We present a novel investigation into the impact of inter-drone interference on delivery efficiencies within multi-drone skyway networks. We conduct controlled experiments to analyze the behavior of drones in an indoor testbed environment. Our study compares performance between solo flights and concurrent multi-drone operations along predefined routes. This analysis captures interference occurring during both flight and at charging stations, providing a comprehensive evaluation of its effects on overall network performance. We conduct a comprehensive series of experiments across diverse scenarios to systematically understand and model the dynamics of inter-drone interference. Key metrics, such as power consumption and delivery times, are considered. This generates a comprehensive dataset for in-depth analysis of interference at both the node and segment levels. These findings are then formalized into a predictive model. The results validate the effectiveness of the developed model, demonstrating its potential to accurately forecast inter-drone interferences.

We propose a distributed Trust Information Management Framework (TIMF) for crowdsourced IoT services. TIMF is a stateful multi-agent framework for detecting and governing tampered trust information in the crowdsourced IoT service environment. The framework combines specialized detection agents, confidence-aware aggregation, and hierarchical belief modeling, and applies a utility-based governance mechanism to select optimal mitigation actions for tampered trust information. Experiments on real-world datasets show that TIMF achieves over 95% detection accuracy with high precision and recall, outperforming state-of-the-art baselines.

We propose Meta-DPMAPPO /met(sic)''' di:pi: m ae p(sic)o/, a metaverse multi-user service migration framework that combines Multi-Agent Proximal Policy Optimization (MAPPO) with Differential Privacy (DP)-enabled dual-domain perturbation. To maintain usability, we incorporate trajectory topology constraints that balance privacy strength with data availability. The framework enables dynamic service migration, i.e., transferring services to follow mobile users, to ensure low-latency access while safeguarding sensitive user data. We design a migration strategy with multiple migration actions (i.e., reuse, follow, and no migration) to minimize global delay and improve resource utilization. We conduct a series of experiments using a combination of public, collected, and synthetic datasets. The results demonstrate that our approach significantly reduces global migration delay in multi-user environments while ensuring privacy protection, and adapts well to different metaverse application scenarios.

We propose a distributed trust information management framework for crowdsourced IoT services. The crowdsourced IoT service environment consists of distributed entities that store and manage trust information. Traditional trust management frameworks often assume the trustworthiness of these entities. However, they may tamper with trust data, making the system vulnerable to internal attacks. The rise of AI tools, such as ChatGPT, has further lowered the barrier for adversaries, enabling even low-skilled actors to manipulate trust information with alarming sophistication. AI-assisted tampering could severely compromise trust assessments and mislead IoT service users. To counter this emerging threat, we propose a novel AI-based tampering detection approach, complemented by a heuristic-based approach to identify tampered trust information. We conduct a series of experiments to evaluate the effectiveness of the proposed approaches. The results demonstrate more than 95

We propose an integrity-preserving framework for managing trust information in crowdsourced IoT environments. The integrity of trust information is paramount for ensuring accurate trust assessment. Traditional trust frameworks assume that distributed storing entities of trust information are trustworthy, making them vulnerable to internal attacks. In this respect, entities responsible for storing trust data could tamper with information for personal gain and competitive advantage. Trust assessment using such tampered data could lead to inaccurate evaluations and may mislead IoT users within the environment. We propose a novel Tampering Detection Approach (TDA) to identify the tampering in trust information. Furthermore, we propose a technique to discover the tampering sophistication level. A set of experiments is conducted to evaluate the effectiveness and efficiency of the proposed approaches. Results demonstrate that our TDA achieves a 40% accuracy improvement in detecting tampered data compared to state-of-the-art methods.

We propose a novel Energy-Predictive Drone Service (EPDS) framework for efficient package delivery within a skyway network. The EPDS framework incorporates a formal modeling of an EPDS and an adaptive bidirectional Long Short-Term Memory (Bi-LSTM) machine learning model. This model predicts the energy status and stochastic arrival times of other drones operating in the same skyway network. Leveraging these predictions, we develop a heuristic optimization approach for composite drone services. This approach identifies the most time-efficient and energy-efficient skyway path and recharging schedule for each drone in the network. We conduct extensive experiments using a real-world drone flight dataset to evaluate the performance of the proposed framework.

The dynamic mobility of IoT devices poses challenges to the sustainability of energy crowdsourcing ecosystems. This mobility often leads to imbalanced energy supply and demand across different locations. We propose a preference-aware crowdsourcing approach that aligns energy provisioning with providers’ mobility patterns. This approach balances under-supplied microcells by allocating providers based on their spatial and temporal proximity to energy demand. Considering providers’ preferences reduces behavioural resistance and lowers incentive costs. We develop a mobile energy service model that captures providers’ spatio-temporal provisioning preferences. Our approach utilises this model to maximise energy fulfilment and minimise rewards. We evaluated our approach using real datasets that are combined to simulate realistic crowdsourcing scenarios. The experiments demonstrate that our approach is faster and more cost-efficient than state-of-the-art heuristics.

We propose a novel framework for optimizing Quality of Service (QoS) fulfillment to meet drone providers’ satisfaction. The proposed framework leverages the provisioning of drone service needs in terms of on-time recharging to maximize providers’ satisfaction. A QoS fulfillment impact model is developed to assess the effect of inter-drone interference in meeting desired delivery time and energy consumption targets. A novel interference-aware algorithm is proposed for effective and efficient provisioning of drone service needs to fulfill their desired QoS targets. Experimental results conducted on real-world data validate the efficiency and effectiveness of the proposed approach.

We conduct a survey on drones used as a service, denoted as drone-as-a-service (DaaS). We develop a novel taxonomy based on DaaS functions, research tasks, and application domains. We provide a discussion on drones and their associated capabilities based on their type of use. We propose a three-layered DaaS system architecture that vertically integrates cloud computing, drones, and services as a reference framework to compare existing drone service implementations. Additionally, we propose a representative uncertainty-aware DaaS model for delivery scenarios, illustrating how service definitions can incorporate both functional and nonfunctional attributes under dynamic environmental conditions. Finally, we identify and discuss future research directions and open problems related to the use of drones for service delivery.

We present a new service framework designed to determine the network provenance of social media images. This framework identifies the online platforms where an image has appeared, offering essential insights to accurately trace its origin. Ultimately, it assists in ascertaining the trustworthiness of online images. The innovative aspect of our design is its exclusive reliance on image metadata. We begin by analyzing how various social media platforms handle image metadata during the upload process. We then map these images into a high-dimensional Cartesian space, reflecting the metadata pruning that occur during upload. This projection captures the unique metadata pruning patterns of each platform, allowing us to identify their distinct fingerprints. This approach reveals the trajectory of images across various social media platforms. We conduct experiments on a subset of the Multimodal C4, Metadata Extractor and Image Ballistics on Social Data datasets. The results demonstrate almost 89 % accuracy in identifying the platform from which an image is sourced.

Precise drone landing remains a persistent challenge due to the high level of accuracy needed. We propose a novel technique that collects actual drone landing data and employs machine learning algorithms to predict errors in autonomous landing. Our model considers variables like battery charge, flight path, altitude, and velocity for prediction. Various trends associated with the drone's flight and landing are determined and visualised. We propose neural network models that use time series data from the drone's flight before landing to predict its landing position. Our best model reduced landing error to 2.34 cm, a 7% improvement over the baseline.

Fall detection is critical to support the growing elderly population, projected to reach 2.1 billion by 2050. However, existing methods often face data scarcity challenges or compromise privacy. We propose a novel IoT-based Fall Detection as a Service (FDaaS) framework to assist the elderly in living independently and safely by accurately detecting falls. We design a service-oriented architecture that leverages Ultra-wideband (UWB) radar sensors as an IoT health-sensing service, ensuring privacy and minimal intrusion. We address the challenges of data scarcity by utilizing a Fall Detection Generative Pre-trained Transformer (FD-GPT) that uses augmentation techniques. We developed a protocol to collect a comprehensive dataset of the elderly daily activities and fall events. This resulted in a real dataset that carefully mimics the elderly's routine. We rigorously evaluate and compare various models using this dataset. Experimental results show our approach achieves 90.72% accuracy and 89.33% precision in distinguishing between fall events and regular activities of daily living.

We propose a novel dynamic and immersive 3D framework designed to facilitate the setup and customization of drone scheduling algorithms for evaluating service-based drone delivery systems. This framework features a robust system architecture that supports user-defined behavior logic. It also incorporates real-time data communication protocols for relaying timely instructions to the drones. Additionally, it integrates a comprehensive drone energy consumption model that accurately simulates the physics of drone operations and accounts for both internal and external factors affecting energy usage. The framework includes a sophisticated 3D visualization component, depicting drone deliveries from source to destination through a realistic skyway network within an interactive virtual urban environment. It also enables automated data tracking, which is crucial for testing algorithms and collecting data to support data-driven decisions and optimizations. We evaluate the framework by conducting a comprehensive usability test to assess its user interface and overall user experience. Additionally, we test the framework using a drone swarm to execute delivery requests under both simple and complex energy consumption models. The results show that the framework has a user-friendly interface and effectively supports drone delivery simulations under the complex physics-based energy consumption model.

Social media platforms usually contain several modified versions of an image. This proliferation of versions questions the trust of social media images. We propose a novel framework to find modified versions of social media images using only their metadata. We consider several aspects to determine if an image is a modified version of another image. These aspects include topic of an image, spatio-temporal information, and semantic similarity. We first do topic modeling to find images linked to the same context. Secondly, we perform spatio-temporal clustering to group spatio-temporally close images. Finally, we perform hierarchical clustering to form more precise clusters of versions. Notably, the proposed framework also considers modifications introduced in an image's metadata while determining versions of the image. Modifications in social media images pose a significant challenge to correctly cluster versions together as a version may exhibit significant deviations from its original image. We address this issue by exploring inconsistencies in the image metadata. These inconsistencies are reflective of the changes in an image. We validate our model on a fact-checked image verification corpus and the Multimodal C4 dataset. We achieve around 95% accuracy, validating the effectiveness of the proposed approach.

We propose a novel service-based interference resolution framework for drones operating in a shared skyway network. This network consists of interconnected line-of-sight segments between designated building rooftops that serve as charging and delivery stations for drones. We propose an approach that effectively and efficiently mitigates delays in service delivery caused by interference between drones operating in close proximity within skyway segments. We use a range of constraints to determine the likelihood of impactful interferences to map out proximity distances for the safe and efficient delivery of drone services. Experimental results conducted on real-world data validate the effectiveness of the proposed approach.

We propose a novel Quality of Experience (QoE) metric as a key criterion for optimizing the composition of energy services within a crowdsourced IoT environment. Two novel composition approaches, namely, Importance-based and Heuristic-based, are proposed to ensure the highest QoE for consumers. The Importance-based approach prioritizes time slots based on their significance. The Heuristic-based approach considers the importance of time slots and the availability of services to maximize QoE while minimizing service provisioning costs. We conduct extensive experiments using real-world datasets to evaluate the effectiveness and efficiency of the proposed approaches. The results demonstrate that both approaches enhance consumer satisfaction by optimizing energy allocation, with the Heuristic-based approach outperforming the Importance-based method in minimizing rewards.

We propose a distributed trust information management framework for crowdsourced IoT services. The distributed entities responsible for storing trust information may sometimes be unavailable or untrustworthy, meaning they might either withhold trust information or provide tampered trust data. In our framework, we introduce a trust information availability improvement approach to obtain additional trust information while detecting tampered trust records. Moreover, we present an adaptive trust information sufficiency estimate method to assess whether the available trust data is sufficient to compute a statistically reliable trust score. A series of experiments were conducted to evaluate the effectiveness of the proposed approaches. The results demonstrate that the estimated trust scores deviate by no more than 2% from the actual scores, confirming the effectiveness of our approach.

We propose a novel service-based framework for drone service resilience. Our framework monitors inter-drone interference that may lead to drone service failure. We present a novel drone service interference taxonomy to formally identify different interference types in a skyway network. We then propose a heuristic-based approach that leverages spatio-temporal proximity analysis to detect the occurrence of inter-drone interference. In addition, we present an interference severity assessment to quantify their impact on drone services' efficiency. We conduct a set of experiments using real-world datasets to evaluate the effectiveness and efficiency of our proposed approach. The results indicate that the proposed heuristic-based approach detects the occurrence of inter-drone interferences with an accuracy of 95%. In addition, the proposed method is $\approx$approximate to 70% more efficient than the baseline exhaustive approach and $\approx$approximate to 48% faster than the K-means approach.

We propose a novel drone traffic monitoring system for smart cities, featuring skyway networks that connect rooftop hubs equipped with recharging stations for long-distance deliveries. However, inter-drone interference may impact the safe and efficient provisioning of drone delivery services as drones operate in shared aerial pathways and utilize recharging stations. To address this challenge, we propose a framework to evaluate the impact of interferences on drones' delivery efficiency and safety, accompanied by a purposebuilt tool implementing the framework. The tool is based on real data gathered through drones' flights in an indoor testbed. The insights generated by the tool allowfor optimizing drones' flight paths by mitigating and resolving potential inter-drone interferences.

We propose a novel change detection framework to identify changes in the long-term performance behavior of an IaaS service. An IaaS service's long-term performance behavior is represented by an IaaS performance signature. The proposed framework leverages time series similarity measures and a sliding window technique to detect changes in IaaS performance signatures. We introduce a new IaaS performance noise model that enables the proposed framework to distinguish between performance noise and actual changes in performance. The proposed framework utilizes a novel Signal-to-Noise Ratio (SNR) based approach to detect changes when prior knowledge about performance noise is available. A set of experiments is conducted using real-world datasets to demonstrate the effectiveness of the proposed change detection framework.