Search

Brain age prediction from 3D MRI volumes using deep learning has recently become a popular research topic, as brain age has been shown to be an important biomarker. Training deep networks can be very computationally demanding for large datasets like the U.K. Biobank (currently 29,035 subjects). In our previous work, it was demonstrated that using a few 2D projections (mean and standard deviation along three axes) instead of each full 3D volume leads to much faster training at the cost of a reduction in prediction accuracy. Here, we investigated if another set of 2D projections, based on higher-order statistical central moments and eigenslices, leads to a higher accuracy. Our results show that higher-order moments do not lead to a higher accuracy, but that eigenslices provide a small improvement. We also show that an ensemble of such models provides further improvement. [ABSTRACT FROM AUTHOR]

Human Action Recognition is a challenging task used in many applications. It interacts with many aspects of Computer Vision, Machine Learning, Deep Learning and Image Processing in order to understand human behaviours as well as identify them. It makes a significant contribution to sport analysis, by indicating players' performance level and training evaluation. The main purpose of this study is to investigate how the content of three-dimensional data influences on classification accuracy of four basic tennis strokes: forehand, backhand, volley forehand, and volley backhand. An entire player's silhouette and its combination with a tennis racket were taken into consideration as input to the classifier. Three-dimensional data were recorded using the motion capture system (Vicon Oxford, UK). The Plug-in Gait model consisting of 39 retro-reflective markers was used for the player's body acquisition. A seven-marker model was created for tennis racket capturing. The racket is represented in the form of a rigid body; therefore, all points associated with it changed their coordinates simultaneously. The Attention Temporal Graph Convolutional Network was applied for these sophisticated data. The highest accuracy, up to 93%, was achieved for the data of the whole player's silhouette together with a tennis racket. The obtained results indicated that for dynamic movements, such as tennis strokes, it is necessary to analyze the position of the whole body of the player as well as the racket position. [ABSTRACT FROM AUTHOR]

Trees in urban environments hold significant value in providing ecosystem services, which will become increasingly important as urban populations grow. Tree phenology is highly sensitive to climatic variation, and resultant phenological shifts have significant impact on ecosystem function. Data on urban tree phenology is important to collect. Typical remote methods to monitor tree phenological transitions, such as satellite remote sensing and fixed digital camera networks, are limited by financial costs and coarse resolutions, both spatially and temporally and thus there exists a data gap in urban settings. Here, we report on a pilot study to evaluate the potential to estimate phenological metrics from imagery acquired with a conventional dashcam fitted to a car. Dashcam images were acquired daily in spring 2020, March to May, for a 2000 m stretch of road in Melksham, UK. This pilot study indicates that time series imagery of urban trees, from which meaningful phenological data can be extracted, is obtainable from a car-mounted dashcam. The method based on the YOLOv3 deep learning algorithm demonstrated suitability for automating stages of processing towards deriving a greenness metric from which the date of tree green-up was calculated. These dates of green-up are similar to those obtained by visual analyses, with a maximum of a 4-day difference; and differences in green-up between trees (species-dependent) were evident. Further work is required to fully automate such an approach for other remote sensing capture methods, and to scale-up through authoritative and citizen science agencies. [ABSTRACT FROM AUTHOR]

Weed infestation is a global threat to agricultural productivity, leading to low yields and financial losses. Weed detection, based on applying machine learning to imagery collected by Unmanned Aerial Vehicles (UAV) has shown potential in the past; however, validation on large data-sets (e.g., across a wide number of different fields) remains lacking, with few solutions actually made operational. Here, we demonstrate the feasibility of automatically detecting weeds in winter wheat fields based on deep learning methods applied to UAV data at scale. Focusing on black-grass (the most pernicious weed across northwest Europe), we show high performance (i.e., accuracy above 0.9) and highly statistically significant correlation (i.e., ro > 0.75 and p < 0.00001) between imagery-derived local and global weed maps and out-of-bag field survey data, collected by experts over 31 fields (205 hectares) in the UK. We demonstrate how the developed deep learning model can be made available via an easy-to-use docker container, with results accessible through an interactive dashboard. Using this approach, clickable weed maps can be created and deployed rapidly, allowing the user to explore actual model predictions for each field. This shows the potential for this approach to be used operationally and influence agronomic decision-making in the real world. [ABSTRACT FROM AUTHOR]

Lung cancer (LC) is the most common cause of cancer-related deaths in the UK due to delayed diagnosis. The existing literature establishes a variety of factors which contribute to this, including the misjudgement of anatomical structure by doctors and radiologists. This study set out to develop a solution which utilises multiple modalities in order to detect the presence of LC. A review of the existing literature established failings within methods to exploit rich intermediate feature representations, such that it can capture complex multimodal associations between heterogenous data sources. The methodological approach involved the development of a novel machine learning (ML) model to facilitate quantitative analysis. The proposed solution, named EMM-LC Fusion, extracts intermediate features from a pre-trained modified AlignedXception model and concatenates these with linearly inflated features of Clinical Data Elements (CDE). The implementation was evaluated and compared against existing literature using F1 score, average precision (AP), and area under curve (AUC) as metrics. The findings presented in this study show a statistically significant improvement (p < 0.05) upon the previous fusion method, with an increase in F-Score from 0.402 to 0.508. The significance of this establishes that the extraction of intermediate features produces a fertile environment for the detection of intermodal relationships for the task of LC classification. This research also provides an architecture to facilitate the future implementation of alternative biomarkers for lung cancer, one of the acknowledged limitations of this study. [ABSTRACT FROM AUTHOR]

Structural health monitoring (SHM) by using remote sensing and synthetic aperture radar (SAR) images is a promising approach to assessing the safety and the integrity of civil structures. Apart from this issue, artificial intelligence and machine learning have brought great opportunities to SHM by learning an automated computational model for damage detection. Accordingly, this article proposes online hybrid learning methods to firstly deal with some major challenges in data-driven SHM and secondly detect damage via small displacement data from SAR images in a real-time manner. The proposed methods contain three main parts: (i) data augmentation by Hamiltonian Monte Carlo and slice sampling for addressing the problem of small displacement data, (ii) data normalization by an online deep transfer learning algorithm for removing the effects of environmental and/or operational variability from augmented data, and (iii) feature classification via a scalar novelty score. The major contributions of this research include proposing two online hybrid unsupervised learning methods and providing effective frameworks for online damage detection. A small set of displacement samples extracted from SAR images of TerraSar-X regarding a long-term monitoring scheme of the Tadcaster Bridge in United Kingdom is applied to validate the proposed methods. [ABSTRACT FROM AUTHOR]

Multisource energy data, including from distributed energy resources and its multivariate nature, necessitate the integration of robust data predictive frameworks to minimise prediction error. This work presents a hybrid deep learning framework to accurately predict the energy consumption of different building types, both commercial and domestic, spanning different countries, including Canada and the UK. Specifically, we propose architectures comprising convolutional neural network (CNN), an autoencoder (AE) with bidirectional long short-term memory (LSTM), and bidirectional LSTM BLSTM). The CNN layer extracts important features from the dataset and the AE-BLSTM and LSTM layers are used for prediction. We use the individual household electric power consumption dataset from the University of California, Irvine to compare the skillfulness of the proposed framework to the state-of-the-art frameworks. Results show performance improvement in computation time of 56% and 75.2%, and mean squared error (MSE) of 80% and 98.7% in comparison with a CNN BLSTM-based framework (EECP-CBL) and vanilla LSTM, respectively. In addition, we use various datasets from Canada and the UK to further validate the generalisation ability of the proposed framework to underfitting and overfitting, which was tested on real consumers' smart boxes. The results show that the framework generalises well to varying data and constraints, giving an average MSE of ∼0.09 across all datasets, demonstrating its robustness to different building types, locations, weather, and load distributions. [ABSTRACT FROM AUTHOR]