Most human deaths are caused by heart diseases. Such diseases cannot be efficiently detected for the lack of specialized knowledge and experience. Data science is important in healthcare sector for the role it plays in bulk data processing. Machine learning (ML) also plays a significant part in disease prediction and decision-making in medical care industry. This study reviews and evaluates the ML approaches applied in heart disease detection. The primary goal is to find mathematically effective ML algorithm to predict heart diseases more accurately. Various ML approaches including Logistic Regression, Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), t-Distributed Stochastic Neighbor Embedding (t-SNE), Nave Bayes, and Random Forest were utilized to process heart disease dataset and extract the unknown patterns of heart disease detection. An analysis was conducted on their performance to examine the effecacy and efficiency. The results show that Random Forest out-performed other ML algorithms with an accuracy of 97%. 相似文献
One of the ongoing issues with time fractional diffusion models is the design of efficient high-order numerical schemes for the solutions of limited regularity. We construct in this paper two efficient Galerkin spectral algorithms for solving multi-dimensional time fractional advection–diffusion–reaction equations with constant and variable coefficients. The model solution is discretized in time with a spectral expansion of fractional-order Jacobi orthogonal functions. For the space discretization, the proposed schemes accommodate high-order Jacobi Galerkin spectral discretization. The numerical schemes do not require imposition of artificial smoothness assumptions in time direction as is required for most methods based on polynomial interpolation. We illustrate the flexibility of the algorithms by comparing the standard Jacobi and the fractional Jacobi spectral methods for three numerical examples. The numerical results indicate that the global character of the fractional Jacobi functions makes them well-suited to time fractional diffusion equations because they naturally take the irregular behavior of the solution into account and thus preserve the singularity of the solution.
Regiocontrolled deprotonation (e.g. lithiation) of 3-methyl-4-H-5,6-dihydro-1,2-oxazine 1 is achieved at −65°C. The lithiated compound reacts cleanly with the halogens Cl2, Br2 and I2 at low temperatures (−65°C) to give the corresponding 4-halo derivatives. Reaction of the 4-iodo compound 2a with KF in diethyleneglycol gives the elimination product 4 whereas the bromo compound 2b reacts under substitution to the 4-fluoro derivatives 5. The fluorooxazine derivatives 8a-c were converted to the αfluoroenones 11 a-c via the oxoiminium salts 10a-c. The U.V. and 1HNMR of the novel series of halides 2a-c and 5 were studied. 相似文献
Super-thermites can offer large amount of energy up to 16736 J/g. Flares based on super-thermites can offer superior thermal signature to countermeasure infrared (IR) guided missile seekers. This study reports on the sustainable fabrication of mono-dispersed Fe2O3 nanoparticles of 3 nm average particle size. Colloidal Fe2O3 nanoparticles were harvested from their synthesis medium and re-dispersed in acetone. Fluorocarbon polymers (teflon and viton) as well as aluminum metal fuel were integrated into Fe2O3/acetone colloid. The colloid mixture was granulated and mold pressed to develop the desired grain. The impact of Fe2O3 nanoparticles on thermal signature was assessed using (FT-MIR 1–6 µm) spectrometer. Flame propagation was investigated by video imaging of combustion wave. Combustion zones were quantified using image analysis. Quantification of flame temperature and main IR emitting species was performed using ICT thermodynamic code (virgin 2008). Nanocomposite flare with 12 wt% Fe2O3 offered an increase in the intensity of β band by 230% to that of reference formulation. The primary reaction zone was extended by 164%. Super-thermite particles not only offered superior spectral performance but also altered the combustion mechanism. 相似文献
Quadrotor helicopter is an unstable system subject to matched and mismatched disturbances. To stabilize the quadrotor dynamics in the presence of these disturbances, the application of a composite hierarchical anti-disturbance controller, combining a sliding mode controller and a disturbance observer, is presented in this paper. The disturbance observer is used to attenuate the effect of constant and slow time-varying disturbances. Whereas, the sliding mode controller is used to attenuate the effect of fast time-varying disturbances. In addition, sliding mode control attenuates the effect of the disturbance observer estimation errors of the constant and slow time-varying disturbances. In this approach, the upper bounds of the disturbance observer estimation errors are required instead of the disturbances’ upper bounds. The disturbance observer estimation errors are found to be bounded when the disturbance observer dynamics are asymptotically stable and the disturbance derivatives and initial disturbances are bounded. Moreover, due to the highly nonlinear nature of the quadrotor dynamics, the upper bounds of a part of the quadrotor states and disturbance estimates are required. The nonlinear terms in the rotational dynamics are considered as disturbances, part of which is mismatched. This assumption simplifies the control system design by dividing the quadrotor’s model into a position subsystem and a heading subsystem, and designing a controller for each separately. The stability analysis of the closed loop system is carried out using Lyapunov stability arguments. The effectiveness of the developed control scheme is demonstrated in simulations by applying different sources of disturbances such as wind gusts and partial actuator failure. 相似文献
Electrohydraulic calibration (EHC) of springback is a novel method of removing springback from stamped sheet metal panels and is based upon the electro-hydraulic effect: a complex phenomenon related to the discharge of high voltage electrical current through a liquid. The EHC process involves clamping a stamped panel against a female die with the desired part shape and then applying several pulses of pressure onto and through the thickness of the sheet, in a process somewhat similar to conventional coining operations. However, in EHC the pressure is applied by a fluid and through the use of the electrohydraulic effect, and not with a matching hard tool as done in coining. In EHC, electrical energy is stored in a bank of capacitors and is converted into kinetic energy within the liquid by rapidly discharging the stored energy across a pair of electrodes submerged in a fluid. The objective of this paper is to describe the newly developed EHC process, to report the results of early proof-of-concept experiments, to present the results of more advanced experiments using a more industrial tool and actual part geometry, and to describe how numerical modeling techniques were used to optimize the design of the larger and more industrial tool. The developed concept of electrohydraulic stress relieving calibration is based upon clamping a stamped panel to the calibration die surface with the target shape and then applying pulses of pressure to eliminate internal stresses in the stamped panel. When a stamped blank is removed from a forming die, allowed to springback, and then clamped to a calibration die, the internal elastic stresses within the panel in such a configuration serve as a memory of the shape of the blank after springback, and it is these residual stresses that EH calibration is intended to remove from the panel. The developed concept of stress relieving calibration was initially validated by a simple experiment consisting of submerging a bent strip of aluminum into the fluid within an EH chamber, so that both the outer and inner surfaces of the strip (where the internal stresses from bending are located) were exposed to the fluid and the pressure pulse. This experiment served as an initial confirmation that impact with the tool is not necessary to achieve the calibration effect. The sheet metal materials used in this study, and for which springback was eliminated after forming, include DP 980 at 1.0 mm and 1.4 mm thick, and also DP600 at 1.0 mm thick. 相似文献