Recent advances in Tiny Machine Learning (TinyML) empower low-footprint embedded devices for real-time on-device Machine Learning (ML). While many acknowledge the potential benefits of TinyML, its practical implementation presents unique challenges. This study aims to bridge the gap between prototyping single TinyML models and developing reliable TinyML systems in production: (1) Embedded devices operate in dynamically changing conditions. Existing TinyML solutions primarily focus on inference, with models trained offline on powerful machines and deployed as static objects. However, static models may underperform in the real world due to evolving input data distributions. We propose online learning to enable training on constrained devices, adapting local models toward the latest field conditions. (2) Nevertheless, current on-device learning methods struggle with heterogeneous deployment conditions and the scarcity of labeled data when applied across numerous devices. We introduce federated meta-learning incorporating online learning to enhance model generalization, facilitating rapid learning. This approach ensures optimal performance among distributed devices by knowledge sharing. (3) Moreover, TinyML’s pivotal advantage is widespread adoption. Embedded devices and TinyML models prioritize extreme efficiency, leading to diverse characteristics ranging from memory and sensors to model architectures. Given their diversity and non-standardized representations, managing these resources becomes challenging as TinyML systems scale up. We present semantic management for the joint management of models and devices at scale. We demonstrate our methods through a basic regression example and then assess them in three real-world TinyML applications: handwritten character image classification, keyword audio classification, and smart building presence detection. The results confirm the effectiveness of our approaches from various perspectives, such as accuracy improvement, resource savings, and engineering effort reduction.

Tiny machine learning (TinyML) is a rapidly growing field aiming to democratize machine learning (ML) for resource-constrained microcontrollers (MCUs). Given the pervasiveness of these tiny devices, it is inherent to ask whether TinyML applications can benefit from aggregating their knowledge. Federated learning (FL) enables decentralized agents to jointly learn a global model without sharing sensitive local data. However, a common global model may not work for all devices due to the complexity of the actual deployment environment and the heterogeneity of the data available on each device. In addition, the deployment of TinyML hardware has significant computational and communication constraints, which traditional ML fails to address. Considering these challenges, we propose TinyReptile, a simple but efficient algorithm inspired by meta-learning and online learning, to collaboratively learn a solid initialization for a neural network (NN) across tiny devices that can be quickly adapted to a new device with respect to its data. We demonstrate TinyReptile on Raspberry Pi 4 and Cortex-M4 MCU with only 256-KB RAM. The evaluations on various TinyML use cases confirm a resource reduction and training time saving by at least two factors compared with baseline algorithms with comparable performance.

The Internet of Things (IoT) is revolutionizing the industry. Powered by pervasive embedded devices, the Industrial IoT (IIoT) provides a unique solution for retrieving and analyzing data near the source in real-time. Many emerging techniques, such as Tiny Machine Learning (TinyML) and Complex Event Processing (CEP) , are actively being developed to support decision making at the edge, shifting the paradigm from centralized processing to distributed computing. However, distributed computing presents management challenges, as IoT devices are diverse and constrained, and their number is growing exponentially. The situation is even more challenging when various on-device applications (so-called artifacts) are deployed across decentralized IoT networks. Questions to be addressed include how to discover an appropriate function, whether that function can be executed on a certain device, and how to orchestrate a cross-platform service. To tackle these challenges, we propose an approach for the scalable management of on-device applications among distributed IoT devices. By leveraging the W3C Web of Things (WoT) , the capabilities of each IoT device, or more precisely, its interaction patterns, can be semantically expressed in a Thing Description (TD) . In addition, we introduce semantic modeling of on-device applications to supplement an TD with additional information regarding applications on the device. Specifically, we demonstrate two examples of semantic modeling: neural networks (NN) and CEP rules. The ontologies are evaluated by answering a set of competency questions. By hosting the enriched semantic knowledge of the entire IoT system in a Knowledge Graph (KG) , we can discover and interoperate edge devices and artifacts across the decentralized network. This can reduce fragmentation and increase the reusability of IoT components. We demonstrate the feasibility of our concept on an industrial workstation consisting of a conveyor belt and several IoT devices. Finally, the requirements for constructing an IoT semantic management system are discussed.

Tiny machine learning (TinyML) is a fast-growing research area committed to democratizing deep learning for all-pervasive microcontrollers (MCUs). Challenged by the constraints on power, memory, and computation, TinyML has achieved significant advancement in the last few years. However, the current TinyML solutions are based on batch/offline setting and support only the neural network's inference on MCUs. The neural network is first trained using a large amount of pre-collected data on a powerful machine and then flashed to MCUs. This results in a static model, hard to adapt to new data, and impossible to adjust for different scenarios, which impedes the flexibility of the Internet of Things (IoT). To address these problems, we propose a novel system called TinyOL (TinyML with Online-Learning), which enables incremental on-device training on streaming data. TinyOL is based on the concept of online learning and is suitable for constrained IoT devices. We experiment TinyOL under supervised and unsupervised setups using an autoencoder neural network. Finally, we report the performance of the proposed solution and show its effectiveness and feasibility.

Interoperability stands for the capacity of a system to interact with the units of another entity. Although it is quite easy to accomplish this within the products of the same brand, it is not facile to provide compatibility for the whole spectrum of the Internet-of-Things (IoT) and the Linked Data (LD) world. Currently, the different applications and devices operate in their own cloud/platform, without supporting sufficient interaction with different vendor-products. As it concerns the meaning of data, which is the main focus of this paper, semantics can settle commonly agreed information models and ontologies for the used terms. However, as there are several ontologies for describing each distinct 'Thing', we need Semantic Mediators (SMs) in order to perform common data mapping across the various utilized formats (i.e. XML or JSON) and ontology alignment (e.g. resolve conflicts). Our goal is to enable end-to-end vertical compatibility and horizontal cooperation at all levels (field/network/backend). Moreover, the implication of security must be taken into consideration as the unsafe adoption of semantic technologies exposes the linking data and the user's privacy, issues that are neglected by the majority of the semantic-web studies. A motivating example of smart sensing is described along with a preliminary implementation on real heterogeneous devices. Two different IoT platforms are integrating in the case study, detailing the main SM features. The proposed setting is secure, scalable, and the overall overhead is sufficient for runtime operation, while providing significant advances over state-of-the-art solutions.

Streams of events appear increasingly today in various Web applications such as blogs, feeds, sensor data streams, geospatial information, on-line financial data, etc. Event Processing (EP) is concerned with timely detection of compound events within streams of simple events. State-of-the-art EP provides on-the-fly analysis of event streams, but cannot combine streams with background knowledge and cannot perform reasoning tasks. On the other hand, semantic tools can effectively handle background knowledge and perform reasoning thereon, but cannot deal with rapidly changing data provided by event streams.