Denoising EEG Signals for Real-World BCI Applications Using GANs

As a measure of the brain's electrical activity, electroencephalography (EEG) is the primary signal of interest for brain-computer-interfaces (BCI). BCIs offer a communication pathway between a brain and an external device, translating thought into action with suitable processing. EEG data is the most common signal source for such technologies. However, artefacts induced in BCIs in the real-world context can severely degrade their performance relative to their in-laboratory performance. In most cases, the recorded signals are so heavily corrupted by noise that they are unusable and restrict BCI's broader applicability. To realise the use of portable BCIs capable of high-quality performance in a real-world setting, we use Generative Adversarial Networks (GANs) that can adopt both supervised and unsupervised learning approaches. Although our approach is supervised, the same model can be used for unsupervised tasks such as data augmentation/imputation in the low resource setting. Exploiting recent advancements in Generative Adversarial Networks (GAN), we construct a pipeline capable of denoising artefacts from EEG time series data. In the case of denoising data, it maps noisy EEG signals to clean EEG signals, given the nature of the respective artefact. We demonstrate the capability of our network on a toy dataset and a benchmark EEG dataset developed explicitly for deep learning denoising techniques. Our datasets consist of an artificially added mains noise (50/60 Hz) artefact dataset and an open-source EEG benchmark dataset with two artificially added artefacts. Artificially inducing myogenic and ocular artefacts for the benchmark dataset allows us to present qualitative and quantitative evidence of the GANs denoising capabilities and rank it among the current gold standard deep learning EEG denoising techniques. We show the power spectral density (PSD), signal-to-noise ratio (SNR), and other classical time series similarity measures for quantitative metrics and compare our model to those previously used in the literature. To our knowledge, this framework is the first example of a GAN capable of EEG artefact removal and generalisable to more than one artefact type. Our model has provided a competitive performance in advancing the state-of-the-art deep learning EEG denoising techniques. Furthermore, given the integration of AI into wearable technology, our method would allow for portable EEG devices with less noisy and more stable brain signals.

Global User-Level Perception of COVID-19 Contact Tracing Applications: A Data-Driven Approach Using Natural Language Processing (Preprint)

BACKGROUND Contact tracing has been globally adopted in the fight to control the infection rate of COVID-19. Thanks to digital technologies, such as smartphones and wearable devices, contacts of COVID-19 patients can be easily traced and informed about their potential exposure to the virus. To this aim, several mobile applications have been developed. However, there are ever-growing concerns over the working mechanism and performance of these applications. The literature already provides some interesting exploratory studies on the community’s response to the applications by analyzing information from different sources, such as news and users’ reviews of the applications. However, to the best of our knowledge, there is no existing solution that automatically analyzes users’ reviews and extracts the evoked sentiments. We believe such solutions combined with a user-friendly interface can be used as a rapid surveillance tool to monitor how effective an application is and to make immediate changes without going through an intense participatory design method which, although in normal circumstances is optimal, but not optimal in emergency situations where a mobile device needs to be deployed immediately with little to no user input from the beginning for the greater public good. OBJECTIVE In this paper, we aim to analyze the efficacy of AI models and Natural Language Processing (NLP) techniques in automatically extracting and classifying the polarity of users’ sentiments by proposing a sentiment analysis framework to automatically analyze users’ reviews on COVID-19 contact tracing mobile applications. We also aim to provide a large-scale annotated benchmark dataset to facilitate future research in the domain. As a proof of concepts, we also develop a potential web application, based on the proposed solutions, with a user-friendly interface to automatically analyze and classify users’ reviews on the COVID-19 contact tracing applications. The proposed framework combined with the interface which is expected to help the community in quickly analyzing users’ perception about such mobile applications and can be used as a rapid surveillance tool to monitor effectiveness of mobile applications and to make immediate changes without going through an intense participatory design method in emergency situations. METHODS We propose a pipeline starting from manual annotation via a crowd-sourcing study and concluding on the development and training of AI models for automatic sentiment analysis of users’ reviews. In detail, we collected and annotated a large- scale dataset of Android and iOS mobile applications users’ reviews for COVID-19 contact tracing. After manually analyzing and annotating users’ reviews, we employed both classical (i.e., Naïve Bayes, SVM, Random Forest) and deep learning (i.e., fastText, and different transformers) methods for classification experiments. This resulted in eight different classification models. RESULTS We employed eight different methods on three different tasks achieving up to an average F1-Scores 94.8% indicating the feasibility and applicability of automatic sentiment analysis of users’ reviews on the COVID-19 contact tracing applications. Moreover, the crowd-sourcing activity resulted in a large-scale benchmark dataset composed of 34,534 reviews manually annotated from the contract tracing applications of 46 distinct countries. The resulted dataset is also made publicly available for research usage. CONCLUSIONS The existing literature mostly relies on the manual/exploratory analysis of users’ reviews on the application, which is a tedious and time-consuming process. Moreover, in the existing studies, generally, data from fewer applications are analyzed. In this work, we showed that AI and NLP techniques provide good results in analyzing and classifying users’ sentiments’ polarity, and that the automatic sentiment analysis can help in analyzing users’ responses to the application more quickly with a significant accuracy. Moreover, we also provided a large-scale benchmark dataset composed of 34,534 reviews from 47 different applications. We believe the presented analysis, dataset, and the proposed solutions combined with a user-friendly interface can be used as a rapid surveillance tool to analyze and monitor mobile applications deployed in emergency situations leading to rapid changes in the applications without going through an intense participatory design method.

WaterBench: A Large-scale Benchmark Dataset for Data-Driven Streamflow Forecasting

This study proposes a comprehensive benchmark dataset for streamflow forecasting, WaterBench, that follows FAIR data principles that is prepared with a focus on convenience for utilizing in data-driven and machine learning studies, and provides benchmark performance for state-of-art deep learning architectures on the dataset for comparative analysis. By aggregating the datasets of streamflow, precipitation, watershed area, slope, soil types, and evapotranspiration from federal agencies and state organizations (i.e., NASA, NOAA, USGS, and Iowa Flood Center), we provided the WaterBench for hourly streamflow forecast studies. This dataset has a high temporal and spatial resolution with rich metadata and relational information, which can be used for varieties of deep learning and machine learning research. We defined a sample streamflow forecasting task for the next 120 hours and provided performance benchmarks on this task with sample linear regression and deep learning models, including Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), and S2S (Sequence-to-sequence). To some extent, WaterBench makes up for the lack of a unified benchmark in earth science research. We highly encourage researchers to use the WaterBench for deep learning research in hydrology.

scMARK an 'MNIST' like benchmark to evaluate and optimize models for unifying scRNA data

Today's single-cell RNA analysis tools provide enormous value in enabling researchers to make sense of large single-cell RNA (scRNA) studies, yet their ability to integrate different studies at scale remains untested. Here we present a novel benchmark dataset (scMARK), that consists of 100,000 cells over 10 studies and can test how well models unify data from different scRNA studies. We also introduce a two-step framework that uses supervised models, to evaluate how well unsupervised models integrate scRNA data from the 10 studies. Using this framework, we show that the Variational Autoencoder, scVI, represents the only tool tested that can integrate scRNA studies at scale. Overall, this work paves the way to creating large scRNA atlases and 'off-the-shelf' analysis tools.