Abstract
As we transition from centralized machine learning to distributed learning, new practices can significantly enhance intelligent Internet of Things (IoT) systems. This article introduces the concept of Opportunistic Distributed Learning (ODL), a general framework that enables any node in a network to initiates learning tasks by leveraging local, unused distributed resources collaboratively. ODL, facilitated by edge intelligence, promotes collective responsibility, pervasive and flexible distributed learning, allowing participating nodes to freely move, group, and regroup based on their conditions and benefits. The article discusses key research challenges of ODL in intelligent IoT systems, presents the ODL framework, proposes a reputation-based node selection scheme, and highlights the benefits and future research directions of the ODL system.

Abstract

Abstract
TADA is a unique toolkit designed to foster the use and implementation of approximate distributed agreement primitives. Developed in Java, TADA provides ready-to-use implementations of several approximate agreement algorithms, as well as the tools to enable programmers/researchers to easily implement further protocols: A template that enables new protocol implementations to be created by simply changing specific functions; and high-level abstractions for communication and concurrency control. As an example, the toolkit includes a ready-to-use implementation for clock synchronisation between distributed processes. Further use cases can include sensor input stabilisation and distributed machine learning, or other instances of distributed agreement where network synchrony cannot be assumed, byzantine fault tolerance may be required and a bounded divergence in decision values can be tolerated.

Abstract
The deep-sea environment still presents many challenges for systematic, comprehensive data acquisition. The current generation of SMART cables incorporates low-power sensors in long-range telecommunication cables to improve knowledge of ocean variables, aid in earthquake and tsunami warnings, and enhance coastal protection. The K2D Project seeks to expand SMART cables' capabilities by increasing the diversity of sensors along deep water cables, integrating active devices, and leveraging mobile platforms like deep-water AUVs, thereby improving spatial coverage and advancing ocean monitoring technology. This paper discusses a demonstration of these capabilities, focusing on the description of the main building blocks developed along the project, with results from a sea deployment in September 2023.

Abstract
Interferometric Synthetic Aperture Radar (InSAR) revolutionizes surface study by measuring precise ground surface changes. Phase unwrapping, a key challenge in InSAR, involves removing ambiguity in measured phase. Deep learning algorithms like Generative Adversarial Networks (GANs) offer a potential solution for simplifying the unwrapping process. This work evaluates GANs for InSAR phase unwrapping, replacing SNAPHU with GANs. GANs achieve significantly faster processing times (2.38 interferograms per minute compared to SNAPHU's 0.78 interferograms per minute) with minimal quality degradation. A comparison of SBAS results shows that approximately 84% of GANs points are within 3 millimeters of SNAPHU. These results represent a significant advancement in phase unwrapping methods. While this experiment does not declare a definitive winner, it demonstrates that GANs are a viable alternative in certain scenarios and may replace SNAPHU as the preferred unwrapping method. © 2024 The Author(s). Published by Elsevier B.V.

Abstract
Virtual assistants offer a new type of solution to handle interaction between human and machine and can be applied in various business contexts such as Industry or Education. When designing and building a virtual assistant the developers must ensure a set of parameters to achieve a good solution. Various platforms and frameworks emerged to allow developers to create virtual assistant solutions easier and faster. This paper provides a review of available platforms and frameworks used by authors to create their own solutions in different areas. Big tech companies like Google with Dialogflow, IBM with Watson Assistant and Microsoft with Bot Framework, present mature solutions to build virtual assistants that provide to the developer all components of the basic architecture to build a fast and solid solution. Open-Source solutions focus on providing to the developer the main components to build a virtual assistant, namely language understanding and response generation.