DR-NTU (Data) (Nanyang Technological University)
DR-NTU (Data) (Nanyang Technological University)Not a member yet
1955 research outputs found
Sort by
Using Twitter Dataset for Social Listening in Singapore
No full textThis study delves into analyzing social media data sourced from Twitter within the context of Singapore, forming a crucial component of a broader social listening initiative. We provide a decade’s worth of social data from Singapore, offering invaluable insights for the research community. This work presents two analytical approaches utilizing this dataset: sentiment analysis and bursty topic detection. Sentiment analysis for direct search is based on zero shot pretrained model while busrty topic analysis is based on biterm topic model. The detailed experiments demonstrate the efficacy of the approach for analyzing social trends using Twitter data.
We collected all twitter data posted in Singapore from 2008 to 2023. The geocode setting as (1.346353, 103.807526, 25km) was used in Twitter API to cover the whole of Singapore. The total number of tweets in this dataset is 96,686,894.
There are 3 data files: 1. place.json includes 10k detailed places information in Singapore.2.subzones.json includes 332 subzone information in Singapore 3.tweets.json includes 96M+tweets posted in Singapore. MongoDB was used as the database to store and manage the data.</p
Hybrid Mamba for Few-Shot Segmentation
No full textMany few-shot segmentation (FSS) methods use cross attention to fuse support foreground (FG) into query features, regardless of the quadratic complexity. A recent advance Mamba can also well capture intra-sequence dependencies, yet the complexity is only linear. Hence, we aim to devise a cross (attention-like) Mamba to capture inter-sequence dependencies for FSS. A simple idea is to scan on support features to selectively compress them into the hidden state, which is then used as the initial hidden state to sequentially scan query features. Nevertheless, it suffers from (1) support forgetting issue: query features will also gradually be compressed when scanning on them, so the support features in hidden state keep reducing, and many query pixels cannot fuse sufficient support features; (2) intra-class gap issue: query FG is essentially more similar to itself rather than to support FG, i.e., query may prefer not to fuse support features but their own ones from the hidden state, yet the success of FSS relies on the effective use of support information. To tackle them, we design a hybrid Mamba network (HMNet), including (1) a support recapped Mamba to periodically recap the support features when scanning query, so the hidden state can always contain rich support information; (2) a query intercepted Mamba to forbid the mutual interactions among query pixels, and encourage them to fuse more support features from the hidden state. Consequently, the support information is better utilized, leading to better performance. Extensive experiments have been conducted on two public benchmarks, showing the superiority of HMNet
Telehealth adoption in Singapore and US
No full textThis is a large scale survey of telehealth adoption in Singapore and U
Tracing curves in the plane: geometric-invariant learning from human demonstrations
No full textThe empirical laws governing human-curvilinear movements have been studied using various relationships, including minimum jerk, the 2/3 power law, and the piecewise power law. These laws quantify the speed-curvature relationships of human movements during curve tracing using critical speed and curvature as regressors. In this work, we provide a reservoir computing-based framework that can learn and reproduce human-like movements. Specifically, the geometric invariance of the observations, i.e., lateral distance from the closest point on the curve, instantaneous velocity, and curvature, when viewed from the moving frame of reference, are exploited to train the reservoir system. The artificially produced movements are evaluated using the power law to assess whether they are indistinguishable from their human counterparts. The generalisation capabilities of the trained reservoir to curves that have not been used during training are also shown
Replication Data for: Highly stable ladder-type conjugated polymer based organic electrochemical transistors for low power and signal processing-free surface electromyogram triggered robotic hand control
No full textThis dataset contains the data used for the article titled: Highly stable ladder-type conjugated polymer based organic electrochemical transistors for low power and signal processing-free surface electromyogram triggered robotic hand control, published in Advanced Functional Materials
Developing academic writing skills through the video essay and measuring the advantages
No full textThe aim of the project was to assess if and how creating a video essay would impact the revision process for students working on an essay.
We ended up with 13 participants. The biggest challenge was getting participants. We did not get enough in Sem 1, and so had to extend the IRB and data gathering into Sem 2. While 13 is a small number, we have some rich data. We have interviews with each participant, journal entries, and the actual first draft/final submission for each essay. This has allowed us to triangulate our findings. For example, if a student claimed in the interview and journal entries that doing the video essay helped her to edit out inessential details, we can then review her draft and final essay to see if she actually did this editing.
We have completed the analysis of the data and are in the process of drafting an article
Work, Religion and Health Survey
No full textThe 2021 Work, Religion and Health (WRH) Survey is a nationwide study of working adults in Singapore to examine the effects of religion, job demands, and job resources on workers’ well- being. Eligible participants had to be (a) aged 20 years or older; (2) in the paid labor force; (3) Singaporean or Singapore permanent resident; and (4) employed full time. The sampling frame was purchased from the Singapore Department of Statistics, and field surveyors visited participants' residences to interview them. A total of 508 working adults were interviewed between September 2021 through April 2022. Interviews were conducted in English or Mandarin. Approval to conduct this study was granted by the Institutional Review Board at Nanyang Technological University (IRB-2021-02-052)
Game Theoretic Approach for Cooperative Control of Connected and Automated Vehicles
No full textData for Game Theoretic Approach for Cooperative Control of Connected and Automated Vehicle
Replication Data for: Non-Abelian Braiding of Topological Edge Bands
No full textExperimental data for the paper "Non-Abelian Braiding of Topological Edge Bands
Boosting energy efficiency and selectivity of glucose oxidation to glucuronic acid in high frequency ultrasound using multicavity CuO catalytic cavitation agents
No full textResearch data for the manuscript "Boosting energy efficiency and selectivity of glucose oxidation to glucuronic acid in high frequency ultrasound using multicavity CuO catalytic cavitation agents