COVID-19 is a rapidly spreading viral disease and has affected over 100 countries worldwide. The numbers of casualties and cases of infection have escalated particularly in countries with weakened healthcare systems. Recently, reverse transcription-polymerase chain reaction (RT-PCR) is the test of choice for diagnosing COVID-19. However, current evidence suggests that COVID-19 infected patients are mostly stimulated from a lung infection after coming in contact with this virus. Therefore, chest X-ray (i.e., radiography) and chest CT can be a surrogate in some countries where PCR is not readily available. This has forced the scientific community to detect COVID-19 infection from X-ray images and recently proposed machine learning methods offer great promise for fast and accurate detection. Deep learning with convolutional neural networks (CNNs) has been successfully applied to radiological imaging for improving the accuracy of diagnosis. However, the performance remains limited due to the lack of representative X-ray images available in public benchmark datasets. To alleviate this issue, we propose a self-augmentation mechanism for data augmentation in the feature space rather than in the data space using reconstruction independent component analysis (RICA). Specifically, a unified architecture is proposed which contains a deep convolutional neural network (CNN), a feature augmentation mechanism, and a bidirectional LSTM (BiLSTM). The CNN provides the high-level features extracted at the pooling layer where the augmentation mechanism chooses the most relevant features and generates low-dimensional augmented features. Finally, BiLSTM is used to classify the processed sequential information. We conducted experiments on three publicly available databases to show that the proposed approach achieves the state-of-the-art results with accuracy of 97%, 84% and 98%. Explainability analysis has been carried out using feature visualization through PCA projection and t-SNE plots.

Face presentation attack detection (PAD) plays a pivotal role in securing face recognition systems against spoofing attacks. Although great progress has been made in designing face PAD methods, developing a model that can generalize well to unseen test domains remains a significant challenge. Moreover, due to the different types of spoofing attacks, creating a dataset with a sufficient number of samples for training deep neural networks is a laborious task. This work proposes a comprehensive solution that combines synthetic data generation and deep ensemble learning to enhance the generalization capabilities of face PAD. Specifically, synthetic data is generated by blending a static image with spatiotemporal-encoded images using alpha composition and video distillation. In this way, we simulate motion blur with varying alpha values, thereby generating diverse subsets of synthetic data that contribute to a more enriched training set. Furthermore, multiple base models are trained on each subset of synthetic data using stacked ensemble learning. This allows the models to learn complementary features and representations from different synthetic subsets. The meta-features generated by the base models are used as input for a new model called the meta-model. The latter combines the predictions from the base models, leveraging their complementary information to better handle unseen target domains and enhance overall performance. Experimental results from seven datasets—WMCA, CASIA-SURF, OULU-NPU, CASIA-MFSD, Replay-Attack, MSU-MFSD, and SiW-Mv2—highlight the potential to enhance presentation attack detection by using large-scale synthetic data and a stacking-based ensemble approach.

The research focus in remote sensing scene image classification has been recently shifting towards deep learning (DL) techniques. However, even the state-of-the-art deep-learning-based models have shown limited performance due to the inter-class similarity and the intra-class diversity among scene categories. To alleviate this issue, we propose to explore the spatial dependencies between different image regions and introduce patch-based discriminative learning (PBDL) for remote sensing scene classification. In particular, the proposed method employs multi-level feature learning based on small, medium, and large neighborhood regions to enhance the discriminative power of image representation. To achieve this, image patches are selected through a fixed-size sliding window, and sampling redundancy, a novel concept, is developed to minimize the occurrence of redundant features while sustaining the relevant features for the model. Apart from multi-level learning, we explicitly impose image pyramids to magnify the visual information of the scene images and optimize their positions and scale parameters locally. Motivated by this, a local descriptor is exploited to extract multi-level and multi-scale features that we represent in terms of a codeword histogram by performing k-means clustering. Finally, a simple fusion strategy is proposed to balance the contribution of individual features where the fused features are incorporated into a bidirectional long short-term memory (BiLSTM) network. Experimental results on the NWPU-RESISC45, AID, UC-Merced, and WHU-RS datasets demonstrate that the proposed approach yields significantly higher classification performance in comparison with existing state-of-the-art deep-learning-based methods.

Although machine learning techniques have been repeatedly used for activity prediction from wearable devices, accurate classification of 24-hour activity behaviour categories from accelerometry data remains a challenge. We developed and validated a deep learning-based framework for classifying 24-hour activity behaviours from wrist-worn accelerometers. Using an openly available dataset with free-living wrist-based raw accelerometry data from 151 participants (aged 18-91 years), we developed a deep learning framework named AccNet24 to classify 24-hour activity behaviours. First, the acceleration signal (x, y, and z-axes) was segmented into 30-second nonoverlapping windows, and signal-to-image conversion was performed for each segment. Deep features were automatically extracted from the signal images using transfer learning and transformed into a lower-dimensional feature space. These transformed features were then employed to classify the activity behaviours as sleep, sedentary behaviour, and light-intensity (LPA) and moderate-to-vigorous physical activity (MVPA) using a bidirectional long short-term memory (BiLSTM) recurrent neural network. AccNet24 was trained and validated with data from 101 and 25 randomly selected participants and tested with the remaining unseen 25 participants. We also extracted 112 hand-crafted time and frequency domain features from 30-second windows and used them as inputs to five commonly used machine learning classifiers, including random forest, support vector machines, artificial neural networks, decision tree, and naïve Bayes to classify the 24-hour activity behaviour categories. Using the same training, validation, and test data and window size, the classification accuracy of AccNet24 outperformed the accuracy of the other five machine learning classification algorithms by 16%-30% on unseen data. AccNet24, relying on signal-to-image conversion, deep feature extraction, and BiLSTM achieved consistently high accuracy (>95 %) in classifying the 24-hour activity behaviour categories as sleep, sedentary, LPA, and MVPA. The next generation accelerometry analytics may rely on deep learning techniques for activity prediction.