Yazar "Kiani, F." seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    An application of artificial neural networks for solving fractional higher-order linear integro-differential equations
    (Springer, 2023) Allahviranloo, T.; Jafarian, A.; Saneifard, R.; Ghalami, N.; Nia, S. Measoomy; Kiani, F.; Fernandez-Gamiz, U.
    This ongoing work is vehemently dedicated to the investigation of a class of ordinary linear Volterra type integro-differential equations with fractional order in numerical mode. By replacing the unknown function by an appropriate multilayered feed-forward type neural structure, the fractional problem of such initial value is changed into a course of non-linear minimization equations, to some extent. Put differently, interest was sparked in structuring an optimized iterative first-order algorithm to estimate solutions for the origin fractional problem. On top of that, some computer simulation models exemplify the preciseness and well-functioning of the indicated iterative technique. The outstanding accomplished numerical outcomes conveniently reflect the productivity and competency of artificial neural network methods compared to customary approaches.
  • Küçük Resim Yok
    Öğe
    Parallel molecular alteration between Alzheimer’s disease and major depressive disorder in the human brain dorsolateral prefrontal cortex: an insight from gene expression and methylation profile analyses
    (Genetics Society of Japan, 2022) Rastad, S.; Barjaste, N.; Lanjanian, H.; Moeini, A.; Kiani, F.; Masoudi-Nejad, A.
    Alzheimer’s disease (AD) and major depressive disorder (MDD) are comorbid neuropsychiatric disorders that are among the leading causes of long-term dis-ability worldwide. Recent research has indicated the existence of parallel molecular mechanisms between AD and MDD in the dorsolateral prefrontal cortex (DLPFC). However, the premorbid history and molecular mechanisms have not yet been well characterized. In this study, differentially expressed gene (DEG), differentially co-expressed gene and protein–protein interaction (PPI) network propagation analyses were applied to gene expression data of postmortem DLPFC samples from human individuals diagnosed with and without AD or MDD (AD: cases = 310, control = 157; MDD: cases = 75, control = 161) to identify the main genes in the two disorders’ specific and shared biological pathways. Subsequently, the results were evaluated using another four assessment datasets (n1 = 230, n2 = 65, n3 = 58, n4 = 48). Moreover, the postmortem DLPFC methylation status of human subjects with AD or MDD was compared using 68 and 608 samples for AD and MDD, respectively. Eight genes (XIST, RPS4Y1, DDX3Y, USP9Y, DDX3X, TMSB4Y, ZFY and E1FAY) were common DEGs in DLPFC of subjects with AD or MDD. These genes play important roles in the nervous system and the innate immune system. Furthermore, we found HSPG2, DAB2IP, ARHGAP22, TXNRD1, MYO10, SDK1 and KRT82 as common differentially methylated genes in the DLPFC of cases with AD or MDD. Finally, as evidence of shared molecular mechanisms behind this comorbidity, we propose some genes as candidate biomarkers for both AD and MDD. However, more research is required to clarify the molecular mechanisms underlying the co-existence of these two important neuropsychiatric disorders. © 2023 The Author(s).
  • Küçük Resim
    Öğe
    Tuning hyperparameters of machine learning algorithms and deep neural networks using metaheuristics: A bioinformatics study on biomedical and biological cases
    (Elsevier, 2022) Nematzadeh, S.; Kiani, F.; Torkamanian-Afshar, M.; Aydin, N.
    The performance of a model in machine learning problems highly depends on the dataset and training algorithms. Choosing the right training algorithm can change the tale of a model. While some algorithms have a great performance in some datasets, they may fall into trouble in other datasets. Moreover, by adjusting hyperparameters of an algorithm, which controls the training processes, the performance can be improved. This study contributes a method to tune hyperparameters of machine learning algorithms using Grey Wolf Optimization (GWO) and Genetic algorithm (GA) metaheuristics. Also, 11 different algorithms including Averaged Perceptron, FastTree, FastForest, Light Gradient Boost Machine (LGBM), Limited memory Broyden Fletcher Goldfarb Shanno algorithm Maximum Entropy (LbfgsMxEnt), Linear Support Vector Machine (LinearSVM), and a Deep Neural Network (DNN) including four architectures are employed on 11 datasets in different biological, biomedical, and nature categories such as molecular interactions, cancer, clinical diagnosis, behavior related predictions, RGB images of human skin, and X-rays images of Covid19 and cardiomegaly patients. Our results show that in all trials, the performance of the training phases is improved. Also, GWO demonstrates a better performance with a p-value of 2.6E-5. Moreover, in most experiment cases of this study, the metaheuristic methods demonstrate better performance and faster convergence than Exhaustive Grid Search (EGS). The proposed method just receives a dataset as an input and suggests the best-explored algorithm with related arguments. So, it is appropriate for datasets with unknown distribution, machine learning algorithms with complex behavior, or users who are not experts in analytical statistics and data science algorithms. © 2022 Elsevier Ltd