The Industrial Internet of Things (IIoT) generates heterogeneous, high-volume data across diverse devices, posing challenges for anomaly detection while preserving privacy. Traditional federated learning approaches struggle with nonIID data, limited edge resources, and a lack of device-specific adaptation. These limitations often result in suboptimal bias handling, poor personalisation, and unstable convergence in complex IIoT environments. To address these challenges, this paper proposes a novel theoretical Hierarchical Boosting with Bayesian Fusion (HBBF) framework that extends the conventional federated learning paradigm into a three-tier architecture, with multiple devices per edge layer and edge nodes aggregated via a global server layer. Within this hierarchy, each device performs sequential boosting with bias fixation, ensuring that local LightGBM models progressively correct residual errors while maintaining personalised adaptation. The resulting leaf one-hot encoded embeddings from each device/edge are then blended at the edge layer, allowing correlated local knowledge to be synthesised before global Bayesian Aggregation. At the global layer, Bayesian Aggregation fuses the edge-level embeddings and uncertainties, providing a principled probabilistic integration of distributed knowledge. Through this hierarchical design, HBBF enhances robustness and accuracy under heterogeneous data conditions, reduces residual variance through structured bias fixation, and maintains communication efficiency and privacy. Compared to conventional methods like FedAvg and FedPer, HBBF achieves scalable, stable, and high-accuracy federated learning.

The identification of biological echoes in radar data has revolutionized research into airborne migratory species. Deep learning applied to polarimetric weather radar observations can reveal signature patterns of mass movement by bio-scatterers such as birds, bats, and insects. However, due to the difficulties in labelling bio-scatterers in these data, threshold approaches have been proposed in the literature. In this research, we used the depolarization ratio (DR) based on differential reflectivity (zDR) and the cross-correlation coefficient (pHV), along with citizen scientist-reported data, to label bio-scatterers for deep learning. This method of labeling biological echoes in radar signatures is prone to noise, which impacts the accuracy of any model that relies on it. We introduce a novel semi-supervised co-training approach that uses a bootstrap ensemble with a confidence threshold. Our ensemble consists of the newly proposed STNet and two modified FNet models, which incorporate co-learning through bootstrap sampling for label correction. This innovative method significantly improves classification accuracy across all three multivariate numerical datasets compared to baseline models that lack co-learning with bootstrap-based label correction. • We used depolarization ratio and citizen science data to label biological echoes in polarimetric weather radar observation. • We used a deep learning approach to correct noisy biological-scatterer labels in polarimetric weather radar observations. • We developed a novel approach that uses semi-supervised co-training method based on bootstrap ensemble with a confidence threshold. • We introduced ensembles comprising STNet and a modified FNet with bootstrap sparse categorical cross-entropy loss. • We tested our method on other similar multivariate numerical datasets.

The emergence of Edge Computing has shifted the processing capabilities in proximity to the Internet of Things (IoT) data sources, offering solutions to latency and bandwidth constraints applications. This shift complements Cloud Computing, especially in handling real-time data processing and enhancing processing. Image processing, particularly image captioning for smart monitoring systems, benefits greatly from this synergy. Image captioning plays a crucial role in understanding visual data. While early methods excelled in encoder-decoder frameworks and attention mechanisms, they often overlooked semantic representations which are essential for comprehensive image understanding. To address this gap, we introduce the EdgeScan framework, leveraging Edge Computing for image analysis and semantic feature extractions closer to data sources. EdgeScan integrates visual and semantic features to create more informative and enriched image captions that enhance image captioning accuracy. The EdgeScan image captioning model architecture is capable of 1) learning the salient image region’s specific feature representation and 2) co-embedding visual attention and semantic attributes in one space for feature fusion. This improves models’ ability to interpret and respond to data in a meaningful way, which is particularly valuable for IoT applications that require a deep understanding of the semantics of diverse and constantly changing data for efficient operation. Extensive experiments were conducted on the MS-COCO dataset to demonstrate the superiority of EdgeScan in both quantitative and qualitative performance, achieving highest consensus-based image description evaluation score of 120.9, as well as notable scores of 78.6 for BLEU@1 and 57.7 for recall-oriented understudy for gisting evaluation metrics, promising advancements in IoT-driven image understanding and competitiveness against the state of the art.

Abstract This paper sheds light on the complexity of designing Internet of Things (IoT) ecosystems where a high number of things reside and thus must collaborate despite their reduced size, restricted connectivity, and constrained storage limitations. To address this complexity, a novel concept referred to as thing artifact is devised abstracting the roles that things play in an IoT ecosystem. The abstraction focuses on 3 crosscutting aspects, namely functionality in terms of what to perform, life cycle in terms of how to behave, and interaction flow in terms of with whom to exchange. Building upon the concept of data artifact commonly used in data-driven business applications design, thing artifacts engage in relations with peers to coordinate their individual behaviors and hence avoid conflicts that could result from the quality of exchanged data. Putting functionality, life cycle, interaction flow, and relation together contributes to abstracting IoT ecosystems design. A system implementing a thing artifact-based ecosystem along with some experiments is presented in the paper as well.

The Internet of Things refers to a vast and interconnected distributed systems in which components have a high degree of heterogeneity in terms of software, hardware, and connectivity, while they deliver different services. The quality of service for users accessing the Internet of Things supported by cloud computing is increasing exponentially. However, the deployment of Internet of Things applications in a cloud environment can be very dynamic, resulting in service demands and high resource requirements. The task of effectively managing and optimising resource allocation while taking into account time-sensitive requests is a significant and complex problem that has implications on service quality. The proposed solution aims to improve task scheduling in a hybrid cloud environment for Internet of Things applications. This improvement involves implementing load-balancing techniques to achieve cost reduction, energy consumption, and enhanced overall execution time. The designed solution encompasses two main phases. In the first phase, clustering is performed on computing hosts. In the subsequent phase, user requests are assigned to a suitable cluster, utilising the enhanced Firefly algorithm. The simulation results demonstrated the efficiency of the proposed solution in terms of energy consumption and execution time compared to a benchmark algorithm.

Vision is a vital sense that plays a pivotal role in our understanding of the world. The majority of our external information is acquired through our visual system, which significantly impacts various aspects of our lives, including mobility, cognitive abilities, access to information, and how we interact with both our surroundings and other individuals. Hence, individuals who need assisted living due to visual challenges are left behind and rely on human-driven image captioning services to make sense of their surroundings. In response to this challenge, we have developed a proof-of-concept system that integrates a large language model like ChatGPT to provide assistance to individuals with visual impairments in their daily lives through the utilisation of image captioning techniques. Our proposed model leverages the image captioning technique to describe the user’s environment. It is a fusion of concepts from Deep Learning and the Internet of Things, enabling it to provide more informative and enriched image captions. In this process, ChatGPT is stimulated to generate increasingly detailed and informative descriptions of images, allowing users to gain a deeper understanding of their surroundings. Our findings show that the proposed system generates captions that are contextually relevant to the visual content. These captions can assist individuals in various day-today activities, contributing to an improved quality of life.

Multimedia applications such as video streaming services have become popular, especially with the rapid growth of users, devices, increased availability and diversity of these services over the internet. In this case, service providers and network administrators have difficulties ensuring end-user satisfaction because the traffic generated by such services is more exposed to multiple network quality of service impairments, including bandwidth, delay, jitter, and loss ratio. This paper proposes an intelligent-based multimedia traffic routing framework that exploits the integration of a reinforcement learning technique with software-defined networking to explore, learn and find potential routes for video streaming traffic. Simulation results through a realistic network and under various traffic loads, demonstrate the proposed scheme's effectiveness in providing improved end-user viewing quality, higher throughput and lower video quality switches when compared to the existing techniques.

The recognition of hand palm print through veins is one of the promising biometric techniques, which has received great interest lately due to its accuracy in identifying individuals. Although the literature witnessed several techniques and devel-opments to deal with the problem of identifying people through the veins in the palm, the technology is still in its infancy. In this research, we propose our palm print recognition model which use convolution neural networks preceded by the pre-processing stages to optimise the data and to extract the important regions. The pre-processing helped in extracting the vein pattern which feed into the proposed convolution neural network model. The CASIA database has been used; it contains 7200 images taken form 100 people based on 6 wavelengths (940 nm, 850 nm, 700 nm, 630 nm, 460 nm, and white). The model has been tested with all wavelengths in the database. AlexNet is used for benchmarking. The results show that our approach using the proposed pre-processing has helped to surpass AlexNet in terms of performance, speed, and accuracy.

Education providers are increasingly using artificial techniques for predicting students' performance based on their interactions in Virtual Learning Environments (VLE). In this paper, the Open University Learning Analytics Dataset (OULAD), which contains student demographic information, assessment scores, number of clicks in the virtual learning environment and final results, etc, has been used to predict student performance. Various techniques such as standardisation and normalisation have been employed in the pre-processing stage. Spearman's correlation coefficient is used to measure the correlation between the activity types and the students' final results to determine the importance of the activities. Deep learning has been utilised to predict students' performance based on their engagement in the VLE. The empirical results show that our model has the ability to accurately predict student academic performance.

There have been significant advances in the field of Internet of Things (IoT) recently, which have not always considered security or data security concerns: A high degree of security is required when considering the sharing of medical data over networks. In most IoT-based systems, especially those within smart-homes and smart-cities, there is a bridging point (fog computing) between a sensor network and the Internet which often just performs basic functions such as translating between the protocols used in the Internet and sensor networks, as well as small amounts of data processing. The fog nodes can have useful knowledge and potential for constructive security and control over both the sensor network and the data transmitted over the Internet. Smart healthcare services utilise such networks of IoT systems. It is therefore vital that medical data emanating from IoT systems is highly secure, to prevent fraudulent use, whilst maintaining quality of service providing assured, verified and complete data. In this article, we examine the development of a Cognitive Fog (CF) model, for secure, smart healthcare services, that is able to make decisions such as opting-in and opting-out from running processes and invoking new processes when required, and providing security for the operational processes within the fog system. Overall, the proposed ensemble security model performed better in terms of Accuracy Rate, Detection Rate, and a lower False Positive Rate (standard intrusion detection measurements) than three base classifiers (K-NN, DBSCAN, and DT) using a standard security dataset (NSL-KDD).

Fog computing is a promising network paradigm in the IoT area as it has a great potential to reduce processing time for time-sensitive IoT applications. However, fog can get congested very easily due to fog resources limitations in term of capacity and computational power. In this paper, we tackle the issue of fog congestion through a request offloading algorithm. The result shows that the performance of fogs nodes can be increased be sharing fog's overload over several fog nodes. The proposed offloading algorithm could have the potential to achieve a sustainable network paradigm and highlights the significant benefits of fog offloading for the future networking paradigm.

With the emerge of Internet of Things, billions of devices and humans are connected directly or indirectly to the internet. This significant growth in the number of connected devices rises the needs for a new development for the current network paradigm (e.g., cloud computing). The new network paradigm, such as fog computing, along with its related edge computing paradigms, are seen as promising solutions for handling the large volume of securely-critical and delay-sensitive data that is being produced by the IoT nodes. In this paper, we give a brief overview on the IoT related computing paradigms, including their similarities and differences as well as challenges. Next, we provide a summary of the challenges and processing and storage capabilities of each network paradigm.

The construction sector, which has a long history to use visualisation to envisage proposed designs and project delivery, is beginning to see the benefits of augmented reality and agile project management methodologies. This study investigated the benefits of augmented reality and agile project management methodologies. Convergent design method was considered valuable and the most straightforward for this study, as different types of quantitative and qualitative data were required to be collected and analysed. The participants drawn from the construction sector revealed a number of augmented and agile determinants that facilitated the delivery of construction and integration of project teams. The participants suggested that the proposed ARGILE framework increases client understanding of the tasks output, increases client involvement and collaboration with the project team. It was further established that the proposed ARGILE framework enhances project time management, embeds the client and empowers multidisciplinary team, increases collaboration and communication.

Due to a rapidly increasing aging population and its associated challenges in health and social care, Ambient Assistive Living has become the focal point for both researchers and industry alike. The need to manage or even reduce healthcare costs while improving the quality of service is high government agendas. Although, technology has a major role to play in achieving these aspirations, any solution must be designed, implemented and validated using appropriate domain knowledge. In order to overcome these challenges, the remote real-time monitoring of a person’s health can be used to identify relapses in conditions, therefore, enabling early intervention. Thus, the development of a smart healthcare monitoring system, which is capable of observing elderly people remotely, is the focus of the research presented in this paper. The technology outlined in this paper focuses on the ability to track a person’s physiological data to detect specific disorders which can aid in Early Intervention Practices. This is achieved by accurately processing and analysing the acquired sensory data while transmitting the detection of a disorder to an appropriate career. The finding reveals that the proposed system can improve clinical decision supports while facilitating Early Intervention Practices. Our extensive simulation results indicate a superior performance of the proposed system: low latency (96% of the packets are received with less than 1 millisecond) and low packets-lost (only 2.2% of total packets are dropped). Thus, the system runs efficiently and is cost-effective in terms of data acquisition and manipulation.

In recent years, the UK’s emergency call and response has shown elements of great strain as of today. The strain on emergency call systems estimated by a 9 million calls (including both landline and mobile) made in 2014 alone. Coupled with an increasing population and cuts in government funding, this has resulted in lower percentages of emergency response vehicles at hand and longer response times. In this paper, we highlight the main challenges of emergency services and overview of previous solutions. In addition, we propose a new system call Smart Hospital Emergency System (SHES). The main aim of SHES is to save lives through improving communications between patient and emergency services. Utilising the latest of technologies and algorithms within SHES is aiming to increase emergency communication throughput, while reducing emergency call systems issues and making the process of emergency response more efficient. Utilising health data held within a personal smartphone, and internal tracked data (GPU, Accelerometer, Gyroscope etc.), SHES aims to process the mentioned data efficiently, and securely, through automatic communications with emergency services, ultimately reducing communication bottlenecks. Live video-streaming through real-time video communication protocols is also a focus of SHES to improve initial communications between emergency services and patients. A prototype of this system has been developed. The system has been evaluated by a preliminary usability, reliability, and communication performance study.

Within the Internet of Things (IoT) era, a big volume of data is generated/gathered every second from billions of connected devices. The current network paradigm, which relies on centralised data centres (a.k.a. Cloud computing), becomes impractical solution for IoT data storing and processing due to the long distance between the data source (e.g., sensors) and designated data centres. In other words, by the time the data reaches a far data centre, the importance of the data would be vanished. Therefore, the network topologies have been evolved to permit data processing and storage at the edge of the network, introducing what so-called "Fog computing". The later will obviously lead to improvements in quality of service (QoS) via processing and responding quickly and efficiently to varieties of data processing requests. Therefore, understanding Fog computing architecture and its role in improving QoS is a paramount research topic. In this research, we are proposing a Fog computing architecture and framework to improve QoS for IoT applications. Proposed system supports cooperation among Fog nodes in a given location, in order to permit data processing in a shared mode, hence satisfies QoS and serves largest number of service requests. The proposed framework could have the potential in achieving sustainable network paradigm and highlights significant benefits of Fog computing into the computing ecosystem.

Abstract: This paper discusses the blend of cognitive computing with the Internet-of-Things that should result into developing cognitive things. Today’s things are confined into a data-supplier role, which deprives them from being the technology of choice for smart applications development. Cognitive computing is about reasoning, learning, explaining, acting, etc. In this paper, cognitive things’ features include functional and non-functional restrictions along with a 3 stage operation cycle that takes into account these restrictions during reasoning, adaptation, and learning. Some implementation details about cognitive things are included in this paper based on a water pipe case-study.