Wireless sensor networks (WSNs) have aroused the conspectus attention of scholars due to their extensive deployment in the emerging fields of the Internet of Things (IoT's) and self-driven devices. But WSNs technologies having a major bottleneck has been associated with limited energy. Mostly research in WSNs has been focused on minimizing energy usage to extend the survival time of limited power source in a network. Energy harvesting can be addressing its energy-scarcity problem of WSNs, so it is giving popularity to Energy Harvesting in Wireless Sensor Networks (EH-WSNs). The paper presents a comprehensive taxonomic survey on recently energy harvesting techniques and algorithms that proposed by various authors and also examined the work done by the various researchers in the field of EH-WSNs. For the ready reference of the researchers, a concise summary and comparative analysis of various promising techniques for energy harvesting have also been included in the systematic survey. However, many equipment developed using the hybridization method in a singular package to get full advantages of available free energy, are explored in this review. The review on hybrid energy harvesting (HEH) systems can be considered as the originality of this article. However, the outdoor photovoltaics have been provided maximum power density about ≈100 mW/cm 3 , and the piezoelectric harvesters have been given maximum voltage about 325 V but the current in very minute amount. The thermoelectric, rectenna and hybrid energy harvesters (EHs) have been given high efficiency more than 80%. Additionally, hybrid EHs have location/timeindependent characteristics which harnessed power from more than one source that can be became more popular for upcoming leading technologies of self-driven or autonomous devices shifting from battery operated devices. Finally, the survey also identifies often challenges and various significant issues that still essential to be addressed to develop a cost effective, efficient, long-lasting, and almost maintenance-free energy harvesting systems for WSNs along with trail to their possible solutions for future perspectives.

No abstract

This paper introduces a comparative analysis of the proficiencies of various textures and geometric features in the diagnosis of breast masses on mammograms. An improved machine learning-based framework was developed for this study. The proposed system was tested using 106 full field digital mammography images from the INbreast dataset, containing a total of 115 breast mass lesions. The proficiencies of individual and various combinations of computed textures and geometric features were investigated by evaluating their contributions towards attaining higher classification accuracies. Four state-of-the-art filter-based feature selection algorithms (Relief-F, Pearson correlation coefficient, neighborhood component analysis, and term variance) were employed to select the top 20 most discriminative features. The Relief-F algorithm outperformed other feature selection algorithms in terms of classification results by reporting 85.2% accuracy, 82.0% sensitivity, and 88.0% specificity. A set of nine most discriminative features were then selected, out of the earlier mentioned 20 features obtained using Relief-F, as a result of further simulations. The classification performances of six state-of-the-art machine learning classifiers, namely k-nearest neighbor (k-NN), support vector machine, decision tree, Naive Bayes, random forest, and ensemble tree, were investigated, and the obtained results revealed that the best classification results (accuracy = 90.4%, sensitivity = 92.0%, specificity = 88.0%) were obtained for the k-NN classifier with the number of neighbors having k = 5 and squared inverse distance weight. The key findings include the identification of the nine most discriminative features, that is, FD26 (Fourier Descriptor), Euler number, solidity, mean, FD14, FD13, periodicity, skewness, and contrast out of a pool of 125 texture and geometric features. The proposed results revealed that the selected nine features can be used for the classification of breast masses in mammograms.

No abstract

No abstract