With the rapid digital transformation of manufacturing, vast amounts of data are being generated and analyzed to uncover valuable patterns in areas such as energy efficiency, predictive maintenance, production scheduling etc. However, much of this data and the intelligence derived from it remain isolated within individual companies. This is strongly influenced by companies reluctance to share data due to concerns over privacy and security associated with the commercially sensitive information. Asa result, the potential shared value that can be derived from a richer, larger pool of data and intelligence across multiple companies remains untapped. While solutions such as federated learning exist to address privacy and security issues, strong governance so that the privacy is preserved is crucial to its successful implementation. Currently, there is a lack of software infrastructure that guarantees data sovereignty and governance for data owners in this space. This paper introduces COllaboRative Data Space (CORDS), a framework that enables companies to engage in a machine learning model-sharing ecosystem, providing full control over the access and usage of their data. Aligned with the European Data Space initiative, CORDS aims to foster trusted collaboration by providing a software infrastructure constituting a set of tools for both intra and inter-organization data asset management and ML model exchange. To the best of our knowledge, CORDS is the first minimum viable data space (MUDS) designed to address the broader challenges of sovereignty, interoperability, compliance & governance in cross-party ML model sharing. This paper also highlights the value of data sharing by applying CORDS to a use-case focused on improving energy efficiency in manufacturing. Extensive performance evaluation showcases CORDS' utility in securely managing data assets and facilitating machine learning model exchanges. CORDS is available as open-source software, supporting further research and practical applications of trusted data spaces in both academia and industry.

Recent developments in Distributed Ledger Technology (DLT), including Blockchain offer new opportunities in the manufacturing domain, by providing mechanisms to automate trust services (digital identity, trusted interactions, and auditable transactions) and when combined with other advanced digital technologies (e.g. machine learning) can provide a secure backbone for trusted data flows between independent entities. This paper presents an DLT-based architectural pattern and technology solution known as SmartQC that aims to provide an extensible and flexible approach to integrating DLT technology into existing workflows and processes. SmartQC offers an opportunity to make processes more time efficient, reliable, and robust by providing two key features i) data integrity through immutable ledgers and ii) automation of business workflows leveraging smart contracts. The paper will present the system architecture, extensible data model and the application of SmartQC in the context of example smart manufacturing applications.

The centralised nature of the current Internet i.e., Web 2.0, brings data privacy and security issues to the fore as critical barriers to the realisation of the digital economy. Due to such issues, it is difficult for data-driven services such as ‘ML-as-a-service’ to prosper under the umbrella of Web 2.0. Therefore, it is important to explore the platform utilities Web 3.0 can provide to support such services as they require to be executed and served in a highly distributed manner. This paper envisages an ML model marketplace for Industrial IoT applications exploiting next-generation IIoT components. A theoretical analysis of the ML economy and the technical components required to realize this marketplace are presented in this paper along with the specification of key open research questions.

Traditional federated learning (FL) adopts a client-server architecture where FL clients (e.g., IoT edge devices) train a common global model with the help of a centralized orchestrator (cloud server). However, current approaches are moving away from centralized orchestration toward a decentralized one in order to fully adapt FL for a cross-silo configuration with multiple organizations acting as clients. State-of-the-art decentralized FL mechanisms make at least one of the following assumptions: 1) clients are trusted organizations and cannot inject low-quality model updates for aggregation and 2) client local models can be shared with other clients or a third party for verification of low-quality updates. This article proposes a Blockchain-based decentralized framework for scenarios where participatory organizations are believed to be fully capable of injecting low-quality model updates as they are not willing to expose their local models to any other entity for verification purpose. The proposed decentralized FL framework adopts a novel hierarchical network of aggregators with the ability to punish/reward organizations in proportion to their local model quality updates. The framework is flexible and unlike state-of-the-art solutions, prevents a single entity from possessing the aggregated model in any FL round of training. The proposed framework is tested with respect to off-chain and on-chain performance in two Industry 4.0 use cases: 1) predictive maintenance and 2) product visual inspection. A comparative evaluation against the state-of-the-art reveals the proposed framework’s utility in terms of minimizing model convergence time and latency while maximizing accuracy and throughput.

This paper presents a decentralized district energy management platform leveraging permissioned Blockchain, Smart Contracts, IoT, and Cloud Computing. This platform facilitates digitizing assets and data in a decentralized energy ecosystem in a trusted manner without a central point of authority, enabling the implementation of distributed applications to create new value-added services. As part of the distributed application design, this paper investigates Blockchain integration and trust aspects. Different Blockchain configurations are deployed and analyzed under real-world operating conditions, using a Blockchain network based on the Hyperledger Fabric framework. Our analysis shows that the platform can handle up to 150 transactions per second with a 0.5 second latency under the baseline configurations provided. The paper further investigates strategies to improve scalability to meet future application requirements.

The EU data strategy postulates that by 2025 there will be a paradigm shift towards more decentralized intelligence and data processing at the edge. The convergence of a large number of nodes at the IoT edge along with multiple service providers and network operators exposes data owners and resource providers to potential threats. To address cloud-edge risks, trust-based decentralized management is needed. Blockchain technology has created an opportunity to decentralize IoT ecosystems, through its intrinsic properties and together with machine learning (ML) it can be used to provide a trusted backbone for managing IoT ecosystems to support automated and adaptive trust management. This paper presents a novel approach for crosslayer intelligent trust computation modelling leveraging ML and Blockchain for decentralized trust management in IoT ecosystems. The effectiveness of the proposed approach for flow-based trust assessment is demonstrated using the Hyperledger Framework and the Cooja-based simulation environment. Finally, an initial evaluation is presented to understand the performance in terms of scalability and trust convergence of the proposed model.

An IoT eco-system includes IoT network components, network services and network participants such as organizations, consumers, governments, and businesses. Due to its diversity and scale, trustworthiness is a critical concern to be considered during architectural design and the operational phase of these eco-systems. To do this, security, privacy, reliability, resilience and safety must be assured. However, existing solutions partially address these requirements using centralized approaches that come with challenges such as a single point of failure, scalability, and dependence on a third party. In this context, Distributed Ledger Technology (DLT) and Smart Contracts, due to its intrinsic properties of transparency, immutability, and underlying secure-by-design architecture, allows distributed, decentralized, automated workflows, which can be incorporated to automate the management of the next generation IoT networks. In this paper, we propose a framework for IoT eco-systems providing seamless integration between IoT and DLT to create a decentralized trusted architecture, which ensures trustworthiness of IoT eco-systems at design time and a trust reputation model based on the architecture to protect it during the run-time. Furthermore, we have presented the initial steps towards the implementation of this framework.

The human-elephant conflict is causing significant damages to the life of human and elephants in Sri Lanka. Minimizing encounters between humans and elephants is hence crucial in alleviating the human-elephant conflict. We have earlier introduced Eloc, a cost-effective localization system that is based on infrasonic emissions from wild elephants. One of the remaining challenges is a resource-efficient method to detect the elephants' infrasonic emissions. We present our efforts on devising a support vector machine (SVM) that is able to detect elephant rumbles on Eloc nodes.

A significant number of human and elephant lives have been lost due to the human-elephant conflict in Sri Lanka. To save lives of humans and elephants, it is therefore important to minimize encounters between them. In this paper, we present Eloc, a system that detects the presence of elephants using their infrasonic emissions near human habitats and then localize their positions. The high cost of infrasonic detectors is an important challenge to the real-world deployment of such localization systems, in particular in developing countries where the human-elephant conflict occurs. In order to address this problem, we design a low cost infrasonic detector that can be easily built using commodity off-the-shelf hardware. We present promising results in localizing an artificial infrasonic source and real-world experiments that suggest that we can localize free ranging elephants in the wild using this low cost infrasonic detector with an accuracy of around 10 m at distances of several hundred meters.

The human-elephant conflict is affecting the day-to-day life of villagers and farmers of rural Sri Lanka. To protect humans from elephants, reliable mechanisms to identify the presence of wild elephants around human habitats are necessary. In this work, we present the design and preliminary results of our elephant localization system that is based on infrasonic emissions from wild elephants.