A key factor in the fight against viral diseases such as the coronavirus (COVID-19) is the identification of virus carriers as early and quickly as possible, in a cheap and efficient manner. The application of deep learning for image classification of chest X-ray images of COVID-19 patients could become a useful pre-diagnostic detection methodology. However, deep learning architectures require large labelled datasets. This is often a limitation when the subject of research is relatively new as in the case of the virus outbreak, where dealing with small labelled datasets is a challenge. Moreover, in such context, the datasets are also highly imbalanced, with few observations from positive cases of the new disease. In this work we evaluate the performance of the semi-supervised deep learning architecture known as MixMatch with a very limited number of labelled observations and highly imbalanced labelled datasets. We demonstrate the critical impact of data imbalance to the model’s accuracy. Therefore, we propose a simple approach for correcting data imbalance, by re-weighting each observation in the loss function, giving a higher weight to the observations corresponding to the under-represented class. For unlabelled observations, we use the pseudo and augmented labels calculated by MixMatch to choose the appropriate weight. The proposed method improved classification accuracy by up to 18%, with respect to the non balanced MixMatch algorithm. We tested our proposed approach with several available datasets using 10, 15 and 20 labelled observations, for binary classification (COVID-19 positive and normal cases). For multi-class classification (COVID-19 positive, pneumonia and normal cases), we tested 30, 50, 70 and 90 labelled observations. Additionally, a new dataset is included among the tested datasets, composed of chest X-ray images of Costa Rican adult patients.

We suggest an improved software pipeline for mixture analysis.

No abstract

This paper presents a proof of concept of a method to identify substructures in 2D NMR spectra of mixtures using a bespoke image‐based convolutional neural network application. This is done using HSQC and HMBC spectra separately and in combination. The application can reliably detect substructures in pure compounds, using a simple network. Results indicate that it can work for mixtures when trained on pure compounds only. HMBC data and the combination of HMBC and HSQC show better results than HSQC alone in this pilot study.

In this work we implement a COVID-19 infection detection system based on chest Xray images with uncertainty estimation. Uncertainty estimation is vital for safe usage of computer aided diagnosis tools in medical applications. Model estimations with high uncertainty should be carefully analyzed by a trained radiologist. We aim to improve uncertainty estimations using unlabelled data through the MixMatch semi-supervised framework. We test popular uncertainty estimation approaches, comprising Softmax scores, Monte-Carlo dropout and deterministic uncertainty quantification. To compare the reliability of the uncertainty estimates, we propose the usage of the Jensen-Shannon distance between the uncertainty distributions of correct and incorrect estimations. This metric is statistically relevant, unlike most previously used metrics, which often ignore the distribution of the uncertainty estimations. Our test results show a significant improvement in uncertainty estimates when using unlabelled data. The best results are obtained with the use of the Monte Carlo dropout method.

The issue of detecting improvised explosive devices, henceforth IEDs, in rural or built-up urban environments is a persistent and serious concern for governments in the developing world. In many cases, such devices are plastic, or varied metallic objects containing rudimentary explosives, which are not visible to the naked eye and are difficult to detect autonomously. The most effective strategy for detecting land mines also happens to be the most dangerous. This paper intends to leverage the use of a Convolutional Neural Network (CNN) to aid in the discovery of such IEDs. As part of a related project, an autonomous sensor array was used to detect the devices in terrains too hazardous for a human to survey. This paper presents a CNN and its training methodology, suitable to make use of the sensor system. This convolutional neural network can accurately distinguish between a potential IED and surrounding undergrowth and natural features of the environment in real-time. The training methodology enabled the CNN to successfully recognise the IEDs with an accuracy of 98.7%, in well-lit conditions. The results are evaluated against other convolutional neural systems as well as against a deterministic algorithm, showing that the proposed CNN outperforms its competitors including the deterministic method.

No abstract

Developments in artificial intelligence can be leveraged to support the diagnosis of degenerative disorders, such as epilepsy and Parkinson's disease. This study aims to provide a software solution, focused initially towards Parkinson's disease, which can positively impact medical practice surrounding degenerative diagnoses. Through the use of a dataset containing numerical data representing acoustic features extracted from an audio recording of an individual, it is determined if a neural approach can provide an improvement over previous results in the area. This is achieved through the implementation of a feedforward neural network and a layer recurrent neural network. By comparison with the state-of-the-art, a Bayesian approach providing a classification accuracy benchmark of 87.1%, it is found that the implemented neural networks are capable of average accuracy of 96%, highlighting improved accuracy for the classification process. The solution is capable of supporting the diagnosis of Parkinson's disease in an advisory capacity and is envisioned to inform the process of referral through general practice.