In modern-day medicine, medical imaging has undergone immense advancements and can capture several biomedical images from patients. In the wake of this, to assist medical specialists, these images can be used and trained in an intelligent system in order to aid the determination of the different diseases that can be identified from analyzing these images. Classification plays an important role in this regard; it enhances the grouping of these images into categories of diseases and optimizes the next step of a computer-aided diagnosis system. The concept of classification in machine learning deals with the problem of identifying to which set of categories a new population belongs. When category membership is known, the classification is done on the basis of a training set of data containing observations. The goal of this paper is to perform a survey of classification algorithms for biomedical images. The paper then describes how these algorithms can be applied to a big data architecture by using the Spark framework. This paper further proposes the classification workflow based on the observed optimal algorithms, Support Vector Machine and Deep Learning as drawn from the literature. The algorithm for the feature extraction step during the classification process is presented and can be customized in all other steps of the proposed classification workflow.

No abstract

Background and Objective. To mitigate the spread of the virus responsible for COVID-19, known as SARS-CoV-2, there is an urgent need for massive population testing. Due to the constant shortage of PCR (polymerase chain reaction) test reagents, which are the tests for COVID-19 by excellence, several medical centers have opted for immunological tests to look for the presence of antibodies produced against this virus. However, these tests have a high rate of false positives (positive but actually negative test results) and false negatives (negative but actually positive test results) and are therefore not always reliable. In this paper, we proposed a solution based on Data Analysis and Machine Learning to detect COVID-19 infections. Methods. Our analysis and machine learning algorithm is based on most cited two clinical datasets from the literature: one from San Raffaele Hospital Milan Italia and the other from Hospital Israelita Albert Einstein São Paulo Brasilia. The datasets were processed to select the best features that most influence the target, and it turned out that almost all of them are blood parameters. EDA (Exploratory Data Analysis) methods were applied to the datasets, and a comparative study of supervised machine learning models was done, after which the support vector machine (SVM) was selected as the one with the best performance. Results. SVM being the best performant is used as our proposed supervised machine learning algorithm. An accuracy of 99.29%, sensitivity of 92.79%, and specificity of 100% were obtained with the dataset from Kaggle (https://www.kaggle.com/einsteindata4u/covid19) after applying optimization to SVM. The same procedure and work were performed with the dataset taken from San Raffaele Hospital (https://zenodo.org/record/3886927#.YIluB5AzbMV). Once more, the SVM presented the best performance among other machine learning algorithms, and 92.86%, 93.55%, and 90.91% for accuracy, sensitivity, and specificity, respectively, were obtained. Conclusion. The obtained results, when compared with others from the literature based on these same datasets, are superior, leading us to conclude that our proposed solution is reliable for the COVID-19 diagnosis.

In this contribution, the nonlinear dynamics of a non-autonomous model of two neurons based on the Hopfield neural network is considered. Using activation gradients as bifurcation control parameters, the properties of the model include dissipation with the existence of attractors and equilibrium points with their stability. Using traditional nonlinear analysis tools such as bifurcation diagrams, the graph of the maximum Lyapunov exponent, phase portraits, two-parameter diagrams, and attraction basins, the complex behaviour of the two-dimensional Hopfield neural network has been investigated and several windows of multistability involving the coexistence of up to four coexisting attractors have been found. Besides, the results of our numerical simulation of the multistability have been further supported using some Pspice simulation. The effect of the fractional-order derivative is also explored, and it is found that the route toward chaos is completely different when the order q of the HNN is varied between $$0<q<1$$ 0 < q < 1 . Finally, a compressive sensing approach is used to compress and encrypt color images based on the sequences of the above-mentioned system. The plain color image is decomposed into Red, Green, and Blue components. The Discrete Wavelet Transform (DWT) is applied to each component to obtain the corresponding sparse components. Confusion keys are obtained from the proposed chaotic system to scramble each sparse component. The measurement matrices obtained from the chaotic sequence are used to compress the confused sparse matrices corresponding to the Red, Green, and Blue components. Each component is quantified and a diffusion step is then applied to improve the randomness and, consequently, the information entropy. Experimental analysis of the proposed method yields a running time (t) of 6.85 ms, a maximum entropy value of 7.9996 for global and 7.9153 for local, an encryption throughput (ET) value of 114.80, and a number of cycles (NC) of 20.90. Analysis of these metrics indicates that the proposed scheme is competitive with some recent literature.

Although the control of multistability has already been reported, the one with preselection of the desired attractor is still uncovered in systems with more than two coexisting attractors. This work reports the control of coexisting attractors with preselection of the survived attractors in paradigmatic Chua’s system with smooth cubic nonlinearity. Techniques of linear augmentation combined to system invariant parameters like equilibrium points are used to choose the desired surviving attractors among the coexisting ones. Nonlinear dynamical tools including bifurcation diagrams, standard Lyapunov exponents, phase portraits, and cross section of initial conditions are exploited to reveal the selection scenarios of the survived attractor in the multistability control process of Chua’s system. The main crisis towards annihilation of multistability in Chua’s system when varying the coupling strength is interior crisis and border collision. Theoretical and numerical results obtained are further validated with PSpice analysis.