Effective Features to Classify Big Data Using Social Internet of Things

Lakshmanaprabu, S.K.; Shankar, K.; Khanna, Ashish; Gupta, Deepak; Rodrigues, Joel J. P. C.; Pinheiro, Plácido Rogério; Albuquerque, Victor Hugo C. de

doi:10.1109/access.2018.2830651

Cited by 114 publications

(50 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of the proposed FABC+CFFRideNN algorithm is analyzed and is compared with the existing methods, such as Leach+Mapreduce +Elephant Heard Optimization +Linear Kernel-Support Vector machine (Leach+Mapreduce+EHO+LK-SVM) [28], Wireless Body Area Network +Deep Convolutional Neural Network (WBAN+Deep CNN) [29], Random Forest (Artificial Bee Colony +RF) [30], and Particle Swarm Optimization+Neural network (PSO+NN).…”

Section: Comparative Methodsmentioning

confidence: 99%

“…However, it attained better performance in terms of accuracy, and runtime, but failed to consider the semi-supervised model. Lakshmanaprabu et al [28] developed an SVM-based classifier model to extract the features from big data through Mapreduce framework. The unwanted data and noise present in the data were eliminated using gabor filter.…”

Section: A Literature Surveymentioning

confidence: 99%

“… To perform the data cleaning, storage, and data collection in the real time analytics model faces several challenges in the IoT technology. However, providing utility to the IoT classification model is a challenging issue in the optimization mechanism [28].  To deal with the diversity, complexity, and volume in the big data poses a challenging issue in the research community.…”

Section: B Challengesmentioning

confidence: 99%

See 2 more Smart Citations

Spark Architecture and Fractional Artificial Bee Colony-Chaotic Fruitfly RideNN for Big data Classification in Internet of Things

Yousir*¹

2019

IJEAT

View full text Add to dashboard Cite

The typical Internet of Things (IoT) device gathers a huge amount of data specifically termed as big data framework, which transfers the collected data from the sensing layer to the information processing layer. Various big data classification methods are adopted in the industrial applications, and smart cities, but accurately classifying the data in the IoT network poses a challenging task in the research community. Therefore, an effective big data classification model using spark-based architecture is proposed in this research. The big data classification is performed at the master node using the proposed Fractional Artificial Bee Colony- Chaotic Fruitfly Rider Optimization Algorithm (FABC-CFFRideNN). The concept of fictional computing is adopted by the rider optimization algorithm (ROA) to update the position of rider groups based on success rate and the foraging behavior of fruit flies along with the rider parameters is used to enhance to performance of data classification using the proposed CFFRideNN classifier. Moreover, the proposed Fractional Artificial Bee Colony- Chaotic Fruitfly Rider Optimization Algorithm attained better performance using the metrics, namely accuracy, specificity, and sensitivity with the values of 95.382%, 95.81%, and 98.824% for training percentage without node velocity.

show abstract

Section: Comparative Methodsmentioning

confidence: 99%

Section: A Literature Surveymentioning

confidence: 99%

Section: B Challengesmentioning

confidence: 99%

See 1 more Smart Citation

Spark Architecture and Fractional Artificial Bee Colony-Chaotic Fruitfly RideNN for Big data Classification in Internet of Things

Yousir*¹

2019

IJEAT

View full text Add to dashboard Cite

show abstract

“…Various evolutionary techniques have been used to attain the best choice of features. At recent times, gravitational search algorithm as well as Elephant Herd optimization which are used to choose optimum features [8,9]. [10] designed a ANN based model to classify the CT cancer images.…”

Section: Deep Learning Based Depthwise Separable Model For Effective mentioning

confidence: 99%

Deep Learning Based Depthwise Separable Model For Effective Diagnosis And Classification of Lung Ct Images

Jayaraj,

Sathiamoorthy

2019

IJEAT

View full text Add to dashboard Cite

Lung cancer is a serious illness which leads to increased mortality rate globally. The identification of lung cancer at the beginning stage is the probable method of improving the survival rate of the patients. Generally, Computed Tomography (CT) scan is applied for finding the location of the tumor and determines the stage of cancer. Existing works has presented an effective diagnosis classification model for CT lung images. This paper designs an effective diagnosis and classification model for CT lung images. The presented model involves different stages namely pre-processing, segmentation, feature extraction and classification. The initial stage includes an adaptive histogram based equalization (AHE) model for image enhancement and bilateral filtering (BF) model for noise removal. The pre-processed images are fed into the second stage of watershed segmentation model for effectively segment the images. Then, a deep learning based Xception model is applied for prominent feature extraction and the classification takes place by the use of logistic regression (LR) classifier. A comprehensive simulation is carried out to ensure the effective classification of the lung CT images using a benchmark dataset. The outcome implied the outstanding performance of the presented model on the applied test images.

show abstract

“…The social IoT has become a larger social network which supports multiple applications and advances networking services for IoT in a very powerful and productive way. In [24] Lakshmana Prabu et al introduced a hierarchical model for social IoT systems using map-reduce and supervised classification paradigm. More even, a Gabor filtering scheme is applied to reduce the noisy and redundant as well as unwanted data from the data repository.…”

Section: Literature Reviewmentioning

confidence: 99%

NFDDC: Novel Neuro-Fuzzy Logic based Methodology for Distributed Data Classification

Parveen M*

2019

IJRTE

View full text Add to dashboard Cite

With the growing culture of Internet applications and their usage lead to challenging task for storing a massive volume of high-velocity data from different fields. This result an evolution of big data with integrated, i.e. Volume, Velocity, and Variety (3V's). The voluminous data extraction is a very complex task which is not possible form classical data mining techniques. Therefore, a big data mining technique is introducing by modifying traditional data mining scheme using a novel of Neuro-Fuzzy Logic based approach, i.e. named as NFDDC. The proposed distributed data classification model performs into three stages first- reduce the data set dimension, second- data clustering, and third-data classification using the neuro-fuzzy method. The performance of the NFDDC system is analysed using two different datasets, i.e. medical data and e-commerce datasets. Additionally, comparative analysis is performed by measuring the accuracy of existing CCSA algorithm with proposed NFDDC algorithm and will get 90% accuracy in data classification

show abstract

Effective Features to Classify Big Data Using Social Internet of Things

Cited by 114 publications

References 19 publications

Spark Architecture and Fractional Artificial Bee Colony-Chaotic Fruitfly RideNN for Big data Classification in Internet of Things

Spark Architecture and Fractional Artificial Bee Colony-Chaotic Fruitfly RideNN for Big data Classification in Internet of Things

Deep Learning Based Depthwise Separable Model For Effective Diagnosis And Classification of Lung Ct Images

NFDDC: Novel Neuro-Fuzzy Logic based Methodology for Distributed Data Classification

Contact Info

Product

Resources

About