In ophthalmic diagnostics, achieving precise segmentation of retinal blood vessels is a critical yet challenging task, primarily due to the complex nature of retinal images. The intricacies of these images often hinder the accuracy and efficiency of segmentation processes. To overcome these challenges, we introduce the cognitive DL retinal blood vessel segmentation (CoDLRBVS), a novel hybrid model that synergistically combines the deep learning capabilities of the U-Net architecture with a suite of advanced image processing techniques. This model uniquely integrates a preprocessing phase using a matched filter (MF) for feature enhancement and a post-processing phase employing morphological techniques (MT) for refining the segmentation output. Also, the model incorporates multi-scale line detection and scale space methods to enhance its segmentation capabilities. Hence, CoDLRBVS leverages the strengths of these combined approaches within the cognitive computing framework, endowing the system with human-like adaptability and reasoning. This strategic integration enables the model to emphasize blood vessels, accurately segment effectively, and proficiently detect vessels of varying sizes. CoDLRBVS achieves a notable mean accuracy of 96.7%, precision of 96.9%, sensitivity of 99.3%, and specificity of 80.4% across all of the studied datasets, including DRIVE, STARE, HRF, retinal blood vessel and Chase-DB1. CoDLRBVS has been compared with different models, and the resulting metrics surpass the compared models and establish a new benchmark in retinal vessel segmentation. The success of CoDLRBVS underscores its significant potential in advancing medical image processing, particularly in the realm of retinal blood vessel segmentation.

Software quality is critical, as low quality, or "Code smell," increases technical debt and maintenance costs. There is a timely need for a collaborative model that detects and manages code smells by learning from diverse and distributed data sources while respecting privacy and providing a scalable solution for continuously integrating new patterns and practices in code quality management. However, the current literature is still missing such capabilities. This paper addresses the previous challenges by proposing a Federated Learning Code Smell Detection (FedCSD) approach, specifically targeting "God Class," to enable organizations to train distributed ML models while safeguarding data privacy collaboratively. We conduct experiments using manually validated datasets to detect and analyze code smell scenarios to validate our approach. Experiment 1, a centralized training experiment, revealed varying accuracies across datasets, with dataset two achieving the lowest accuracy (92.30%) and datasets one and three achieving the highest (98.90% and 99.5%, respectively). Experiment 2, focusing on cross-evaluation, showed a significant drop in accuracy (lowest: 63.80%) when fewer smells were present in the training dataset, reflecting technical debt. Experiment 3 involved splitting the dataset across 10 companies, resulting in a global model accuracy of 98.34%, comparable to the centralized model's highest accuracy. The application of federated ML techniques demonstrates promising performance improvements in code-smell detection, benefiting both software developers and researchers.

The integration of the Internet of Things (IoT) and Machine Learning (ML) technologies has opened up for the development of novel types of systems and services. Federated Learning (FL) has enabled the systems to collaboratively train their ML models while preserving the privacy of the data collected by their IoT devices and objects. Several FL frameworks have been developed, however, they do not enable FL in open, distributed, and heterogeneous IoT environments. Specifically, they do not support systems that collect similar data to dynamically discover each other, communicate, and negotiate about the training terms (e.g., accuracy, communication latency, and cost). Towards bridging this gap, we propose ART4FL, an end-to-end framework that enables FL in open IoT settings. The framework enables systems' users to configure agents that participate in FL on their behalf. Those agents negotiate and make commitments (i.e., contractual agreements) to dynamically form federations. To perform FL, the framework deploys the needed services dynamically, monitors the training rounds, and calculates agents' trust scores based on the established commitments. ART4FL exploits a blockchain network to maintain the trust scores, and it provides those scores to negotiating agents' during the federations' formation phase.

The international community has largely recognized that the Earth's climate is changing. Mitigating its global effects requires international actions. The European Union (EU) is leading several initiatives focused on reducing the problems. Specifically, the Climate Action tries to both decrease EU greenhouse gas emissions and improve energy efficiency by reducing the amount of primary energy consumed, and it has pointed to the development of efficient building energy management systems as key. In traditional buildings, households are responsible for continuously monitoring and controlling the installed Heating, Ventilation, and Air Conditioning (HVAC) system. Unnecessary energy consumption might occur due to, for example, forgetting devices turned on, which overwhelms users due to the need to tune the devices manually. Nowadays, smart buildings are automating this process by automatically tuning HVAC systems according to user preferences in order to improve user satisfaction and optimize energy consumption. Towards achieving this goal, in this paper, we compare 36 Machine Learning algorithms that could be used to forecast indoor temperature in a smart building. More specifically, we run experiments using real data to compare their accuracy in terms of R-coefficient and Root Mean Squared Error and their performance in terms of Friedman rank. The results reveal that the ExtraTrees regressor has obtained the highest average accuracy (0.97%) and performance (0,058%) over all horizons.

Internet of Things (IoT) systems are complex systems that can manage mission-critical, costly operations or the collection, storage, and processing of sensitive data. Therefore, security represents a primary concern that should be considered when engineering IoT systems. Additionally, several challenges need to be addressed, including the following ones. IoT systems' environments are dynamic and uncertain. For instance, IoT devices can be mobile or might run out of batteries, so they can become suddenly unavailable. To cope with such environments, IoT systems can be engineered as goal-driven and self-adaptive systems. A goal-driven IoT system is composed of a dynamic set of IoT devices and services that temporarily connect and cooperate to achieve a specific goal. Several approaches have been proposed to engineer goal-driven and self-adaptive IoT systems. However, none of the existing approaches enable goal-driven IoT systems to automatically detect security threats and autonomously adapt to mitigate them. Toward bridging these gaps, this paper proposes a distributed architectural Approach for engineering goal-driven IoT Systems that can autonomously SElf-adapt to secuRity Threats in their environments (ASSERT). ASSERT exploits techniques and adopts notions, such as agents, federated learning, feedback loops, and blockchain, for maintaining the systems' security and enhancing the trustworthiness of the adaptations they perform. The results of the experiments that we conducted to validate the approach's feasibility show that it performs and scales well when detecting security threats, performing autonomous security adaptations to mitigate the threats and enabling systems' constituents to learn about security threats in their environments collaboratively.

Remote health monitoring is a trend for better health management which necessitates the need for secure monitoring and privacy-preservation of patient data. Moreover, accurate and continuous monitoring of personal health status may require expert validation in an active learning strategy. As a result, this paper proposes a Federated Interactive Learning IoT-based Health Monitoring Platform (FIL-IoT-HMP) which incorporates multi-expert feedback as ‘Human-in-the-loop’ in an active learning strategy in order to improve the clients’ Machine Learning (ML) models. The authors have proposed an architecture and conducted an experiment as a proof of concept. Federated learning approach has been preferred in this context given that it strengthens privacy by allowing the global model to be trained while sensitive data is retained at the local edge nodes. Also, each model’s accuracy is improved while privacy and security of data has been upheld.

Modern Information and Communication Technology (ICT)-based applications utilize currenttechnological advancements for purposes of streaming data, as a way of adapting to the ever-changingtechnological landscape. Such efforts require providing accurate, meaningful, and trustworthy output fromthe streaming sensors particularly during dynamic virtual sensing. However, to ensure that the sensingecosystem is devoid of any sensor threats or active attacks, it is paramount to implement secure real-timestrategies. Fundamentally, real-time detection of adversarial attacks/instances during the User FeedbackProcess (UFP) is the key to forecasting potential attacks in active learning. Also, according to existingliterature, there lacks a comprehensive study that has a focus on adversarial detection from an activemachine learning perspective at the time of writing this paper. Therefore, the authors posit the importance ofdetecting adversarial attacks in active learning strategy. Attack in the context of this paper through a UFPThreat driven model has been presented as any action that exerts an alteration to the learning system ordata. To achieve this, the study employed ambient data collected from a smart environment human activityrecognition from (Continuous Ambient Sensors Dataset, CASA) with fully labeled connections, where weintentionally subject the Dataset to wrong labels as a targeted/manipulative attack (by a malevolent labeler)in the UFP, with an assumption that the user-labels were connected to unique identities. While the dataset’sfocus is to classify tasks and predict activities, our study gives a focus on active adversarial strategies froman information security point of view. Furthermore, the strategies for modeling threats have been presentedusing the Meta Attack Language (MAL) compiler for purposes adversarial detection. The findings fromthe experiments conducted have shown that real-time adversarial identification and profiling during the UFPcould significantly increase the accuracy during the learning process with a high degree of certainty and pavesthe way towards an automated adversarial detection and profiling approaches on the Internet of CognitiveThings (ICoT).

Internet of Things (IoT) environments encompass different types of devices and objects that offer a wide range of services. The dynamicity and uncertainty of those environments, including the mobility of users and devices, make it hard to foresee at design time available devices, objects, and services. For the users to benefit from such environments, they should be proposed services that are relevant to the specific context and can be provided by available things. Moreover, environments should be configured automatically based on users' preferences. To address these challenges, we propose an approach that leverages Artificial Intelligence techniques to recognize users' activities and provides relevant services to support users to perform their activities. Moreover, our approach learns users' preferences and configures their environments accordingly by dynamically forming, enacting, and adapting goal-driven IoT systems. In this paper, we present a conceptual model, a multi-tier architecture, and processes of our approach. Moreover, we report about how we validated the feasibility and evaluated the scalability of the approach through a prototype that we developed and used.

Whereas data labelling in IoT applications is costly, it is also time consuming to train a supervised Machine Learning (ML) algorithm. Hence, a human oracle is required to gradually annotate the data patterns at run-time to improve the models’ learning behavior, through an active learning strategy in form of User Feedback Process (UFP). Consequently, it is worth to note that during UFP there may exist malicious content that may subject the learning model to be vulnerable to adversarial attacks, more so, manipulative attacks. We argue in this position paper, that there are instances during incremental learning, where the local data model may present wrong output, if retraining is done using data that has already been subjected to adversarial attack. We propose a Distributed Interactive Secure Federated Learning (DISFL) framework that utilizes UFP in the edge and fog node, that subsequently increases the amount of labelled personal local data for the ML model during incremental training. Furthermore, the DISFL framework addresses data privacy by leveraging federated learning, where only the model's knowledge is moved to a global unit, herein referred to as Collective Intelligence Node (CIN). During incremental learning, this would then allow the creation of an immutable chain of data that has to be trained, which in its entirety is tamper-free while increasing trust between parties. With a degree of certainty, this approach counters adversarial manipulation during incremental learning in active learning context at the same time strengthens data privacy, while reducing the computation costs.

Machine learning has been shown as a promising approach to mine larger datasets, such as those that comprise datafrom a broad range of Internet of Things devices, across complex environment(s) to solve different problems. Thispaper surveys existing literature on the potential of using supervised classical machine learning techniques, such asK-Nearest Neigbour, Support Vector Machines, Naive Bayes and Random Forest algorithms, in performing livedigital forensics for different IoT configurations. There are also a number of challenges associated with the use ofmachine learning techniques, as discussed in this paper.