Machine learning based decision support systems (DSS) for heart disease diagnosis: a review

The current review contributes with an extensive overview of decision support systems in diagnosing heart diseases in clinical settings. The investigators independently screened and abstracted studies related to heart diseases-based clinical decision support system (DSS) published until 8-June-2015 in PubMed, CINAHL and Cochrane Library. The data extracted from the twenty full-text articles that met the inclusion criteria was classified under the following fields; heart diseases, methods for data sets formation, machine learning algorithms, machine learning-based DSS, comparator types, outcome evaluation and clinical implications of the reported DSS. Out of total of 331 studies 20 met the inclusion criteria. Most of the studies relate to ischemic heart diseases with neural network being the most common machine learning (ML) technique. Among the ML techniques, ANN classifies myocardial infarction with 97% and myocardial perfusion scintigraphy with 87.5% accuracy, CART classifies heart failure with 87.6%, neural network ensembles classifies heart valve with 97.4%, support vector machine classifies arrhythmia screening with 95.6%, logistic regression classifies acute coronary syndrome with 72%, artificial immune recognition system classifies coronary artery disease with 92.5% and genetic algorithms and multi-criteria decision analysis classifies chest-pain patients with 91% accuracy respectively. There were 55% studies that validated the results in clinical settings while 25% validated the results through experimental setups. Rest of the studies (20%) did not report the applicability and feasibility of their methods in clinical settings. The study categorizes the ML techniques according to their performance in diagnosing various heart diseases. It categorizes, compares and evaluates the comparator based on physician’s performance, gold standards, other ML techniques, different models of same ML technique and studies with no comparison. It also investigates the current, future and no clinical implications. In addition, trends of machine learning techniques and algorithms used in the diagnosis of heart diseases along with the identification of research gaps are reported in this study. The reported results suggest reliable interpretations and detailed graphical self-explanatory representations by DSS. The study reveals the need for establishment of non-ambiguous real-time clinical data for proper training of DSS before it can be used in clinical settings. The future research directions of the ML-based DSS is mostly directed towards development of generalized systems that can decide on clinical measurements which are easily accessible and assessable in real-time.     

Simulation,modeling and analysis of master node election algorithm based on signal strength for VANETs through Colored Petri nets

The broadcast storm problem causes redundancy, contention and collision of messages in a network, particularly in vehicular ad hoc networks (VANETs) where number of participants can grow arbitrarily. This paper presents a solution to this problem in which a node is designated as a master through an election process. Moreover, an algorithm is proposed for asynchronous VANETs to select a master node, where the participants (i.e., vehicles) can communicate with each other directly (single-hop). The proposed algorithm is extrema-finding in a way that a node having maximum signal strength is elected as a master node and each vehicle continues communication with the master until the master node keeps its signal strength at the highest level and remains operational too. This paper further presents the Petri net-based modeling of the proposed algorithm for evaluation which is going to be presented for the first time in leader election algorithm in VANETs. Verification of the proposed algorithm is carried out through state space analysis technique.

     

Dynamics of Newtonian fluid through curved domain by considering unsteady effects

Cross-diffusion gradients, such as the Soret and Dufour effects, play a big role in the formation of binary alloys, the movement of oil and groundwater contaminants, and the separation of gas mixtures. Other applications where cross-diffusion gradients are useful include: Temperature fluctuations cause matter diffusion, known as Soret effects. Concentration gradients drive heat diffusion, or the Dufour effect. This effect is named after its French discoverer. These findings could be applied to many engineering and industrial contexts and have many intriguing and potentially useful effects. Joule heating unites Soret and Dufour's work. The traditional nonlinear differential approach yields enough permutations. Convergent series can be used to solve temperature, velocity, and concentration problems. These changes can occur in temperature, velocity, or concentration. The drawings clarify all about the system's most important qualities and components. A comprehensive analysis of the Nusselt and Sherwood values is also done. After graphing the Nusselt and Sherwood values, they are analyzed. We are discussing computer science. This study found that Hartman number increases reduce one's perception of radial velocity. As Prandtl and Soret molecules increase, fluid temperature decreases. In this study, we employ numerical methods to solve the micropolar fluid flow problem on a stretched and curved disk. Our methods allow us to model fluid flow in three dimensions. We focus on micropolar fluid flow. Applying the necessary transformations to a set of partial differential equations simplifies it into a set of ordinary differential equations. The equations in both sets are transformed using similarities to convert one set of partial differential equations into another set of ordinary differential equations. The gunshot method and the Runge–Kutta algorithm can solve coupled equations numerically. The nondimensional radius of curvature can quantify and characterize many physical phenomena. Strain, microrotation velocity, and fluid velocity are examples. Due to the variances between curved and flat stretched sheets, the border layer strain cannot be neglected. Due to differences in stretching sheets,     

Polarity-Based Solvents Extraction of Opuntia dillenii and Zingiber officinale for In Vitro Antimicrobial Activities

Extracts from dried stem of Opuntia dillenii and rhizome of Zingiber officinale were evaluated for antimicrobial activities by extraction in non-polar (petroleum ether and chloroform) and polar solvents (methanol and water). Bacillus subtilis and Staphylococcus aureus showed considerable susceptibility to all extracts of Opuntia dillenii and Zingiber officinale. Ether and chloroform extracts of Opuntia dillenii showed improved antimicrobial activity against Escherichia coli (gram negative) as compared to that of its methanolic and water extracts. On the other hand, methanolic and water extracts of Zingiber officinale showed better susceptibility for Escherichia coli. Salmonella typhi (gram negative) was found to be resistant to all extracts of both Opuntia dillenii and Zingiber officinale. Our results indicated that both Opuntia dillenii and Zingiber officinale have potent antimicrobial activity that is also based on solvent polarity during extraction.     

Characterization of multilayer graphene prepared from short-time processed graphite oxide flake

Multilayer graphene has been prepared by thermal reduction of graphene oxide film. The graphite oxide flake was first synthesized by using modified Hummers method with a relatively small amount of oxidizing agent and short-time processing at ambient temperature. The graphite oxide flake was dispersed in deionized water and deposited on quartz substrates to form graphene oxide film. The red shift of absorption peak and decrease of interlayer distance as interpreted from the X-ray diffraction spectrum indicate the formation of multilayer graphene. The resultant multilayer graphene has been successfully used as counter electrode in FTO/ZnO nanorods/electrolyte/multilayer graphene dye sensitized solar cell.     

Differential topology of adiabatically controlled quantum processes

It is shown that in a controlled adiabatic homotopy between two Hamiltonians, H ₀ and H ₁, the gap or “anti-crossing” phenomenon can be viewed as the development of cusps and swallow tails in the region of the complex plane where two critical value curves of the quadratic map associated with the numerical range of H ₀ + i H ₁ come close. The “near crossing” in the energy level plots happens to be a generic situation, in the sense that a crossing is a manifestation of the quadratic numerical range map being unstable in the sense of differential topology. The stable singularities that can develop are identified and it is shown that they could occur near the gap, making those singularities of paramount importance. Various applications, including the quantum random walk, are provided to illustrate this theory.     

Temperature dependence of electronic parameters of organic Schottky diode based on fluorescein sodium salt

The electrical properties of an organic Schottky diode based on fluorescein sodium salt were investigated by current density–voltage and capacitance–voltage measurements. The crystal structure of fluorescein sodium salt, FSS in powder form was analyzed by X-ray diffraction method. X-ray diffraction results showed that the fluorescein sodium salt has a polycrystalline structure with a monoclinic system. The current density–voltage and capacitance–voltage characteristics of Al/FSS Schottky diode were investigated in the temperature range of 300–400 K. The diode exhibits a rectifying behavior, indicating the formation of the Schottky type junction at the interface of Al/FSS. The predominant charge transport mechanism of the Al/FSS Schottky diode was discussed and the proposed current injection processes was presented. The temperature dependence of the calculated acceptor concentration, the built-in potential and the width of the depletion region of Al/FSS Schottky barrier was also determined.     

Threshold voltage control of 2,3 benzanthracene organic thin-film transistor by visible light for integration of transistors into electronic circuits

The organic field-effect transistor having 2,3 benzanthracene as active layer grown on SiO₂ dielectric layer was fabricated. AFM results indicate that 2,3 benzanthracene thin film is formed from homogeneous small crystal grains with an average diameter about 200 nm. The electrical parameters such as mobility, threshold voltage, I_on/I_off ratio and SS value were determined. The obtained I_on/I_off and S values increase with visible light illumination due to more photogenerated charges. The mobility and threshold values were changed by visible light illumination. The organic thin film transistor exhibits a photovoltaic effect in turn-on state. The control of the threshold voltage of 2,3 benzanthracene-based organic thin film transistor was achieved by visible light illumination. The change in the threshold voltage is enough for the electronic technology applications of organic thin film transistors.     

V2O4-PEPC composite based pressure sensor

In this study, V₂O₄-PEPC based pressure sensor was designed and fabricated by drop-casting the blend of V₂O₄-PEPC microcomposite thin films of vanadium oxide (V₂O₄) micropowder (10 wt.%) and poly-N-epoxypropylcarbazole, PEPC (2 wt.%) in benzol (1 ml) on steel substrates. The thickness of the V₂O₄-PEPC films was in the range of 20-40 μm. The DC resistance of the sensor was decreased in average by 24 times as the pressure was increased up to 11.7 kNm⁻². The resistance-pressure relationships were simulated.     

Magnetic dipole effects on non-Newtonian ferrofluid over a stretching sheet

In this study, we analyzed the characteristics of heat transfer in non-Newtonian ferrofluids produced by stretchable sheet. Further, we investigated in this study the effects of Arrhenius activation energy and magnetic dipole. We use in this study, a similarity ansatz to simplify the governing system into a nonlinear coupled ordinary differential equations system. We determined the computational solution of the resulting ordinary differential system by applying method with Runge–Kutta method. The influence of beneficial physical parameters on momentum, energy, and concentration profile are shown through graphs. The major finding of this study, the variation of velocity field is reduces for the higher values of $M$, $\beta$, and $H$. The temperature field increases for higher values of $R$, and reduce for $Pr$. Further, we conclude in this study the arising or reducing in the concentration, temperature, and velocity field for various physical parameters. The impacts of physical quantities namely skin fraction, Nusselt, and Sherwood numbers are examined through numerically via tables.