Machine Learning Techniques in Designing the Efficient Platforms for the Internet of Behaviors (IoB)

Dear Colleagues,

The Internet-of-Behavior (IoB) is thought to be the next generation of the Internet of Things (IoT). Its defining characteristic is the dynamic generation of behavior (prescriptions) based on detailed data analytics. As emerging technologies and their combinations, such as IoB, algorithmic decision-making, and Deep Learning (DL), become ingrained in people's lives, suitable IoB application design is increasingly crucial. An IoB emerges as a follow-up to IoT as a result of gradually linking individual activities to digital actions via various technologies. As a result, behavioral data drive the real-time behaviors of socio-technical systems, either supporting or punishing human conduct. Additionally, any platform for strengthening the competitive advantages of developing systems in improving many aspects of the quality of experiences is characterized by sustainable development. In recent years, the relevance of sustainable development has expanded dramatically for IoT-based systems. As a subfield of Machine Learning (ML) techniques, DL will soon impact nearly every aspect of our daily lives. As a result, DL is a driving force of long-term development in IoT and IoB platforms. A home healthcare support system, for example, can adapt its behavior based on sensor data obtained and trigger specific actuator activity based on algorithmic processing and data analytics. This trigger has the potential to alter human behavior, such as influencing the order in which sustainable medical products are utilized. As a result, creating IoB systems based on behavior (specifications) is a moving target and thus a pressing engineering challenge. The IoB, on the other hand, is based on the IoT and leads to dynamic adaptation and behavior formation. The development of ML applications thus appears to be necessary.

ML will enable future communication networks and apps, such as the IoB, to take advantage of big data analytics to improve situational awareness and overall network performance, in addition to intelligent network management. The combination of ML and the IoB opens the door to future efficiency gains, accuracy, sustainable productivity, and total cost savings for resource-constrained IoB devices. In the pervasive context of the sustainable IoB, ML has the potential to be a game changer. The use of ML to reveal various smart IoB applications aids in the observation, systematic analysis, processing, and smart applications of massive amounts of data across multiple domains. To fully achieve the IoB's promise, many businesses could benefit from ML, particularly ML as a service.

This Special Issue will gather peer-reviewed articles on the use of ML techniques to create efficient IoB systems. We will also look at how these technologies may be used in new ways to assist commercial and corporate applications. We invite submissions of high-quality original technical and survey papers, which have not been published previously, on artificial intelligence and ML techniques and their applications for IoB networks. Topics of interest include, but are not limited to, the following:

1. Personal health applications using ML in IoB;
2. Sustainable platforms for the Internet of Behaviors;
3. Blockchain and edge-integrated architecture for IoB-ML applications;
4. Sustainable AI-enabled blockchain for IoB;
5. IoB network management using DL methods;
6. Security and privacy concerns in integrated IoB-edge ML applications;
7. Intrusion detection systems in IoB scenarios using ML methods;
8. Improving edge computing infrastructure based on ML in IoB scenarios;
9. Advanced AI techniques for the management of dependable IoB applications;
10. Integration of smart fog-IoB architectures in 5G/6G mobile networks;
11. Sustainable Smart healthcare applications in IoB;
12. Combining ML applications with ambient computers for the IoB devices;
13. Edge computing applications using ML methods for the IoB devices;
14. Sustainable Real-time and online analysis by ML methods for IoB apps;
15. Saving computing resources for ML application with energy harvesting methods in IoB devices (Green IoB);
16. Green AI-enabled IoB;
17. Intelligent applications and services for energy-efficient IoB including automation, location tracking for tools, and predictive maintenance for maximizing uptime;
18. Using ML applications for IoB unstructured data sources;
19. Sustainable IoB offloading using DL methods;
20. Task scheduling mechanisms using DNN methods for the IoB applications;
21. Designing smart industrial applications for improving social healthcare;
22. Sustainable DL methods for interoperability of IoB systems;
23. Identification and authentication of the IoB devices and apps using ML methods for improving privacy;
24. ML applications for secure IoB device communication;
25. Integration of data from multiple sources with ML methods for the IoB devices;
26. Resources and energy management for IoB apps and devices;
27. ML, data mining, and big data analytics for IoB network;
28. ML for resource allocation in IoB networks;
29. Distributed ML for IoB communications;
30. Data-driven optimization of IoB networks;
31. IoB network problem diagnosis through ML;
32. Energy-efficient IoB network operations via AI/ML algorithms;
33. Reliability, robustness, and safety for IoB networks optimized and operated based on AI techniques;
34. Security concepts for IoB networks optimized and operated based on ML concepts;
35. ML/AI-based physical-layer methods for secrecy and privacy for 5G and the IoB;
36. Emerging technology on sustainable ML for IoB networks;
37. ML methods for network forensics, fault detection, and auto-diagnosing;
38. Advanced AI models for real/industry applications and systems for IoB;
39. Advanced AI model for a future generation the IoB applications;
40. Advanced ML/DL models for handling IoB applications and predictive analysis of big data.

Dr. Nima Jafari Navimipour
Dr. Arash Heidari
Dr. Antonino Galletta
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. Sustainability is an international peer-reviewed open access semimonthly 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 2400 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.

• Internet of things
• Internet of Behaviors
• machine learning
• deep learning
• security issues
• energy management
• green IoT