DR-NTU (Data) (Nanyang Technological University)
DR-NTU (Data) (Nanyang Technological University)Not a member yet
1955 research outputs found
Sort by
Replication Data for: On-Site Precise Screening of SARS-CoV-2 Systems Using an Attention-Based PLS-1D-CNN Model with Biomolecular Infrared Signatures
No full textDuring the early stages of respiratory virus outbreaks, such as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the effective use of limited nasopharyngeal swabs for rapid and accurate screening is crucial for public health. In this study, we present a methodology that integrates attenuated total reflection-Fourier transform infrared spectroscopy (ATR-FTIR) with the adaptive iteratively reweighted penalized least squares (airPLS) preprocessing algorithm and a channel-wise attention-based partial least squares one-dimensional convolutional neural network (PLS-1D-CNN) model, enabling accurate screening of infected individuals within 10 minutes. Two cohorts of nasopharyngeal swab samples, comprising 126 and 112 samples from suspected SARS-CoV-2 Omicron variant cases, were collected at Beijing Youan Hospital for verification. To assess signal quality across different experimental procedures, we introduce a biomolecular importance (BMI) evaluation method, which quantitatively measures the significance of virus-related biomolecules in feature extraction, helping differentiate the quality of spectral signals collected under varying conditions. This approach reveals underlying biological correlations, facilitating the selection of higher-quality spectra and standardizing protocols to ensure consistent, high-quality spectral signal collection.
For ATR-FTIR signals in cohort 2, which showed higher BMI, airPLS was used for signal preprocessing, followed by application of the channel-wise attention-based PLS-1D-CNN model for screening. Experimental results demonstrate that our model achieves a screening accuracy of 96.48%, sensitivity of 96.24%, specificity of 97.14%, F1-score of 96.12%, and an AUC of 0.99, meeting the World Health Organization’s recommended criteria for acceptable screening products
Topological and Geometrical Characterization of the Complex Dynamics of Stock Markets and Science Citation Networks at Multiple Length Scales
No full textSecondary datasets, MATLAB scripts, and Python scripts for the manuscript titled "Topological and Geometrical Characterization of the Complex Dynamics of Stock Markets and Science Citation Networks at Multiple Length Scales
Data for: Systematic Review on Unintended Effects of Healthcare Nudges During the COVID-19 Pandemic
No full textDespite reported success of nudge interventions on influencing behaviour in the public health domain, there have been cases where nudges fail to work as intended. Such findings hold importance, especially during high-stakes situations like the COVID-19 pandemic where governments implemented public health safety measures to combat the spread of the virus. This systematic review investigated the conditions that cause healthcare nudges to result in unintended or negative outcomes in the context of the pandemic. Papers were identified to include peer-reviewed journal articles and academic grey literature published between 2020-2024, where 791 unique papers were yielded from Scopus, PubMed, Web of Science, and PsychINFO. A total of 14 papers met inclusion criteria, and were assessed for their quality, heterogeneity, WEIRD+ bias, and open access. The MINDSPACE framework was used to categorise the nudges. Findings suggest three characteristics may lead nudges to result in unintended outcomes: (1) A mismatch in target audience; (2) the use of prosocial and self-interest nudges; and (3) the elicitation of strong emotional responses. It was observed that there were scenarios in which nudges with the identified characteristics may still succeed. Comparing situations when similar nudges backfired or succeeded revealed that context-dependent factors may be the reason for such differences. Findings from this review may aid in designing future behavioural interventions to minimise potential negative outcomes. Future research on nudge effects could benefit from more studies assessing actual behaviours rather than intentions and investigate the characteristics identified in this review. This repository contains data collected during literature search and data extraction stages of the systematic review. Project initiated as part of a final year project in Psychology at Nanyang Technological University in 2024
Related data for: Acute chromatin decompaction stiffens the nucleus as revealed by nanopillar-induced nuclear deformation in cells
No full textThis dataset contains source data acquired by the atomic force microscope, representative images of cells analyzed via AFM, and excel files containing fitted Young's moduli at each 2 x 2 µm^2 area
TacoDepth: Towards Efficient Radar-Camera Depth Estimation with One-stage Fusion
No full textRadar-Camera depth estimation aims to predict dense and accurate metric depth by fusing input images and Radar data. Model efficiency is crucial for this task in pursuit of real-time processing on autonomous vehicles and robotic platforms. However, due to the sparsity of Radar returns, the prevailing methods adopt multi-stage frameworks with intermediate quasi-dense depth, which are time-consuming and not robust. To address these challenges, we propose TacoDepth, an efficient and accurate Radar-Camera depth estimation model with one-stage fusion. Specifically, the graph-based Radar structure extractor and the pyramid-based Radar fusion module are designed to capture and integrate the graph structures of Radar point clouds, delivering superior model efficiency and robustness without relying on the intermediate depth results. Moreover, TacoDepth can be flexible for different inference modes, providing a better balance of speed and accuracy. Extensive experiments are conducted to demonstrate the efficacy of our method. Compared with the previous state-of-the-art approach, TacoDepth improves depth accuracy and processing speed by 12.8% and 91.8%. Our work provides a new perspective on efficient Radar-Camera depth estimation
Related Data for: 022116-00001
No full textPolymer Electrolyte Membrane (PEM) and Seawater Electrolyzers Assembled from Single-Atom Catalyst
Text4Seg: Reimagining Image Segmentation as Text Generation
No full textMultimodal Large Language Models (MLLMs) have shown exceptional capabilities in vision-language tasks; however, effectively integrating image segmentation into these models remains a significant challenge. In this paper, we introduce Text4Seg, a novel text-as-mask paradigm that casts image segmentation as a text generation problem, eliminating the need for additional decoders and significantly simplifying the segmentation process. Our key innovation is semantic descriptors, a new textual representation of segmentation masks where each image patch is mapped to its corresponding text label. This unified representation allows seamless integration into the auto-regressive training pipeline of MLLMs for easier optimization. We demonstrate that representing an image with 16×16 semantic descriptors yields competitive segmentation performance. To enhance efficiency, we introduce the Row-wise Run-Length Encoding (R-RLE), which compresses redundant text sequences, reducing the length of semantic descriptors by 74% and accelerating inference by 3×, without compromising performance. Extensive experiments across various vision tasks, such as referring expression segmentation and comprehension, show that Text4Seg achieves state-of-the-art performance on multiple datasets by fine-tuning different MLLM backbones. Our approach provides an efficient, scalable solution for vision-centric tasks within the MLLM framework
Replication Data for: Benthic mud content is a strong indicator of coral cover and ecosystem recovery on turbid coral reefs
No full textThis dataset comprises the raw data of grain size composition and sediment constituents of reef sediments sampled in Singapore, November 2021. It also includes Benthic community data collected in the same time period
Related Data for: Hybrid Near- and Far-Field THz UM-MIMO Channel Estimation: A Sparsifying Matrix Learning-Aided Bayesian Approach
No full textPython source code associated with the publication titled "Hybrid Near- and Far-Field THz UM-MIMO Channel Estimation: A Sparsifying Matrix Learning-Aided Bayesian Approach". These codes can be used to produce simulation figures in this publication
Climates. Habitats. Environments. Database
No full textThe Environmentally-Engaged Artistic Practices in South, Southeast Asia and the Pacific Database aspires to provide a comprehensive and rich data source for artists, climate scientists, and policymakers on the artistic practices of artists and collectives from the South, Southeast Asian and Pacific Regions. The complexity of the climate crisis at hand requires a transdisciplinary approach to research and practice, even as we see climate change becoming an ever-pressing theme across the disciplines of science and art. This database does not aim to be an exhaustive list of artists from the South, Southeast Asian and Pacific region but a carefully crafted list of artists and collectives that have a keen focus on environmental themes. Drawing on the expertise built up by NTU CCA over the years, this database animates the expansive network of artists from around the South, Southeast Asian and Pacific regions dedicated to themes related to traditional knowledge, biodiversity and ecosystems, anthropogenic impacts and risk and resilience. The hope is that this database presents an easy to use and initial source of information for scientists, policymakers and artists to find artists relevant to their area of expertise or region of study with the possibility of collaborating with artists in the database toward building transdisciplinary research methods