Search

Scanning electron microscopy (SEM) is a reference approach for determining the dimensional properties of the nanocomposites or black particles (BPs). Numerous approaches can be available for extracting BPs from SEM images and evaluating their diameters. However, the existing models are subjective as well as very time-consuming. Moreover, they need help to collect the complete quantitative information of interest. For that reason, in this study, an automated SEM analysis with the help of image orientation detection is proposed using the adaptive density-based spatial clustering of application with noise (ADBSCAN) clustering algorithm. The detection of image orientation using the proposed approach helps to find out the material strength of BPs. Here, the images of eggshell powder with 20 µm having different weights, such as 1%, 2%, 3%, 4% and 5%, are taken as input. Later, pre-processing is carried out in which noise removal using Cosine Distance induced Bilateral Filter is performed. Then, the image's contrast is enhanced through the Gaussian distribution adapted contrast limited adaptive histogram equalization technique. Next, the canny edge detector is used, followed by segmentation with Threshold-based Otsu. Finally, clustering takes place via ADBSCAN model. After that, quantitative analysis is done using Gaussian, scatterplot and histogram for all weight percentages. The outcome revealed that the proposed work computes the orientation more accurately, and effectively estimates the material strength of the eggshell powder. [ABSTRACT FROM AUTHOR]

The wireless mesh network (WMN) is a challenging technology that offers high quality services to the end users. With growing demand for real-time services in the wireless networks, quality-of-service-based routing offers vital challenges in WMNs. In this paper, a discrete multi-objective differential evolution (DMODE) approach for finding optimal route from a given source to a destination with multiple and competing objectives is proposed. The objective functions are maximization of packet delivery ratio and minimization of delay. For maintaining good diversity, the concepts of weight mapping crossover (WMX)-based recombination and dynamic crowding distances are implemented in the DMODE algorithm. The simulation is carried out in NS-2 and it is observed that DMODE substantially improves the packet delivery ratio and significantly minimizes the delay for various scenarios. The performance of DMODE, DEPT and NSGA-II is compared with respect to multi-objective performance measures namely as 'spread'. The results demonstrate that DMODE generates true and well-distributed Pareto-optimal solutions for the multi-objective routing problem in a single run. [ABSTRACT FROM AUTHOR]

Road traffic accidents are a major social concern as well as a crucial issue for the public in recent days due to the risk factors involved. Analysing and identifying the major risk factors of road accident is still a challenging task. In this paper, a fuzzy Context-free Grammar (FCFG)-based association rule mining (ARM) technique is proposed to categorize a heterogeneous road accident dataset into two categories based on the critical factors such as total number of accidents (TA), persons killed (PK) and persons injured (PI). The role of the fuzzy grammar in this paper is to govern the entire algorithm using the prescribed grammar rules to proceed further. The considered road accident dataset does not have class labels; hence there is a need to assign class labels for the available data instance. The accident data with assigned class labels are given as input to K-nearest neighbour (KNN) machine learning algorithm in order to train the classifier for testing purpose. Further, the collected test data from the user are utilized by the KNN classifier for carrying out the performance analysis of the proposed algorithm. The case study is conducted on the National Highway roads, India, to examine the proposed approach. The experimentations are executed for road accident records using MATLAB software and the analysis is made using the following performance measures: accuracy, recall or sensitivity, precision or specificity and F1 score. A comparative study is accomplished with existing algorithms in order to show that the proposed algorithm works with improved accuracy of more than 83%. The results suggested that the road users are responsible for the acceptance or rejection of safe or un-safe roads, respectively. [ABSTRACT FROM AUTHOR]