Multiple weak supervision for short text classification

For short text classification, insufficient labeled data, data sparsity, and imbalanced classification have become three major challenges. For this, we proposed multiple weak supervision, which can label unlabeled data automatically. Different from prior work, the proposed method can generate probabilistic labels through conditional independent model. What’s more, experiments were conducted to verify the effectiveness of multiple weak supervision. According to experimental results on public dadasets, real datasets and synthetic datasets, unlabeled imbalanced short text classification problem can be solved effectively by multiple weak supervision. Notably, without reducing precision, recall, and F1-score can be improved by adding distant supervision clustering, which can be used to meet different application needs.

Data Soup Webinar, December 16, 2021: hosted by the Data Curation Network and the Journal of eScience Librarianship

Data Soup is a collaboration between the Journal of eScience Librarianship (JeSLIB) and the Data Curation Networkto host a series of community focused webinars/discussions to exchange practices for curating research data of different formats or subject areas among data curators. The lineup of the inaugural webinar includes the following speakers and topics from the recent JeSLIB Special Issue: Data Curation in Practice: Creating Guidance for Canadian Dataverse Curators: Portage Network’s Dataverse Curation Guide Alexandra Cooper, Michael Steeleworthy, Ève Paquette-Bigras, Erin Clary, Erin MacPherson, Louise Gillis, and Jason Brodeur, https://escholarship.umassmed.edu/jeslib/vol10/iss3/2; Active Curation of Large Longitudinal Surveys: A Case Study Inna Kouper, Karen L. Tucker, Kevin Tharp, Mary Ellen van Booven, and Ashley Clark, https://doi.org/10.7191/jeslib.2021.1210; Data Curation through Catalogs: A Repository-Independent Model for Data Discovery Helenmary Sheridan, Anthony J. Dellureficio, Melissa A. Ratajeski, Sara Mannheimer, and Terrie R. Wheeler, https://doi.org/10.7191/jeslib.2021.1203.

The Consortium of Australian Academic Psychiatrists for Independent Policy Research and Analysis (CAPIPRA): Aims, model, outputs, and implications for clinical academic advocacy

Objective: We describe an independent model of clinical academic mental health services research that is able to provide synthesised views for medico-political organisations that are engaged in advocacy for national and state evidence-based policy and planning of mental healthcare. Conclusions: CAPIPRA focuses on independent research and policy analysis using publicly available datasets on population mental health at national and state/territory levels, published in international and national peer-reviewed journals (>50 papers since 2019). We partner with medico-political organisations in evidence-based advocacy across a wide range of issues.

Development and Internal Validation of a Preoperative Prediction Model for Sentinel Lymph Node Status in Breast Cancer: Combining Radiomics Signature and Clinical Factors

PurposeTo develop and internally validate a nomogram combining radiomics signature of primary tumor and fibroglandular tissue (FGT) based on pharmacokinetic dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and clinical factors for preoperative prediction of sentinel lymph node (SLN) status in breast cancer patients.MethodsThis study retrospectively enrolled 186 breast cancer patients who underwent pretreatment pharmacokinetic DCE-MRI with positive (n = 93) and negative (n = 93) SLN. Logistic regression models and radiomics signatures of tumor and FGT were constructed after feature extraction and selection. The radiomics signatures were further combined with independent predictors of clinical factors for constructing a combined model. Prediction performance was assessed by receiver operating characteristic (ROC), calibration, and decision curve analysis. The areas under the ROC curve (AUCs) of models were corrected by 1,000-times bootstrapping method and compared by Delong’s test. The added value of each independent model or their combinations was also assessed by net reclassification improvement (NRI) and integrated discrimination improvement (IDI) indices. This report referred to the “Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis” (TRIPOD) statement.ResultsThe AUCs of the tumor radiomic model (eight features) and the FGT radiomic model (three features) were 0.783 (95% confidence interval [CI], 0.717–0.849) and 0.680 (95% CI, 0.604–0.757), respectively. A higher AUC of 0.799 (95% CI, 0.737–0.862) was obtained by combining tumor and FGT radiomics signatures. By further combining tumor and FGT radiomics signatures with progesterone receptor (PR) status, a nomogram was developed and showed better discriminative ability for SLN status [AUC 0.839 (95% CI, 0.783–0.895)]. The IDI and NRI indices also showed significant improvement when combining tumor, FGT, and PR compared with each independent model or a combination of any two of them (all p < 0.05).ConclusionFGT and clinical factors improved the prediction performance of SLN status in breast cancer. A nomogram integrating the DCE-MRI radiomics signature of tumor and FGT and PR expression achieved good performance for the prediction of SLN status, which provides a potential biomarker for clinical treatment decision-making.

The generative capacity of probabilistic protein sequence models

Potts models and variational autoencoders (VAEs) have recently gained popularity as generative protein sequence models (GPSMs) to explore fitness landscapes and predict mutation effects. Despite encouraging results, current model evaluation metrics leave unclear whether GPSMs faithfully reproduce the complex multi-residue mutational patterns observed in natural sequences due to epistasis. Here, we develop a set of sequence statistics to assess the “generative capacity” of three current GPSMs: the pairwise Potts Hamiltonian, the VAE, and the site-independent model. We show that the Potts model’s generative capacity is largest, as the higher-order mutational statistics generated by the model agree with those observed for natural sequences, while the VAE’s lies between the Potts and site-independent models. Importantly, our work provides a new framework for evaluating and interpreting GPSM accuracy which emphasizes the role of higher-order covariation and epistasis, with broader implications for probabilistic sequence models in general.

A hydrography upscaling method for scale-invariant parametrization of distributed hydrological models

Distributed hydrological models rely on hydrography data such as flow direction, river length, slope and width. For large-scale applications, many of these models still rely on a few flow direction datasets, which are often manually derived. We propose the Iterative Hydrography Upscaling (IHU) method to upscale high-resolution flow direction data to the typically coarser resolutions of distributed hydrological models. The IHU aims to preserve the upstream–downstream relationship of river structure, including basin boundaries, river meanders and confluences, in the D8 format, which is commonly used to describe river networks in models. Additionally, it derives representative sub-grid river length and slope parameters, which are required for resolution-independent model results. We derived the multi-resolution MERIT Hydro IHU dataset at resolutions of 30 arcsec (∼ 1 km), 5 arcmin (∼ 10 km) and 15 arcmin (∼ 30 km) by applying IHU to the recently published 3 arcsec MERIT Hydro data. Results indicate improved accuracy of IHU at all resolutions studied compared to other often-applied upscaling methods. Furthermore, we show that MERIT Hydro IHU minimizes the errors made in the timing and magnitude of simulated peak discharge throughout the Rhine basin compared to simulations at the native data resolutions. As the method is open source and fully automated, it can be applied to other high-resolution hydrography datasets to increase the accuracy and enhance the uptake of new datasets in distributed hydrological models in the future.

SwingNet

Sports analytics in the wild (i.e., ubiquitously) is a thriving industry. Swing tracking is a key feature in sports analytics. Therefore, a centimeter-level tracking resolution solution is required. Recent research has explored deep neural networks for sensor fusion to produce consistent swing-tracking performance. This is achieved by combining the advantages of two sensor modalities (IMUs and depth sensors) for golf swing tracking. Here, the IMUs are not affected by occlusion and can support high sampling rates. Meanwhile, depth sensors produce significantly more accurate motion measurements than those produced by IMUs. Nevertheless, this method can be further improved in terms of accuracy and lacking information for different domains (e.g., subjects, sports, and devices). Unfortunately, designing a deep neural network with good performance is time consuming and labor intensive, which is challenging when a network model is deployed to be used in new settings. To this end, we propose a network based on Neural Architecture Search (NAS), called SwingNet, which is a regression-based automatic generated deep neural network via stochastic neural network search. The proposed network aims to learn the swing tracking feature for better prediction automatically. Furthermore, SwingNet features a domain discriminator by using unsupervised learning and adversarial learning to ensure that it can be adaptive to unobserved domains. We implemented SwingNet prototypes with a smart wristband (IMU) and smartphone (depth sensor), which are ubiquitously available. They enable accurate sports analytics (e.g., coaching, tracking, analysis and assessment) in the wild. Our comprehensive experiment shows that SwingNet achieves less than 10 cm errors of swing tracking with a subject-independent model covering multiple sports (e.g., golf and tennis) and depth sensor hardware, which outperforms state-of-the-art approaches.