Heart disease (HD) is a serious widespread life-threatening disease. The heart of patients with HD fails to pump sufficient amounts of blood to the entire body. Diagnosing the occurrence of HD early and efficiently may prevent the manifestation of the debilitating effects of this disease and aid in its effective treatment. Classical methods for diagnosing HD are sometimes unreliable and insufficient in analyzing the related symptoms. As an alternative, noninvasive medical procedures based on machine learning (ML) methods provide reliable HD diagnosis and efficient prediction of HD conditions. However, the existing models of automated ML-based HD diagnostic methods cannot satisfy clinical evaluation criteria because of their inability to recognize anomalies in extracted symptoms represented as classification features from patients with HD. In this study, we propose an automated heart disease diagnosis (AHDD) system that integrates a binary convolutional neural network (CNN) with a new multi-agent feature wrapper (MAFW) model. The MAFW model consists of four software agents that operate a genetic algorithm (GA), a support vector machine (SVM), and Naïve Bayes (NB). The agents instruct the GA to perform a global search on HD features and adjust the weights of SVM and BN during initial classification. A final tuning to CNN is then performed to ensure that the best set of features are included in HD identification. The CNN consists of five layers that categorize patients as healthy or with HD according to the analysis of optimized HD features. We evaluate the classification performance of the proposed AHDD system via 12 common ML techniques and conventional CNN models by using a cross-validation technique and by assessing six evaluation criteria. The AHDD system achieves the highest accuracy of 90.1%, whereas the other ML and conventional CNN models attain only 72.3%–83.8% accuracy on average. Therefore, the AHDD system proposed herein has the highest capability to identify patients with HD. This system can be used by medical practitioners to diagnose HD efficiently. 相似文献
The development in Information and Communication Technology has led to the evolution of new computing and communication environment. Technological revolution with Internet of Things (IoTs) has developed various applications in almost all domains from health care, education to entertainment with sensors and smart devices. One of the subsets of IoT is Internet of Medical things (IoMT) which connects medical devices, hardware and software applications through internet. IoMT enables secure wireless communication over the Internet to allow efficient analysis of medical data. With these smart advancements and exploitation of smart IoT devices in health care technology there increases threat and malware attacks during transmission of highly confidential medical data. This work proposes a scheme by integrating machine learning approach and block chain technology to detect malware during data transmission in IoMT. The proposed Machine Learning based Block Chain Technology malware detection scheme (MLBCT-Mdetect) is implemented in three steps namely: feature extraction, Classification and blockchain. Feature extraction is performed by calculating the weight of each feature and reduces the features with less weight. Support Vector Machine classifier is employed in the second step to classify the malware and benign nodes. Furthermore, third step uses blockchain to store details of the selected features which eventually improves the detection of malware with significant improvement in speed and accuracy. ML-BCT-Mdetect achieves higher accuracy with low false positive rate and higher True positive rate. 相似文献
Clean Technologies and Environmental Policy - In this paper, an optimal sizing of a grid-connected PV system to accommodate the load demands of a public building (i.e., Faculty of Sciences and... 相似文献
This paper describes the reversible chemical locking of sypiropyran switches bound to metallic surfaces to enable the encoding of nonvolatile information. Data are encoded spatially by selectively locking the spiropyran moieties in their merocyanine form using a combination of exposure to acid and UV light. Without exposure to acid, the merocyanine form spontaneously converts back to the spiropyran form. Bits are resolved by defining the regions of the monolayer that are exposed to acid, using a “soft punchcard” fabricated from a silicone elastomer. Information is read by measuring the tunneling charge–transport through the monolayer using eutectic Ga–In top‐contacts. The merocyanine form is more than three orders of magnitude more conductive than the spiropyran form, allowing the differentiation of bits. Photoelectron spectroscopy shows that the monolayers are undamaged by exposure to light, acid, base, and applied bias, enabling proof‐of‐concept devices in which an 8‐bit ASCII encoded six‐character string is written, erased, and rewritten. 相似文献
Journal of Materials Science - The LiNi0.6Co0.2Mn0.2O2 (NCM) cathode material is highly potential for the wide application in lithium-ion batteries due to its moderate cost and high specific... 相似文献
This work aims to highlight the beneficial effect of annealing of Cu2ZnSn(S,Se)4 (CZTSSe) nanoparticles (NPs) on the properties of the obtained films by RF-magnetron sputtering at room temperature (RT) and at 200 °C. The CZTSSe targets used for the deposition are obtained using nanoparticles synthesized by solvothermal technique. It is denoted that the elemental composition of thin films becomes independent of the growth temperature in the case of annealed CZTSSe NPs. The optical investigation gives that the gap energy is ranging between 1.26 and 1.40 eV with an Urbach’s energy between 100 and 200 meV. By using the Wemple and Didominico model to analyze the refractive index spectra, we have identified common oscillator energy for all CZTSSe thin films and dispersion energy ranging from 2.63 to 5.81 eV. CZTSSe thin films obtained by means of annealed NPs exhibit higher dielectric constant and refractive index. The dispersion of different parameters with experimental conditions is analyzed via a common relationship that illustrates the linear dependence of n0, Ed, εs, and εL on the square of the valence difference (ΔZ). The conductivity spectra are deduced, and a theoretical model was identified to fit the permittivity spectra. The obtained results are promising for solar cell applications.
The accurate evaluation of electrical energy demanded by a CNC toolpath during a machining process is essential to determine its efficiency. Actually, the dynamic behavior of cutting forces seems to be neglected by investigators despite its influence on the consumed cutting energy during a face milling operation. This paper aims to investigate the effect of dynamic behavior of the machining system in order to take into account the dynamic response of the cutting forces on the axis feed power prediction. A dynamic cutting power model is developed in order to predict the consumed cutting energy. A parametric study is performed in order to show the impact of cutting conditions on the consumed energy values. The numerical results are compared to experimental ones. 相似文献
Nonlinear optical microscopy has become a powerful tool in bioimaging research due to its unique capabilities of deep optical sectioning, high‐spatial‐resolution imaging, and 3D reconstruction of biological specimens. Developing organic fluorescent probes with strong nonlinear optical effects, in particular third‐harmonic generation (THG), is promising for exploiting nonlinear microscopic imaging for biomedical applications. Herein, a simple method for preparing organic nanocrystals based on an aggregation‐induced emission (AIE) luminogen (DCCN) with bright near‐infrared emission is successfully demonstrated. Aggregation‐induced nonlinear optical effects, including two‐photon fluorescence (2PF), three‐photon fluorescence (3PF), and THG, of DCCN are observed in nanoparticles, especially for crystalline nanoparticles. The nanocrystals of DCCN are successfully applied for 2PF microscopy at 1040 nm NIR‐II excitation and THG microscopy at 1560 nm NIR‐II excitation, respectively, to reconstruct the 3D vasculature of the mouse cerebral vasculature. Impressively, the THG microscopy provides much higher spatial resolution and brightness than the 2PF microscopy and can visualize small vessels with diameters of ≈2.7 µm at the deepest depth of 800 µm in a mouse brain. Thus, this is expected to inspire new insights into the development of advanced AIE materials with multiple nonlinearity, in particular THG, for multimodal nonlinear optical microscopy. 相似文献