Simulated Annealing Algorithm  for Feature Selection

Rosario, Francisca; Thangadurai, K.

doi:10.24297/ijct.v15i2.565

Cited by 4 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, the Relief algorithm was used to evaluate the importance of features. The Relief algorithm was first proposed by Kira (Kira and Rendell, 1992 ) and has been widely applied in selecting features for classification (Rosario and Thangadurai, 2015 ). As shown in Figure 5 , to verify the validity of the proposed method, the brain region feature, subgraph feature, and multi-feature methods were each evaluated by the Relief algorithm.…”

Section: Resultsmentioning

confidence: 99%

Machine Learning Classification Combining Multiple Features of A Hyper-Network of fMRI Data in Alzheimer's Disease

et al. 2017

View full text Add to dashboard Cite

Exploring functional interactions among various brain regions is helpful for understanding the pathological underpinnings of neurological disorders. Brain networks provide an important representation of those functional interactions, and thus are widely applied in the diagnosis and classification of neurodegenerative diseases. Many mental disorders involve a sharp decline in cognitive ability as a major symptom, which can be caused by abnormal connectivity patterns among several brain regions. However, conventional functional connectivity networks are usually constructed based on pairwise correlations among different brain regions. This approach ignores higher-order relationships, and cannot effectively characterize the high-order interactions of many brain regions working together. Recent neuroscience research suggests that higher-order relationships between brain regions are important for brain network analysis. Hyper-networks have been proposed that can effectively represent the interactions among brain regions. However, this method extracts the local properties of brain regions as features, but ignores the global topology information, which affects the evaluation of network topology and reduces the performance of the classifier. This problem can be compensated by a subgraph feature-based method, but it is not sensitive to change in a single brain region. Considering that both of these feature extraction methods result in the loss of information, we propose a novel machine learning classification method that combines multiple features of a hyper-network based on functional magnetic resonance imaging in Alzheimer's disease. The method combines the brain region features and subgraph features, and then uses a multi-kernel SVM for classification. This retains not only the global topological information, but also the sensitivity to change in a single brain region. To certify the proposed method, 28 normal control subjects and 38 Alzheimer's disease patients were selected to participate in an experiment. The proposed method achieved satisfactory classification accuracy, with an average of 91.60%. The abnormal brain regions included the bilateral precuneus, right parahippocampal gyrus\hippocampus, right posterior cingulate gyrus, and other regions that are known to be important in Alzheimer's disease. Machine learning classification combining multiple features of a hyper-network of functional magnetic resonance imaging data in Alzheimer's disease obtains better classification performance.

show abstract

Section: Resultsmentioning

confidence: 99%

Machine Learning Classification Combining Multiple Features of A Hyper-Network of fMRI Data in Alzheimer's Disease

et al. 2017

View full text Add to dashboard Cite

show abstract

“…This illustrates the potential for the integration of the two different types of features to significantly improve classification performance. We used the Relief method [ 49 ] to calculate the average weights of subgraph pattern features, the minimum spanning tree of quantifiable local network features, and both types of features combined ( Figure 3 ). The average weight of the subgraph pattern features was 550.31, that of the minimum spanning tree of the quantifiable local network features was 915.42, and that for both feature types together was 945.16.…”

Section: Resultsmentioning

confidence: 99%

“…In the field of data mining, a large number of frequent subgraph mining methods have been proposed [ 45 , 46 ], including a priori-based graph mining [ 47 ] and the frequent subgraph discovery algorithm [ 48 ]. Here, we used the well-known gSpan algorithm [ 49 ] to extract the frequent subnetworks from the functional connectivity network. Because of its high efficiency in graph traversal and subgraph mining, the gSpan algorithm has been widely applied in many research fields, including neural imaging [ 25 – 27 ].…”

Section: Methodsmentioning

confidence: 99%

Machine-Learning Classifier for Patients with Major Depressive Disorder: Multifeature Approach Based on a High-Order Minimum Spanning Tree Functional Brain Network

Guo

Qin

Chen

et al. 2017

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

High-order functional connectivity networks are rich in time information that can reflect dynamic changes in functional connectivity between brain regions. Accordingly, such networks are widely used to classify brain diseases. However, traditional methods for processing high-order functional connectivity networks generally include the clustering method, which reduces data dimensionality. As a result, such networks cannot be effectively interpreted in the context of neurology. Additionally, due to the large scale of high-order functional connectivity networks, it can be computationally very expensive to use complex network or graph theory to calculate certain topological properties. Here, we propose a novel method of generating a high-order minimum spanning tree functional connectivity network. This method increases the neurological significance of the high-order functional connectivity network, reduces network computing consumption, and produces a network scale that is conducive to subsequent network analysis. To ensure the quality of the topological information in the network structure, we used frequent subgraph mining technology to capture the discriminative subnetworks as features and combined this with quantifiable local network features. Then we applied a multikernel learning technique to the corresponding selected features to obtain the final classification results. We evaluated our proposed method using a data set containing 38 patients with major depressive disorder and 28 healthy controls. The experimental results showed a classification accuracy of up to 97.54%.

show abstract

“…The resulting weights from each feature selection model were normalized between 0 and 1 to ensure comparable significance. A weight closer to 1 indicated higher importance of a gene in distinguishing infected and healthy conditions, as determined by the employed feature selection model [22][23][24][25].…”

Section: Machine Learning Modelsmentioning

confidence: 99%

Using meta-analysis and machine learning to investigate the transcriptional response of immune cells to Leishmania infection

Rezaei,

Tahmasebi,

Pourabbas

2024

PLoS Negl Trop Dis

View full text Add to dashboard Cite

Background Leishmaniasis is a parasitic disease caused by the Leishmania protozoan affecting millions of people worldwide, especially in tropical and subtropical regions. The immune response involves the activation of various cells to eliminate the infection. Understanding the complex interplay between Leishmania and the host immune system is crucial for developing effective treatments against this disease. Methods This study collected extensive transcriptomic data from macrophages, dendritic, and NK cells exposed to Leishmania spp. Our objective was to determine the Leishmania-responsive genes in immune system cells by applying meta-analysis and feature selection algorithms, followed by co-expression analysis. Results As a result of meta-analysis, we discovered 703 differentially expressed genes (DEGs), primarily associated with the immune system and cellular metabolic processes. In addition, we have substantiated the significance of transcription factor families, such as bZIP and C2H2 ZF, in response to Leishmania infection. Furthermore, the feature selection techniques revealed the potential of two genes, namely G0S2 and CXCL8, as biomarkers and therapeutic targets for Leishmania infection. Lastly, our co-expression analysis has unveiled seven hub genes, including PFKFB3, DIAPH1, BSG, BIRC3, GOT2, EIF3H, and ATF3, chiefly related to signaling pathways. Conclusions These findings provide valuable insights into the molecular mechanisms underlying the response of immune system cells to Leishmania infection and offer novel potential targets for the therapeutic goals.

show abstract

Simulated Annealing Algorithm for Feature Selection

Cited by 4 publications

References 9 publications

Machine Learning Classification Combining Multiple Features of A Hyper-Network of fMRI Data in Alzheimer's Disease

Machine Learning Classification Combining Multiple Features of A Hyper-Network of fMRI Data in Alzheimer's Disease

Machine-Learning Classifier for Patients with Major Depressive Disorder: Multifeature Approach Based on a High-Order Minimum Spanning Tree Functional Brain Network

Using meta-analysis and machine learning to investigate the transcriptional response of immune cells to Leishmania infection

Contact Info

Product

Resources

About