The effect of weight quantization in multilayer neural networks is discussed. A method is derived by which one can predict the performance degradation at the output given the properties of the network and number of bits of quantization. Predictions from this method are evaluated against simulation results. An algorithm to decrease the noise at the output is presented and the results are compared with those above. 相似文献
Purpose: Secondary caries can occur around the restoration, fixed prosthesis, and orthodontic band margins because of cariogenic bacteria. Long-lasting antibacterial effectiveness of dental cements used contemporarily can reduce this phenomenon. The purpose of this study was to examine the antibacterial activities of nine dental cements (BisCem®, Super-Bond C&B, Rely XTM, PanaviaTM F 2.0, Variolink® II, UnitekTM Multi Cure, Multilink® Automix, ClearfilTM Esthetic Cement, TransbondTM LR) using agar diffusion test. Materials and methods: The test materials were inserted into the wells of Muller Hinton agar plates inoculated with Streptococcus mutans and Streptococcus salivarious. The diameters of the inhibition zones produced around the materials were measured after 24 h of incubation. Two-Way ANOVA, the Kruskal-Wallis, and the Mann–Whitney U tests at a significance level of p < 0.05 were analyzed for the results. Results: Unitek Multi Cure cement exhibited a significant difference from the control group against both S. mutans and S. salivarious (p < 0.05). While the zone of inhibition of Unitek Multi Cure cement was shorter (8.50 ± 1.77) than the control group (12.63 ± 1.30), Unitek Multi Cure had antibacterial effect against S. mutans and S. salivarious (p < 0.05). S. mutans displayed a significantly lower resistance to Unitek Multi Cure, BisCem, and Superbond C&B than S. salivarious (p < 0.05). Conclusion: Conventional glass ionomer cement, Unitek Multi Cure, exhibited greatest in vitro antibacterial activity against both S. mutans and S. salivarious. Formation of dental caries had been suppressed by the fluoride-releasing GICs. 相似文献
This article presents an approach for automatic building database updating from high-resolution space imagery based on the support vector machine (SVM) classification and building models. The developed approach relies on an idea that the buildings are similar in shape within an urban block or a neighbourhood unit. First, the building patches are detected through classification of the pan-sharpened high-resolution space imagery along with the normalized digital surface model (nDSM) and the normalized difference vegetation index (NDVI) using the binary SVM classifier. Then, the buildings that exist in the vector database but not seen in the image are detected through the analyses of the detected building patches. The buildings, which were constructed after the compilation date of the existing vector database, are extracted through the proposed model-based approach that utilizes the existing building database as a building model library. The approach was implemented in selected urban areas of the Batikent district of Ankara, the capital city of Turkey, using the IKONOS images and the existing building database. The results validated the success of the developed approach, with the building extraction accuracy computed to be higher than 80%. 相似文献
An experimental investigation on the structural behaviour of steel tubular columns in-filled with plain and steel fiber reinforced concrete is presented in this study. A total of 16 concrete-filled steel tubular columns were constructed and tested subjected to biaxial bending and short-term axial load. The main variables considered in the test study were the cross section, slenderness, concrete compressive strength and the load eccentricity. In the presented study, a theoretical method for the prediction of ultimate strength capacity and load-deflection curves of concrete filled steel tube columns is proposed. In the analysis procedure, the nonlinear behaviour of the materials is considered and the slenderness effect has been taken into account. The experimental ultimate strength capacities and load-deflection curves of both plain and steel fiber concrete-filled tube columns have been compared with the analysis results and discussed in the paper. The results indicate that the addition of steel fibers in core concrete has considerable effect on the behaviour of concrete-filled steel tube columns. 相似文献
Environmental friendly Halloysite nanotubes (HNTs) are used to fabricate novel nanofiltration membranes by in situ interfacial polymerization of piperazine and trimesoyl chloride. The removal of excess amine solution from the porous support membrane surface is a critical step to obtain defect free active layer. Hereby, two main removal tools for the excess aqueous amine solution; a rubber roll or air knife are compared to fabricate a defect free thin film nanocomposite (TFN) nanofiltration (NF) membrane. Removal by the rubber roll is eventuated more favorable than air knife in terms of the reproducibility of NF membranes by comparing salt rejections. By determining the removal step of excess amines, various HNTs concentrations are used to fabricate NF membranes and, these membranes are tested with salt and dye solutions at various pH and temperature ranges. R2 membrane (containing 0.02% [w/v] HNTs) performs the best flux results beside higher rejections of MgSO4 (93.0%) and dye (99.5%). To evaluate the extreme conditionals, further performance tests such as pH and temperature resistance are also performed for R2 membrane. Considering the performances of R2 membrane, HNTs can be demonstrated for tailoring the balance between flux and separation performance of NF membranes. 相似文献
Agricultural field boundary information is important and often required for the geosciences and the agricultural sector. In this paper, a novel method is developed to extract sub-boundaries within the permanent boundaries of agricultural land parcels from high-resolution optical satellite imagery using an improved cluster-based snake model. The method takes the advantage of the results of an automatic fuzzy c-means (FCM) clustering and edge detection to compute external forces for an improved gradient vector flow (GVF) snake model. The GVF snake algorithm is improved by using an automatic seeding model based on clustering results and image moment functions. To seed the improved GVF algorithm, an ellipse is automatically delineated for each cluster within agricultural parcel by utilizing image moment functions (in particular silhouette moments). The GVF snake model is then implemented for each seed, one seed at a time. Active contours tend to have curve shapes rather than straight lines due to their structure that consists of several connected nodes within each contour. Therefore, the final accurate results are obtained after performing a three-stage line simplification operation.
The experiments of the method were conducted on 20 test fields in a study area located near to the town of Karacabey, Turkey, using the 4-m resolution IKONOS multispectral (xs) image, the 2.44-m resolution QuickBird xs image, and the 0.61-m resolution QuickBird pan-sharpened (PS) image. Experimental results demonstrate that using both the clustering and edge detection results as external forces for the improved GVF snake model increases the accuracy of the results. In addition, the developed method showed a fairly good performance in extracting sub-boundaries for the fields comprising crops with an inherent high inner heterogeneity, such as rice and corn. The method can potentially be applied in the extraction of within-field sub-boundaries from high-resolution satellite imagery in agricultural areas. 相似文献