Rodrigo N. Calheiros’s research while affiliated with Western Sydney University and other places

Multiview systems have become a key technology in modern computer vision, offering advanced capabilities in scene understanding and analysis. However, these systems face critical challenges in bandwidth limitations and computational constraints, particularly for resource-limited camera nodes like drones. This paper presents a novel approach for communication-efficient distributed multiview detection and tracking using masked autoencoders (MAEs). We introduce a semantic-guided masking strategy that leverages pre-trained segmentation models and a tunable power function to prioritize informative image regions. This approach, combined with an MAE, reduces communication overhead while preserving essential visual information. We evaluate our method on both virtual and real-world multiview datasets, demonstrating comparable performance in terms of detection and tracking performance metrics compared to state-of-the-art techniques, even at high masking ratios. Our selective masking algorithm outperforms random masking, maintaining higher accuracy and precision as the masking ratio increases. Furthermore, our approach achieves a significant reduction in transmission data volume compared to baseline methods, thereby balancing multiview tracking performance with communication efficiency.

Blockchain is becoming a game-changer for many sectors, noted for its tamper-proof nature that boosts data structures' integrity, auditability, and transparency. It provides the pragmatics within which data exchange between construction supply chain (CSC) stakeholders notably addresses its fragmented character. However, the construction industry is lagging compared to other sectors regarding the share of blockchain business activities. On the other hand, Building Information Modelling (BIM) is globally recognized as the primary catalyst for digital transformation within the construction industry to expedite coordination and data exchange between CSC stakeholders. Even though some existing researchers propose software prototypes to establish the technological feasibility of BIM integration with blockchain, there is a lack of a management model that CSC stakeholders can follow to help the industry manage change and obtain maximum value from the technology to put processes in motion. The philosophy behind the sensing-shaping-seizing framework is used in this paper to reflect what is required to propel companies towards integrating BIM and Blockchain in the Construction Supply Chain through a stakeholder's development stack, drivers and barriers to adoption, and potential disruption points. The research approach was an induction involving two construction enterprises in Australia selected for the knowledge elicitation case studies. The primary contribution of this research to knowledge is the translation of the blockchain technology stack, consisting of the application, protocol, and networking layers, into a holistic understanding of the roles played by each CSC data stakeholder and their motivation to adopt the potential solution at each layer.

Cloud computing has several benefits over traditional systems, such as scalability and high availability. However, these benefits, to be eventuated, require efforts in the area of resource provisioning and scaling, to match resources to current and future demand, and this is not always trivial to achieve. Since workload may fluctuate substantially in cloud environments, over-provisioning is a common practice to avoid abrupt quality of service (QoS) drops that may result in service level agreement (SLA) violations, but at the price of increased provisioning costs and energy consumption. Workload prediction is one of the strategies by which efficiency and operational cost of a clouds can be improved. Therefore, in this paper, we show the potential benefits of a proactive resource provisioning scheme augmented by three of the most promising machine learning prediction techniques in this context, namely ARIMA, MLP, and GRU, that are known to be able to cope with the dynamic behavior of our target applications. We analyze the trade-off between resource consumption and quality of service using SLA violations in web workloads, considering real case provisioning requirements and constraints, extensively simulating and analyzing the impact of prediction and scaling intervals, and publishing all used tools and datasets to allow reproducibility. Simulation experiments with a proactive approach are executed using real traces from NASA and Wikipedia workloads and achieved a reduction of 40% in SLA violations on average when compared to a reactive approach, while reducing the provisioned resources by almost 3%.

The emergence of the Internet of Things (IoT) introduced new classes of applications whose latency and bandwidth requirements could not be satisfied by the traditional Cloud Computing model. Consequently, the IT community promoted the cooperation of two paradigms, Cloud Computing and Edge Computing, combining large-scale computing power and real-time processing capabilities. A significant management challenge in such complex infrastructure concerns the development of efficient maintenance strategies to preserve the environment’s performance and security. While the abundant resources from the academic literature could support the design of novel maintenance solutions, extracting actionable insights from the existing approaches is challenging, given the massive number of published papers. Furthermore, existing review papers, which could help summarize the state-of-the-art, scope their investigations to the maintenance of certain components in particular scenarios. This work fills this gap with a broader literature analysis that covers maintenance strategies targeting physical and logical components in cloud, edge, and IoT environments. First, we introduce a taxonomy that organizes existing solutions according to several characteristics. Then, we review the literature following the taxonomy structure to facilitate the understanding of the research landscape and the comparison between existing works. Finally, we shed light on open challenges that represent promising research directions.

Low Earth Orbit (LEO) satellite constellations have diverse applications, including earth observation, communication services, navigation, and positioning. These constellations have evolved into a valuable data source; however, their use in a ground station (GS) for analysis via machine learning algorithms presents challenges due to constraints on power consumption, communication bandwidth, and onboard computing capabilities. While the combination of Federated Learning (FL) and Orbital Edge Computing has been employed to address these challenges, its heavy reliance on the GS for model aggregation and edge resource limitations remains a research challenge. This paper presents FedOrbit, a novel energy-efficient and decentralised FL method to optimise communication with the GS and reduce power consumption. FedOrbit utilises reinforcement learning for cluster formation, satellite visiting patterns for master satellite selection, and block minifloat arithmetic for power reduction. Extensive performance evaluation under Walker Delta-based LEO constellation configurations and different datasets reveals that FedOrbit can maintain high accuracy while significantly reduce communication demand, power consumption and training time in comparison to state-of-the-art FL approaches. The proposed technique can also reduce the training time by 5× compared with the centralised FL approaches. In addition, the utilisation of block minifloat representation as low-precision arithmetic enhanced the energy consumption by 3.5× compared with the single-precision (FP32) format.