In this paper, we propose an approach to detect and geotag advertisement billboard in real-time condition. Our approach is using AlexNet's Deep Convolutional Neural Network (DCNN) as a pre-trained neural network with 1000 categories for image classification. To improve the performance of the pre-trained neural network, we retrain the network by adding more advertisement billboard images using inductive transfer learning approach. Then, we fine-tuned the output layer into advertisement billboard related categories. Furthermore, the detected advertisement billboard images will be geotagged by inserting Exif metadata into the image file. Experimental results show that the approach achieves 92.7% training accuracy for advertisement billboard detection, while for overall testing results it will give 71.86% testing accuracy.

No abstract

No abstract

BACKGROUNDAdding a binder to improve the mechanical properties of heat polymerised polymethylmethacrylate such as its transverse strength is now being developed. One of them is by adding high molecular nanochitosan. This study aims to determine the effect of adding high molecular nanochitosan on transverse strength of heat polymerised polymethylmethacrylate denture base resin.

BACKGROUNDEndodontically treated teeth are more susceptible to fracture as a result of increased brittleness and are weakened because of coronal destruction. Endodontically treated teeth with small or minimal cavities can be restored with direct composites in the presence of buccal and palatal cusp with intact marginal ridge. Bulk fill has minimal polymerisation shrinkage rate, curing depth of 4 mm, better bond strength and good physical properties. Other advantages include fewer void in the restorative material and lesser risk of contamination between layers. MATERIALS AND METHODSForty intact human upper premolars were selected for this study. In G1 to G4 standard class I cavity preparation with mesiodistal length of 4 mm and bucco-palatal width of 3 mm were done. A conservative endodontic access was done. All canals were prepared with Ni-Ti K files using a step-back technique. All teeth were obturated with gutta-percha. The teeth were randomly divided into four groups, G1 Tetric N Ceram bulk fill, G2 Filtek bulk fill, G3 Smart Dentin Replacement bulk fill and G4 Packable composite Filtek P60. RESULTSThere was a statistically significant effect on the fracture resistance of endodontically treated premolars with class I cavities using bulk fill composites (p < 0.05). CONCLUSIONBulk fill composite can be used as a final restoration in endodontically treated premolars with class I cavity, as it can also preserve sound tooth structure which can increase fracture resistance of the tooth.