Special lssues
Table of Content

Trends in Machine Learning and Internet of Things for Industrial Applications

Submission Deadline: 05 October 2023 (closed)

Guest Editors

Prof. Ruben Gonzalez Crespo, Universidad Internacional de la Rioja (UNIR), Spain.
Dr. Oscar Sanjuán Martínez, LUMEN TECHONOLOGIES, USA.
Dr. J. Javier Rainer Granados, Universidad Internacional de La Rioja (UNIR), Spain.

Summary

Intelligent Internet-of-Things (IoT) will transform artificial intelligence and high dimensional data analysis, by means of shifting from “connected things” to “collective intelligence”.


The recent advancements in artificial intelligence AI; machine learning ML and big data, with a variety of algorithms and platforms, have started to transform conventional software applications into a set of smart and interconnected components that base decision on data capturing, sensing and filtering, proactive collaboration and the integration of federated devices. Deep machine learning and networks components are becoming the backbone of current tendencies such as cyber-physical systems (CPS). Likewise, intelligent integrations and collaborations of smart devices along with their outstanding data collection capabilities are a perfect application domain for such sophisticated learning algorithms. The usefulness of smart and connected mobile devices governed by software utilities has already been demonstrated in several industrial application domains such as healthcare, agriculture and farming, manufacturing, smart buildings, transportation, energy, and environmental surveillance monitoring systems. While these IoT-based systems can capture a good amount of data, the usage of these valuable along with hard-to-produce data are not being fully utilized. ML enables exploring this data in further detail and capturing the hidden relationships that exist among their key factors and parameters, thus providing further insight into the underlying application domains. Furthermore, ML and IoT can be extended for addressing other challenging and unsolved problem such as real time optimization problems, modeling non-linear characteristics of IoT devices and components, and better prediction and classification algorithms.


This Special Issue aims to move forward the state-of-the-art of ML for industrial IoT and to promote innovative applications, methodologies, and trends in research and real-world applications. It seeks to find new uses of ML and IoT, including reinforcement learning scenarios, convolutional and recurrent deep neural networks, the capture of real features and the modeling the behavior of intelligent software and hardware systems.


Keywords

Probable themes include, but are not limited to:
• Modeling IoT systems using ML
• Attention-based approaches to capture significant features in IoT
• Deep learning-based modeling and experience in IoT-based applications such as smart building, healthcare, agriculture, manufacturing, and left-driving cars
• AI technologies for Industry 4.0
• Human–robot interactions
• Cooperative robots
• Mobile applications using ML and IoT for the industry
• Reinforcement learning for modeling decision-making and uncertainty in IoT.

Published Papers


  • Open Access

    ARTICLE

    Bearing Fault Diagnosis with DDCNN Based on Intelligent Feature Fusion Strategy in Strong Noise

    Chaoqian He, Runfang Hao, Kun Yang, Zhongyun Yuan, Shengbo Sang, Xiaorui Wang
    CMC-Computers, Materials & Continua, Vol.77, No.3, pp. 3423-3442, 2023, DOI:10.32604/cmc.2023.045718
    (This article belongs to this Special Issue: Trends in Machine Learning and Internet of Things for Industrial Applications)
    Abstract Intelligent fault diagnosis in modern mechanical equipment maintenance is increasingly adopting deep learning technology. However, conventional bearing fault diagnosis models often suffer from low accuracy and unstable performance in noisy environments due to their reliance on a single input data. Therefore, this paper proposes a dual-channel convolutional neural network (DDCNN) model that leverages dual data inputs. The DDCNN model introduces two key improvements. Firstly, one of the channels substitutes its convolution with a larger kernel, simplifying the structure while addressing the lack of global information and shallow features. Secondly, the feature layer combines data from different sensors based on their… More >

  • Open Access

    ARTICLE

    Approach to Simplify the Development of IoT Systems that Interconnect Embedded Devices Using a Single Program

    Enol Matilla Blanco, Jordán Pascual Espada, Rubén Gonzalez Crespo
    CMC-Computers, Materials & Continua, Vol.77, No.2, pp. 2463-2480, 2023, DOI:10.32604/cmc.2023.042793
    (This article belongs to this Special Issue: Trends in Machine Learning and Internet of Things for Industrial Applications)
    Abstract Many Internet of Things (IoT) systems are based on the intercommunication among different devices and centralized systems. Nowadays, there are several commercial and research platforms available to simplify the creation of such IoT systems. However, developing these systems can often be a tedious task. To address this challenge, a proposed solution involves the implementation of a unified program or script that encompasses the entire system, including IoT devices functionality. This approach is based on an abstraction, integrating the control of the devices in a single program through a programmable object. Subsequently, the proposal processes the unified script to generate the… More >

Share Link