Prediction of cardiovascular disease (CVD) is a critical challenge in the area of clinical data analysis. In this study, an efficient heart disease prediction is developed based on optimal feature selection. Initially, the data pre‐processing process is performed using data cleaning, data transformation, missing values imputation, and data normalisation. Then the decision function‐based chaotic salp swarm (DFCSS) algorithm is used to select the optimal features in the feature selection process. Then the chosen attributes are given to the improved Elman neural network (IENN) for data classification. Here, the sailfish optimisation (SFO) algorithm is used to compute the optimal weight value of IENN. The combination of DFCSS–IENN‐based SFO (IESFO) algorithm effectively predicts heart disease. The proposed (DFCSS–IESFO) approach is implemented in the Python environment using two different datasets such as the University of California Irvine (UCI) Cleveland heart disease dataset and CVD dataset. The simulation results proved that the proposed scheme achieved a high‐classification accuracy of 98.7% for the CVD dataset and 98% for the UCI dataset compared to other classifiers, such as support vector machine, K‐nearest neighbour, Elman neural network, Gaussian Naive Bayes, logistic regression, random forest, and decision tree.Inspec keywords: cardiovascular system, medical diagnostic computing, feature extraction, regression analysis, data mining, learning (artificial intelligence), Bayes methods, neural nets, support vector machines, diseases, pattern classification, data handling, decision trees, cardiology, data analysis, feature selectionOther keywords: efficient heart disease prediction‐based, optimal feature selection, improved Elman‐SFO, cardiovascular disease, clinical data analysis, data pre‐processing process, data cleaning, data transformation, values imputation, data normalisation, decision function‐based chaotic salp swarm algorithm, optimal features, feature selection process, improved Elman neural network, data classification, sailfish optimisation algorithm, optimal weight value, DFCSS–IENN‐based SFO algorithm, DFCSS–IESFO, California Irvine Cleveland heart disease dataset, CVD dataset, high‐classification accuracy相似文献
The present research is focused on the development of ecofriendly biopolymer blend based nanocomposites to enhance the effect of cytotoxic activity. Novel eco-friendly synthesis of pure Chitosan–Agar blend and Chitosan–Agar/ZnO nanocomposites was successfully synthesized by in-situ chemical synthesis method. The influence of Chitosan–Agar (1:1 wt/wt%) concentrations (0.1, 0.5, 1 and 3 g) was studied. The presence of ZnO nanoparticles in Chitosan–Agar polymer matrix was confirmed by UV, FTIR, XRD, FESEM, EDAX and TEM. The crystallite size of the nanocomposites in the range of 12–17 nm is observed from XRD analysis. PL and UV reveal that Nanocomposites shows an blue shift by increase in the blend concentrations. TEM analysis shows that 0.1 and 3 g of Chitosan–Agar/ZnO Nanocomposites are in spindle and spherical shape with polycrystalline nature. The prepared Nanocomposites shows the respectable Antibacterial activity against Gram-positive (Staphylococcus aureus and Bacillus subtilis) and Gram-negative (Pseudomonas aureginosa and Klebsilla pneumonia) bacteria. The potential toxicity of Chitosan–Agar/ZnO nanocomposites was studied for normal (L929) and breast cancer cell line (MB231). The result of this investigation shows that the Chitosan–Agar/ZnO nanocomposites deliver a dose dependent toxicity in normal and cancer cell line. 相似文献
Head and neck squamous cell carcinoma (HNSCC) tumor phenotypes and clinical outcomes are significantly influenced by etiological agents, such as HPV infection, smoking, and alcohol consumption. Accordingly, the intratumor microbiome has been increasingly implicated in cancer progression and metastasis. However, few studies characterize the intratumor microbial landscape of HNSCC with respect to these etiological agents. In this study, we aimed to investigate the bacterial and fungal landscape of HNSCC in association with HPV infection, smoking, and alcohol consumption. RNA-sequencing data were extracted from The Cancer Genome Atlas (TCGA) regarding 449 tissue samples and 44 normal samples. Pathoscope 2.0 was used to extract the microbial reads. Microbe abundance was compared to clinical variables, oncogenic signatures, and immune-associated pathways. Our results demonstrated that a similar number of dysregulated microbes was overabundant in smokers and nonsmokers, while heavy drinkers were characterized by an underabundance of dysregulated microbes. Conversely, the majority of dysregulated microbes were overabundant in HPV+ tumor samples when compared to HPV- tumor samples. Moreover, we observed that many dysregulated microbes were associated with oncogenic and metastatic pathways, suggesting their roles in influencing carcinogenesis. These microbes provide insights regarding potential mechanisms for tumor pathogenesis and progression with respect to the three etiological agents. 相似文献
Diesel Particulate Matter (DPM) is regulated in the U.S. for both underground coal and metal/nonmetal mines. Today, many underground
mines still face difficulty in compliance with DPM regulations. The DPM research carried out in Missouri University of Science
and Technology (MST) is to use computational fluid dynamics (CFD) to study the DPM distribution in commonly used face areas.
The result is expected to be used for selection of DPM reduction strategies and better working practices, which can help the
underground mines to meet regulation limits and improve the working environment for the miners. An experiment was conducted
at MST’s Experimental Mine to validate CFD simulation. DPM was collected at four locations downstream of a stationary diesel
engine. The experiment data were then compared with the CFD simulation results. The comparison shows that CFD simulation can
forecast the location of DPM concentration with practical accuracy (less than 0.15 m). CFD can be used to further study DPM
distribution in commonly used working faces and give guidance to DPM reduction. 相似文献
The Catteno–Christov heat flux plays a dynamic role in flow of heat enhancement in various manufacturing, industrial, and engineering applications. This present work focuses on the influence of Catteno–Christov heat flux model on Darcy–Forchheimer flow of a hybrid nanofluid placed in a porous medium. The formulation of the mathematical model is done by considering a fluid with two different nanoparticles Al2O3 and Cu dispersed in the water as the base fluid. The set of partial differntial equations is reduced by using similarity variables and boundary conditions to obtain ordinary differntial equations. The coupled nonlinear governing differential equations are solved using Runge–Kutta fourth–fifth order (RKF-45). The impact of numerous dimensionless parameters on the velocity, thermal, and concentration profiles are plotted and studied. Furthermore, the coefficient of skin friction for the relevant parameters are analysed through graphs. Result reveals that, increase in the porosity parameter declines the velocity gradient and shoots up the thermal and concentration gradients. Inclination in magnetic parameter declines velocity and concentration profiles due to the Lorentz force. Enhancement in the thermal relaxation parameter declines the thermal profile. Inclination in homogeneous-heterogeneous reaction parameters declines the mass transfer rate. Also, the well-known differential transform method is used for the validity of RKF-45 method and an impressive agreement is noticed between the results of RKF-45 and DTM. 相似文献
In flip-chip design, voltage drop reduction in the power ground network has become a challenging problem particularly in the modern Multiple Supply Voltage(MSV) designs. An effective P/G network design and floorplanning- based solutions helps to produce a quality power plan in the layout. Hence, this paper proposes an iterative MSV floorplanning methodology that performs modifications in the existing floorplan representation that satisfies the voltage island constraint and produce an IR drop-aware quality layout. Furthermore, the proposed methodology is integrated with commercial tool design flow to analyze the reduction of IR drop in the layout. Two simulation-based experiments are performed in this paper to showcase the significance of this work. Firstly, it presents the simulation results that benchmark the proposed idealogy in non-flip chip designs. Secondly, the presented framework is integrated in flip-chip layouts of FIR design operating with two voltage islands for low power consumption. To understand the ability of the proposed floorplanning approach, the simulation were performed for two different sized P/G mesh structure for various mesh width. Experimental results from both simulations demonstrate that the proposed MSV floorplanning technique is effective in reducing IR drop while optimizing the design for low power dissipation.
Four types of human sialidases have been cloned and characterized at the molecular level. They are classified according to their major intracellular location as intralysomal (NEU1), cytosolic (NEU2), plasma membrane (NEU3) and lysosomal or mitochondrial membrane (NEU4) associated sialidases. These human isoforms are distinct from each other in their enzymatic properties as well as their substrate specificity. Altered expression of sialidases has been correlated with malignant transformation of cells and different sialidases have been known to behave differently during carcinogenesis. Particularly, increased expression of NEU3 has been implicated in the survival of various cancer cells and also in the development of insulin resistance. In the present study, we have modeled three-dimensional structures of NEU1, NEU3 and NEU4 based on the crystal structure of NEU2 using the homology modeling program MODELER. The best model in each enzyme case was chosen on the basis of various standard protein analysis programs. Predicted structures and the experimental protein-ligand complex of NEU2 were compared to identify similarities and differences among the active sites. The molecular electrostatic potential (MEP) was calculated for the predicted models to identify the differences in charge distribution around the active site and its vicinity. The primary objective of the present work is to identify the structural differences between the different isoforms of human sialidases, namely NEU1, NEU2, NEU3 and NEU4, thus providing a better insight into the differences in the active sites of these enzymes. This can in turn guide us in the better understanding and rationale of the differential substrate recognition and activity, thereby aiding in the structure-based design of selective NEU3 inhibitors. 相似文献
Journal of Superconductivity and Novel Magnetism - A series of Ni0.5Zn0.5AlxFe2–xO4 (0.0 ≤ x ≤ 0.25) nanoferrites have been prepared by sol-gel auto combustion and followed by... 相似文献