Federated Learning (FL) enables decentralized learning while preserving data privacy. However, ensuring security and optimizing resource utilization in FL remains challenging, particularly in untrusted environments. To address this, we propose SecureFedPROM, a novel zero-trust FL framework that integrates Attribute-Based Access Control (ABAC) for secure client authorization and Preference Ranking Organization Method for Enrichment of Evaluations (PROMETHEE) for dynamic, multi-criteria client selection. Unlike traditional FL client selection methods that prioritize security or efficiency, SecureFedPROM optimizes trustworthiness, computational efficiency, and performance, ensuring robust participation in each training round. We evaluate SecureFedPROM across multiple real-world datasets, demonstrating its superiority over state-of-the-art client selection protocols. Our results show that SecureFedPROM achieves a 7.19% improvement in model accuracy, accelerates convergence, and reduces the number of training rounds. Additionally, it minimizes wall-clock time and computational overhead, making it highly scalable for edge AI environments. These findings highlight the importance of integrating zero-trust security principles with multi-criteria decision-making to enhance security and efficiency in FL.

With the advent of Industry 4.0 (I4.0) leading to the proliferation of industrial process data, deep learning (DL) techniques have become instrumental in developing intelligent fault diagnosis (FD) applications. However, despite their potentially superior process monitoring capabilities, DL-based FD models are poorly calibrated and generate point estimate predictions without the associated uncertainty estimates. For DL-based FD models, accurate predictive uncertainty estimates from well-calibrated models are essential in ensuring industrial process safety and reliability. This article proposes ensemble-to-distribution (E2D), an uncertainty-aware combination method for quality monitoring FD based on an ensemble of deep neural networks. First, E2D addresses safety by providing accurate uncertainty estimates on model predictions, enabling informed decision-making to minimize operational risks. Second, E2D improves model performance on out-of-distribution detection tasks to facilitate deployments in the real world. Third, E2D is a post hoc application, implementable at inference time, and compatible with diverse pretrained models. Finally, to demonstrate the effectiveness of E2D, we explore the problem of monitoring the stability of industrial processes and product quality using case studies on the steel plates faults and APS failure at Scania trucks datasets.

Invariable of the agriculture type (precision, smart, or digital), the monitoring process of factors that increase the crop yield and growth is mostly non-ML, manually structured approaches with practical pain points. In this scenario, to reduce monitoring costs and maintenance efforts, there is a requirement for low-cost semi-autonomous distributed systems that can remotely collect plant data and perform standalone ML-based analytics without depending on cloud servers or the internet. In this work, we provide an embedded ML pipeline, which users can use/follow for end-to-end solution design and implementation for any of their use-cases. To demonstrate the pipeline, we use it to collect image data, train a CNN-based regression algorithm, perform hardware-specific tuning, generate optimized code, and deploy binaries on Sony Spresense setup. The initial testing shows that even the resource-constrained MCU-based Spresense, in real-time (992 ms), high performance (96.2% accuracy, 1.86 cm2RMSE), could analyze a plant in a semi-autonomous environment to predict the leaf area and plant growth.

The majority of IoT edge devices are embedded systems with a tiny microcontroller unit (MCU), which acts as its brain. When users want their edge devices to continuously improve for better edge-analytics results, there is a need to equip their devices with algorithms that can learn/train from the continuously evolving real-world data. Currently, such devices are not capable of executing any machine learning (ML)-based model training tasks due to their resource constraints such as: limited memory (SRAM, Flash, and EEPROM), low operations per second, its inability to perform parallel processing, etc. In this article, we provide ML-MCU, a framework with our novelOptimized-Stochastic Gradient Descent (Opt-SGD)andOptimized One-Versus-One (Opt-OVO)algorithms to enable both binary and multiclass ML classifier training directly on MCUs. Thus,ML-MCUenables billions of MCU-based IoT edge devices to self learn/train (offline) after their deployment, using live data from a wide range of IoT use cases. When evaluating our algorithms on multiple popular MCUs, using various data sets of different sizes and feature dimensions, one of the most exciting findings was, ourOpt-OVOalgorithm trained a multiclass classifier using a data set of class count 50, on a$\$ $3 resource-constrained MCU and also performed onboard unit inference for the same 50 class data in super real time (6.2 ms).

Typically a Neural Networks (NN) is trained on data centers using historic datasets, then a C source file (model as a char array) of the trained model is generated and flashed on IoT devices. This standard process impedes the flexibility of billions of deployed ML-powered devices as they cannot learn unseen/fresh data patterns (static intelligence) and are impossible to adapt to dynamic scenarios. Currently, to address this issue, Online Machine Learning (OL) algorithms are deployed on IoT devices that provide devices the ability to locally re-train themselves -continuously updating the last few NN layers using unseen data patterns encountered after deployment.In OL, catastrophic forgetting is common when NNs are trained using non-stationary data distribution. The majority of recent work in the OL domain embraces the implicit assumption that the distribution of local training data is balanced. But the fact is, the sensor data streams in real-world IoT are severely imbalanced and temporally correlated. This paper introduces Imbal-OL, a resource-friendly technique that can be used as an OL plugin to balance the size of classes in a range of data streams. When Imbal-OL processed stream is used for OL, the models can adapt faster to changes in the stream while parallelly preventing catastrophic forgetting. Experimental evaluation of Imbal-OL using CIFAR datasets over ResNet-18 demonstrates its ability to deal with imperfect data streams, as it manages to produce high-quality models even under challenging learning settings.

Transmitting updates of high-dimensional models between client IoT devices and the central aggregating server has always been a bottleneck in collaborative learning - especially in uncertain real-world IoT networks where congestion, latency, bandwidth issues are common. In this scenario, gradient quantization is an effective way to reduce bits count when transmitting each model update, but with a trade-off of having an elevated error floor due to higher variance of the stochastic gradients. In this paper, we propose ElastiCL, an elastic quantization strategy that achieves transmission efficiency plus a low error floor by dynamically altering the number of quantization levels during training on distributed IoT devices. Experiments on training ResNet-18, Vanilla CNN shows that ElastiCL can converge in much fewer transmitted bits than fixed quantization level, with little or no compromise on training and test accuracy.

Industry 4.0 is a recent trend of automation for manufacturing technologies and represents the fourth industrial revolution which transforms current industrial processes with the use of technologies such as automation, data analytics, cyber-physical systems, IoT, artificial intelligence, etc. The vision of Industry 4.0 is to build an end-to-end industrial transformation with the support of digitization. Data analytics plays a key role to get a better understanding of business processes and to design intelligent decision support systems. However, a key challenge faced by industry is to integrate multiple autonomous processes, machines and businesses to get an integrated view for data analytics activities. Another challenge is to develop methods and mechanisms for real-time data acquisition and analytics on-the-fly. In this paper, we propose a semantically interoperable framework for historical data analysis combined with real-time data acquisition, event detection, and real-time data analytics for very precise production forecasting within a manufacturing unit. Besides historical data analysis techniques, our middleware is capable of collecting data from diverse autonomous applications and operations in real time using various IoT devices, analyzing the collected data on the fly, and evaluating the impact of any detected unexpected events. Using semantic technologies we integrate multiple autonomous systems (e.g. production system, supply chain management and open data). The outcome of real-time data analytics is used in combination with machine learning models trained over historical data in order to precisely forecast production in a manufacturing unit in real time. We also present our key findings and challenges faced while deploying our solution in real industrial settings for a large manufacturing unit.

An increasing number of cities are confronted with challenges resulting from the rapid urbanization and new demands that a rapidly growing digital economy imposes on current applications and information systems. Smart city applications enable city authorities to monitor, manage, and provide plans for public resources and infrastructures in city environments, while offering citizens and businesses to develop and use intelligent services in cities. However, providing such smart city applications gives rise to several issues, such as semantic heterogeneity and trustworthiness of data sources, and extracting up-to-date information in real time from large-scale dynamic data streams. In order to address these issues, we propose a novel framework with an efficient semantic data processing pipeline, allowing for real-time observation of the pulse of a city. The proposed framework enables efficient semantic integration of data streams, and complex event processing on top of real-time data aggregation and quality analysis in a semantic Web environment. To evaluate our system, we use real-time sensor observations that have been published via an open platform called Open Data Aarhus by the City of Aarhus. We examine the framework utilizing symbolic aggregate approximation to reduce the size of data streams, and perform quality analysis taking into account both single and multiple data streams. We also investigate the optimization of the semantic data discovery and integration based on the proposed stream quality analysis and data aggregation techniques.

The admiration of social networks (SNs) and the advent of the Internet of Things (IoT) direct to a new research paradigm called Social IoT (SIoT), where real-world physical objects can form their own SN like the human SN. This effort leads to an immense possibility of unique applications for a smart cognitive society. However, it is still a challenge to explore these applications due to a lack of an adequate SIoT framework, where SIoT nodes can be controlled, managed, and monitored in realtime under a cognitive framework. Hence, in this paper, we propose a framework to create, manage, control, and monitor the SIoT objects intelligently and cognitively in real-time. In our proposed framework, we enable virtual representation of realworld objects known as virtual objects (VOs) and ensure their relationship semantically to compose new services by combining VOs and called composite VOs. Additionally, we identify special skills (e.g., expertise, and/or willingness to help others, etc.) as abstract objects. We also enable real-time interaction by using stream processing techniques. We also evaluated the performance of VO selection to understand the resource consumption and latency during the process.

Stream reasoning is an emerging research area focused on providing continuous reasoning solutions for data streams. The high expressiveness of non-monotonic reasoning enables complex decision making by managing defaults, commonsense, preferences, recursion, and non-determinism, but it is computationally intensive. The exponential growth in the availability of streaming data on the Web has seriously hindered the applicability of state-of-the-art non-monotonic reasoners to be applied to streaming information in a scalable way. In this paper, we address the issue of scalability for nonmonotonic stream reasoning based on Answer Set Programming (ASP) - an expressive reasoning approach based on disjunctive logic Datalog with negation under the stable model semantics, by analyzing input dependency. We introduce an input dependency graph to represent the relationships between input events based on the structure of a given logical rule set. The input dependency graph allows us to dynamically configure the streaming window size in order to maximise the scalability of the non-monotonic reasoner. We conduct an experimental evaluation to demonstrate the effectiveness and ability of our proposed approach in improving the scalability of disjunctive logic programming with ASP in dynamic environments.

The proliferation of sensor devices and services along with the advances in event processing brings many new opportunities as well as challenges. It is now possible to provide, analyze and react upon real-time, complex events in urban environments. When existing event services do not provide such complex events directly, an event service composition maybe required. However, it is difficult to determine which event service candidates (or service compositions) best suit users' and applications' quality-of-service requirements. A sub-optimal service composition may lead to inaccurate event detection, lack of system robustness etc. In this paper, the authors address these issues by first providing a quality-of-service aggregation schema for complex event service compositions and then developing a genetic algorithm to efficiently create near-optimal event service compositions. The authors evaluate their approach with both real sensor data collected via Internet-of-Things services as well as synthesised datasets.