State prediction from noisy time series measurements is a challenging task found in areas like intelligent transport, structural health monitoring, and environmental monitoring. This paper proposes a Spatio-Temporal Deep Kernel Gaussian Process (STDK GP) approach, which leverages the feature extraction capabilities of convolutional neural networks with the uncertainty quantification of Gaussian Process (GP) methods. The model features a composite spatio-temporal kernel that operates on learned deep features. A key aspect of our approach is that this kernel is learned end-to-end with the feature extractor, allowing it to effectively capture complex spatial and temporal patterns and enabling robust uncertainty quantification. Evaluated on a real-world vehicular traffic forecasting task, the proposed STDK GP demonstrates superior performance. Specifically, it achieves a root mean square error of 2.67105 km/h and improves prediction accuracy by approximately 15.28% over the standard GP approach, 21.23% over the state-of-the-art structural recurrent neural network and by more than 53% over stand-alone deep neural networks.

Active sensing plays an essential role in searching and tracking a target without initial target state information. This paper studies the active sensing approach for sensor management problems using multiple unmanned aerial vehicles based on the received signal strength measurements of the target. A Bayesian optimisation-based approach is proposed which adopts the Gaussian process method to model the received signal strength in an area over time and then the expected improvement acquisition function is leveraged to decide where to take new measurements considering the uncertainty of the Gaussian process. A unique contribution of this paper consists of the designed spatial-temporal composite kernel function that accounts for the time-varying nature of the signal strength. Numerical results obtained from different measurement noise levels and varying initial Bayesian optimisation settings demonstrate that the proposed approach can efficiently schedule multiple unmanned aerial vehicles to locate the target within a minimum number of initial data. Particularly, it achieves at most $57 \%$ lower tracking error and $46 \%$ lower lost-track probability as compared to the benchmark approach.

This paper explores the application of centralised and distributed Gaussian process algorithms to real-time target tracking and compares their performance. By embedding the algorithms into the Stone Soup, the focus is on the innovative implementation of Gaussian process methods with learning hyperparameters and implementation with a factorised variance of the Gaussian kernel. The performance of the methods with different kernels was evaluated, not only with the Gaussian kernel. Extensive experiments with various kernel configurations demonstrate their importance in enhancing prediction accuracy and efficiency, especially in real-time tracking. The case studies with manoeuvring targets show significant advancements in tracking capabilities, particularly in wireless sensor networks, using optimised Gaussian process methods. This work advances Stone Soup’s capabilities and lays the groundwork for future investigations into adaptive Gaussian Process applications in tracking and sensor data analysis.

This paper proposes an edge-assisted crowdsourced live video transcoding approach where the transcoding capabilities of the edge transcoders are unknown and dynamic. The resilience and trustworthiness of highly unstable transcoders in decision making are characterized with mean-variance-based measures to avoid making highly risky decisions. The risk level of each device’s situation is assessed and two upper confidence bounds of the variance of transcoding performance are presented. Based on the derived bounds and by leveraging the contextual information of devices, two risk-aware contextual learning schemes are developed to efficiently estimate the transcoding capabilities of the edge devices. Combining context awareness and risk sensitivity, a novel transcoding task assignment and viewer association algorithm is proposed. Simulation results demonstrate that the proposed algorithm achieves robust task offloading with superior network utility performance as compared to the linear upper confidence bound and the risk-aware mean-variance upper confidence bound-based algorithms. In particular, an epoch-based task assignment strategy is designed to reduce the task switching costs incurred in assigning the same transcoding task to different transcoders over time. This strategy also reduces the computational time needed. Numerical results confirm that this strategy achieves up to 86.8% switching costs reduction and 92.3% computational time reduction.

Radio signal-based (indoor) localisation technique is important for IoT applications such as smart factory and warehouse. Through machine learning, especially neural networks methods, more accurate mapping from signal features to target positions can be achieved. However, different radio protocols, such as WiFi, Bluetooth, etc., have different features in the transmitted signals that can be exploited for localisation purposes. Also, neural networks methods often rely on carefully configured models and extensive training processes to obtain satisfactory performance in individual localisation scenarios. The above poses a major challenge in the process of determining neural network model structure, or hyperparameters, as well as the selection of training features from the available data. This paper proposes a neural network model hyperparameter tuning and training method based on Bayesian optimisation. Adaptive selection of model hyperparameters and training features can be realised with minimal need for manual model training design. With the proposed technique, the training process is optimised in a more automatic and efficient way, enhancing the applicability of neural networks in localisation.

The classical multi-armed bandit (MAB) framework studies the exploration-exploitation dilemma of the decisionmaking problem and always treats the arm with the highest expected reward as the optimal choice. However, in some applications, an arm with a high expected reward can be risky to play if the variance is high. Hence, the variation of the reward should be considered to make the arm-selection process risk-aware. In this letter, the mean-variance metric is investigated to measure the uncertainty of the received rewards. We first study a risk-aware MAB problem when the reward follows a Gaussian distribution, and a concentration inequality on the variance is developed to design a Gaussian risk aware-upper confidence bound algorithm. Furthermore, we extend this algorithm to a novel asymptotic risk aware-upper confidence bound algorithm by developing an upper confidence bound of the variance based on the asymptotic distribution of the sample variance. Theoretical analysis proves that both proposed algorithms achieve the O(log(T)) regret. Finally, numerical results demonstrate that our algorithms outperform several risk-aware MAB algorithms.

With the rapid development of social networks and high-quality video sharing services, the demand for delivering large quantity and high quality contents under stringent end-to-end delay requirement is increasing. To meet this demand, we study the content caching problem modelled as a Markov decision process in the network edge server when the popularity profiles are unknown and time-varying. In order to adapt to the changing trends of content popularity, a context-aware popularity learning algorithm is proposed. We prove that the learning error of this scheme is sublinear in the number of requests. In light of the learned popularities, a reinforcement learning-based caching scheme is designed on top of the state-action-reward-state-action algorithm with a function approximation. A reactive caching algorithm is also proposed to reduce the complexity. The time complexities of both the caching schemes are studied to demonstrate their feasibility in real time systems and a theoretical analysis is performed to prove that the cache hit rate of the reactive caching algorithm asymptotically converges to the optimal cache hit rate. Finally the simulations are presented to demonstrate the superiority of the proposed algorithms.