Informatics 2018 - Special Issue on Applying Machine Learning Systems for IoT Services in Industrial Informatics

Machine learning techniques are delivering a promising solution to the industry for building Internet of Things (IoT) systems and to make innovation at a rapid pace. The Open IoT cloud platform offers a framework for building large scale IoT applications relying on data gathered from a complex infrastructure of sensors and smart devices. Numerous challenges exist in implementing such a framework, one of them being to meet the IoT data and services (quality of service (QoS)) requirements on Industrial informatics based applications in terms of energy efficiency, sensing data quality, network resource consumption, and latency. The new era of convergence of machine learning techniques (supervised-unsupervised and reinforcement learning) with reference to IoT quality of data and services for Industrial applications has three main components: (a) intelligent devices, (b) intelligent system of systems, and (c) end-to-end analytics. This special issue is integrating machine learning methods, advanced data analytics optimization opportunities to bring more computer IoT data and services. Further, machine learning approaches had addressed various challenges of IoT such as anomaly detection, multivariate analysis, streaming and visualization of data.
In fact, recent literatures have addressed the inherent power of fusion between machine learning algorithms and IoT applications in industrial informatics. It can provide effective solutions for machine understanding of data (structured/semi structured), optimization problems, specifically, dealing with incomplete or inconsistent information, with limited computational capability related to Internet of Things (IoT). This special issue aims to address the machine learning techniques, recent developments in diverse IoT data, services and applications as well as theoretical studies. Besides, we can consider that machine learning re-enforcement paradigms and predictive learning algorithms are more applicable to IoT datasets, time series data from IoT devices with sensor fusion and streaming. Further, it is important to make a note that machine learning systems and optimization techniques has not been adequately investigated from the perspective of IoT data and services (Quality of Services) and its related research issues in industrial applications. Furthermore, there are many noteworthy QoS metrics (system life time, latency, quality, delay, bandwidth and throughput) that need to be addressed in the view of machine learning algorithms with relate to IoT data and services. Obviously, these challenges also create immense opportunities for researchers. For the aforementioned reasons, this special issue focuses to address comprehensive nature of machine learning and to emphasize its character in modelling, identification, optimization, prediction, forecasting, and control of future IoT systems for industrial systems. Submissions should be original, unpublished, and present in-depth fundamental research contributions either from a methodological/application perspective in understanding machine learning approaches and their capabilities in solving diverse range of problems in IoT and its real-world industrial applications.
Topics of interest include (but are not limited to):
We seek original and high quality submissions related to (but not limited to) one or more of the following topics: (Note that this special issue emphasizes "real world" applications)
-Design and Evaluation of Energy Efficient Networks and Services in IoT
-Machine-Learning and Artificial Intelligence for Traffic/Quality of Experience Management in IoT
-Hybrid Intelligent Models and Applications for IoT in Industrial applications
-Nature-Inspired Smart Hybrid Systems for IoT Context-Aware Systems
-Machine learning and Data Analytics and Decision Automation in IoT for Industry
-Knowledge-Based Discovery with Evolutionary Algorithms for QoS in IoT devices
-Fuzzy Fusion of Sensors, Data and Information
-Meta-Heuristic Algorithms for IoT and wearable Computing
-Hybrid Optimization Methods Emerging real world and theoretical applications of IoT in Industry
-Innovative Deep Learning Architectures/Algorithms for Time Series Data and IoT
-Neural network modelling, analysis and synthesis techniques in ubiquitous communications
-Multi-Objective IoT System Modelling and Analysis—Performance, Energy, Reliability, Robustness
-Modelling and simulation of large-scale IoT scenarios and IoT standardization
-Machine learning for IoT and sensor research challenges: battery of sensor, routing, prediction of nodes etc.
-Quality aspects in the IoT (e.g., runtime dependability, assurances, validation, verification, privacy, security)
-State-of-practice, experience reports, industrial experiments, and case studies in the IoT
Submission Guidelines
Original submissions of high-quality contributions are expected.
The format of all submissions should follow the specifications described in “Guide for Authors” of the Applied Soft Computing (ASOC) shown in https://www.journals.elsevier.com/applied-soft-com...
Papers will be refereed according to the procedures and standards of the journal
Please be advised that all articles for this special issue will need to be submitted via the editorial system: https://ees.elsevier.com/asoc/default.asp?pg=login...
As regards the online submission system of Computers, Environment and Urban Systems, the authors are invited to follow the link “Submit your Paper”, located in the main page of the Journal website, and submit manuscript to Article Type “SI: ML for IoT” in ASOC.
Each paper will undergo a thorough evaluation by at least two reviewers. The authors will have some time to incorporate the comments of the reviewers and submit a revised version of their papers, which will be evaluated again by the reviewers to make a final decision.
Important Dates
November 20, 2017: Deadline for paper submission
February20, 2018: Initial decision notification
April 20, 2018: Revised submissions due
June 30, 2018: Second-round decision notification
August 30, 2018: Final decision notification
Guest Editors
Dr. Xizhao Wang (Leading Guest Editor)
Shenzhen University, China
Email:xizhaowang-AT-ieee.org
Dr. Arun Kumar Sangaiah
VIT University, Vellore, India
Email:arunkumarsangaiah-AT-gmail.com
Dr. Michael Sheng
Macquarie University, Australia
Email:michael.sheng-AT-mq.edu.au
Dr. Syed Hassan Ahmed
Kyungpook National University, Republic of Korea
Email:s.h.ahmed-AT-ieee.org