Permanent URI for this community
Browse
93 results
Search results
Publication A Scalable MDP-Based Sensing and Processing Framework for Vehicular Networks(IEEE, 2019-03) Chattopadhyay, Rajarshi; Tham, Chen-Khong; Assoc Prof Tham Chen Khong; ECONOMICS; ELECTRICAL AND COMPUTER ENGINEERINGPublication Shorter-is-Better: Venue Category Estimation from Micro-Video(Association for Computing Machinery, Inc, 2016-10-15) Jianglong Zhang; Liqiang Nie; Xiang Wang; Xiangnan He; Xianglin Huang; Tat-Seng Chua; DEPARTMENT OF COMPUTER SCIENCEAccording to our statistics on over 2 million micro-videos, only 1.22% of them are associated with venue information, which greatly hinders the location-oriented applications and personalized services. To alleviate this problem, we aim to label the bite-sized video clips with venue categories. It is, however, nontrivial due to three reasons: 1) no available benchmark dataset; 2) insufficient information, low quality, and information loss; and 3) complex relatedness among venue categories. Towards this end, we propose a scheme comprising of two components. In particular, we first crawl a representative set of micro-videos from Vine and extract a rich set of features from textual, visual and acoustic modalities. We then, in the second component, build a tree-guided multi-task multi-modal learning model to estimate the venue category for each unseen micro-video. This model is able to jointly learn a common space from multi-modalities and leverage the predefined Foursquare hierarchical structure to regularize the relatedness among venue categories. Extensive experiments have well-validated our model. As a side research contribution, we have released our data, codes and involved parameters. © 2016 ACM.Publication Trimming outliers using trees: Winning solution of the Large-scale Energy Anomaly Detection (LEAD) competition(ACM, 2022-11-09) Fu, C; Arjunan, P; Miller, C; Dr Clayton Carl Miller; BUILDINGPrediction of building energy consumption using machine learning models has been a focal point of research for decades. However, some causes of forecast errors, particularly data quality, have not been adequately addressed, which may affect the accuracy of forecasting models and subsequent energy management. To solve the issue of data quality, a classifier that can automatically detect time series anomalies is the goal that researchers have been pursuing. Large-scale Energy Anomaly Detection (LEAD), a community competition hosted on the Kaggle platform, was created for this purpose as well as to provide a foundation for benchmarking solutions. In this competition, 200 energy time series worldwide with labeled anomalies were provided to train a classification model to predict anomalies of another 206 unseen time series. The proposed winning solution is a tree-based supervised learning anomaly classifier with ROC-AUC score as high as 0.9866 on private leaderboard. This article describes and analyzes in depth a variety of commonly employed techniques for improving the classification model. Among these strategies, feature engineering requires the most effort and dominates all other techniques; value-changing features that can represent the level of time-series variation have a particularly positive impact. Besides, the classification accuracy of solutions in the competition can serve as a benchmark for future research on supervised learning of energy anomaly detection.Publication Performance of pilot test of geotextile tube filled with lightly cemented clay(2018-01-01) Chew, SH; Audrey Yim, HM; Koh, JW; Eng, ZX; Chua, KE; Danette Tan, SE; Mr Juan Wei Koh; CIVIL AND ENVIRONMENTAL ENGINEERINGThe sand-filled geotextile tube is common, and has been well-established in coastal engineering applications. However, the use of soft clay or dredged material as the infill material for geotextile tube containment bunds is not widely used due to technical concerns on the stability and excessive settlement of the geotextile tubes. To minimize shape deformation and settlement of geotextile tubes associated with the use of soft clay, a modified infill material is proposed – lightly cement-mixed-soil (CMS). This study is aims to investigate the response of a full-scale, instrumented geotextile tube of 20m length, 12.6m circumference and inflated height of approximately 2m when filled with lightly CMS and subjected to surcharge. The surcharge simulates the condition where the geotextile tubes are stacked on top of each other to form a containment bund. The shear strength development at 3-days and 7-days curing of the CMS were also evaluated. This study will provide valuable insights into the design and construction of containment bunds using geotextile tubes infilled with soft clay or dredged material.Publication Digital Twin: A Conceptualization of the Task-Technology Fit for Individual Users in the Building Maintenance Sector(2022-06-27) Teo, Ai Lin; Wong, Peng Hoong; Assoc Prof Ai Lin Teo; BUILDINGPublication Efficient Calibration of RFSoC Full Digital Receiving Beamformer(2024-02-14) Peizhuo Yang; Wang Jiahao; Koen Mouthaan; ELECTRICAL AND COMPUTER ENGINEERINGPublication Singapore Public Housing Dynamics: Exploring Plausible Future of Public Housing Market(Residential College 4, NUS, 2017-02-19) Phua, Kian Ming; NAVIYN PRABHU BALAKRISHNAN; Dr Naviyn Prabhu Balakrishnan; Residential College 4Housing Development Board (HDB) flats have become an iconic feature of Singapore’s landscape. Singapore’s government has played a significant role in ensuring that all segments of society are not left out and are empowered to realize their aspirations. One major aspiration of all Singaporeans would be that of home ownership. Ensuring the affordability in homeownership is thus a key policy objective of the Singapore government since her days of inception following independence. This paper mainly focuses on aspects of the property market which are affecting the transaction price of HDB flats in the new HDB flats segment under the Build-To-Order scheme, from system dynamics perspective, which is accomplished via two objectives: (i) evaluating the trend of the recent surge in property prices in Singapore’s property market; (ii) exploring plausible outcomes to the prices of new HDB flats in the future with the continued implementation/ termination/ modification of the ‘cooling’ measures.Publication Identification of a Novel CEBPE Enhancer Essential for Granulocytic Differentiation(AMER SOC HEMATOLOGY, 2018-11-29) Shyamsunder, Pavithra; Shanmugasundaram, Mahalakshmi; Mayakonda, Anand; Teoh, Weoi Woon; Han, Lin; Lim, Mei Chee; Fullwood, Melissa; An, Omer; Yang, Henry; Shi, Jizhong; Hossain, Md Zakhir; Madan, Vikas; Koeffler, H Phillip; Dr Omer An; CANCER SCIENCE INSTITUTE OF SINGAPOREPublication Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression(Springer Nature Switzerland, 2022-01-01) Jin, Y; Yang, W; Tan, RT; DEAN'S OFFICE (YALE-NUS COLLEGE); DEAN'S OFFICE (YALE-NUS COLLEGE)Night images suffer not only from low light, but also from uneven distributions of light. Most existing night visibility enhancement methods focus mainly on enhancing low-light regions. This inevitably leads to over enhancement and saturation in bright regions, such as those regions affected by light effects (glare, floodlight, etc.). To address this problem, we need to suppress the light effects in bright regions while, at the same time, boosting the intensity of dark regions. With this idea in mind, we introduce an unsupervised method that integrates a layer decomposition network and a light-effects suppression network. Given a single night image as input, our decomposition network learns to decompose shading, reflectance and light-effects layers, guided by unsupervised layer-specific prior losses. Our light-effects suppression network further suppresses the light effects and, at the same time, enhances the illumination in dark regions. This light-effects suppression network exploits the estimated light-effects layer as the guidance to focus on the light-effects regions. To recover the background details and reduce hallucination/artefacts, we propose structure and high-frequency consistency losses. Our quantitative and qualitative evaluations on real images show that our method outperforms state-of-the-art methods in suppressing night light effects and boosting the intensity of dark regions.Publication The role of Smurf2 in microglial activation(2017-07-05) Jamal, Shamieraah; Nayar, Kashmiira; Karthikeyan, Aparna; Gupta, Neelima; Dheen, ST; Assoc Prof Dheen, Shaikali Thameem; ANATOMY