In the last years, Federated learning (FL) has become a popular solution to train machine learning models in domains with high privacy concerns. However, FL scalability and performance face significant challenges in real-world deployments where data across devices are non-independently and identically distributed (non-IID). The heterogeneity in data distribution frequently arises from spatial distribution of devices, leading to degraded model performance in the absence of proper handling. Additionally, FL typical reliance on centralized architectures introduces bottlenecks and single-point-of-failure risks, particularly problematic at scale or in dynamic environments. To close this gap, we propose Field-Based Federated Learning (FBFL), a novel approach leveraging macroprogramming and field coordination to address these limitations through: (i) distributed spatial-based leader election for personalization to mitigate non-IID data challenges; and (ii) construction of a self-organizing, hierarchical architecture using advanced macroprogramming patterns. Moreover, FBFL not only overcomes the aforementioned limitations, but also enables the development of more specialized models tailored to the specific data distribution in each subregion. This paper formalizes FBFL and evaluates it extensively using MNIST, FashionMNIST, and Extended MNIST datasets. We demonstrate that, when operating under IID data conditions, FBFL performs comparably to the widely-used FedAvg algorithm. Furthermore, in challenging non-IID scenarios, FBFL not only outperforms FedAvg but also surpasses other state-of-the-art methods, namely FedProx and Scaffold, which have been specifically designed to address non-IID data distributions. Additionally, we showcase the resilience of FBFL's self-organizing hierarchical architecture against server failures.

Federated Learning (FL) has emerged as a powerful paradigm for training machine learning models across distributed data sources while preserving data locality. However, the privacy of local data is always a pivotal concern and has received a lot of attention in recent research on the FL regime. Moreover, the lack of domain heterogeneity and client-specific segregation in the benchmarks remains a critical bottleneck for rigorous evaluation. In this paper, we introduce ModelNet, a novel image classification dataset constructed from the embeddings extracted from a pre-trained ResNet50 model. First, we modify the CI-F AR100 dataset into three client-specific variants, considering three domain heterogeneities (homogeneous, heterogeneous, and random). Subsequently, we train each client-specific subset of all three variants on the pre-trained ResNet50 model to save model parameters. In addition to multi-domain image data, we propose a new hypothesis to define the FL algorithm that can access the anonymized model parameters to preserve the local privacy in a more effective manner compared to existing ones. ModelNet is designed to simulate realistic FL settings by incorporating non-IID data distributions and client diversity design principles in the mainframe for both conventional and futuristic graph-driven FL algorithms. The three variants are ModelNet-S, ModelNet-D, and ModelNet-R, which are based on homogeneous, heterogeneous, and random data settings, respectively. To the best of our knowledge, we are the first to propose a cross-environment client-specific FL dataset along with the graph-based variant. Extensive experiments based on domain shifts and aggregation strategies show the effectiveness of the above variants, making it a practical benchmark for classical and graph-based FL research. The dataset and related code are available here11https://github.com/rayabhisek123/ModelNet

This paper presents the FactoryML framework that simplifies the deployment and integration of Machine Learning (ML) models in manufacturing factory environments. FactoryML facilitates packaging of ML models into a portable format and it facilitates the communication of deployed ML models in factory environments via Programmable Logic Controllers. In general FactoryML reduces the barrier to take learned models from a research and development side into an operational setting. The value of FactoryML has been demonstrated in a case study with a Danish company as well.

Industrial drying is one of the most energy inten-sive manufacturing processes and it is utilized across various industries, making it an ideal target for optimization. To achieve this condition based drying can be implemented, which requires knowledge of the product's internal moisture content (MC). This knowledge can be approximated through MC estimation. In this work, we frame MC estimation as a Time Series Extrinsic Regression (TSER) problem and investigate the performance of state-of-the-art TSER models. Additionally, insufficient training data is a major challenge in machine learning, especially for industrial applications, due to the prohibitively high cost of production line experiments. This acts as a barrier to the adoption of machine learning methods in industrial settings. In this work we propose a data augmentation method for TSER problems called Time Slicing. The proposed data augmentation method and TSER models are applied to a TSER dataset of industrial drying of bulky filter media products. It is shown that the TSER approach using an LSTM is able to out-perform the tabular data approach. Furthermore, it is shown that the proposed data augmentation method, when applied to the LSTM, improves its performance by 17.4% and 30.1% with regard to mean absolute error and mean squared error, respectively.

Self-aware computing systems enable computing systems to reflect on their actions and behavior. This becomes even more relevant in Cyber-Physical Systems where computing systems have to control and interact with elements in the real world. This paper reports on recent advances made in computational self-awareness for cyber-physical systems.

The development of cyber-physical systems is heavily relying on model-driven approaches. After deployment, these models can be utilised in a Digital Twin setting, acting as virtual replicas of the physical components and reflecting the behaviour of the running system in real-time. Complex systems often consist of numerous models interacting with each other and individual models may need to be updated after deployment. This means that new models need to be integrated and swapped during runtime without interrupting the running system. In this paper, we propose an approach for model-based Digital Twins to replace individual models without stopping or halting the operation of a cyber-physical system. Furthermore, our approach allows to replace not only individual models, but also update the overall structure of the interaction of models in the Digital Twin setting. The use of the proposed mechanism is illustrated through two case-studies with an agricultural robot prototype.

We focus on the online multi-object k -coverage problem (OMOkC), where mobile robots are required to sense a mobile target from k diverse points of view, coordinating themselves in a scalable and possibly decentralised way. There is active research on OMOkC, particularly in the design of decentralised algorithms for solving it. We propose a new take on the issue: Rather than classically developing new algorithms, we apply a macro-level paradigm, called aggregate computing , specifically designed to directly program the global behaviour of a whole ensemble of devices at once. To understand the potential of the application of aggregate computing to OMOkC, we extend the Alchemist simulator (supporting aggregate computing natively) with a novel toolchain component supporting the simulation of mobile robots. This way, we build a software engineering toolchain comprising language and simulation tooling for addressing OMOkC. Finally, we exercise our approach and related toolchain by introducing new algorithms for OMOkC; we show that they can be expressed concisely, reuse existing software components and perform better than the current state-of-the-art in terms of coverage over time and number of objects covered overall.

The research initiative “self-improving system integration” (SISSY) was established with the goal to master the ever-changing demands of system organisation in the presence of autonomous subsystems, evolving architectures, and highly-dynamic open environments. It aims to move integration-related decisions from design-time to run-time, implying a further shift of expertise and responsibility from human engineers to autonomous systems . This introduces a qualitative shift from existing self-adaptive and self-organising systems, moving from self-adaptation based on predefined variation types, towards more open contexts involving novel autonomous subsystems, collaborative behaviours, and emerging goals. In this article, we revisit existing SISSY research efforts and establish a corresponding terminology focusing on how SISSY relates to the broad field of integration sciences. We then investigate SISSY-related research efforts and derive a taxonomy of SISSY technology. This is concluded by establishing a research road-map for developing operational self-improving self-integrating systems.

Large pervasive systems, deployed in dynamic environments, require flexible control mechanisms to meet the demands of chaotic state changes while accomplishing system goals. As centralized control approaches may falter in environments where centralized communication and knowledge may be impossible to implement, researchers have proposed decentralized control methods that leverage agent-driven, self-organizing behaviors, to achieve reliable, flexible systems. This article presents and compares the performance of three decentralized control approaches in the online multi-object k -assignment problem. In this domain, a set of sensors is tasked to detect and track an unknown and changing set of targets. Results show that a proposed hybrid approach that incorporates supervisory devices within the population while allowing semi-autonomous operations in non-supervisory devices produces a flexible and reliable system capable of both high detection and coverage rates.

When multiple robots are required to collaborate in order to accomplish a specific task, they need to be coordinated in order to operate efficiently. To allow for scalability and robustness, we pro ...

Abstract In this article, we explore the online multiobject k ‐coverage problem in visual sensor networks. This problem combines k ‐coverage and the cooperative multirobot observation of multiple moving targets problem, and thereby captures key features of rapidly deployed camera networks, including redundancy and team‐based tracking of evasive or unpredictable targets. The benefits of using mobile cameras are demonstrated and we explore the balance of autonomy between cameras generating new subgoals, and those responders able to fulfill them. We show that higher performance against global goals is achieved when decisions are delegated to potential responders who treat subgoals as optional, rather than as obligations that override existing goals without question. This is because responders have up‐to‐date knowledge of their own state and progress toward goals where they are situated, which is typically old or incomplete at locations remote from them. Examining the extent to which approaches overprovision or underprovision coverage, we find that being well suited for achieving 1‐coverage does not imply good performance at k ‐coverage. Depending on the structure of the environment, the problems of 1‐coverage and k ‐coverage are not necessarily aligned and that there is often a trade‐off to be made between standard coverage maximization and achieving k ‐coverage.

In this article, we make the case for the new class of Self-aware Cyber-physical Systems. By bringing together the two established fields of cyber-physical systems and self-aware computing, we aim at creating systems with strongly increased yet managed autonomy, which is a main requirement for many emerging and future applications and technologies. Self-aware cyber-physical systems are situated in a physical environment and constrained in their resources, and they understand their own state and environment and, based on that understanding, are able to make decisions autonomously at runtime in a self-explanatory way. In an attempt to lay out a research agenda, we bring up and elaborate on five key challenges for future self-aware cyber-physical systems: (i) How can we build resource-sensitive yet self-aware systems? (ii) How to acknowledge situatedness and subjectivity? (iii) What are effective infrastructures for implementing self-awareness processes? (iv) How can we verify self-aware cyber-physical systems and, in particular, which guarantees can we give? (v) What novel development processes will be required to engineer self-aware cyber-physical systems? We review each of these challenges in some detail and emphasize that addressing all of them requires the system to make a comprehensive assessment of the situation and a continual introspection of its own state to sensibly balance diverse requirements, constraints, short-term and long-term objectives. Throughout, we draw on three examples of cyber-physical systems that may benefit from self-awareness: a multi-processor system-on-chip, a Mars rover, and an implanted insulin pump. These three very different systems nevertheless have similar characteristics: limited resources, complex unforeseeable environmental dynamics, high expectations on their reliability, and substantial levels of risk associated with malfunctioning. Using these examples, we discuss the potential role of self-awareness in both highly complex and rather more simple systems, and as a main conclusion we highlight the need for research on above listed topics.

Cyber-physical systems operate in our real world, constantly interacting with the environment and collaborating with other systems. The increasing number of devices will make it infeasible to control each one individually. It will also be infeasible to prepare each of them for every imaginable rapidly unfolding situation. Therefore, we must increase the autonomy of future Cyber-physical Systems. Making these systems self-aware allows them to reason about their own capabilities and their immediate environment. In this article, we extend the idea of the self-awareness of individual systems toward networked self-awareness . This gives systems the ability to reason about how they are being affected by the actions and interactions of others within their perceived environment, as well as in the extended environment that is beyond their direct perception. We propose that different levels of networked self-awareness can develop over time in systems as they do in humans. Furthermore, we propose that this could have the same benefits for networks of systems that it has had for communities of humans, increasing performance and adaptability.

The Internet-of-Things (IoT) becomes more and more pervasive and supports us in our daily activities. However, when individual devices struggle in accomplishing certain tasks, they have to cooperate in order to achieve desired outcomes. In the absence of a central controller, devices have to coordinate autonomously within the network in order to attain and complete as many tasks as possible. We propose CHAINMAIL, a novel, distributed approach to coordinate sensors to attain tasks that cannot be accomplished by single, but only by cooperation of multiple devices. We demonstrate our approach with an IoT case study on multi-object k-coverage with autonomously operating mobile cameras and show that our approach does not over-provision tasks, allowing the remaining devices to attain other duties. This enables our network to provision more tasks in the same time as other comparable solutions.

Future Internet of Things (IoT) applications will face challenges in increased flexibility, uncertainty, dynamics and scalability. Self-aware computing maintains knowledge about the applications state and environment and then uses this knowledge to reason about and adapt behaviours. In this position paper, we introduce self-aware computing as design approach for IoT applications which is centred around a self-aware architecture for IoT nodes. This architecture particularly supports adaptations based on node interactions. We demonstrate our approach with an IoT case study on multi-object coverage with mobile cameras.

There is a clear trend in camera networks toward enhanced functionality and flexibility, and a fixed static deployment is typically not sufficient to fulfill these increased requirements. Dynamic network reconfiguration helps to optimize the network performance to the currently required specific tasks while considering the available resources. Although several reconfiguration methods have been recently proposed, e.g., for maximizing the global scene coverage or maximizing the image quality of specific targets, there is a lack of a general framework highlighting the key components shared by all these systems. In this paper, we propose a reference framework for network reconfiguration and present a short survey of some of the most relevant state-of-the-art works in this field, showing how they can be reformulated in our framework. Finally, we discuss the main open research challenges in camera network reconfiguration.

We study heterogeneity among nodes in self-organizing smart camera networks, which use strategies based on social and economic knowledge to target communication activity efficiently. We compare homogeneous configurations, when cameras use the same strategy, with heterogeneous configurations, when cameras use different strategies. Our first contribution is to establish that static heterogeneity leads to new outcomes that are more efficient than those possible with homogeneity. Next, two forms of dynamic heterogeneity are investigated: nonadaptive mixed strategies and adaptive strategies, which learn online. Our second contribution is to show that mixed strategies offer Pareto efficiency consistently comparable with the most efficient static heterogeneous configurations. Since the particular configuration required for high Pareto efficiency in a scenario will not be known in advance, our third contribution is to show how decentralized online learning can lead to more efficient outcomes than the homogeneous case. In some cases, outcomes from online learning were more efficient than all other evaluated configuration types. Our fourth contribution is to show that online learning typically leads to outcomes more evenly spread over the objective space. Our results provide insight into the relationship between static, dynamic, and adaptive heterogeneity, suggesting that all have a key role in achieving efficient self-organization.

To solve multi-objective problems, multiple reward signals are often scalarized into a single value and further processed using established single-objective problem solving techniques. While the field of multi-objective optimization has made many advances in applying scalarization techniques to obtain good solution trade-offs, the utility of applying these techniques in the multi-objective multi-agent learning domain has not yet been thoroughly investigated. Agents learn the value of their decisions by linearly scalarizing their reward signals at the local level, while acceptable system wide behaviour results. However, the non-linear relationship between weighting parameters of the scalarization function and the learned policy makes the discovery of system wide trade-offs time consuming. Our first contribution is a thorough analysis of well known scalarization schemes within the multi-objective multi-agent reinforcement learning setup. The analysed approaches intelligently explore the weight-space in order to find a wider range of system trade-offs. In our second contribution, we propose a novel adaptive weight algorithm which interacts with the underlying local multi-objective solvers and allows for a better coverage of the Pareto front. Our third contribution is the experimental validation of our approach by learning bi-objective policies in self-organising smart camera networks. We note that our algorithm (i) explores the objective space faster on many problem instances, (ii) obtained solutions that exhibit a larger hypervolume, while (iii) acquiring a greater spread in the objective space.

In this article we present an approach to object tracking handover in a network of smart cameras, based on self-interested autonomous agents, which exchange responsibility for tracking objects in a market mechanism, in order to maximise their own utility. A novel ant-colony inspired mechanism is used to learn the vision graph, that is, the camera neighbourhood relations, during runtime, which may then be used to optimise communication between cameras. The key benefits of our completely decentralised approach are on the one hand generating the vision graph online, enabling efficient deployment in unknown scenarios and camera network topologies, and on the other hand relying only on local information, increasing the robustness of the system. Since our market-based approach does not rely on a priori topology information, the need for any multicamera calibration can be avoided. We have evaluated our approach both in a simulation study and in network of real distributed smart cameras.