Validation metrics are key for tracking scientific progress and bridging the current chasm between artificial intelligence research and its translation into practice. However, increasing evidence shows that, particularly in image analysis, metrics are often chosen inadequately. Although taking into account the individual strengths, weaknesses and limitations of validation metrics is a critical ...

Modern artificial intelligence (AI) technologies, led by machine learning (ML), have gained unprecedented momentum over the past decade. Following this wave of "AI summer," the network research community has also embraced AI/ML algorithms to address many problems related to network operations and management. However, compared to their counterparts in other domains, most ML-based solutions have yet ...

Containerized cluster systems and edge devices are vulnerable to security breaches when configuration errors occur. In this paper, we propose more experiments on the self-healing approach for misconfigurations that adopt a Markov Decision Process to determine the optimal recovery action or policy that maximizes performance metrics. The experiments conducted are an improvement on our previous ...

It has been noted that a number of metaheuristics are applied with success to power system optimal reactive power dispatch (ORPD) challenges. These algorithms’ convergence rates are also determined to be low, and the results they provide are deemed to be inadequate. It suggests that there is insufficient investigation and exploitation in the algorithm. Therefore, an appropriate approach is needed ...

Current convolutional neural networks (CNNs) are not designed for large scientific images with rich multi-scale features, such as in satellite and microscopy domain. A new phase of development of CNNs especially designed for large images is awaited. However, application-independent high-quality and challenging datasets needed for such development are still missing. We present the ‘UltraMNIST ...

Integrating Machine Learning (ML) models into healthcare system, especially by Natural Language Processing (NLP), holds tremendous potential for improving hospital workflows and patient outcomes. This thesis presents the challenges and deployment of an NLP model, Automated Medical Entity Recognition (AMER), designed to extract medical entities from clinical text, within in cloud-based Machine Learning ...

This paper outlines a research roadmap of the INTEND project towards the development of a cognitive computing continuum that leverages human-like intelligence for intent-based data operations. The primary objective of this initiative is to create a system that can adapt dynamically to varying contexts by understanding and acting upon the intents of stakeholders in a decentralised and strategic manner. ...

This study explores the thermal conductivity and viscosity of water-based nanofluids containing silicon dioxide, graphene oxide, titanium dioxide, and their hybrids across various concentrations (0 to 1 vol%) and temperatures (30 to 60 °C). The nanofluids, characterized using multiple methods, exhibited increased viscosity and thermal conductivity compared to water, with hybrid nanofluids ...

A Cyber-Physical System (CPS) deployed in remote and resource-constrained environments faces multiple challenges. It has, no or limited: network coverage, possibility of energy replenishment, physical access by humans.<p> <p>Cyber-physical nodes deployed to observe and interact with the Arctic tundra face these challenges. They are subject to environmental factors such as avalanches, low temperatures, ...

Background: As type 2 diabetes (T2D) is expected to increase, self-management becomes more crucial. Mobile apps are increasingly supporting self-management with tasks like blood glucose monitoring and medication management. Understanding the behavioral intervention functions used by diabetes apps today, is essential for improving future apps and systems for diabetes management.<p> <p>Objective: ...