Artificial intelligence for sustainable internet research

1. Introduction

Artificial intelligence, machine learning, deep learning, and neural networks are the logical continuation of automation provided by higher computing power. Artificial intelligence has already made its entry into everyday life through enormous increases in efficiency, especially for businesses and internet technology. Artificial Intelligence is impacting every single sector and we are particularly excited about Internet of healthcare and neuroscience, design and art, Internet of Things, computer vision and speech processing, imaging and 3D data, education and learning, climate, economy, and finance.

This special issue focuses on artificial intelligence complex challenges, with a need to leverage large amounts of heterogeneous data to develop computational intelligence solutions for process optimizations, monitoring and control applications, intelligence, perception process of human, to produce their possible theories and design intelligent machines, especially internet research programs.

2. Summary of the contributions

This special issue focuses high-quality research papers that address significant and new Artificial Intelligent internet research and related system development issues in the emerging sustainable application domains. This special issue features 16 selected papers with high-quality aspects of Internet research and their applications in various artificial intelligence environments.

The first article focuses enhanced deep convolutional neural network for malarial parasite classification. The proposed work uses a deep convolutional neural network and intelligence techniques to detect the malarial parasites from smear blood cell images. The second article covers a pre-processing method combined with an ensemble framework for multi-class imbalanced data classification using stacked generalization framework.

The third article introduces a method for creating CAPTCHAs using regional languages which are user friendly. This technique provides a reliable platform by preventing various attacks for websites with high-level security and service. The fourth article proposes a symbolic approach to predict the histologic subtypes of lung cancer and investigates different techniques of feature selection in order by using either symbolic data or the radiomic features which are extracted by using a gray level co-occurrence matrix (GLCM).

The fifth article proposes a multilevel discrete wavelet transform (DWT) transformation over transformed image components where Optimal pixels are selected using Multi-objective Whale Optimization. An Advanced Encryption Standard and Signcryption algorithm is performed over R, G and B separated components, respectively. The sixth article outlines a secure cluster-based authentication, key management (SCAKM) protocol for machine-type communication in the long-term evolution (LTE) network. An optimal spiral dynamic algorithm and CH selection is designed and signcryption algorithm is proposed for authentication.

The seventh work focuses on the conservative methods for online assessment in terms of stability check for voltage problems. An Artificial intelligence-based method called slap swarm algorithm-based artificial neural network (SSA–ANN) is opted for online monitoring of voltage stability, which is used for tuning the met parameters such as the activation functions and number of nodes along with the learning rate. The eighth article proposes an Automatic medical image classification technique using the IRSG feature descriptor. The proposed hybrid method is developed by implementing autocorrelation Gabor filter responses on the high-frequency DWT coefficients.

The ninth article enhances IoT security authentication by utilizing cryptographic-based methodologies. A Step size Firefly (SFF) optimization algorithm is proposed to select optimal key and enhance privacy-preserving data in IoT. The tenth work focuses on the resolved spectrum shortage problem concept of the cognitive radio network (CRN) and a dynamic spectrum access methodology is proposed to check the free channel for the SU during handoff.

The eleventh article, An Intelligent Multi-floor Indoor Positioning System for Cloud-based Environment, covers an intelligent scheme to form multi-floor clusters by subdividing the topology into regions by determining the number of neighboring nodes in each floor of the indoor surrounding. The twelfth article, Subspace-based Aggregation for Enhancing Utility, Information Measures and Cluster Identification in Privacy Preserved Data Mining on High Dimensional Continuous Data, proposes the subspace-based aggregation (SBA) that categorizes the dimensions into dense and non-dense subspaces based on the density of points and aggregation is performed separately for dense and non-dense subspaces. This approach helps to maximize utility measures, information measures, and retention of clusters.

The next paper, An Empirical Evaluation of Teaching–Learning-based Optimization, Genetic Algorithm and Particle Swarm Optimization, introduces an innovative metaheuristic method called teaching–learning-based optimization (TLBO) which is used as an innovative and robust method to solve the global optimization problem, inspired by the teaching–learning phenomenon. The next paper, An Ontology Learning-based Approach for Focused Web Crawling Using Combined Normalized Pointwise Mutual Information and Resnik Algorithm, presents a new focused web crawler based on combined Normalized Pointwise Mutual Information (NPMI) and Resnik-based semantic similarity algorithm, called as P-crawler for focused web crawlers.

The last paper, An Analysis of Mobile Passcodes in Case of Criminal Investigations through Social Network Data, explains how passwords can be cracked easily with the help of survey and training of large dataset. It outlines few key characteristics to identify the passcode.

We anticipate that the special issue will open new entrance for further research and technology improvements in this important area.

Acknowledgements

The Guest Editors wish to thank all the authors of this special issue for contributing their dedicated, novel, and high-quality research papers for publication. We would also like to thank all the reviewers who have critically evaluated and shortlisted the research papers within the short-stipulated time. Finally, we hope that the special issue will be informative and useful for all the readers.