Second Order Mutual Information based Grey Wolf Optimization for effective storage and de-duplication

Malhotra, Jyoti; Bakal, J. W.

doi:10.1007/s12046-018-0939-2

Cited by 12 publications

(5 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, the proposed BU‐SLnO was used to optimize the extracted features and the hidden neurons of CNN, and the spread value of PNN. The proposed BU‐SLnO‐AP‐CNN was compared with several optimization algorithms like PSO‐AP‐CNN (Wang et al, 2018), GWO‐AP‐CNN (Keshtegar & Nehdi, 2020; Malhotra et al, 2018b), FF‐AP‐CNN (Murlidhar et al, 2020), and SLnO‐AP‐CNN (Masadeh et al, 2019), and machine learning algorithms such as CNN (Zarie et al, 2020), PNN (Mahmood et al, 2020), Neural Network (NN) (Beck et al, 2019), support vector machine (SVM) (Borkar et al, 2019), and decision tree (DT) (Shahgoli et al, 2020) concerning Type I or positive measures like, ‘accuracy, sensitivity, specificity, precision, net present value (NPV), F1 score, and Matthews correlation coefficient (MCC)’, as well as Type II or negative measures like, ‘false positive rate (FPR), false negative rate (FNR), and false discovery rate (FDR)’.…”

Section: Resultsmentioning

confidence: 99%

Human activity recognition by wireless body area networks through multi‐objective feature selection with deep learning

Boga

Kumar

2022

Expert Systems

View full text Add to dashboard Cite

Wireless body area network (WBAN) is a novel technology with the incorporation of numerous types of devices, which is also employed in health monitoring applications.Human activity recognition (HAR) receives more interest in recent times along with wearable sensors. HAR system provides information about a person's identity, personality, and psychological state. In the present scenario, it becomes important to model the active learning paradigms with the help of wearable sensors for analysing human activities. Although various deep learning models and existing algorithms secure better outcomes through the sensor data analysis regarding HAR, the decision-making evaluation seems to be a complex one. The main intent of this paper is to implement the WBAN-based HAR system using the improved deep learning model. By connecting the wearable sensors, the signals are gathered regarding human activity from diverse benchmark sources. After collecting the required signals, the pre-processing of the input signals is done using artefact removal and median filtering. Further, the feature extraction is performed, which intends to extract a set of features by utilizing short-time Fourier transform (STFT) and statistical features. For reducing the feature-length, a multi-objective-based optimal feature selection is adopted. Human activities such as 'walking, walking upstairs, walking downstairs, sitting, standing, lying, and jogging' are recognized with help of selected optimal features. The optimized probabilistic neural network (PNN) and convolutional neural network (CNN) are combined and named as adaptive probabilistic-based CNN (AP-CNN). The effective performance of optimal feature selection and recognition is accomplished by incorporating the developed backward updating position-based sea lion optimization algorithm (BU-SLnO). Finally, the performance of the BU-SLnO-AP-CNN-based suggested model is analysed, which shows 1.001%, 1.237%, 0.811%, and 0.859% advanced than SLnO-AP-CNN, feed-forward-AP-CNN (FF-AP-CNN), grey wolf optimization-AP-CNN (GWO-AP-CNN), particle swarm optimization-AP-CNN (PSO-AP-CNN) when observing the dataset 1. The experimental outcomes from comparison with various classification techniques demonstrate the efficiency of the developed technique.

show abstract

Section: Resultsmentioning

confidence: 99%

Human activity recognition by wireless body area networks through multi‐objective feature selection with deep learning

Boga

Kumar

2022

Expert Systems

View full text Add to dashboard Cite

show abstract

“…So scheduling techniques are developed such that the constraints specified by the users should be satisfied. Like a job should be finished in a given amount of time period within specified budget constraints [68] [69]. Optimization criteria can be a combination of various constraints, used when making scheduling decisions and it represents the goal of scheduling process.…”

Section: Optimization In Scheduling Techniquesmentioning

confidence: 99%

Metaheuristics for scheduling of heterogeneous tasks in cloud computing environments: Analysis, performance evaluation, and future directions

Singh

Tyagi

Kumar

et al. 2021

Simulation Modelling Practice and Theory

View full text Add to dashboard Cite

“…Alternatively, the network energy, throughput and security of the system should be maximal for the efficient transmission of data. The objective function of the presented CH technique is defined as in Equation ( 14), in which η lies between η 0 < < 1, o m and o n are computed as shown in Equation (15) and Equation (16), respectively. The modules on delay, energy, distance, security, throughput and overhead are explained by γ 1 , γ 2 , γ 3 , γ 4 , γ 5 , and γ 6 .…”

Section: Objective Model For Optimal Cluster Head Selectionmentioning

confidence: 99%

“…[12][13][14] The conventional techniques for modeling networks using layered design may be inefficient and inappropriate. 15,16 Cross-layer design is a promising scenario that helps in optimizing and improving the performance of the wireless system by deploying the interaction among varied protocol layers. 17,18 More benefits can be expected while executing a cross-layer design along with an optimization framework.…”

Section: Introductionmentioning

confidence: 99%

Secured cross‐layer cross‐domain routing in dense wireless sensor network: A new hybrid based clustering approach

Lahane

Jariwala

2021

Int J Intell Syst

View full text Add to dashboard Cite

In wireless sensor network (WSN), increasing the network life span remains as a crucial challenge yet to be resolved. The modeling of effectual methods is necessary for conserving the scarce energy resources in WSN. To overcome such issues, cross‐layer protocols are exploited, which concerns routing the messages with increased lifetime. This study introduces a new cross‐layer design routing model under a clustering‐based approach. More importantly, the cluster head is optimally selected by a new hybrid algorithm termed as moth flame integrated dragonfly algorithm. Moreover, the optimal selection of cluster head is carried out based on parameters such as energy consumption, delay, distance, throughput, security, and overhead. Finally, the supremacy of the presented model is proved over existing models in terms of alive node analysis and network lifetime analysis. The experimental outcomes show that the proposed algorithm for test case 3 has accomplished a higher value of 66.229, which is 29.07%, 13.33%, 26.36%, and 9.67% better than conventional ant lion optimisation approach, grouped grey wolf search optimisation, firefly replaced position update in da, and alpha wolf‐assisted whale optimization algorithm, respectively, for median case scenario.

show abstract

Second Order Mutual Information based Grey Wolf Optimization for effective storage and de-duplication

Cited by 12 publications

References 46 publications

Human activity recognition by wireless body area networks through multi‐objective feature selection with deep learning

Human activity recognition by wireless body area networks through multi‐objective feature selection with deep learning

Metaheuristics for scheduling of heterogeneous tasks in cloud computing environments: Analysis, performance evaluation, and future directions

Secured cross‐layer cross‐domain routing in dense wireless sensor network: A new hybrid based clustering approach

Contact Info

Product

Resources

About