: Horse mackerel) were created. A novel hybrid model structure has been proposed to determine fish freshness using fish eye and gill regions on these two datasets. In the proposed model, Yolo-v5 and Inception-ResNet-v2 and Xception model structures are used through transfer learning. Whether the fish is fresh in both of the Yolo-v5 + Inception-ResNet-v2 (Dataset1: 97.67%, Dataset2: 96.0%) and Yolo-v5 + Xception (Dataset1: 88.00%, Dataset2: 94.67%) hybrid models created using these model structures has been successfully detected. Thanks to the model we have proposed, it will make an important contribution to the studies that will be conducted in the freshness studies of fish using different storage days and the estimation of fish size.

Biomechanical and fracture characteristics of different filling and fixation methods applied to various proximal tibial metaphyseal defect sizes in an ovine model.

BACKGROUND: Ideal treatment method based on the size of the defect in local aggressive bone tumors is yet to be described. We evaluated the mechanical behavior of different fixation methods for various defect sizes located in the proximal tibia. METHODS: Ninety-one sheep tibiae were distributed in five groups. Each study group was further divided into three subgroups, forming 25%, 50%, and 75% metaphyseal defects. The five groups were divided as follows: 1) control group where tibiae remained intact (n = 7); 2) isolated defect created, without filling (n = 21); 3) filling with cement (n = 21); 4) application of two subchondral cortical screws in addition to cement (n = 21); and 5) application of plate-screw fixation in addition to cement (n = 21). A loading test simulating the axial load applied by the distal femur to the tibia plateau was performed. The maximum failure load was compared between groups according to the defect size and fixation method. FINDINGS: In 25% defects, group 5 had significantly higher failure load than other groups. However, in 50% and 75% defects, additional fixation did not increase the failure load. Also, additional screw fixation did not increase failure load in all defect sizes. There was a significant positive correlation between fracture morphology and defect size, fixation method, and failure load. INTERPRETATION: Additional plate-screw fixation would increase the stability in defects ≤25%. In defects ≥50%, additional fixation does not increase stability. Screw fixation in addition to cementing does not increase stability in all defect sizes.