The complexity of the internet is dramatically increasing, meaning the ability to process various data mining problems across multiple fields is becoming both more important and more challenging. The rapid growth of storage technologies, in combination with other factors, such as the appearance of mobile networks, digital society, and new technologies, has enabled the emergence of big data. However, big data comes with a certain amount of redundancy, and so while transmitting and processing these redundant data, the time and complexity increase dramatically. To resolve this, redundant data within big data can be mined or removed by data mining techniques. However, the application of data mining in a variety of problems, for example, network traffic monitoring, financial market analysis, and medical data analysis, remains poorly understood.

To find a solution, machine learning (ML) techniques have been proposed as a way to implement data mining in big data, and to implement intelligent analysis in various applications, such as face recognition, image processing, voice recognition, medical diagnoses, signal processing, DNA classification, social networks, or the Internet of Things (IoT). ML is a collection of computer algorithms that allow computer programs to improve automatically through experience to implement an intelligent process. ML builds models based on training data in engineering problems to make predictions or decisions without being explicitly programmed to do so. ML is also one of the main branches of artificial intelligence (AI), and is accelerating rapid development in AI. Its primary objective is to use computer algorithms to extract information from collected data. However, traditional machine learning techniques are not very effective in mining useful information from big data due to their limitations in handling complex tasks. Neural networks are widely accepted as AI approaches, offering an alternative way to control complex and ill-defined problems. Thus, neural network-based machine learning is necessary to solve these problems in complex and in-depth data mining in big data systems. Examples include back propagation neural networks with genetic algorithms (BPNN-GA), back propagation neural networks with particle swarm optimization (BPNN-PSO), deep learning (DL), neural networks with principal component analysis (PCA-NN), neural networks with multilayer perceptron-genetic algorithms (GA-MLP-NN), radial basis function neural networks with GA (RBFNN-GA), anatomically constrained neural networks (AC-NN), and graph neural networks (GNN).

The aim of this Special Issue is to stimulate discussions on the design, use, and evaluation of neural network-based machine learning in data mining for big data systems. This Special Issue will bring together academics and industrial practitioners to exchange and discuss the latest innovations and applications of these methods.

Potential topics include but are not limited to the following:

• BPNN-based particle swarm optimization in data analysis for transportation big data
• BPNN-based genetic algorithms in data processing for medical big data
• NN-based iterative learning in data control for nonlinear big data systems
• Artificial neural network (ANN)-based ensemble approaches for data visualization in big social media data
• Convolutional neural network (CNN)-based context-aware learning for data security and privacy in big data for IoT
• CNN-based long short-term memory (LSTM) for fault diagnosis in mechanical big data systems
• Novel theories and applications of neural network-based machine learning in data mining