检索结果-内蒙古大学图书馆

JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY 2023年第3期38卷 1299-1306页

作者： Akalin, Fatma Yumusak, Nejat Sakarya Univ Fac & Informat Sci Dept Informat Syst Engn TR-54187 Sakarya Turkiye Sakarya Univ Fac & Informat Sci Dept Comp Engn TR-54187 Sakarya Turkiye

In this study, it is realized to differentiate ALL, AML and MLL malignancies, which are the types of leukaemia, using the microarray dataset. The flow chart related to the classification of malignancies is given in Figure A. Figure A. Flow chart related to the classification of ALL, AML and MLL malignanciesPurpose: Classification of ALL, AML and MLL malignancies using LSTM neural network architecture on microarray *** and Methods: In this study, the microarray dataset obtained from https://*** /biolab/supp/bi-cancer/projections/ is used. microarray dataset, which has dimensional superiority, creates a complex and costly situation. For this reason, it is planned to facilitate the analysis process with computer -aided systems. In the presented study;ALL, AML and MLL malignancies are analyzed with an artificial intelligence-supported system. Firstly, qualified disease-associated genes are selected from the microarray dataset using the whale optimization algorithm in this scope. Then, ALL, AML and MLL malignancies are classified using the LSTM neural network on selected potential genes. This present study which has a simple hierarchy and low computational complexity produced an efficient ***: This study classified ALL, AML and MLL malignancies using the microarray dataset. In this context, LSTM neural network architecture was used on the potential genes selected with the whale optimization algorithm and an accuracy rate of 89.883% was ***: Diagnostic and prognostic prediction of leukaemia disease is important in terms of determining the category of the disease and planning the treatment process. In the current study conducted for this purpose, ALL, AML and MLL leukaemia types were distinguished successfully.

关键词： microarray dataset Whale optimization algorithm LSTM neural network

来源：评论

学校读者我要写书评

暂无评论

A scalable association rule learning and recommendation algorithm for large-scale microarray datasets

引用

JOURNAL OF BIG DATA 2022年第1期9卷 1-25页

作者： Li, Haosong Sheu, Phillip C-Y Univ Calif Irvine Dept Elect Engn & Comp Sci Irvine CA 92697 USA

Association rule learning algorithms have been applied to microarray datasets to find association rules among genes. With the development of microarray technology, larger datasets have been generated recently that challenge the current association rule learning algorithms. Specifically, the large number of items per transaction significantly increases the running time and memory consumption of such tasks. In this paper, we propose the Scalable Association Rule Learning (SARL) heuristic that efficiently learns gene-disease association rules and gene-gene association rules from large-scale microarray datasets. The rules are ranked based on their importance. Our experiments show the SARL algorithm outperforms the Apriori algorithm by one to three orders of magnitude.

关键词： Association rule learning microarray dataset Frequent itemset mining Scalability Graph partitioning Apriori algorithm

来源：评论

学校读者我要写书评

暂无评论

Supervised feature selection on gene expression microarray datasets using manifold learning

引用

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS 2023年第1期237卷

作者： Zare, Masoumeh Azizizadeh, Najmeh Kazemipour, Ali Shahid Bahonar Univ Kerman Res Inst Plant Prod Technol Kerman Iran Shahid Bahonar Univ Kerman Fac Math & Comp Dept Appl Math Kerman Iran Shahid Bahonar Univ Kerman Dept Agron & Plant Breeding Kerman Iran

In recent decades, the ultimate output from microarray assay, has produced enormous numbers of microarray datasets, regardless of the used technology. These datasets include complex and high dimensional samples and genes that the number of samples is much smaller than the number of genes (features). Due to the redundant dimensions in these datasets, processing them directly not only leads to poor performance but also increases computation time and memory usage. Feature selection reduces computational expense while improving or maintaining diagnosis accuracy. In this study, we propose a new supervised feature selection method based on a manifold learning approach. We focus in two different directions to address this issue. First, maximum relevancy criterion that achieves by integrating Supervised Laplacian Eigenmaps (S-LE) and a matrix, which can realize the process of feature selection. The applied criterion simultaneously opts the features that make same-class samples closer to each other and ignores the features that cause different-class samples be near. Second, minimum redundancy among selected features by applying the Pearson correlation coefficient. In the test phase, the proposed method is compared with ten state-of-the-art algorithms on seven microarray datasets. Reported results show that the proposed method has more promising performance than the other methods.

关键词： Supervised feature selection microarray dataset Discriminative features Redundant features

来源：评论

学校读者我要写书评

暂无评论

Feature selection techniques for microarray datasets:a comprehensive review,taxonomy,and future directions

引用

Frontiers of Information Technology & Electronic Engineering 2022年第10期23卷 1451-1478页

作者： Kulanthaivel BALAKRISHNAN Ramasamy DHANALAKSHMI Department of Computer Science and Engineering Indian Institute of Information TechnologyTiruchirappalli 620012India

For optimal results,retrieving a relevant feature from a microarray dataset has become a hot topic for researchers involved in the study of feature selection(FS)*** aim of this review is to provide a thorough description of various,recent FS *** review also focuses on the techniques proposed for microarray datasets to work on multiclass classification problems and on different ways to enhance the performance of learning *** attempt to understand and resolve the imbalance problem of datasets to substantiate the work of researchers working on microarray *** analysis of the literature paves the way for comprehending and highlighting the multitude of challenges and issues in finding the optimal feature subset using various FS techniques.A case study is provided to demonstrate the process of implementation,in which three microarray cancer datasets are used to evaluate the classification accuracy and convergence ability of several wrappers and hybrid algorithms to identify the optimal feature subset.

关键词： Feature selection High dimensionality Learning techniques microarray dataset

来源：评论

学校读者我要写书评

暂无评论

Dual regularized subspace learning using adaptive graph learning and rank constraint: Unsupervised feature selection on gene expression microarray datasets

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2023年 167卷 107659-107659页

作者： Moslemi, Amir Ahmadian, Arash Sunnybrook Hlth Sci Ctr Imaging Res & Phys Sci Toronto ON Canada Univ Toronto Edward S Rogers Sr Dept Elect & Comp Engn Toronto ON Canada

High-dimensional problems have increasingly drawn attention in gene selection and analysis. To add insult to injury, usually the number of features is greater than number of samples in microarray gene dataset which leads to an ill-posed underdetermined equation system. Poor performance and high computational time for learning algorithms are consequences of redundant features in high-dimensional data. Feature selection is a noteworthy pre-processing method to ameliorate the curse of dimensionality with aim of maximum relevancy and minimum redundancy information preservation. Likewise, unsupervised feature selection has been important since collecting labels for data is expensive. In this paper, we develop a novel robust unsupervised feature selection to select discriminative subset of features for unlabeled data based on rank constrained and dual regularized nonnegative matrix factorization. The major focus of the proposed technique is to discard redundant features while keeping the informative features. Proposed feature selection technique consists of nonnegative matrix factorization to decompose the data into feature weight matrix and representation matrix, inner product norm as regularization for both feature weight matrix and representation matrix, adaptive structure learning to preserve local information and Schatten-p norm as rank constraint. To demonstrate the effectiveness of the proposed method, numerical studies are conducted on six benchmark microarray datasets. The results show that the proposed technique outperforms eight state-of-art unsupervised feature selection techniques in terms of clustering accuracy and normalized mutual information.

关键词： Gene selection microarray dataset Unsupervised feature selection Nonnegative matrix factorization Inner product norm Local information preserving Rank constraint

来源：评论

学校读者我要写书评

暂无评论

Identification and preliminary validation of differently expressed genes as candidate biomarkers associated with atherosclerosis

引用

GENE 2024年 915卷 148410页

作者： Zhou, Liqin Zhou, Liping Chen, Qiliang Chen, Congying Qian, Yuanyuan Lou, Dayong Ma, Huanjie Wang, Suying Zhuji Peoples Hosp Zhejiang Prov Dept Pharm Zhuji 311800 Zhejiang Peoples R China Zhuji Renze Rehabil Hosp Dept Pharm Zhuji 311899 Zhejiang Peoples R China Zhejiang Univ Dept Pharm Sch Med Run Run Shaw Hosp Hangzhou 310018 Zhejiang Peoples R China Shengzhou Chinese Med Hosp Dept Pharm 208 Yiyuan Rd Shengzhou 312400 Zhejiang Peoples R China

Objective: Atherosclerosis (AS) is the primary cause of deadly cardio-cerebro vascular diseases globally. This study aims to explore the key differentially expressed genes (DEGs), potentially serving as predictive biomarkers for AS. Methods: microarray datasets were retrieved from the GEO database for DEGs and DE-miRNAs identification. Then biological function of DEGs were elucidated based on gene ontology (GO) and KEGG pathway enrichment analysis. The protein-protein interaction (PPI) network and DEGs-DE-miRNAs network were constructed, with emphasis on hub DEGs selection and their interconnections. Additionally, receiver operating characteristic (ROC) curve analysis was performed to evaluate the diagnostic precision of hub DEGs for AS. More importantly, an AS Syrian Golden hamster model was established to validate the expression levels of hub DEGs in AS. Results: A total of 203 DEGs and 10 DE-miRNAs were screened, with six genes were chosen as hub DEGs. These DEGs were significantly enriched in AS-related biological processes and pathways, such as immune and inflammatory response, cellular response to IL-1 and TNF, positive regulation of angiogenesis, Type I diabetes mellitus, Cytokine-cytokine receptor interaction, TLR signaling pathway. Also, these DEGs and DE-miRNAs formed a closely-interacted DE-miRNAs- DEGs- KEGG pathway network. Besides, hub DEGs presented promising diagnostic potential for AS (AUC: 0.781 similar to 0.887). In addition, the protein expression levels of TNF-alpha, CXCL8, CCL4, IL-1 beta, CCL3 and CCR8 were significantly increased in AS group Syrian Golden hamsters. Conclusion: The identified candidate genes TNF, CXCL8, CCL4, IL1B, CCL3 and CCR8 may have the potential to serve as prognostic biomarker in diagnosing AS.

关键词： Atherosclerosis microarray dataset Differentially expressed genes Biomarker Validation

来源：评论

学校读者我要写书评

暂无评论

Instigating the Sailfish Optimization Algorithm Based on Opposition-Based Learning to Determine the Salient Features From a High-Dimensional dataset

引用

INTERNATIONAL JOURNAL OF INFORMATION TECHNOLOGY & DECISION MAKING 2023年第5期22卷 1617-1649页

作者： Khaire, Utkarsh Mahadeo Dhanalakshmi, R. Balakrishnan, K. Akila, M. Indian Inst Informat Technol Dharwad Dept Data Sci & Intelligent Syst Dharwad 580009 Karnataka India Indian Inst Informat Technol Tiruchirappalli Dept Comp Sci & Engn Tiruchirappalli 620012 Tamil Nadu India KPR Inst Engn & Technol Dept Comp Sci & Engn Coimbatore 641407 Tamil Nadu India

The aim of this research critique is to propose a hybrid combination of Opposition-Based Learning and Sailfish Optimization strategy to recognize the salient features from a high-dimensional dataset. The Sailfish Optimization is a swarm-based metaheuristics optimization algorithm inspired by the foraging strategy of a group of Sailfish. Sailfish Optimization explores the search space in only one direction, limiting its converging capacity and causing local minima stagnation. Convergence will be optimal if the search space is reconnoitred in both directions, improving classification accuracy. As a result, combining the Opposition-Based Learning and Sailfish Optimization strategies improves SFO's exploration capability by patrolling the search space in all directions. Sailfish Optimization Algorithm based on Opposition-Based Learning successfully amalgamates the model to global optima at a faster convergence rate and better classification accuracy. The recommended method is tested with six different cancer microarray datasets for two different classifiers: the Support Vector Machine classifier and the K-Nearest Neighbor classifier. From the results obtained, the proposed model aided with Support Vector Machine outperforms the existing Sailfish Optimization with or without K-Nearest Neighbor in terms of convergence capability, classification accuracy, and selection of the most delicate salient features from the dataset.

关键词： Feature selection Opposition-based Learning Sailfish Optimization metaheuristic optimization microarray dataset

来源：评论

学校读者我要写书评

暂无评论

JNK/MAPK pathway regulation by BEX2 gene silencing in alcoholic hepatitis mice: Effects on oxidative stress

引用

ALCOHOL-CLINICAL AND EXPERIMENTAL RESEARCH 2023年第10期47卷 1869-1882页

作者： Zhou, Shuai Zhong, Hai Wang, Yong Wang, Xiaoguang Pan, Hongtao Liu, Xiaolin Hu, Lingyu Anhui Med Univ Hosp 2 Dept Gen Surg Hefei Anhui Peoples R China Jiaxing Univ Affiliated Hosp 2 Dept Surg Jiaxing Peoples R China Jiaxing Univ Affiliated Hosp 2 Dept Surg 1518 North Huancheng Rd Jiaxing 314000 Zhejiang Peoples R China

Background: Alcoholic hepatitis (AH) is a severe alcoholic-related liver disease that is a leading cause of morbidity and mortality, for which effective treatments are lacking. Brain-expressed X-linked gene 2 (BEX2) has been implicated in various diseases, but its association with AH has received limited attention. Thus, this study investigated BEX2's impact on the progression of AH by affecting the c-Jun NH2-terminal kinase/mitogen-activated protein kinase (JNK/MAPK) ***: microarray dataset GSE28619 from the Gene Expression Omnibus database was used to identify differentially expressed genes in AH. Immunohistochemistry, terminal deoxynucleotidyl transferase-mediated dUTP-biotin nick end labeling (TUNEL), Western blot analysis, and flow cytometry were used to measure various factors in the liver tissue of AH ***: BEX2 expression was significantly upregulated in the model. BEX2 gene silencing increased the levels of glutathione peroxidase and superoxide dismutase while decreasing malondialdehyde content;phosphorylation of JNK, c-JUN, and p38MAPK;apoptosis rate;and the extent of JNK/MAPK pathway ***: These findings provide valuable insights into the mechanisms underlying AH development and highlight the potential role of BEX2 gene expression as a promising therapeutic target for AH.

关键词： alcoholic hepatitis brain expressed X-linked gene 2 (BEX2) gene silencing JNK/MAPK pathway liver tissue microarray dataset oxidative stress

来源：评论

学校读者我要写书评

暂无评论

SVAD: Stacked Variational Autoencoder Deep Neural Network-Based Dimensionality Reduction and Classification of Small Sample Size and High Dimensional Data

引用

SN Computer Science 2024年第7期5卷 956页

作者： Srivastava, Neha Tayal, Devendra K. Indira Gandhi Delhi Technical University for Women James Church New Church Rd. Opp. St Kashmere Gate New Delhi 110006 India

The “curse of dimensionality” is a major concern in the field of computational biology, especially when there are many fewer samples then to the number of features. Many strategies for dimension reduction have been developed;however, they all have drawbacks when it comes to high-dimensional and small sample size data, such as high value of variance gradients and *** address these issues, we proposed a dynamic variational autoencoder based deep neural network architecture, based on a mathematical foundation for unsupervised learning. The objective of this research is to propose a low-error classification algorithm for limited sample numbers and high-dimensional datasets. The study's innovation is that it guarantees the permissible dimension size regardless of reduction, in contrast to several previous approaches that typically reduce the dimension too heavily. The experimental findings reveal that the suggested method outperforms existing traditional methods such as RNN, CNN, and deep network architecture. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Learning microarray dataset Neural nets Small sample size dataset

来源：评论

学校读者我要写书评

暂无评论

A novel control factor and Brownian motion-based improved Harris Hawks Optimization for feature selection

引用

JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING 2022年第7期14卷 8631-8653页

作者： Balakrishnan, K. Dhanalakshmi, R. Khaire, Utkarsh Mahadeo Indian Inst Informat Technol Dept Comp Sci & Engn Tiruchirappalli 620012 Tamil Nadu India Indian Inst Informat Technol Dept Data Sci & Intelligent Syst Dharwad 580009 Karnataka India

The massive growth in data size has prompted proliferation in need for Feature Selection (FS). Hence, FS has become an imperative method for dealing with high-dimensional data. This research critique proposes an enhanced feature selection of Harris Hawks Optimization (HHO) based on the novel control factor and Brownian motion. The Brownian motion augments the exploitation of foragers. It also replicates the deceptive movement of prey, allowing predators to correct their location and direction according to the prey's position. At the same time, the novel control factor imitates the exact behavior of the prey's escaping energy. The comparative analysis with the existing technique using six real high-dimensional microarray datasets highlights the impact of the proposed Improved Harris Hawks Optimization (iHHO). The experimental results of FS and classification accuracy vividly depict how the proposed model outperforms the existing techniques.

关键词： Feature selection Harris Hawks Optimization Meta-heuristic optimization microarray dataset

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：