No abstract

The version in the Kent Academic Repository may differ from the final published version. Users are advised to check http://kar.kent.ac.uk for the status of the paper. Users should always cite the published version of record.

Aims Most patients who receive implantable cardioverter defibrillators (ICDs) for primary prevention do not receive therapy during the lifespan of the ICD, whilst up to 50% of sudden cardiac death (SCD) occur in individuals who are considered low risk by conventional criteria. Machine learning offers a novel approach to risk stratification for ICD assignment. Methods and results Systematic search was performed in MEDLINE, Embase, Emcare, CINAHL, Cochrane Library, OpenGrey, MedrXiv, arXiv, Scopus, and Web of Science. Studies modelling SCD risk prediction within days to years using machine learning were eligible for inclusion. Transparency and quality of reporting (TRIPOD) and risk of bias (PROBAST) were assessed. A total of 4356 studies were screened with 11 meeting the inclusion criteria with heterogeneous populations, methods, and outcome measures preventing meta-analysis. The study size ranged from 122 to 124 097 participants. Input data sources included demographic, clinical, electrocardiogram, electrophysiological, imaging, and genetic data ranging from 4 to 72 variables per model. The most common outcome metric reported was the area under the receiver operator characteristic (n = 7) ranging between 0.71 and 0.96. In six studies comparing machine learning models and regression, machine learning improved performance in five. No studies adhered to a reporting standard. Five of the papers were at high risk of bias. Conclusion Machine learning for SCD prediction has been under-applied and incorrectly implemented but is ripe for future investigation. It may have some incremental utility in predicting SCD over traditional models. The development of reporting standards for machine learning is required to improve the quality of evidence reporting in the field.

No abstract

The study of mouse social behaviours has been increasingly undertaken in neuroscience research. However, automated quantification of mouse behaviours from the videos of interacting mice is still a challenging problem, where object tracking plays a key role in locating mice in their living spaces. Artificial markers are often applied for multiple mice tracking, which are intrusive and consequently interfere with the movements of mice in a dynamic environment. In this paper, we propose a novel method to continuously track several mice and individual parts without requiring any specific tagging. Firstly, we propose an efficient and robust deep learning based mouse part detection scheme to generate part candidates. Subsequently, we propose a novel Bayesianinference Integer Linear Programming Model that jointly assigns the part candidates to individual targets with necessary geometric constraints whilst establishing pair-wise association between the detected parts. There is no publicly available dataset in the research community that provides a quantitative test-bed for the part detection and tracking of multiple mice, and we here introduce a new challenging Multi-Mice PartsTrack dataset that is made of complex behaviours. Finally, we evaluate our proposed approach against several baselines on our new datasets, where the results show that our method outperforms the other state-of-the-art approaches in terms of accuracy. We also demonstrate the generalization ability of the proposed approach on tracking zebra and locust.

The images captured in the underwater scene frequently suffer from blur effects due to the insufficient light and the relative motion between the captured scenes and the imaging system, which severely hinders the visual-based exploration and investigation in the ocean. In this paper, we propose a feature pyramid attention network (FPAN) to remove the motion blur and restore the blurry underwater images. FPAN incorporates the cascaded attention modules into the feature pyramid network (FPN) that enables it to learn more discriminative information. To facilitate the training of FPAN, we construct a weighted loss function, which consists of a content loss, an adversarial loss, and a perceptual loss. The cascaded attention module and the weighted loss function enable our proposed FPAN to generate more realistic high-quality images from the blurry underwater images. In addition, to deal with the lack of publicly available datasets in underwater image deblurring, we built two specific underwater deblurring datasets, namely Underwater Convolutional Deblurring Dataset (UCDD) and Underwater Multi-frame Averaging Deblurring Dataset (UMADD), to train and examine different deep learning-based networks. Finally, we conduct sea trial experiments on our autonomous underwater vehicle (AUV). Experimental results on two underwater deblurring datasets demonstrate our proposed method achieves satisfactory results, which validates the potential practical values of our proposed method in real-world applications.