About
432
Publications
249,996
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
13,956
Citations
Introduction
Current institution
Additional affiliations
July 2016 - July 2019
June 2016 - present
Publications
Publications (432)
This paper is concerned with the application of wireless sensor network (WSN) technology to long-duration and large-scale environmental monitoring. The holy grail is a system that can be deployed and operated by domain specialists not engineers, but this remains some distance into the future. We present our views as to why this field has progressed...
Context-aware services rely critically on accurate and energy-efficient location tracking. While GPS receivers offer high accuracy positioning, energy harvesting and storage constraints of battery-powered devices necessitate duty-cycling of GPS to prolong the system lifetime. Furthermore, real-world dynamics dictate that the GPS sampling strategy a...
Internet of Things (IoT) security and privacy remain a major challenge, mainly due to the massive scale and distributed nature of IoT networks. Blockchain-based approaches provide decentralized security and privacy, yet they involve significant energy, delay, and computational overhead that is not suitable for most resource-constrained IoT devices....
There has been increasing interest in adopting BlockChain (BC), that underpins the crypto-currency Bitcoin, in Internet of ings (IoT) for security and privacy. However, BCs are computation-ally expensive and involve high bandwidth overhead and delays, which are not suitable for most IoT devices. is paper proposes a lightweight BC-based architecture...
Figure 1 A future smart vehicle utilizing a wireless vehicle interface (WVI) to interconnect the vehicle and its vehicular bus systems to the Internet. Future smart vehicles will be part of the Internet of Things to offer beneficial development opportunities for both end users as well as the automotive industry. This will potentially expose smart v...
As conventional storage density reaches its physical limits, the cost of a gigabyte of storage is no longer plummeting, but rather has remained mostly flat for the past decade. Meanwhile, file sizes continue to grow, leading to ever fuller drives. When a user's storage is full, they must disrupt their workflow to laboriously find large files that a...
Malicious Python packages make software supply chains vulnerable by exploiting trust in open-source repositories like Python Package Index (PyPI). Lack of real-time behavioral monitoring makes metadata inspection and static code analysis inadequate against advanced attack strategies such as typosquatting, covert remote access activation, and dynami...
The widespread adoption of Electric Vehicles (EVs) poses critical challenges for energy providers, particularly in predicting charging time (temporal prediction), ensuring user privacy, and managing resources efficiently in mobility-driven networks. This paper introduces the Hierarchical Federated Learning Transformer Network (H-FLTN) framework to...
By 2050, electric vehicles (EVs) are projected to account for 70% of global vehicle sales. While EVs provide environmental benefits, they also pose challenges for energy generation, grid infrastructure, and data privacy. Current research on EV routing and charge management often overlooks privacy when predicting energy demands, leaving sensitive mo...
Federated Learning (FL) has emerged as a promising paradigm for secure data sharing in Industrial Internet of Things (IIoT), enabling collaborative model training without direct exchange of raw data. However, recent studies have shown that FL still suffers from privacy vulnerabilities, where adversaries can reconstruct sensitive information by anal...
The Internet of Things (IoT) detects context through sensors capturing data from dynamic physical environments, in order to inform automation decisions within cyber physical systems (CPS). Diverse types of uncertainty in the IoT pipeline can propagate within and across nodes, involving complex interactions with security, privacy, and trust that rem...
Modern distributed applications in healthcare, supply chain, and the Internet of Things handle a large amount of data in a diverse application setting with multiple stakeholders. Such applications leverage advanced artificial intelligence (AI) and machine learning algorithms to automate business processes. The proliferation of modern AI technologie...
The widespread adoption of deep learning across various industries has introduced substantial challenges, particularly in terms of model explainability and security. The inherent complexity of deep learning models, while contributing to their effectiveness, also renders them susceptible to adversarial attacks. Among these, backdoor attacks are espe...
In the current digital landscape, supply chains have transformed into complex networks driven by the Internet of Things (IoT), necessitating enhanced data sharing and processing capabilities to ensure traceability and transparency. Leveraging Blockchain technology in IoT applications advances reliability and transparency in near-real-time insight e...
By 2050, global sales of electric vehicles (EVs) are predicted to account for approximately 70% of all vehicle sales. However, whilst transitioning from combustion engine vehicles to EVs would result in reduced carbon dioxide emissions, it would place significant strain on energy generation, and grid infrastructure. Many EV studies investigated rou...
Neighborhood area networks (NANs) lay the foundation for robust communication in smart grids to support stable and secure end-user connectivity with substations. Firstly, the current solutions are unrealistic to meet the time-bound requirements for smart grid applications with large number of intermediate node connectivity in NANs. Secondly, the ex...
Blockchain offers immutability, transparency, and security in a decentralised way for many applications, including finance, supply chain, and the Internet of Things (IoT). Due to its popularity and widespread adoption, it has started to process an enormous number of transactions, placing an ever-growing demand for storage. As the technology gains m...
Federated learning (FL) has emerged as a powerful privacy-preserving approach that enables multiple devices to collaboratively train a machine learning model without sharing raw data. To motivate client participation and protect against malicious threats such as poisoning attacks, it is necessary to design a fair trading platform with an incentive...
Seeking more secure and effective digital representations.
Contemporary applications harness microservices architecture to attain scalability, loose coupling, and abstraction advantages. This approach involves breaking down applications into smaller, composable services, which are hosted in the cloud. Cloud deployment offers advantages like elastic load balancing, cost-efficiency, and ease of management. H...
Conventional manufacturing systems are shifting toward smart manufacturing where a wide range of devices are connected to the Internet, thanks to advances in Internet of Things (IoT) technology. The high connectivity of such devices introduces security risks because malicious nodes may attempt to compromise or tamper with data generated by the devi...
Due to the advancements in technology and microelectromechanical systems, there is an exceptional development in the capabilities of sensors and smart devices. Nowadays people interact with these devices regularly in their daily lives due to the enhanced computational power, compact size, user-friendly interface and reduced cost of these devices.
In the previous chapter, we employed a KEH transducer as a simultaneous source of energy and context information and showed that the harvested power from the transducer can be employed for signal acquisition leading towards energy-positive sensing.
In contrast to conventional activity sensors, energy harvesters provide both energy as well as context information. We have discussed in the previous chapter that kinetic, solar, thermal and RF energy harvesters can be used to detect the underlying activity in various applications. Among the available options, KEH is the most common harvesting mech...
Recent advancements in technology have led researchers and companies towards the design and development of low-power energy harvesting circuits [1] to harvest energy from the ambient environment for powering miniaturised sensor nodes. There are various energy harvesting sources, including radiation energy, mechanical energy and thermal energy, as d...
This book has presented various mechanisms for self-powered activity recognition in IoT. Conventional activity recognition systems use various activity sensors such as accelerometers, magnetometers and gyroscopes for wearable-based activity recognition.
In the previous chapter, we have discussed that SEH can be employed as source of context information and energy simultaneously. However, it may face problems during low light conditions such as at night to harvest sufficient energy to power a sensor node. Therefore, in order to enhance the harvested energy and context recognition performance, a fus...
Energy harvesters offer promising solution to the limited energy availability of IoT sensors by converting the environmental energy into electrical energy to power the tiny devices. Due to the abundantly available environmental energy, the energy harvesting mechanism can ensure perpetual operation of the sensors without the need of manual rechargin...
Today’s wearable Internet of Things (IoT) devices, which have been fêted for numerous applications, suffer from the limited lifetime of batteries due to the high power consumption of conventional inertial activity sensors. Recently, kinetic energy harvesters have been employed as a source of energy as well as context information to replace conventi...
In this paper, we propose to utilise diffusion models for data augmentation in speech emotion recognition (SER). In particular, we present an effective approach to utilise improved denoising diffusion probabilistic models (IDDPM) to generate synthetic emotional data. We condition the IDDPM with the textual embedding from bidirectional encoder repre...
Non-speech emotion recognition has a wide range of applications including healthcare, crime control and rescue, and entertainment, to name a few. Providing these applications using edge computing has great potential, however, recent studies are focused on speech-emotion recognition using complex architectures. In this paper, a non-speech-based emot...
The increasing adoption of clean energy technologies, including solar and wind generation, demand response, energy efficiency, and energy storage (e.g. batteries and electric vehicles) have led to the evolution of the traditional electricity markets from centralised energy trading systems into Distributed Energy Trading (DET) systems. Consequently,...
Food supply chains are increasingly digitised and automated through the use of technologies such as Internet-of-Things (IoT), blockchain and Artificial Intelligence (AI). Such digitization efforts often rely on cloud computing, which creates bandwidth overhead, high latency, security and privacy challenges. In this chapter, we propose the use of ed...
Flexible resources in built environments are seen as a low-cost opportunity for delivering grid management services. Consequently, the centralised aggregator model, where the aggregator is used to bundle demand flexibility from flexible resources and deliver it to flexibility customers such as Distributed/Transmission System Operator (DSO/TSO) in f...
In recent years blockchain technology has received tremendous attention. Blockchain users are known by a changeable Public Key (PK) that introduces a level of anonymity, however, studies have shown that anonymized transactions can be linked to deanonymize the users. Most of the existing studies on user de-anonymization focus on monetary application...
In recent years, there has been an increasing interest in incorporating blockchain for the Internet of Things (IoT) to address the inherent issues of IoT, such as single point of failure and data silos. However, blockchain alone cannot ascertain the authenticity and veracity of the data coming from IoT devices. The append-only nature of blockchain...
Distribution, security, and immutability have led to the great success of blockchain in many applications, while contributing to major increases in ledger size. The storage challenge is one of the major barriers to the adoption of blockchain in the Internet of Things (IoT), which consists of many resource constrained devices. In this paper, we prop...
Real-world applications in healthcare and supply chain domains produce, exchange, and share data in a multi-stakeholder environment. Data owners want to control their data and privacy in such settings. On the other hand, data consumers demand methods to understand when, how, and who produced the data. These requirements necessitate data governance...
Despite the recent progress in speech emotion recognition (SER), state-of-the-art systems lack generalisation across different conditions. A key underlying reason for poor generalisation is the scarcity of emotion datasets, which is a significant roadblock to designing robust machine learning (ML) models. Recent works in SER focus on utilising mult...
The complexity of cyberattacks in Cyber-Physical Systems (CPSs) calls for a mechanism that can evaluate critical infrastructures’ operational behaviour and security without affecting the operation of live systems. In this regard, Digital Twins (DTs) provide actionable insights through monitoring, simulating, predicting, and optimizing the state of...
Cyber Threat Intelligence (CTI) is the knowledge of cyber and physical threats that help mitigate potential cyber attacks. The rapid evolution of the current threat landscape has seen many organisations share CTI to strengthen their security posture for mutual benefit. However, in many cases, CTI data contains attributes (e.g., software versions) t...
COVID-19 has had a substantial impact globally. It spreads readily, particularly in enclosed and crowded spaces, such as public transport carriages, yet there are limited studies on how this risk can be reduced. We developed a tool for exploring the potential impacts of mitigation strategies on public transport networks, called the Systems Analytic...
6G is envisioned to enable futuristic technologies, which exhibit more complexities than the previous generations, as it aims to bring connectivity to a large number of devices, many of which may not be trustworthy. Proper authentication can protect the network from unauthorized adversaries. However, it cannot guarantee in situ reliability and trus...
In recent years, blockchain applications beyond cryptocurrency has received tremendous attention due to its salient features which includes distributed management, security, anonymity, and immutability. However, conventional blockchains suffer from lack of scalability, high complexity, privacy, and governance. In this paper, we study the existing s...
Despite the recent progress in speech emotion recognition (SER), state-of-the-art systems lack generalisation across different conditions. A key underlying reason for poor generalisation is the scarcity of emotion datasets, which is a significant roadblock to designing robust machine learning (ML) models. Recent works in SER focus on utilising mult...
In object detection, false negatives arise when a detector fails to detect a target object. To understand
why
object detectors produce false negatives, we identify five ‘false negative mechanisms,’ where each mechanism describes how a specific component inside the detector architecture failed. Focusing on two-stage and one-stage anchor-box object...
6G is envisioned to enable futuristic technologies, which exhibit more complexities than the previous generations, as it aims to bring connectivity to a large number of devices, many of which may not be trustworthy. Proper authentication can protect the network from unauthorized adversaries. However, it cannot guarantee in situ reliability and trus...
Blockchain has received tremendous attention as a secure, distributed, and anonymous framework for the Internet of Things (IoT). As a distributed system, blockchain trades off scalability for distribution, which limits the technology’s adaptation for large scale networks such as IoT. All transactions and blocks must be broadcast and verified by all...
Despite the recent advancement in speech emotion recognition (SER) within a single corpus setting, the performance of these SER systems degrades significantly for cross-corpus and cross-language scenarios. The key reason is the lack of generalisation in SER systems towards unseen conditions, which causes them to perform poorly in cross-corpus and c...
Despite the recent advancement in speech emotion recognition (SER) within a single corpus setting, the performance of these SER systems degrades significantly for cross-corpus and cross-language scenarios. The key reason is the lack of generalisation in SER systems towards unseen conditions, which causes them to perform poorly in cross-corpus and c...
With the rapid development of wireless sensor networks, smart devices, and traditional information and communication technologies, there is tremendous growth in the use of Internet of Things (IoT) applications and services in our everyday life. IoT systems deal with high volumes of data. This data can be particularly sensitive, as it may include he...
Today massive amounts of data are generated from Internet-of-Things (IoT) sensors that can be streamed in real-time and utilized for building valuable services. As the demand for data sharing has increased, a new business model of data marketplace has emerged that allows individuals to sell their data to buyers for monetary gain. However, these dat...
