Data Stream Mining and Soft Computing Applications

in Special Issue   Posted on December 27, 2016 

Information for the Special Issue

Submission Deadline: Tue 31 Jan 2017
Journal Impact Factor : 5.472
Journal Name : Applied Soft Computing
Journal Publisher:
Website for the Special Issue:
Journal & Submission Website:

Special Issue Call for Papers:

In current industrial systems, the necessity of data stream mining and learning from data streams is increasingly becoming more prevalent and urgent, due to speed, volume and on-line nature of the data generated by such systems. While conventional batch and off-line training approaches provide a possible solution, such approaches are often too time and memory intensive, and cannot process the data at the high enough rate that is often desired. This is true even when batch and off-line approaches are applied to sliding windows or onto streaming samples gathered from reservoir computing techniques.

An important aspect in data stream mining is that the data analysis system, the learner, has no control over the order of samples that arrive over time — they simply arrive in the same order they are acquired and recorded. Also, the learning algorithms usually have to be fast enough in order to cope with real-time and on-line demands. This usually requires a single-pass learning procedure, restricting the algorithm to update models and statistical information in a sample-wise manner, without using any prior data. In literature, this is also termed as incremental or sequential learning and plays a key role in data stream mining frameworks and environments. Practical real-world applications of evolving models include – and are not limited to – on-line quality control of production items, supervision and failure analysis of dynamically changing machine states, decision support systems in medicine, engine control, prediction and quantification in very dynamic production processes, welding processes, user profiling in various applications, forecasting, and internet, among many others.

This special issue intends to draw a picture of the recent advances in data stream mining techniques including all incremental machine learning concepts and evolving soft computing modeling strategies for addressing these important problems discussed above. Finally, all emerging and grand-challenge problems, topics such as interpretability aspects in evolving models, and mimicking intelligent brain – even if at a limited scale – are of particular interest to this special issue. Computational aspects such as real-time capability of the learning methods play central roles within all these issues.


Original contributions are solicited from, but are not limited, the following topics of interest:

Advanced Aspects for Improved Stability, Performance and Usability (but not necessarily restr. to):
New Algorithms, Concepts in Data Stream Mining with Soft Computing Techniques (for supervised regression, classification and unsupervised learning)
New Algorithms, Concepts in Mining with Machine Learning Concepts(for supervised regression, classification and unsupervised learning)
Concepts to address drifts and shifts in Data Streams
On-line single-pass active learning from Data Streams
Semi-supervised learning from Data Streams
Dynamic dimension reduction and feature selection in Streams
Reliability in model predictions and parameters
Stability, process-safety and computational related aspects
Concepts to address linguistic interpretability
Concepts to address visual interpretability (model development over time)
Online tuning via human-machine interaction
Complexity reduction and interpretability issues in evolving models
Incremental and evolving methods for multi-label classification problems
On-line ensembling and fusioning methods for improved model output robustness
Concepts to address dynamic splitting of model components on the fly
Real-World Applications of evolving soft computing techniques such as (but not necessarily restricted to):
Data stream modelling and identification
Online fault detection and decision support systems
Online media stream classification
Process control and condition monitoring
Modeling in high throughput production systems
Web applications
Adaptive chemometric models in dynamic chemical processes
Online time series analysis and stock market forecasting
Robotics, Intelligent Transport and Advanced Manufacturing
Adaptive Evolving Controller Design
User Activities Recognition
Cloud Computing
Multiple Sensor Networks
Big Data

Closed Special Issues