Automated skin lesion diagnosis from dermoscopic images is a difficult process due to several notable problems such as artefacts (hairs), irregularity, lesion shape, and irrelevant features extraction. These problems make the segmentation and classification process difficult. In this research, we proposed an optimized colour feature (OCF) of lesion segmentation and deep convolutional neural network (DCNN)‐based skin lesion classification. A hybrid technique is proposed to remove the artefacts and improve the lesion contrast. Then, colour segmentation technique is presented known as OCFs. The OCF approach is further improved by an existing saliency approach, which is fused by a novel pixel‐based method. A DCNN‐9 model is implemented to extract deep features and fused with OCFs by a novel parallel fusion approach. After this, a normal distribution‐based high‐ranking feature selection technique is utilized to select the most robust features for classification. The suggested method is evaluated on ISBI series (2016, 2017, and 2018) datasets. The experiments are performed in two steps and achieved average segmentation accuracy of more than 90% on selected datasets. Moreover, the achieve classification accuracy of 92.1%, 96.5%, and 85.1%, respectively, on all three datasets shows that the presented method has remarkable performance.

Purpose This paper aims to present a framework to detect phishing websites using stacking model. Phishing is a type of fraud to access users’ credentials. The attackers access users’ personal and sensitive information for monetary purposes. Phishing affects diverse fields, such as e-commerce, online business, banking and digital marketing, and is ordinarily carried out by sending spam emails and developing identical websites resembling the original websites. As people surf the targeted website, the phishers hijack their personal information. Design/methodology/approach Features of phishing data set are analysed by using feature selection techniques including information gain, gain ratio, Relief-F and recursive feature elimination (RFE) for feature selection. Two features are proposed combining the strongest and weakest attributes. Principal component analysis with diverse machine learning algorithms including (random forest [RF], neural network [NN], bagging, support vector machine, Naïve Bayes and k-nearest neighbour) is applied on proposed and remaining features. Afterwards, two stacking models: Stacking1 (RF + NN + Bagging) and Stacking2 (kNN + RF + Bagging) are applied by combining highest scoring classifiers to improve the classification accuracy. Findings The proposed features played an important role in improving the accuracy of all the classifiers. The results show that RFE plays an important role to remove the least important feature from the data set. Furthermore, Stacking1 (RF + NN + Bagging) outperformed all other classifiers in terms of classification accuracy to detect phishing website with 97.4% accuracy. Originality/value This research is novel in this regard that no previous research focusses on using feed forward NN and ensemble learners for detecting phishing websites.

Fault analysis in photovoltaic (PV) arrays is considered important for improving the safety and efficiency of a PV system. Faults do not only reduce efficiency but are also detrimental to the life span of a system. Output can be greatly affected by PV technology, configuration, and other operating conditions. Thus, it is important to consider the impact of different PV configurations and materials for thorough analysis of faults. This paper presents a detailed investigation of faults including non-uniform shading, open circuit and short circuit in different PV interconnections including Series-Parallel (SP), Honey-Comb (HC) and Total-cross-Tied (TCT). A special case of multiple faults in PV array under non-uniform irradiance is also investigated to analyze their combined impact on considered different PV interconnections. In order to be more comprehensive, we have considered monocrystalline and thin-film PV to analyze faults and their impact on power grids. Simulations are conducted in MATLAB/Simulink, and the obtained results in terms of power(P)-voltage(V) curve are compared and discussed. It is found that utilization of thin-film PV technology with appropriated PV interconnections can minimize the impact of faults on a power grid with improved performance of the system.Energies 2020, 13, 156 2 of 23 ground faults which led towards a large fire accident [6]. Another similar accident happened due to undetected faults in a 1 MW PV system of Mount Halley, North Carolina in 2011 [7]. Thus, timely diagnosis of faults in PV systems is very important for the prevention of such large fire accidents [8]. The modeling of a PV system under electrical faults [9] has been studied in the literature [10]. A review of faults in PV systems is presented in [11]. Power generation is also dependent upon the type of PV material [12]. The impact of shading on different PV technologies [13] has been largely investigated in the past [14][15][16][17][18]. The performance of crystalline PV material can be affected greatly by environmental conditions [14]. P-V curve analysis for studying the impact of shading on polycrystalline and thin-film PV modules was performed in [15]. Thin-film PV performed better as compared to polycrystalline PV under severe shading in terms of power output. The experimental analysis of PV material in Anatolia also proved that thin-film technology has less impact on shading and high temperature as compared to crystalline PV material [16]. Only shading and temperature conditions are analyzed for thin-film PV technology [17]. Further research is needed to investigate the impact of short circuit and open circuit faults on thin-film PV technology.Different methods of maximum power point tracking (MPPT) [18] have been investigated but improvements in the algorithm cannot compensate for significant power losses that occurr through fault occurrence in PV arrays. A reconfiguration technique was adopted in [19] to increase power generation but this technique requires a complex switching matrix with many sensors and prope...

No abstract

No abstract