Medicine is one of the fields where the advancement of computer science is making significant progress. Some diseases require an immediate diagnosis in order to improve patient outcomes. The usage of computers in medicine improves precision and accelerates data processing and diagnosis. In order to categorize biological images, hybrid machine learning, a combination of various deep learning approaches, was utilized, and a meta-heuristic algorithm was provided in this research. In addition, two different medical datasets were introduced, one covering the magnetic resonance imaging (MRI) of brain tumors and the other dealing with chest X-rays (CXRs) of COVID-19. These datasets were introduced to the combination network that contained deep learning techniques, which were based on a convolutional neural network (CNN) or autoencoder, to extract features and combine them with the next step of the meta-heuristic algorithm in order to select optimal features using the particle swarm optimization (PSO) algorithm. This combination sought to reduce the dimensionality of the datasets while maintaining the original performance of the data. This is considered an innovative method and ensures highly accurate classification results across various medical datasets. Several classifiers were employed to predict the diseases. The COVID-19 dataset found that the highest accuracy was 99.76% using the combination of CNN-PSO-SVM. In comparison, the brain tumor dataset obtained 99.51% accuracy, the highest accuracy derived using the combination method of autoencoder-PSO-KNN.
APDBN Rashid, The College of Arts/ Al-Mustansiriyya University, 2004
The pandemic SARS-CoV-2 is highly transmittable with its proliferation among nations. This study aims to design and exploring the efficacy of novel nirmatrelvir derivatives as SARS entry inhibitors by adapting a molecular modeling approach combined with theoretical design. The study focuses on the preparation of these derivatives and understanding their effectiveness, with a special focus on their binding affinity to the S protein, which is pivotal for the virus’s access to the host cell. Considering molecular docking aspects in the scope of a study on nirmatrelvir derivatives and S protein, dynamics simulations with 25 nanoseconds of their binding are explored. The study shows that these derivatives might work as effective antivi
... Show MoreIn the present work the nuclear structure of even-even
Ba(A=130-136, Z=56) isotopes was studied using (IBM-1). The reduced matrix element of magnetic dipole moment (11 II f(Ml) II/,) and the magnetic dipole transitions probability B(M 1) were calculated
for one and two bodies of even-even Ba(A=lJ0-136, Z=56). A good
agreement had been found of present with available experimental data.
In this theoretical paper and depending on the optimization synthesis method for electron magnetic lenses a theoretical computational investigation was carried out to calculate the Resolving Power for the symmetrical double pole piece magnetic lenses, under the absence of magnetic saturation, operated by the mode of telescopic operation by using symmetrical magnetic field for some analytical functions well-known in electron optics such as Glaser’s Bell-shaped model, Grivet-Lenz model, Gaussian field model and Hyperbolic tangent field model. This work can be extended further by using the same or other models for asymmetrical or symmetrical axial magnetic field
... Show MoreGas-lift technique plays an important role in sustaining oil production, especially from a mature field when the reservoirs’ natural energy becomes insufficient. However, optimally allocation of the gas injection rate in a large field through its gas-lift network system towards maximization of oil production rate is a challenging task. The conventional gas-lift optimization problems may become inefficient and incapable of modelling the gas-lift optimization in a large network system with problems associated with multi-objective, multi-constrained, and limited gas injection rate. The key objective of this study is to assess the feasibility of utilizing the Genetic Algorithm (GA) technique to optimize t