An enhanced deterministic K-Means clustering algorithm for cancer subtype prediction from gene expression data.

C-HMOSHSSA: Gene selection for cancer classification using multi-objective meta-heuristic and machine learning methods.

Evacuation planning is an important activity in disaster management to reduce the effects of disasters on urban communities. It is regarded as a multi-objective optimization problem that involves conflicting spatial objectives and constraints in a decision-making process. Such problems are difficult to solve by traditional methods. However, metaheuristics methods have been shown to be proper solutions. Well-known classical metaheuristic algorithms—such as simulated annealing (SA), artificial bee colony (ABC), standard particle swarm optimization (SPSO), genetic algorithm (GA), and multi-objective versions of them—have been used in the spatial optimization domain. However, few types of research have applied these classical methods, and their performance has not always been well evaluated, specifically not on evacuation planning problems. This research applies the multi-objective versions of four classical metaheuristic algorithms (AMOSA, MOABC, NSGA-II, and MSPSO) on an urban evacuation problem in Rwanda in order to compare the performances of the four algorithms. The performances of the algorithms have been evaluated based on the effectiveness, efficiency, repeatability, and computational time of each algorithm. The results showed that in terms of effectiveness, AMOSA and MOABC achieve good quality solutions that satisfy the objective functions. NSGA-II and MSPSO showed third and fourth-best effectiveness. For efficiency, NSGA-II is the fastest algorithm in terms of execution time and convergence speed followed by AMOSA, MOABC, and MSPSO. AMOSA, MOABC, and MSPSO showed a high level of repeatability compared to NSGA-II. It seems that by modifying MOABC and increasing its effectiveness, it could be a proper algorithm for evacuation planning.

https://www.mdpi.com/1999-4893/13/1/16/pdf

A Comparative Study of Four Metaheuristic Algorithms, AMOSA, MOABC, MSPSO, and NSGA-II for Evacuation Planning

Deciphering unclassified tumors of non-small-cell lung cancer through radiomics.

High-throughput technologies, like DNA microarray, help in simultaneous monitoring of the expression levels of thousands of genes during important biological processes and over the collection of experimental conditions. Automatically uncovering functionally related genes is a basic building block to solve various problems related to functional genomics. But sometimes a subset of genes may not be similar with respect to all the conditions present in the dataset; thus, bi-clustering concept becomes popular where different subsets of genes and the corresponding subsets of conditions with respect to which genes are most similar are automatically identified. In the current study, we have posed this problem in the multi-objective optimization (MOO) framework where different bi-cluster quality measures are optimized simultaneously. The search potentiality of a simulated annealing-based MOO technique, AMOSA, is used for the simultaneous optimization of these measures. A case study on the suitability of different distance measures in solving the bi-clustering problem is also conducted. The competency of the proposed multi-objective-based bi-clustering approach is shown for three benchmark datasets. The obtained results are further validated using statistical and biological significance tests.

Bi-clustering of microarray data using a symmetry-based multi-objective optimization framework

In the field of pattern recognition, the study of the gene expression profiles of different tissue samples over different experimental conditions has become feasible with the arrival of microarray-based technology. In cancer research, classification of tissue samples is necessary for cancer diagnosis, which can be done with the help of microarray technology. In this paper, we have presented a multiobjective optimization (MOO)-based clustering technique utilizing archived multiobjective simulated annealing(AMOSA) as the underlying optimization strategy for classification of tissue samples from cancer datasets. The presented clustering technique is evaluated for three open source benchmark cancer datasets [Brain tumor dataset, Adult Malignancy, and Small Round Blood Cell Tumors (SRBCT)]. In order to evaluate the quality or goodness of produced clusters, two cluster quality measures viz, adjusted rand index and classification accuracy ( $\% CoA$ ) are calculated. Comparative results of the presented clustering algorithm with ten state-of-the-art existing clustering techniques are shown for three benchmark datasets. Also, we have conducted a statistical significance test called t -test to prove the superiority of our presented MOO-based clustering technique over other clustering techniques. Moreover, significant gene markers have been identified and demonstrated visually from the clustering solutions obtained. In the field of cancer subtype prediction, this study can have important impact.

Multiobjective Simulated Annealing-Based Clustering of Tissue Samples for Cancer Diagnosis

In the field of pattern recognition, the study of the gene expression profiles for different tissue samples over different experimental conditions has became feasible with the arrival of micro-array based technology. In cancer research, classification of tissue samples is necessary for cancer diagnosis, which can be done with the help of micro-array technology. In this article we have presented a multi-objective optimization ( MOO ) based clustering technique utilizing AMOSA ( Archived Multi-Objective Simulated Annealing ) as the underlying optimization strategy for classification of tissue samples from cancer data sets. As objective functions three cluster validity indices namely, XB, PBM, and FCM indices are optimized simultaneously to form more accurate clusters of tissue samples. The presented clustering technique is evaluated for two open source benchmark cancer data sets, which are Brain tumor data set and Adult Malignancy data set. In order to evaluate the quality or goodness of produced clusters two cluster quality measures viz, Adjusted Rand Index ( ARI ) and Classification Accuracy ( %CoA ) are calculated for each data set. Comparative results of the presented clustering algorithm with 10 state-of-the-art existing single-objective, multi-objective based clustering algorithms are shown for two benchmark data sets.

Yamini Thadisina

Papers

Multiobjective Simulated Annealing-Based Clustering of Tissue Samples for Cancer Diagnosis

Multi-objective clustering of tissue samples for cancer diagnosis