The emergence of Tiny Machine Learning (TinyML) has positively revolutionized the field of Artificial Intelligence by promoting the joint design of resource-constrained IoT hardware devices and their learning-based software architectures. TinyML carries an essential role within the fourth and fifth industrial revolutions in helping societies, economies, and individuals employ effective AI-infused computing technologies (e.g., smart cities, automotive, and medical robotics). Given its multidisciplinary nature, the field of TinyML has been approached from many different angles: this comprehensive survey wishes to provide an up-to-date overview focused on all the learning algorithms within TinyML-based solutions. The survey is based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodological flow, allowing for a systematic and complete literature survey. In particular, firstly, we will examine the three different workflows for implementing a TinyML-based system, i.e., ML-oriented, HW-oriented, and co-design. Secondly, we propose a taxonomy that covers the learning panorama under the TinyML lens, examining in detail the different families of model optimization and design, as well as the state-of-the-art learning techniques. Thirdly, this survey will present the distinct features of hardware devices and software tools that represent the current state-of-the-art for TinyML intelligent edge applications. Finally, we discuss the challenges and future directions.

With the advent of Industrial 4.0 and the push toward Industry 5.0, the data generated by the industries have become surprisingly large. This abundance of data significantly boosts machine and deep learning models for Predictive Maintenance (PdM). The PdM plays a vital role in extending the lifespan of industrial equipment and machines while also helping to reduce the risk of unscheduled downtime. Given its multidisciplinary nature, the field of PdM has been approached from many different angles: this comprehensive survey aims at providing an up-to-date overview focused on all the learning-based industrial PdM strategies, discussing weaknesses and strengths. The survey is based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodological flow, allowing a systematic and complete review of the literature. In particular, firstly, we explore the main learning models used for PdM, mainly Convolutional Neural Networks (ConvNets), Autoencoders (AEs), Generative Adversarial Networks (GANs), and Transformers, also giving an overview of the newest models such as diffusion models and foundation models. Then, we discuss the main learning paradigms applied to PdM, i.e., supervised, unsupervised, ensemble, transfer, federated, and reinforcement learning. Furthermore, this work discusses the pipeline of the data-driven PdM and its benefits, practical applications, datasets, and benchmarks. In addition, the evaluation metrics for each PdM stage and the state-of-the-art hardware devices used are discussed. Finally, the challenges and future work are presented.

The revolutionary technologies behind Industry 4.0 have opened a new era for manufacturing: connected and autonomous machines, collaborative robotics, and monitoring techniques are spreading to increase productivity and sustainability. From the workers’ perspective, they bring new safety threats but also opportunities to solve old ones, while concerns about workers’ privacy arise due to the increase of data sensed and transferred from the shop floor. This paper presents the results of a research project addressing the prediction of dangerous conditions through workplace monitoring with privacy guarantees. This work is driven by a realistic approach starting from the fact that it is entirely centered on a real 14-meter production line equipped with an extensive array of top-tier devices, including robotic arms, autonomous mobile robots, a reconfigurable moving belt, a multi-camera system, and a highly efficient data transport and computation infrastructure. This project shows safety and privacy achievements over six representative use cases such as man-on-the-ground, environmental events (e.g., fire incidents), workers’ errors that can lead to potential accidents, compliance of Personal Protective Equipment (PPE), and gatherings restrictions. The benefits of this study extend to stakeholders such as manufacturers and workers offering safety systems that can be deployed in industrial settings while addressing privacy concerns and providing compliance with regulations. The industrial laboratory at the heart of this study represents with realism a dynamic and interconnected Industry 4.0 and 5.0 environment.

Split Computing (SC), where a Deep Neural Network (DNN) is intelligently split with a part of it deployed on an edge device and the rest on a remote server is emerging as a promising approach. It allows the power of DNNs to be leveraged for latency-sensitive applications that do not allow the entire DNN to be deployed remotely, while not having sufficient computation bandwidth available locally. In many such embedded systems scenarios, such as those in the automotive domain, computational resource constraints also necessitate Multi-Task Learning (MTL), where the same DNN is used for multiple inference tasks instead of having dedicated DNNs for each task, which would need more computing bandwidth. However, how to partition such a multi-tasking DNN to be deployed within a SC framework has not been sufficiently studied. This paper studies this problem, and MTL-Split, our novel proposed architecture, shows encouraging results on both synthetic and real-world data. The source code is available at https://github.com/intelligolabs/MTL-Split.