Particle filters are essential for state estimation in non-linear and non-Gaussian systems, with performance hinging on effective proposal distributions. This paper presents the implementation of Kalman Filter and No-U-Turn Sampler (NUTS) proposals within the Stone Soup Python framework. The Kalman Filter proposal offers computational efficiency for structured systems, while NUTS enables robust exploration of complex, highdimensional distributions. Benchmark evaluations demonstrate the complementary strengths of these methods, enhancing Stone Soup's capabilities for diverse state estimation challenges.

Markov chain Monte Carlo (MCMC) methods are a powerful but computationally expensive way of performing nonparametric Bayesian inference. MCMC proposals which utilise gradients, such as Hamiltonian Monte Carlo (HMC), can better explore the parameter space of interest if the additional hyperparameters are chosen well. The No-U-Turn Sampler (NUTS) is a variant of HMC which is extremely effective at selecting these hyper-parameters but is slow to run and is not suited to GPU architectures. An alternative to NUTS, Change in the Estimator of the Expected Square HMC (ChEES-HMC) was shown not only to run faster than NUTS on GPU but also sample from posteriors more efficiently. Sequential Monte Carlo (SMC) samplers are another sampling method which instead output weighted samples from the posterior. They are very amenable to parallelisation and therefore being run on GPUs while having additional flexibility in their choice of proposal over MCMC. We incorporate (ChEES-HMC) as a proposal into SMC samplers and demonstrate competitive but faster performance than NUTS on a number of tasks.

This demo paper introduces an application that is capable of identifying and visualising diagnostic arguments within abstract argumentation systems. The software presented is underpinned by a novel algorithm, called the Diagnostic Argument Identifier, that combines a semantic-based approach with a technique from the information-theoretic literature, to quantify the impact that the removal of an argument has on the acceptability of other arguments.

This paper presents an extended target tracking method to track trains using Distributed Acoustic Sensing (DAS) data. The problem is approached using a measurement likelihood based on a Set of Points on a Rigid Body (SPRB) model applied to a clustered version of the Poisson Multi-Bernoulli Mixture filter. The method efficiently handles asymmetric noise within the set of measurements returned by each train, and proposes a solution to merged measurements appearing at crossings. We use experimental data obtained from trains to show that the proposed algorithm has lower localisation and false target error, leading to better performance in terms generalized optimal sub-pattern assignment (GOSPA) metric.

Markov Chain Monte Carlo (MCMC) is a method for drawing samples from non-standard probability distributions. Hamiltonian Monte Carlo (HMC) is a popular variant of MCMC that uses gradient information to explore the target distribution. The Sequential Monte Carlo (SMC) sampler is an alternative sampling method which, unlike MCMC, can readily utilise parallel computing architectures. It is typical within SMC literature to target a tempered distribution using a proposal with an accept/reject mechanism. In this letter, we show how the proposal used in the No-U-Turn Sampler (NUTS), an advanced variant of HMC, can be incorporated into an SMC sampler without an accept/reject mechanism. Empirical results show that this can remove the need for tempering and gives rise to accurate estimates being generated in fewer iterations which motivates this technique being deployed on parallel hardware.

The growing popularity of social media raises concerns about children’s online safety. Of particular concern are interactions between minors and adults with predatory intentions. Unfortunately, previous research on online sexual grooming has relied on time-intensive manual annotation by domain experts, limiting both the scale and scope of possible interventions. This work explores the possibility of detecting predatory behaviours with accuracy comparable to expert annotators using machine learning (ML). Using a dataset of 6771 chat messages sent by child sex offenders, labelled by two of the authors who are forensic psychology experts, we study how well can deep learning algorithms identify eleven known predatory behaviours. We find that the best-performing ML models are consistent but not on par with expert annotation. We therefore consider a system where an expert annotator validates the ML algorithms outputs. The combination of human decision-making and computer efficiency yields precision—but not recall—comparable to manual annotation, while taking only a fraction of the time needed by a human annotator. Our findings underscore the promise of ML as a tool for assisting researchers in this area, but also highlight the current limitations in reliably detecting online sexual exploitation using ML.

Modern classification problems tackled by using Decision Tree (DT) models often require demanding constraints in terms of accuracy and scalability. This is often hard to achieve due to the ever-increasing volume of data used for training and testing. Bayesian approaches to DTs using Markov Chain Monte Carlo (MCMC) methods have demonstrated great accuracy in a wide range of applications. However, the inherently sequential nature of MCMC makes it unsuitable to meet both accuracy and scaling constraints. One could run multiple MCMC chains in an embarrassingly parallel fashion. Despite the improved run-time, this approach sacrifices accuracy in exchange for strong scaling. Sequential Monte Carlo (SMC) samplers are another class of Bayesian inference methods that also have the appealing property of being parallelizable without trading off accuracy. Nevertheless, finding an effective parallelization for the SMC sampler is difficult, due to the challenges in parallelizing its bottleneck, redistribution, in such a way that the workload is equally divided across the processing elements, especially when dealing with variable-size models such as DTs. This study presents a parallel SMC sampler for DTs on Shared Memory (SM) architectures, with an$O(log_{2} N)$parallel redistribution for variable-size samples. On an SM machine mounting 32 cores, the experimental results show that our proposed method scales up to a factor of 16 compared to its serial implementation, and provides comparable accuracy to MCMC, but 51 times faster.

We consider the problem of detecting small and manoeuvring objects with staring array radars. Coherent processing and long-time integration are key to addressing the undesirably low signal-to-noise/background conditions in this scenario and are complicated by the object manoeuvres. We propose a Bayesian solution that builds upon a Bernoulli state space model equipped with the likelihood of the radar data cubes through the radar ambiguity function. Likelihood evaluation in this model corresponds to coherent long-time integration. The proposed processing scheme consists of Bernoulli filtering within expectation maximisation iterations that aims at approximately finding complex reflection coefficients. We demonstrate the efficacy of our approach in a simulation example.

Depression is a common mental health condition that often occurs in association with other chronic illnesses, and varies considerably in severity. Electronic Health Records (EHRs) contain rich information about a patient's medical history and can be used to train, test and maintain predictive models to support and improve patient care. This work evaluated the feasibility of implementing an environment for predicting mental health crisis among people living with depression based on both structured and unstructured EHRs. A large EHR from a mental health provider, Mersey Care, was pseudonymised and ingested into the Natural Language Processing (NLP) platform CogStack, allowing text content in binary clinical notes to be extracted. All unstructured clinical notes and summaries were semantically annotated by MedCAT and BioYODIE NLP services. Cases of crisis in patients with depression were then identified. Random forest models, gradient boosting trees, and Long Short-Term Memory (LSTM) networks, with varying feature arrangement, were trained to predict the occurrence of crisis. The results showed that all the prediction models can use a combination of structured and unstructured EHR information to predict crisis in patients with depression with good and useful accuracy. The LSTM network that was trained on a modified dataset with only 1000 most-important features from the random forest model with temporality showed the best performance with a mean AUC of 0.901 and a standard deviation of 0.006 using a training dataset and a mean AUC of 0.810 and 0.01 using a hold-out test dataset. Comparing the results from the technical evaluation with the views of psychiatrists shows that there are now opportunities to refine and integrate such prediction models into pragmatic point-of-care clinical decision support tools for supporting mental healthcare delivery.

Can an interviewer influence the cooperativeness of an interviewee? The role of an interviewer in actualising a successful interview is an active field of social psychological research. A large-scale analysis of interviews, however, typically involves time-exorbitant manual tasks and considerable human effort. Despite recent advances in computational fields, many automated methods continue to rely on manually labelled training data to establish ground-truth. This reliance obscures explainability and hinders the mobility of analysis between applications. In this work, we introduce a cross-disciplinary approach to analysing interviewer efficacy. We suggest computational success measures as a transparent, automated, and reproducible alternative for pre-labelled data. We validate these measures with a small-scale study with human-responders. To study the interviewer’s influence on the interviewee we utilise features informed by social psychological theory to predict interview quality based on the interviewer’s linguistic behaviour. Our psychologically informed model significantly outperforms a bag-of-words model, demonstrating the strength of a cross-disciplinary approach toward the analysis of conversational data at scale.

As the largest distance learning university in the UK, the Open University has more than 250,000 students enrolled, making it also the largest academic institute in the UK. However, many students end up failing or withdrawing from online courses, which makes it extremely crucial to identify those “at risk” students and inject necessary interventions to prevent them from dropping out. This study thus aims at exploring an efficient predictive model, using both behavioural and demographical data extracted from the anonymised Open University Learning Analytics Dataset (OULAD). The predictive model was implemented through machine learning methods that included BART. The analytics indicates that the proposed model could predict the final result of the course at a finer granularity, i.e., classifying the students into Withdrawn, Fail, Pass, and Distinction, rather than only Completers and Non-completers (two categories) as proposed in existing studies. Our model’s prediction accuracy was at 80% or above for predicting which students would withdraw, fail and get a distinction. This information could be used to provide more accurate personalised interventions. Importantly, unlike existing similar studies, our model predicts the final result at the very beginning of a course, i.e., using the first assignment mark, among others, which could help reduce the dropout rate before it was too late.

Under the standard multiple target tracking models and a Poisson point process birth model, the Poisson multi-Bernoulli mixture (PMBM) filter provides the closed-form recursion to computing the posterior density over the set of targets. Without approximations, the PMBM computational complexity rapidly rises in time due to the increasing number of data association hypotheses. This paper presents innovative strategies for merging Bernoulli components for the same potential target reducing the number of single-target hypotheses in the PMBM filter, aiming to lower its computational complexity while keeping its performance high. We use several measures to compute the similarity between different Bernoulli components. Simulation results show that the proposed algorithms show performance close to the PMBM filter without Bernoulli merging, as measured by the generalized optimal sub-pattern assignment (GOSPA) metric, with a significantly reduced execution time.

This paper presents the continuous-discrete trajectory probability hypothesis density (CD-TPHD) and the continuous-discrete trajectory cardinality PHD (CD-TCPHD) filter. We consider continuous-time models for target appearance, dynamics and disappearance, which are discretised to obtain the corresponding continuous-discrete models. The CD-TPHD filter propagates a Poisson point process approximation to the posterior (multi-trajectory) density over the set of alive trajectories sampled at the time instants when the measurements have been taken. The CD-TCPHD filter proceeds analogously but propagating a density on an independent and identically distributed (IID) cluster process. An important, novel feature of these filters is that they can infer the time of appearance and the state at appearance time of the trajectories in continuous time, not being constrained to discretised time steps.

In this paper, we discuss the derivations, implementations and performance of target tracking algorithms for a single-target single-sensor system estimating the state, covariance and existence probability of a target. Given the target exists, we simulate measurements of the target with a given probability of detection, along with false measurements (clutter) parametrised by a clutter density. We evaluate the performance of the algorithms by computing the area under Receiver Operating Characteristic (ROC) curves against a range of clutter density values. We give particular attention to the effectiveness of correctly inferring the presence or absence of the target. We select the Integrated Probabilistic Data Association Filter (IPDAF) and the Integrated Expected Likelihood Particle Filter (IELPF) algorithms, with the IELPF implementing a near-optimal proposal which uses the current scan of measurements as well as a prior proposal for comparison. Simulation results indicate the performance of the IPDAF exceeds that of the preexisting particle filter implementing a prior proposal, but a novel particle filter using a near-optimal proposal and a modest number of particles outperforms the IPDAF.

In this paper we describe a Sequential Monte Carlo (SMC) sampler that performs joint tracking and destination estimation of a target traveling along a known road network, as its journey progresses. The destination estimation is based on a simplistic model of driver intent, which assumes no prior knowledge of the history of visited destinations. The proposed algorithm is capable of refining the distribution of destinations that can be inferred from an incoming stream of position estimates. We compare the performance achieved by the proposed algorithm with a mainstay Particle Filter, demonstrating how the later suffers greatly from sample impoverishment, therefore necessitating an ever increasing number of particles as the number of possible destinations increases, while showcasing that the issue is significantly mitigated by the proposed SMC Sampler.

Pixel-based image alignment has always struggled to simultaneously reject outliers, avoid local minima and run quickly. There are many robust cost functions that perform well in terms of rejecting outliers, but they can yield unstable results during long image sequences as a result of their inability to adjust to changes in image content. In this paper, we propose a parameterised student-t cost function that can interpolate between two cost functions that are amongst the most widely used ones in image alignment problems, the L2 norm (quadratic function) and the Cauchy-Lorentzian function. We also propose a parameter estimation method that helps to find optimal parameters for the proposed cost function for a video. Experiments prove that the proposed approach can estimate the alignment variable accurately relative to the existing cost functions without demanding a higher computational cost.

This paper studies the reliability of a real-world learning-enabled system, which conducts dynamic vehicle tracking based on a high-resolution wide-area motion imagery input. The system consists of multiple neural network components - to process the imagery inputs - and multiple symbolic (Kalman filter) components - to analyse the processed information for vehicle tracking. It is known that neural networks suffer from adversarial examples, which make them lack robustness. However, it is unclear if and how the adversarial examples over learning components can affect the overall system-level reliability. By integrating a coverage-guided neural network testing tool, DeepConcolic, with the vehicle tracking system, we found that (1) the overall system can be resilient to some adversarial examples thanks to the existence of other components, and (2) the overall system presents an extra level of uncertainty which cannot be determined by analysing the deep learning components only. This research suggests the need for novel verification and validation methods for learning-enabled systems.

We study for the first time the verification problem on learning-enabled state estimation systems for robotics, which use Bayes filter for localisation, and use deep neural network to process sensory input into observations for the Bayes filter. Specifically, we are interested in a robustness property of the systems: given a certain ability to an adversary for it to attack the neural network without being noticed, whether or not the state estimation system is able to function with only minor loss of localisation precision? For verification purposes, we reduce the state estimation systems to a novel class of labelled transition systems with payoffs and partial order relations, and formally express the robustness property as a constrained optimisation objective. Based on this, practical verification algorithms are developed. As a major case study, we work with a real-world dynamic tracking system that uses a Kalman filter (a special case of the Bayes filter) to localise and track a ground vehicle. Its perception system, based on convolutional neural networks, processes a high-resolution Wide Area Motion Imagery (WAMI) data stream. Experimental results show that our algorithms can not only verify the robustness of the WAMI tracking system but also provide useful counterexamples.

Particle Filters (PFs) are Sequential Monte Carlo methods which are widely used to solve filtering problems of dynamic models under Non-Linear Non-Gaussian noise. Modern PF applications have demanding accuracy and run-time constraints that can be addressed through parallel computing. However, an efficient parallelization of PFs can only be achieved by effectively parallelizing the bottleneck: resampling and its constituent redistribution step. A pre-existing implementation of redistribute on Shared Memory Architectures (SMAs) achieves O(NT log2N) time complexity over T parallel cores. This redistribute implementation is, however, highly computationally intensive and cannot be effectively parallelized due to the inherently limited number of cores of SMAs. In this paper, we propose a novel parallel redistribute on OpenMP 4.5 which takes O(N/T + log2N) steps and fully exploits the computational power of SMAs. The proposed approach is up to six times faster than the O(N/T log2N) one and its implementation on GPU provides a further three-time speed-up vs its equivalent on a 32-core CPU. We also show on an exemplary PF that our redistribution is no longer the bottleneck.

Ahstract-This paper considers the problem of tracking a manoeuvring target when some of the measurements are delayed by the time taken to propagate through some medium. We are especially interested in bearing-only measurements, since it is possible to extract range information by fusing measurements which have negligible propagation delay (such as from electrooptical sensors) and measurements which have a propagation delay proportional to the range to the target (such as from acoustic sensors). This requires us to handle measurements which appear out of sequence, and with emission times unknown to the tracker. Unlike previous approaches, a particle filter is used, which handles out-of-sequence measurements by storing a history of hypothesised target states and measurement emission times for each particle. This allows new target states and times to be inserted into the trajectory of each target by interpolating between adjacent states in the history.

Manifold embedding techniques have properties that render them attractive candidates to learn a compact and general representation of a three dimensional spatial object. In turn this representation can be used for object recognition through classification. This paper presents a comparative study of several supervised spectral embedding techniques and their relationship with the feature space used to describe the exemplars which act as inputs to an embedding procedure. By concentrating on this aspect, we are able to highlight preferential combinations between feature description and embedding, and we formulate recommendations on the use of such methods for fusing multiple views of an object to recognize it under variable poses.

This paper compares the tracking performance that can be achieved when using a nonlinear drag model for a helicopter, a constant drag motion model, and a baseline constant acceleration model. A particle filter is used for state estimation to address problems associated with nonlinear drag and nonlinear measurements of helicopter pose. We demonstrate that the inclusion of this nonlinear kinematic effect provides improved tracking performance for a manoeuvring target.

This paper proposes an improvement to FastSLAM. The approach is applicable when the dynamic model describing the motion of the camera has linear sub-structure. The core novelty of the proposed algorithm is to separate the consideration of the camera's dynamic model into two sub-models without constraining the two sub-models to have independent noise processes. In contrast to commonly-used FastSLAM algorithms, which use a particle filter to consider both these sub-models, a particle filter is used for one sub-model and a Kalman filter for the other. This tactic is Rao-Blackwellisation and is the same as that which underpins the development of FastSLAM, but where the focus was only on exploiting near-linear sub-structure related to the state of the landmarks. Comparisons with Unscented FastSLAM 2.0 indicate that the new approach improves estimation accuracy. Comparisons with cutting-edge SLAM algorithms also reflect the competitive nature of this approach as a solution to navigation problems. Future work will improve the processing of features and consider multi-sensor data input.

An assignment problem is considered with the constraint that the same hypothesis cannot be applied to more than one object. We desire efficiency without approximation. Multiple target tracking methods such as the joint probabilistic association filter (JPDAF) motivate us. Methods of solving this assignment problem involving enumerating all possible joint assignments is infeasible except for small problems. A recent approach circumvents this combinatorial explosion by representing the structure of the target hypotheses in a `net' which exploits redundancy in an ordered list of objects us to describe the problem. Here, we generalize this approach to process the objects in a tree structure this exploits conditional independence between subsets of the objects. This gives a substantial computational saving and allows us to consider scenarios which were previously impractical. In particular, we show the feasibility of using an exact JPDAF implementation to track 400 targets

This paper describes the integration of a particle filter and a continuous version of the transferable belief model. The output from the particle filter is used as input to the transferable belief model. The transferable belief model's continuous nature allows for the prior knowledge over the classification space to be incorporated within the system. Classification of objects is demonstrated within the paper and compared to the more classical Bayesian classification routine. This is the first time that such an approach has been taken to jointly classify and track targets. We show that there is a great deal of flexibility built into the continuous transferable belief model and in our comparison with a Bayesian classifier, we show that our novel approach offers a more robust classification output that is less influenced by noise

We propose efficient particle smoothing methods for generalized state-spaces models. Particle smoothing is an expensive O(N2) algorithm, where N is the number of particles. We overcome this problem by integrating dual tree recursions and fast multipole techniques with forward-backward smoothers, a new generalized two-filter smoother and a maximum a posteriori (MAP) smoother. Our experiments show that these improvements can substantially increase the practicality of particle smoothing.

Most object tracking approaches either assume that the number of objects is constant, or that information about object existence is provided by some external source. Here, we show how object existence can be rigorously integrated within the Bayesian single and multiple object tracking framework. We provide a general treatment that impacts as little as possible on existing tracking algorithms, so that software can be reused, and that allows implementation with Kalman filters, extended Kalman filters, particle filters, etc. We apply the proposed framework to colour-based tracking of multiple objects.