Artificial Intelligence-Enabled Internet of Things (IoT)

Dear Colleagues,

The Internet of Things (IoT) is a technology that enables the interconnection of devices, sensors, and data across various domains and applications. However, the IoT alone cannot fully realize its potential without the integration of Artificial Intelligence (AI), which can provide the intelligence, learning, and decision-making capabilities to the IoT systems. The combination of AI and IoT is a new frontier of innovation that promises to transform various sectors, such as smart homes, smart cities, smart industries, and smart wearables.

The aim of this special issue is to solicit original and high-quality research papers that address the challenges, opportunities, and solutions for the Artificial Intelligence Enabled Internet of Things.

Prof. Dr. Liccardo Annalisa
Prof. Dr. Flora Amato
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Future Internet is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• Artificial Intelligence
• Internet of Things
• edge computing
• AI and IoT platforms
• IoT applications

Title: Exploring sequence-to-sequence models in Italian atypical speech recognition
Authors: Davide Mulfari and Massimo Villari
Affiliation: MIFT Department - University of Messina, Italy
Abstract: In the field of automatic speech recognition (ASR), this study explores the utilization of a Transformer-based sequence-to-sequence model to build a speaker-dependent isolated word recognizer for Italian speakers with speech disorders, such as dysarthria. We adopt a self-supervised learning approach, where the Wav2Vec2 ASR architecture has been fine-tuned on our private impaired speech dataset that contains a total of 59K single speech recordings collected by 191 Italian persons with a speech impairment globally. Furthermore, with the collaboration of sixteen participants with different levels of speech disorders (mild, moderate severe), quantitative experiments have been conducted to evaluate the effectiveness of the proposed approach in terms of word recognition accuracy (WRA). In the end of the paper, experimental evaluation indicates remarkable performance of our ASR system.

Title: Explainable Artificial Intelligence based-approach to enhance decision-making performance in IoT predictive maintenance.
Authors: RAJAOARISOA Lala
Affiliation: Institut Mines-Télécom Nord Europe
Abstract: To fully exploit the capacity of wind turbine systems and meet high power demands, while maintaining the desired power quality, wind farm managers run their systems for as long as possible, even 24 hours a day and 7 days a week. This operating condition, combined with its large size and the complex interactions of its many components operating at high power, means that a wind power system is frequently subject to numerous failures with critical rates. That makes also predictive maintenance more and more important, and has to be upgraded to maintain the performance of the cyber-physical system new generation. In this context, this paper introduces a hybrid approach to design a decision support tool that merges predictive capabilities (deep learning model integration) with anomaly explanations (model transparency, comprehensibility) for an effective IoT predictive maintenance tasks. In essence, the paper presents an approach that integrates a predictive maintenance model with an explicative decision-making system. The challenge is to determine the occurrence of an anomaly and give a plausible cause (or explanation) so that human operators can quickly determine what action to perform. The proposed decision support system explains the onset of degradation and its dynamic evolution based on expert knowledge and the data gathered through IoT technology and inspection reports. The approach enables overall savings of up to 10% in terms of inspection, replacement and repair costs. The methodology is applied to a wind farm dataset, provided by Energias De Portugal.