Digital Commons Network^™

W8-Scope: Fine-Grained, Practical Monitoring Of Weight Stack-Based Exercises, Meera Radhakrishnan, Archan Misra, Rajesh K. Balan

Research Collection School Of Computing and Information Systems

Fine-grained, unobtrusive monitoring of gym exercises can help users track their own exercise routines and also provide corrective feedback. We propose W8-Scope, a system that uses a simple magnetic-cum-accelerometer sensor, mounted on the weight stack of gym exercise machines, to infer various attributes of gym exercise behavior. More specifically, using multiple machine learning models, W8-Scope helps identify who is exercising, what exercise she is doing, how much weight she is lifting, and whether she is committing any common mistakes. Real world studies, conducted with 50 subjects performing 14 different exercises over 103 distinct sessions in two gyms, show that W8-Scope …

Deeprepair: Style-Guided Repairing For Deep Neural Networks In The Real-World Operational Environment, Bing Yu, Hua Qi, Guo Qing, Felix Juefei-Xu, Xiaofei Xie, Lei Ma, Jianjun Zhao

Research Collection School Of Computing and Information Systems

Deep neural networks (DNNs) are continuously expanding their application to various domains due to their high performance. Nevertheless, a well-trained DNN after deployment could oftentimes raise errors during practical use in the operational environment due to the mismatching between distributions of the training dataset and the potential unknown noise factors in the operational environment, e.g., weather, blur, noise, etc. Hence, it poses a rather important problem for the DNNs' real-world applications: how to repair the deployed DNNs for correcting the failure samples under the deployed operational environment while not harming their capability of handling normal or clean data with limited …

Toward Deep Supervised Anomaly Detection: Reinforcement Learning From Partially Labeled Anomaly Data, Guansong Pang, Anton Van Den Hengel, Chunhua Shen, Longbing Cao

Research Collection School Of Computing and Information Systems

We consider the problem of anomaly detection with a small set of partially labeled anomaly examples and a large-scale unlabeled dataset. This is a common scenario in many important applications. Existing related methods either exclusively fit the limited anomaly examples that typically do not span the entire set of anomalies, or proceed with unsupervised learning from the unlabeled data. We propose here instead a deep reinforcement learning-based approach that enables an end-to-end optimization of the detection of both labeled and unlabeled anomalies. This approach learns the known abnormality by automatically interacting with an anomalybiased simulation environment, while continuously extending the …

Reproducibility Companion Paper: Knowledge Enhanced Neural Fashion Trend Forecasting, Yunshan Ma, Yujuan Ding, Xun Yang, Lizi Liao, Wai Keung Wong, Tat-Seng Chua, Jinyoung Moon, Hong-Han Shuai

Research Collection School Of Computing and Information Systems

This companion paper supports the replication of the fashion trend forecasting experiments with the KERN (Knowledge Enhanced Recurrent Network) method that we presented in the ICMR 2020. We provide an artifact that allows the replication of the experiments using a Python implementation. The artifact is easy to deploy with simple installation, training and evaluation. We reproduce the experiments conducted in the original paper and obtain similar performance as previously reported. The replication results of the experiments support the main claims in the original paper.

Unlinkable And Revocable Secret Handshake, Yangguang Tian, Yingliu Li, Guomin Yang, Guomin Yang

Research Collection School Of Computing and Information Systems

In this paper, we introduce a new construction for unlinkable secret handshake that allows a group of users to perform handshakes anonymously. We define formal security models for the proposed construction and prove that it can achieve session key security, anonymity and affiliation hiding. In particular, the proposed construction ensures that (i) anonymity against protocol participants (including group authority) is achieved since a hierarchical identity-based signature is used in generating group user's pseudonym-credential pairs and (ii) revocation is achieved using a secret sharing-based revocation mechanism.

A Lightweight And Privacy-Preserving Answer Collection Scheme For Mobile Crowdsourcing, Yingling Dai, Jian Weng, Anjia Yang, Shui Yu, Robert H. Deng

Research Collection School Of Computing and Information Systems

Mobile Crowdsourcing (MCS) has become an emerging paradigm evolved from crowdsourcing by employing advanced features of mobile devices such as smartphones to perform more complicated, especially spatial tasks. One of the key procedures in MCS is to collect answers from mobile users (workers), which may face several security issues. First, authentication is required to ensure that answers are from authorized workers. In addition, MCS tasks are usually location-dependent, so the collected answers could disclose workers' location privacy, which may discourage workers to participate in the tasks. Finally, the overhead occurred by authentication and privacy protection should be minimized since mobile …

Calculation And Optimization Of Correlation Function In Distillation Method Of Lattice Quantum Chromodynamcis, Ren-Qiang Zhang, Xiang-Yu Jiang, Jiongchi Yu, Chong Zeng, Ming Gong, Shun Xu

Research Collection School Of Computing and Information Systems

Lattice quantum chromodynamics (lattice QCD) is a theory based on quantum chromodynamics, which is widely used in strong interaction related calculations. As a research method that can give accurate and reliable theoretical results, with the improvement of computer ability, Lattice QCD is playing an increasingly important role in recent years. Distillation method is an important numerical method to calculate hadron correlation function in lattice QCD, and can improve the signal-to-noise ratio of calculated physical quantities. Distillation is a method to approximately compute full propagator via replace the laplacian operator with it's outerproduct of laplace eigenvectors. In this way, the construction …

Learning To Interpret Knowledge From Software Q&A Sites, Bowen Xu

Dissertations and Theses Collection (Open Access)

Nowadays, software question and answer (SQA) data has become a treasure for software engineering as it contains a huge volume of programming knowledge. That knowledge can be interpreted in many different ways to support various software activities, such as code recommendation, program repair, and so on. In this dissertation, we interpret SQA data by addressing three novel research problems.

The first research problem is about linkable knowledge unit prediction. In this problem, a question and its answers within a post in Stack Overflow are considered as a knowledge unit (KU). KUs often contain semantically relevant knowledge, and thus linkable for …

Public Cleanliness Satisfaction Survey 2021, Paulin Straughan, Mathews Mathew

Research Collection School of Social Sciences

The Singapore Management University undertook the fourth wave of the Public Cleanliness Satisfaction Survey (PCSS) with 2,007 Singapore resident respondents providing responses to the survey from February 2021 to May 2021, amidst the COVID-19 pandemic.

The 2021 wave of the PCSS continued to reflect the overall satisfaction with public cleanliness in Singapore, similar to the last PCSS in 2019. Majority of survey respondents (92%) were satisfied with the cleanliness of public spaces that they had recently visited, a 1% decrease from the findings in 2019.

There was a substantial drop in satisfaction with the cleanliness of food outlets, with a …

Beyond The "Formidable Circle": Race And The Limits Of Democratic Inclusion In Tocqueville's Democracy In America, Christine Dunn Henderson

Research Collection School of Social Sciences

Despite his assertion that the first volume of Democracy in America (1835) would concentrate upon institutions, Tocqueville found himself finishing the draft manuscript in 1834 and unable to conclude his study without discussing race relations in the United States. In the end, he quickly penned a final chapter. That chapter—by far the book’s longest—offers “Some Considerations on the Present State and Probable Future of the Three Races That Inhabit the Territory of the United States.” Tocqueville begins the chapter by acknowledging that its subject “is American without being democratic” (DA, p. 516), and to the extent that it analyzes slavery …

When A Pandemic Disrupts The Export Of People, Yasmin Y. Ortiga, Karen Anne S. Liao

Research Collection School of Social Sciences

Yasmin Ortiga and Karen Anne S. Liao conducted research supported by the SSRC on the dramatic disruptions that Filipino labor migrants experienced as a result of the Covid-19 pandemic, and the support (or lack thereof) of their plight by the Filipino state. Arguing that labor as well as commodity supply chains have been thrown in upheaval, the authors describe the limits of the Philippines’ labor export strategy. In particular, they focus on two sets of labor migrants—nurses unable to take jobs abroad, and repatriated cruise ship workers—for whom dignified work at home was unavailable. Ortiga and Liao conclude that treating …

Media In A Time Of Crisis: Newspaper Coverage Of Covid-19 In East Asia;, Colm A. Fox

Research Collection School of Social Sciences

How have newspapers covered Covid-19 in Asia? To answer this question, I studied East Asian English-language newspapers published between January and July 2020. First, I measured the level of news media attention on Covid-19 among all reports. Second, I analyzed the tone and content of 330 editorials. I divided the analysis into two time periods: the initial crisis breakout period, when the number of infections was rising or high, and the crisis abatement period, when new infections declined to manageable levels. Findings show that although newspapers were slow to begin addressing the pandemic, their early editorials carried an alarming tone, …

Jobs For Justice(S): Corruption In The Supreme Court Of India, Madhav S. Aney, Shubhankar Dam, Giovanni Ko

Research Collection School Of Economics

We investigate whether judicial decisions are affected by career concerns of judges by analyzing two questions: Do judges respond to incentives to pander by ruling in favor of the government in the hope of receiving jobs after retiring from the Supreme Court? Does the government reward judges who rule in its favor with prestigious jobs? We construct a data set of Supreme Court of India cases involving the government for 1999–2014. We find that incentives to pander have a causal effect on judicial decision-making, and they are jointly determined by the importance of the case and whether the judge retires …

Financing Singapore’S Smes And The Crowdfunding Industry In Singapore, Swee Liang Tan, Yoke Wang Tok, Chansriniyom Thitipat

Research Collection School Of Economics

As new digital technologies emerge that make the provision of financial services more efficient, they hold the potential to address barriers that SMEs face in accessing credit. This paper finds empirical evidence that crowdfunding for SMEs improved SMEs’ timeliness to pay debt in Singapore. Anecdotal evidence from growing SMEs suggests that getting crowdfunding loans also induced financing from banks, leading to more efficient allocation of credit. In just four years, Singapore’s crowdfunding volume has grown rapidly making it one of the top crowdfunding hubs in Southeast Asia in 2018. The rapid development of Singapore’s crowdfunding industry can be attributed to …

Glivenko-Cantelli Theorems For Integrated Functionals Of Stochastic Processes, Jia Li, Congshan Zhang, Yunxiao Liu

Research Collection School Of Economics

We prove a Glivenko-Cantelli theorem for integrated functionals of latent continuous-time stochastic processes. Based on a bracketing condition via random brackets, the theorem establishes the uniform convergence of a sequence of empirical occupation measures towards the occupation measure induced by underlying processes over large classes of test functions, including indicator functions, bounded monotone functions, Lipschitz-in-parameter functions, and Hölder classes as special cases. The general Glivenko-Cantelli theorem is then applied in more concrete high-frequency statistical settings to establish uniform convergence results for general integrated functionals of the volatility of efficient price and local moments of microstructure noise.

Efficient Estimation Of Integrated Volatility Functionals Under General Volatility Dynamics, Jia Li, Yunxiao Liu

Research Collection School Of Economics

We provide an asymptotic theory for the estimation of a general class of smooth nonlinear integrated volatility functionals. Such functionals are broadly useful for measuring financial risk and estimating economic models using high-frequency transaction data. The theory is valid under general volatility dynamics, which accommodates both Itô semimartingales (e.g., jump-diffusions) and long-memory processes (e.g., fractional Brownian motions). We establish the semiparametric efficiency bound under a nonstandard nonergodic setting with infill asymptotics, and show that the proposed estimator attains this efficiency bound. These results on efficient estimation are further extended to a setting with irregularly sampled data.

Receiver-Anonymity In Rerandomizable Rcca-Secure Cryptosystems Resolved, Yi Wang, Rongmao Chen, Guomin Yang, Xinyi Huang, Baosheng Wang, Moti Yung

Research Collection School Of Computing and Information Systems

In this work we resolve the open problem raised by Prabhakaran and Rosulek at CRYPTO 2007, and present the first anonymous, rerandomizable, Replayable-CCA (RCCA) secure public-key encryption scheme. This solution opens the door to numerous privacy-oriented applications with a highly desired RCCA security level. At the core of our construction is a non-trivial extension of smooth projective hash functions (Cramer and Shoup, EUROCRYPT 2002), and a modular generic framework developed for constructing rerandomizable RCCA-secure encryption schemes with receiver-anonymity. The framework gives an enhanced abstraction of the original Prabhakaran and Rosulek’s scheme (which was the first construction of rerandomizable RCCA-secure encryption …

Maintenance-Related Concerns For Post-Deployed Ethereum Smart Contract Development: Issues, Techniques, And Future Challenges, Jiachi Chen, Xin Xia, David Lo, John Grundy, Xiaohu Yang

Research Collection School Of Computing and Information Systems

Software development is a very broad activity that captures the entire life cycle of a software, which includes designing, programming, maintenance and so on. In this study, we focus on the maintenance-related concerns of the post-deployment of smart contracts. Smart contracts are self-executed programs that run on a blockchain. They cannot be modified once deployed and hence they bring unique maintenance challenges compared to conventional software. According to the definition of ISO/IEC 14764, there are four kinds of software maintenance, i.e., corrective, adaptive, perfective, and preventive maintenance. This study aims to answer (i) What kinds of issues will smart contract …

Characterizing Search Activities On Stack Overflow, Jiakun Liu, Sebastian Baltes, Christoph Treude, David Lo, Yun Zhang, Xin Xia

Research Collection School Of Computing and Information Systems

To solve programming issues, developers commonly search on Stack Overflow to seek potential solutions. However, there is a gap between the knowledge developers are interested in and the knowledge they are able to retrieve using search engines. To help developers efficiently retrieve relevant knowledge on Stack Overflow, prior studies proposed several techniques to reformulate queries and generate summarized answers. However, few studies performed a large-scale analysis using real-world search logs. In this paper, we characterize how developers search on Stack Overflow using such logs. By doing so, we identify the challenges developers face when searching on Stack Overflow and seek …

Missing Power: Nostalgia And Disillusionment Among Southern California Water Engineers, Sayd Randle

Research Collection College of Integrative Studies

California's sprawling network of aqueducts and dams is often cited as the embodiment of a high-modernist approach to resource management. But while once widely celebrated, in recent decades this infrastructural system and the institutions that manage it have been the subject of growing criticism and shrinking funding streams. Based on ethnographic research among employees at several California water agencies, this article explores the sense of nostalgia and diminished power experienced by the workers tasked with overseeing these networks. These emic perspectives are frequently articulated in the form of unfavorable comparisons to an imagined past, when the workers believe that their …

To Stay Or Not To Stay? A Clash Of Arbitration And Insolvency Regimes, Darius Chan, Sidharrth B Rajagopal

Research Collection Yong Pung How School Of Law

In the wake of the global Coronavirus disease 2019 (COVID-19) pandemic, a rise in creditorinitiated winding-up proceedings is likely to be impending in coming years (See e.g., RCMA Asia Pte. Ltd. v. Sun Electric Power Pte. Ltd. [2020] SGHC 205). At the same time, geopolitical developments, such as the scale and ambition of Belt & Road Initiative projects, have raised questions over the issue of debt sustainability. Given the prevalence of arbitration clauses in modern international commercial and project agreements, the interplay and relationship between insolvency and dispute resolution, and especially arbitration, requires careful attention. While the intersections between the …

The Connection Between Policies And Decisions Made Pursuant To Policies, Wei Yao, Kenny Chng

Research Collection Yong Pung How School Of Law

Policies are an indispensable feature of administrative governance. By providing default guidelines for decision-making, policies streamline the everyday administrative work of public authorities, helping to manage the gargantuan task of keeping the machinery of the modern administrative state running smoothly. This article will analyse an issue in the law regulating the usage of administrative policies that has received little attention to date – the connection between the unlawfulness of a policy in itself and the unlawfulness of a decision made pursuant to such a policy. This article will highlight that there is a degree of analytical ambiguity in this area …

Radbruch’S Formula Revisited: The ‘Lex Injusta Non Est Lex’ Maxim In Constitutional Democracies, Seow Hon Tan

Research Collection Yong Pung How School Of Law

According to German legal philosopher Gustav Radbruch, laws that are substantively unjust to an intolerable degree should not be regarded as legally valid, even if they were promulgated according to stipulated procedure. Radbruch’s Formula (as his position has been termed) contradicts the central tenet of legal positivism, according to which the existence of laws does not necessarily depend on their merit. While some legal positivists suppose that legal invalidity based on the content of particular laws is a central tenet of natural law theory, natural law theorists such as John Finnis opine that the lex injusta non est lex maxim …

Automating The Removal Of Obsolete Todo Comments, Zhipeng Gao, Xin Xia, David Lo, John C. Grundy, Thomas Zimmermann

Research Collection School Of Computing and Information Systems

TODO comments are very widely used by software developers to describe their pending tasks during software development. However, after performing the task developers sometimes neglect or simply forget to remove the TODO comment, resulting in obsolete TODO comments. These obsolete TODO comments can confuse development teams and may cause the introduction of bugs in the future, decreasing the software’s quality and maintainability. Manually identifying obsolete TODO comments is time-consuming and expensive. It is thus necessary to detect obsolete TODO comments and remove them automatically before they cause any unwanted side effects. In this work, we propose a novel model, named …

A Survey On Complex Knowledge Base Question Answering: Methods, Challenges And Solutions, Yunshi Lan, Gaole He, Jinhao Jiang, Jing Jiang, Wayne Xin Zhao, Ji-Rong Wen

Research Collection School Of Computing and Information Systems

Knowledge base question answering (KBQA) aims to answer a question over a knowledge base (KB). Recently, a large number of studies focus on semantically or syntactically complicated questions. In this paper, we elaborately summarize the typical challenges and solutions for complex KBQA. We begin with introducing the background about the KBQA task. Next, we present the two mainstream categories of methods for complex KBQA, namely semantic parsing-based (SP-based) methods and information retrieval-based (IR-based) methods. We then review the advanced methods comprehensively from the perspective of the two categories. Specifically, we explicate their solutions to the typical challenges. Finally, we conclude …

Integrating Knowledge Compilation With Reinforcement Learning For Routes, Jiajing Ling, Kushagra Chandak, Akshat Kumar

Research Collection School Of Computing and Information Systems

Sequential multiagent decision-making under partial observability and uncertainty poses several challenges. Although multiagent reinforcement learning (MARL) approaches have increased the scalability, addressing combinatorial domains is still challenging as random exploration by agents is unlikely to generate useful reward signals. We address cooperative multiagent pathfinding under uncertainty and partial observability where agents move from their respective sources to destinations while also satisfying constraints (e.g., visiting landmarks). Our main contributions include: (1) compiling domain knowledge such as underlying graph connectivity and domain constraints into propositional logic based decision diagrams, (2) developing modular techniques to integrate such knowledge with deep MARL algorithms, and …

Are Missing Links Predictable? An Inferential Benchmark For Knowledge Graph Completion, Yixin Cao, Xiang Ji, Xin Lv, Juanzi Li, Yonggang Wen, Hanwang Zhang

Research Collection School Of Computing and Information Systems

We present InferWiki, a Knowledge Graph Completion (KGC) dataset that improves upon existing benchmarks in inferential ability, assumptions, and patterns. First, each testing sample is predictable with supportive data in the training set. To ensure it, we propose to utilize rule-guided train/test generation, instead of conventional random split. Second, InferWiki initiates the evaluation following the open-world assumption and improves the inferential difficulty of the closed-world assumption, by providing manually annotated negative and unknown triples. Third, we include various inference patterns (e.g., reasoning path length and types) for comprehensive evaluation. In experiments, we curate two settings of InferWiki varying in sizes …

Learning From Miscellaneous Other-Class Words For Few-Shot Named Entity Recognition, Meihan Tong, Shuai Wang, Bin Xu, Yixin Cao, Minghui Liu, Lei Hou, Juanzi Li

Research Collection School Of Computing and Information Systems

Few-shot Named Entity Recognition (NER) exploits only a handful of annotations to identify and classify named entity mentions. Prototypical network shows superior performance on few-shot NER. However, existing prototypical methods fail to differentiate rich semantics in other-class words, which will aggravate overfitting under few shot scenario. To address the issue, we propose a novel model, Mining Undefined Classes from Other-class (MUCO), that can automatically induce different undefined classes from the other class to improve few-shot NER. With these extra-labeled undefined classes, our method will improve the discriminative ability of NER classifier and enhance the understanding of predefined classes with stand-by …

How Knowledge Graph And Attention Help? A Qualitative Analysis Into Bag-Level Relation Extraction, Zikun Hu, Yixin Cao, Lifu Huang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Knowledge Graph (KG) and attention mechanism have been demonstrated effective in introducing and selecting useful information for weakly supervised methods. However, only qualitative analysis and ablation study are provided as evidence. In this paper, we contribute a dataset and propose a paradigm to quantitatively evaluate the effect of attention and KG on bag-level relation extraction (RE). We find that (1) higher attention accuracy may lead to worse performance as it may harm the model’s ability to extract entity mention features; (2) the performance of attention is largely influenced by various noise distribution patterns, which is closely related to real-world datasets; …

Outsourcing Service Fair Payment Based On Blockchain And Its Applications In Cloud Computing, Yinghui Zhang, Robert H. Deng, Ximeng Liu, Dong Zheng

Research Collection School Of Computing and Information Systems

As a milestone in the development of outsourcing services, cloud computing enables an increasing number of individuals and enterprises to enjoy the most advanced services from outsourcing service providers. Because online payment and data security issues are involved in outsourcing services, the mutual distrust between users and service providers may severely impede the wide adoption of cloud computing. Nevertheless, most existing solutions only consider a specific type of services and rely on a trusted third-party to realize fair payment. In this paper, to realize secure and fair payment of outsourcing services in general without relying on any third-party, trusted or …