The increased use of digital tools such as smart phones, Internet of Things devices, cameras, and microphones, has led to the produuction of big data. Large data dimensionality, redundancy, and irrelevance are inherent challenging problems when it comes to big data. Feature selection is a necessary process to select the optimal subset of features when addressing such problems. In this paper, the authors propose a novel Binary Coronavirus Disease Optimization Algorithm (BCOVIDOA) for feature selection, where the Coronavirus Disease Optimization Algorithm (COVIDOA) is a new optimization technique that mimics the replication mechanism used by Coronavirus when hijacking human cells. The performance of the proposed algorithm is evaluated using twenty-six standard benchmark datasets from UCI Repository. The results are compared with nine recent wrapper feature selection algorithms. The experimental results demonstrate that the proposed BCOVIDOA significantly outperforms the existing algorithms in terms of accuracy, best cost, the average cost (AVG), standard deviation (STD), and size of selected features. Additionally, the Wilcoxon rank-sum test is calculated to prove the statistical significance of the results. 

https://doi.org/10.1016/j.knosys.2022.108789

BCOVIDOA: A Novel Binary Coronavirus Disease Optimization Algorithm for Feature Selection

The RNA-sequencing (RNA-seq) is becoming increasingly popular for quantifying gene expression levels. Since the RNA-seq measurements are relative in nature, between-sample normalization is an essential step in differential expression (DE) analysis. The normalization step of existing DE detection algorithms is usually ad hoc and performed only once prior to DE detection, which may be suboptimal since ideally normalization should be based on non-DE genes only and thus coupled with DE detection. We propose a unified statistical model for joint normalization and DE detection of RNA-seq data. Sample-specific normalization factors are modeled as unknown parameters in the gene-wise linear models and jointly estimated with the regression coefficients. By imposing sparsity-inducing L1 penalty (or mixed L1/L2 penalty for multiple treatment conditions) on the regression coefficients, we formulate the problem as a penalized least-squares regression problem and apply the augmented Lagrangian method to solve it. Simulation and real data studies show that the proposed model and algorithms perform better than or comparably to existing methods in terms of detection power and false-positive rate. The performance gain increases with increasingly larger sample size or higher signal to noise ratio, and is more significant when a large proportion of genes are differentially expressed in an asymmetric manner.

A Unified Model for Joint Normalization and Differential Gene Expression Detection in RNA-Seq data


 Sperm Motility Algorithm (SMA), inspired by the human fertilization process, was proposed by Abdul-Raof and Hezam [1] to solve global optimization problems. Sperm flow obeys the Stokes equation or the Schrۤinger equation as its derived equivalent. This paper combines a classical SMA with quantum computation features to propose two novel Quantum-Inspired Evolutionary Algorithms: The first is called the Quantum Sperm Motility Algorithm (QSMA), and the second is called the Improved Quantum Sperm Motility Algorithm (IQSMA). The IQSMA is based on the characteristics of QSMA and uses an interpolation operator to generate a new solution vector in the search space. The two proposed algorithms are global convergence guaranteed population-based optimization algorithms, which outperform the original SMA in terms of their search-ability and have fewer parameters to control. The two proposed algorithms are tested using thirty-three standard dissimilarities benchmark functions. Performance and optimization results of the QSMA and IQSMA are compared with corresponding results obtained using the original SMA and those obtained from three state-of-the-art metaheuristics algorithms. The algorithms were tested on a series of numerical optimization problems. The results indicate that the two proposed algorithms significantly outperform the other presented algorithms.


A Quantum-Inspired Sperm Motility Algorithm

Feature selection algorithms aim to improve the per-formance of machine learning algorithms by removing irrelevant and redundant features. Various feature selection algorithms have been proposed, but most of them select a global feature subset for characterizing the entire sample space. In contrast, this study proposes an efficient discrete clonal selection algorithm for local feature selection called DCSA-LFS with three features: (1) local sample behaviors are considered, and a local clustering-based evaluation criterion is used to select a distinct optimized feature subset for each different sample region; (2) an improved discrete clonal selection algorithm is proposed, which uses a differential evolution-based mutation operator to enhance the search capability of clonal selection algorithms; and (3) a two-part antibody representation is adopted to automatically adjust the weight-related parameter. Experimental results on twelve UCI datasets show that DCSA-LFS is competitive with traditional filter-based feature selection algorithms and a clonal selection algorithm-based local feature selection algorithm. 

A discrete clonal selection algorithm for filter-based local feature selection

Self-adaptive stacking ensemble approach with attention based deep neural network models for diabetic retinopathy severity prediction

PurposeGene selection is considered as the fundamental process in the bioinformatics field. The existing methodologies pertain to cancer classification are mostly clinical basis, and its diagnosis capability is limited. Nowadays, the significant problems of cancer diagnosis are solved by the utilization of gene expression data. The researchers have been introducing many possibilities to diagnose cancer appropriately and effectively. This paper aims to develop the cancer data classification using gene expression data.Design/methodology/approachThe proposed classification model involves three main phases: “(1) Feature extraction, (2) Optimal Feature Selection and (3) Classification”. Initially, five benchmark gene expression datasets are collected. From the collected gene expression data, the feature extraction is performed. To diminish the length of the feature vectors, optimal feature selection is performed, for which a new meta-heuristic algorithm termed as quantum-inspired immune clone optimization algorithm (QICO) is used. Once the relevant features are selected, the classification is performed by a deep learning model called recurrent neural network (RNN). Finally, the experimental analysis reveals that the proposed QICO-based feature selection model outperforms the other heuristic-based feature selection and optimized RNN outperforms the other machine learning methods.FindingsThe proposed QICO-RNN is acquiring the best outcomes at any learning percentage. On considering the learning percentage 85, the accuracy of the proposed QICO-RNN was 3.2% excellent than RNN, 4.3% excellent than RF, 3.8% excellent than NB and 2.1% excellent than KNN for Dataset 1. For Dataset 2, at learning percentage 35, the accuracy of the proposed QICO-RNN was 13.3% exclusive than RNN, 8.9% exclusive than RF and 14.8% exclusive than NB and KNN. Hence, the developed QICO algorithm is performing well in classifying the cancer data using gene expression data accurately.Originality/valueThis paper introduces a new optimal feature selection model using QICO and QICO-based RNN for effective classification of cancer data using gene expression data. This is the first work that utilizes an optimal feature selection model using QICO and QICO-RNN for effective classification of cancer data using gene expression data.

Cancer data classification by quantum-inspired immune clone optimization-based optimal feature selection using gene expression data: deep learning approach

Ensemble of deep capsule neural networks: an application to pediatric pneumonia prediction

With the enormous increase in data, anomaly detection plays a prominent role in the finer analysis process. IIoT represents the Industrial Internet of Things that at first chiefly alluded to a mechanical system whereby an enormous number of devices or machines are associated and synchronized using programming devices and third stage advancements in a machine-to-machine and Internet of Things, later an Industry 4.0. The data produced by multiple huge numbers of sensors are incredibly complicated, diverse, and massive in IIoT and is raw. These may contain anomalies which are needed to be identified for better data analysis. In this research, we compare the Machine Learning algorithms of classification for detecting anomalies. The algorithms being compared here are Random Forest (RF), Logistic Regression (LR), Light Gradient Boosting Machine (LightGBM), Decision Trees (DT), K Nearest Neighbors (KNN). Three IIOT benchmark datasets were taken into consideration for analysis. The results have shown that RF has outperformed other algorithms used for the detection of anomalies in IIoT data.

/pdf/comparative-analysis-of-machine-learning-based-algorithms-2koazfy6.pdf

Comparative Analysis of Machine Learning-Based Algorithms for Detection of Anomalies in IIoT

Recently, the combined problem of online class imbalance and concept drift (OCI-CD) has received much interest. The effect of this combined problem on the state-of-the-art of online adaptive and non-adaptive learners is not widely investigated. This work explores the impact of the parameters such as current imbalance ratio, length of the stream, type of the drift, levels of the drift, and state of the imbalance (static or dynamic) on adaptive and non-adaptive online learners. The experimental results demonstrate that each parameter considered for the study has a notable impact on learner performance: (a) the minority class performance decreases with the increase of the degree of imbalance, (b) non-adaptive learners are much prone to class imbalance, concept drift and the combined problem of both drifts than adaptive learners, (c) adaptive learners are only susceptible to class imbalance drifts, (d) the impact of the dynamic degree of imbalance on learner performance is more adverse than the static degree of imbalance and (e) the adaptive large scale support vector machine yields stable performance to all the parameters considered for the study. Further, directions to develop new approaches are also presented based on these findings. 

/pdf/analyzing-adaptive-and-non-adaptive-online-learners-on-2yz548tj.pdf

Analyzing Adaptive and Non-Adaptive Online Learners on Imbalanced Evolving Streams

In recent literature surveys low energy adaptive clustering hierarchy (LEACH) protocol got more attention in Wireless Senor Network (WSN) for improving network lifetime in terms of energy consumption. Many versions of LEACH are coming with modifications with single hop communication to multi-hop communications. More work is done on LEACH protocol, and it is a good start for researchers in WSN. In this paper we surveyed various LEACH based routing protocols are discussed with their working models in WSN. This survey classified in two ways single hop communication and multihop communication on basis of transmission in cluster to base station and explains about hierarchical routing protocols with LEACH. This survey describes about various versions of LEACH with analysis of various characteristics like network lifetime, communication type, clustering mechanisms, and so on, of LEACH protocol. This survey describes about pros and cons of each version of LEACH. At last, the paper finishes up with ideas on future research in WSN.

Venkatesulu Dondeti

Papers

Cancer data classification by quantum-inspired immune clone optimization-based optimal feature selection using gene expression data: deep learning approach

Ensemble of deep capsule neural networks: an application to pediatric pneumonia prediction

Comparative Analysis of Machine Learning-Based Algorithms for Detection of Anomalies in IIoT

Analyzing Adaptive and Non-Adaptive Online Learners on Imbalanced Evolving Streams

A Comparative Analysis on Variants of LEACH based routing protocols for prolonging network lifetime: Survey