Electrical and Electronic Engineering - Research Publications
Permanent URI for this collection
Search Results
1 - 6 of 6
-
ItemNo Preview AvailableRobust Ensemble Machine Learning Model for Filtering Phishing URLs: Expandable Random Gradient Stacked Voting Classifier (ERG-SVC)(IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 2021)
-
ItemNo Preview AvailableBlockchain and Cryptocurrencies(IGI Global, 2021)In financial trading, cryptocurrencies like bitcoin use decentralization, traceability, and anonymity features to perform transactional activities. These digital currencies, using the emerging blockchain technologies, are forming the basis of the largest unregulated markets in the world. This creates various regulatory challenges, including the illicit purchase of drugs and weapons, money laundering, and funding terrorist activities. This chapter analyzes various legal and ethical implications, their effects, and various solutions to overcome the inherent issues that are currently faced by the policymakers and regulators. The authors present the result of an analysis of 30 recently published peer-reviewed scientific publications and suggest various mechanisms that can help in the detection and prevention of illegal activities that currently account for a substantial proportion of cryptocurrency trading. They suggest methods and applications that can also be used to identify the dark marketplaces in the future.
-
ItemNo Preview AvailableOptimizing Heating Efficiency of Hyperthermia: Specific Loss Power of Magnetic Sphere Composed of Superparamagnetic Nanoparticles(EMW Publishing, 2020-03-09)Magnetic nanoparticle (MNP) based thermal therapies have shown importance in clinical applications. However, it lacks a compromise between its robustness and limitations. We developed theoretical strategies to enhance the heating efficiency, which could be utilized in thermal therapies and calculated parameter dependence for superparamagnetic MNPs (approximative ellipsoid-shaped) within a sphere-shaped ball. Then we calculated specific loss power (SLP) for magnetic particles in a magnetic ball. The dependency of features of the nanoparticles (such as mean particle size, a number of particles, frequency and amplitude of the exposed field, relaxation time, and volume gap between particles and a sphere-shaped ball) on the SLP or the heating effect in superparamagnetic MNPs was analyzed. In this study, optimal parameter values were calculated using Kneedle Algorithm as the optimization technique to represent the accurate heating efficiency. The influence of a number of particles in a sphere-shaped ball shows that SLP of magnetic particles increases with the increasing number of particles (N); however, after N = 10 particles, the SLP increment is insignificant. The most remarkable result arising from this analysis is that when particles are closer together (less volume gap of a sphere-shaped ball), high SLP is found for the same number of particles. This model also predicts that the frequency dependency on the SLP is negligible when the frequency is higher than 10 kHz depending on the size of a sphere-shaped ball and nanoparticle parameters. This analysis has shown that the SLP of MNPs, in a sphere-shaped ball, strongly depends on magnetic parameters and properties of the particles. In brief, we have demonstrated, for the first time, impact on SLP of the accumulation of ellipsoid-shaped superparamagnetic nanoparticles into a sphere-shaped ball. This finding has essential suggestions for developing links between heating properties with loose aggregate and dense aggregate scenarios in the superparamagnetic condition.
-
ItemSupervised Machine Learning Algorithms for Bioelectromagnetics: Prediction Models and Feature Selection Techniques Using Data from Weak Radiofrequency Radiation Effect on Human and Animals Cells(MDPI AG, 2020-06-26)The emergence of new technologies to incorporate and analyze data with high-performance computing has expanded our capability to accurately predict any incident. Supervised Machine learning (ML) can be utilized for a fast and consistent prediction, and to obtain the underlying pattern of the data better. We develop a prediction strategy, for the first time, using supervised ML to observe the possible impact of weak radiofrequency electromagnetic field (RF-EMF) on human and animal cells without performing in-vitro laboratory experiments. We extracted laboratory experimental data from 300 peer-reviewed scientific publications (1990–2015) describing 1127 experimental case studies of human and animal cells response to RF-EMF. We used domain knowledge, Principal Component Analysis (PCA), and the Chi-squared feature selection techniques to select six optimal features for computation and cost-efficiency. We then develop grouping or clustering strategies to allocate these selected features into five different laboratory experiment scenarios. The dataset has been tested with ten different classifiers, and the outputs are estimated using the k-fold cross-validation method. The assessment of a classifier’s prediction performance is critical for assessing its suitability. Hence, a detailed comparison of the percentage of the model accuracy (PCC), Root Mean Squared Error (RMSE), precision, sensitivity (recall), 1 − specificity, Area under the ROC Curve (AUC), and precision-recall (PRC Area) for each classification method were observed. Our findings suggest that the Random Forest algorithm exceeds in all groups in terms of all performance measures and shows AUC = 0.903 where k-fold = 60. A robust correlation was observed in the specific absorption rate (SAR) with frequency and cumulative effect or exposure time with SAR×time (impact of accumulated SAR within the exposure time) of RF-EMF. In contrast, the relationship between frequency and exposure time was not significant. In future, with more experimental data, the sample size can be increased, leading to more accurate work.
-
ItemReal-Time Cryptocurrency Price Prediction by Exploiting IoT Concept and Beyond: Cloud Computing, Data Parallelism and Deep Learning(The Science and Information (SAI) Organization, 2020-03-01)Cryptocurrency has as of late pulled in extensive consideration in the fields of economics, cryptography, and computer science due to it is an encrypted digital currency, peer- to- peer virtual forex produced using codes, and it is much the same as another medium of the trade like real cash. This study mainly focuses to combine the Deep Learning with Data parallelism and Cloud Computing Machine learning engine as “hybrid architecture” to predict new Cryptocurrency prices by using historical Cryptocurrency data. The study has exploited 266,776 of Cryptocurrency prices values from the pilot experiment, and Deep Learning algorithm used for the price prediction. The four hybrid architecture models, namely, (i) standalone PC, (ii) Cloud computing without data parallelism (GPU-1), (iii) Cloud computing with data parallelism (GPU-4), and (iv) Cloud computing with data parallelism (GPU-8) introduced and utilized for the analysis. The performance of each model is evaluated using different performance evaluation parameters. Then, the efficiency of each model was compared using different batch sizes. An experimental result reveals that Cloud computing technology exposes new era by performing parallel computing in IoT to reduce computation time up to 90% of the Deep Learning algorithm-based Cryptocurrencies price prediction model and many other IoT applications such as character recognition, biomedical field, industrial automation, and natural disaster prediction.
-
ItemA meta-analysis of in vitro exposures to weak radiofrequency radiation exposure from mobile phones (1990–2015)(Elsevier BV, 2020-05-01)To function, mobile phone systems require transmitters that emit and receive radiofrequency signals over an extended geographical area exposing humans in all stages of development ranging from in-utero, early childhood, adolescents and adults. This study evaluates the question of the impact of radiofrequency radiation on living organisms in vitro studies. In this study, we abstract data from 300 peer-reviewed scientific publications (1990–2015) describing 1127 experimental observations in cell-based in vitro models. Our first analysis of these data found that out of 746 human cell experiments, 45.3% indicated cell changes, whereas 54.7% indicated no changes (p = 0.001). Realizing that there are profound distinctions between cell types in terms of age, rate of proliferation and apoptosis, and other characteristics and that RF signals can be characterized in terms of polarity, information content, frequency, Specific Absorption Rate (SAR) and power, we further refined our analysis to determine if there were so e distinct properties of negative and positive findings associated with these specific characteristics. We further analyzed the data taking into account the cumulative effect (SAR × exposure time) to acquire the cumulative energy absorption of experiments due to radiofrequency exposure, which we believe, has not been fully considered previously. When the frequency of signals, length and type of exposure, and maturity, rate of growth (doubling time), apoptosis and other properties of individual cell types are considered, our results identify a number of potential non-thermal effects of radiofrequency fields that are restricted to a subset of specific faster-growing less differentiated cell types such as human spermatozoa (based on 19 reported experiments, p-value = 0.002) and human epithelial cells (based on 89 reported experiments, p-value < 0.0001). In contrast, for mature, differentiated adult cells of Glia (p = 0.001) and Glioblastoma (p < 0.0001) and adult human blood lymphocytes (p < 0.0001) there are no statistically significant differences for these more slowly reproducing cell lines. Thus, we show that RF induces significant changes in human cells (45.3%), and in faster-growing rat/mouse cell dataset (47.3%). In parallel with this finding, further analysis of faster-growing cells from other species (chicken, rabbit, pig, frog, snail) indicates that most undergo significant changes (74.4%) when exposed to RF. This study confirms observations from the REFLEX project, Belyaev and others that cellular response varies with signal properties. We concur that differentiation of cell type thus constitutes a critical piece of information and should be useful as a reference for many researchers planning additional studies. Sponsorship bias is also a factor that we did not take into account in this analysis.