Search

In this study, a novel method combining contour analysis with deep CNN is applied for fire detection. The method was made for fire detection using two main algorithms: one which detects the color properties of the fires, and another which analyzes the shape through contour detection. To overcome the disadvantages of previous methods, we generate a new labeled dataset, which consists of small fire instances and complex scenarios. We elaborated the dataset by selecting regions of interest (ROI) for enhanced fictional small fires and complex environment traits extracted through color characteristics and contour analysis, to better train our model regarding those more intricate features. Results of the experiment showed that our improved CNN model outperformed other networks. The accuracy, precision, recall and F1 score were 99.4%, 99.3%, 99.4% and 99.5%, respectively. The performance of our new approach is enhanced in all metrics compared to the previous CNN model with an accuracy of 99.4%. In addition, our approach beats many other state-of-the-art methods as well: Dilated CNNs (98.1% accuracy), Faster R-CNN (97.8% accuracy) and ResNet (94.3%). This result suggests that the approach can be beneficial for a variety of safety and security applications ranging from home, business to industrial and outdoor settings. [ABSTRACT FROM AUTHOR]

Due to the widespread use of titanium alloy in various applications, such as maritime transportation and aviation, the process of mass production of this material has become more challenging. Traditional methods of removing materials have high wear rates and slow processing speeds. This has prompted the development of new techniques that can handle the complexity of this material. Wire Electrical Discharge Machining (WEDM) is a method frequently utilized in the removal of electrically conductive and hard materials. It can be used to create intricate designs by taking into account the input parameters, such as peak current and pulse duration. The various performance indicators of WEDM such as rate of material removal, surface roughness, dimensional deviation, and form/orientation tolerance errors are analyzed using a technique developed by Taguchi. The factors that influence the performance of this process are then analyzed through an ANOVA analysis. The goal of this research paper is to develop an optimization model based on a hybrid Taguchi grey approach that can be used to determine optimal process variable for achieving best performance in machining. The results of the explorative analysis shows that the various process variables can influence the performance of WEDM in Titanium grade 5. Contour plot and interaction analysis also adopted to divulge the interactive effect of factors on chosen performance measures. Furthermore, regression models were evolved to reveal the relationship amongst the dependent and independent variables. The findings of this study can be utilized by manufacturers to choose the suitable factors for the WEDM process. [ABSTRACT FROM AUTHOR]

In this study, a novel method combining contour analysis with deep CNN is applied for fire detection. The method was made for fire detection using two main algorithms: one which detects the color properties of the fires, and another which analyzes the shape through contour detection. To overcome the disadvantages of previous methods, we generate a new labeled dataset, which consists of small fire instances and complex scenarios. We elaborated the dataset by selecting regions of interest (ROI) for enhanced fictional small fires and complex environment traits extracted through color characteristics and contour analysis, to better train our model regarding those more intricate features. Results of the experiment showed that our improved CNN model outperformed other networks. The accuracy, precision, recall and F1 score were 99.4%, 99.3%, 99.4% and 99.5%, respectively. The performance of our new approach is enhanced in all metrics compared to the previous CNN model with an accuracy of 99.4%. In addition, our approach beats many other state-of-the-art methods as well: Dilated CNNs (98.1% accuracy), Faster R-CNN (97.8% accuracy) and ResNet (94.3%). This result suggests that the approach can be beneficial for a variety of safety and security applications ranging from home, business to industrial and outdoor settings.

Introduction: The objective of this study was to examine the effect of photofunctionalization on the soft-tissue contour formed at the interface of various abutment materials using end-point analyses obtained from the three-dimensional oral mucosal model (3D-OMMs). Methods: Commercially pure titanium (CPTi), alumina-toughened zirconia (ATZ), and yttria-stabilized zirconia (YSZ) made into discs shapes were classified into two groups: UV-treated (PTx) and non-treated (NTx). The materials in PTx groups were exposed to UV light for 12 min. Human gingival fibroblasts and TR146 epithelial cell lines co-cultured on the acellular dermal membrane were used to construct the 3D-OMM. After 4 days of culture, the discs were inserted into the holes prepared within the membrane of 3D-OMMs. The contour formed by the tissue was evaluated after 14 days of culture. Results: The UV treatment of abutment materials resulted in the formation of more non-pocket-tissue types among the PTx group (p = 0.002). Of all materials tested, soft tissue contour around YSZ showed higher scores for the non-pocket type in both non- and UV-treated groups. Conclusions: The non-pocket type of tissue attachment was frequently found in all surfaces modified by photofunctionalization, particularly zirconia. The 3D-OMM can be used to evaluate the biological endpoints of implant surface modifications. [ABSTRACT FROM AUTHOR]

The paper presents some improvements of fast contour recognition algorithm. The main idea of this algorithm is based on calculation of geometric characteristics of a two-dimensional surface in , which encodes digital images. To obtain the contours, Minkowski fractal dimension calculation is used. A postprocessing algorithm of contour thinning without loss of quality of entire contour picture is proposed in the paper. An estimate of the speed of the new algorithm is presented in comparison with the well-known implementation of the Canny algorithm using the OpenCV computer vision library and the parallel architecture of CUDA. Examples demonstrating the efficiency of the new algorithm are presented. [ABSTRACT FROM AUTHOR]

In order to realize the accurate identification of weld features in the digital model of ship welded parts, and to improve the speed and accuracy of welding process selection of welding robots, a weld seam feature recognition algorithm based on triangulation and contour analysis is proposed. First, the concave and convex vertices of the polygon are judged by the angle coefficient method, and based on the Delaunay triangulation of the concave vertices and the triangle rotation, the triangle mesh of the 3D model surface is constructed and the STL file is generated. Second, based on the normal vector angles of adjacent triangles, the contours and points of the model are extracted. Finally, the welding joint and groove shape are identified according to the joint space position and the minimum contour line distance. The test results show that the mesh division based on the triangle rotation is suitable for complex polygons such as "combs", compared with other related methods, the factors of grid average and associated quality are increased by an average of 12.06% and 12.26% respectively, which effectively reduces the generation of deformed triangles and improves the quality of the mesh. Furthermore, after the meshing and contour analysis are merged, 4 types of joint forms and 10 types of groove weld features can not only be identified, but also the recognition efficiency is high and the recognition accuracy is good, which verifies the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Introduction: The objective of this study was to examine the effect of photofunctionalization on the soft-tissue contour formed at the interface of various abutment materials using end-point analyses obtained from the three-dimensional oral mucosal model (3D-OMMs). Methods: Commercially pure titanium (CPTi), alumina-toughened zirconia (ATZ), and yttria-stabilized zirconia (YSZ) made into discs shapes were classified into two groups: UV-treated (PTx) and non-treated (NTx). The materials in PTx groups were exposed to UV light for 12 min. Human gingival fibroblasts and TR146 epithelial cell lines co-cultured on the acellular dermal membrane were used to construct the 3D-OMM. After 4 days of culture, the discs were inserted into the holes prepared within the membrane of 3D-OMMs. The contour formed by the tissue was evaluated after 14 days of culture. Results: The UV treatment of abutment materials resulted in the formation of more non-pocket-tissue types among the PTx group (p = 0.002). Of all materials tested, soft tissue contour around YSZ showed higher scores for the non-pocket type in both non- and UV-treated groups. Conclusions: The non-pocket type of tissue attachment was frequently found in all surfaces modified by photofunctionalization, particularly zirconia. The 3D-OMM can be used to evaluate the biological endpoints of implant surface modifications.

Copyright of Dokuz Eylul University Muhendislik Faculty of Engineering Journal of Science & Engineering / Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi is the property of Dokuz Eylul Universitesi Muhendislik Fakultesi Fen ve Muhendislik Dergisi and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

We report on a methodological framework that analyzes land-use images with engineered (manually designed) features. As older feature engineering methods suffered from excessive computation of their features, we therefore, introduce techniques that are faster and also more elaborate than any previous approach. Feature extraction and description is based on contour and region information. The contour analysis comprises the detection of ridge, river, and edge contours and is based on a technique of minimal complexity (without requiring costly multiplicative operations). The traced contour segments are then partitioned and abstracted; then they are clustered to form group descriptors. The region analysis consists of the detection of brighter, darker, and flatter regions, as well as regions obtained from clustering; the clustering is carried out with minimal complexity using a hierarchical analysis. Region segments are partitioned and abstracted using a fast implementation of the symmetric-axis transform. A total of ca. 70 parameters is developed and land-use classification experiments are performed. On the UC Merced (UCMD) collection, the classification accuracy of Deep Nets is reached; on the NWPU-RESISC45 collection the accuracy still lags somewhat. [ABSTRACT FROM AUTHOR]