Computer Sciences Commons^™

Latent Factors Meet Homophily In Diffusion Modelling, Duc Minh Luu, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Diffusion is an important dynamics that helps spreading information within an online social network. While there are already numerous models for single item diffusion, few have studied diffusion of multiple items, especially when items can interact with one another due to their inter-similarity. Moreover, the well-known homophily effect is rarely considered explicitly in the existing diffusion models. This work therefore fills this gap by proposing a novel model called Topic level Interaction Homophily Aware Diffusion (TIHAD) to include both latent factor level interaction among items and homophily factor in diffusion. The model determines item interaction based on latent factors and …

From Sensors To Sense Making: Leveraging Open-Access Scientific Data To Assess Arctic Maritime Risks, Mark A. Stoddard, Melanie Fournier Ph.D, Laurent Etienne Ph.D, Leah Beveridge Ph.D

ShipArc 2015 Conference

No abstract provided.

A System To Support Clerical Review, Correction, And Confirmation Assertions In Entity Identity Information Management, Cheng Chen

Theses and Dissertations

Clerical review of Entity Resolution(ER) is crucial for maintaining the entity identity integrity of an Entity Identity Information Management (EIIM) system. However, the clerical review process presents several problems. These problems include Entity Identity Structures (EIS) that are difficult to read and interpret, excessive time and effort to review large Identity Knowledgebase (IKB), and the duplication of effort in repeatedly reviewing the same EIS in same EIIM review cycle or across multiple review cycles. Although the original EIIM model envisioned and demonstrated the value of correction assertions, these are applied to correct errors after they have been found. The original …

Web-Based Fragment Library, Junjie Wang, Lyudmila Slipchenko

The Summer Undergraduate Research Fellowship (SURF) Symposium

A new polarized force field BioEFP for modeling process in biology is far superior in accuracy to the common classical force fields. One of the main shortcomings of BioEFP is that the parameters are not readily available, thus it will take a lot of time to be calculated.

Developing an online repository of pre-computed fragment parameters and a similarity algorithm will allow ascribing each fragment of a biological macromolecule to a pre-defined fragment.

This study incorporates three parts to create the online repository. First, the visual design for the website using the Hypertext Markup Language and the Cascading Style Sheets …

Event Identification And Analysis On Twitter, Qiming Diao

Dissertations and Theses Collection (Open Access)

With the rapid growth of social media, Twitter has become one of the most widely adopted platforms for people to post short and instant messages. Because of such wide adoption of Twitter, events like breaking news and release of popular videos can easily capture people’s attention and spread rapidly on Twitter. Therefore, the popularity and importance of an event can be approximately gauged by the volume of tweets covering the event. Moreover, the relevant tweets also reflect the public’s opinions and reactions to events. It is therefore very important to identify and analyze the events on Twitter. In this dissertation, …

Semi-Supervised Hashing With Semantic Confidence For Large Scale Visual Search, Yingwei Pan, Ting Yao, Houqiang Li, Chong-Wah Ngo, Tao Mei

Research Collection School Of Computing and Information Systems

Similarity search is one of the fundamental problems for large scale multimedia applications. Hashing techniques, as one popular strategy, have been intensively investigated owing to the speed and memory efficiency. Recent research has shown that leveraging supervised information can lead to high quality hashing. However, most existing supervised methods learn hashing function by treating each training example equally while ignoring the different semantic degree related to the label, i.e. semantic confidence, of different examples. In this paper, we propose a novel semi-supervised hashing framework by leveraging semantic confidence. Specifically, a confidence factor is first assigned to each example by neighbor …

Gibberish, Assistant, Or Master? Using Tweets Linking To News For Extractive Single-Document Summarization, Zhongyu Wei, Wei Gao

Research Collection School Of Computing and Information Systems

Single-document summarization is a challenging task. In this paper, we explore effective ways using the tweets linking to news for generating extractive summary of each document. We reveal the very basic value of tweets that can be utilized by regarding every tweet as a vote for candidate sentences. Base on such finding, we resort to unsupervised summarization models by leveraging the linking tweets to master the ranking of candidate extracts via random walk on a heterogeneous graph. The advantage is that we can use the linking tweets to opportunistically "supervise" the summarization with no need of reference summaries. Furthermore, we …

Tweet Sentiment: From Classification To Quantification, Wei Gao, Fabrizio Sebastiani

Research Collection School Of Computing and Information Systems

Sentiment classification has become a ubiquitous enabling technology in the Twittersphere, since classifying tweets according to the sentiment they convey towards a given entity (be it a product, a person, a political party, or a policy) has many applications in political science, social science, market research, and many others. In this paper we contend that most previous studies dealing with tweet sentiment classification (TSC) use a suboptimal approach. The reason is that the final goal of most such studies is not estimating the class label (e.g., Positive, Negative, or Neutral) of individual tweets, but estimating the relative frequency (a.k.a. "prevalence") …

Memes As Building Blocks: A Case Study On Evolutionary Optimization + Transfer Learning For Routing Problems, Liang Feng, Yew-Soon Ong, Ah-Hwee Tan, Ivor W. Tsang

Research Collection School Of Computing and Information Systems

A significantly under-explored area of evolutionary optimization in the literature is the study of optimization methodologies that can evolve along with the problems solved. Particularly, present evolutionary optimization approaches generally start their search from scratch or the ground-zero state of knowledge, independent of how similar the given new problem of interest is to those optimized previously. There has thus been the apparent lack of automated knowledge transfers and reuse across problems. Taking this cue, this paper presents a Memetic Computational Paradigm based on Evolutionary Optimization + Transfer Learning for search, one that models how human solves problems, and embarks on …

Neural Modeling Of Sequential Inferences And Learning Over Episodic Memory, Budhitama Subagdja, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Episodic memory is a significant part of cognition for reasoning and decision making. Retrieval in episodic memory depends on the order relationships of memory items which provides flexibility in reasoning and inferences regarding sequential relations for spatio-temporal domain. However, it is still unclear how they are encoded and how they differ from representations in other types of memory like semantic or procedural memory. This paper presents a neural model of sequential representation and inferences on episodic memory. It contrasts with the common views on sequential representation in neural networks that instead of maintaining transitions between events to represent sequences, they …

Fast Object Retrieval Using Direct Spatial Matching, Zhiyuan Zhong, Jianke Zhu, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

The conventional bag-of-visual-words (BoW) model is popular for the large-scale object retrieval system but suffers from the critical drawback of ignoring spatial information. RANSAC-based methods attempt to remedy this drawback, but often require traversing all the feature matches for each hypothesis, leading to the heavy computational cost which limits the number of gallery images to be verified for each online query. We propose an efficient direct spatial matching (DSM) approach to directly estimate the scale variation using region sizes, in which all feature matches voted for estimating geometric transformation. DSM is much faster than RANSAC-based methods and exhaustive enumeration approaches. …

Fusing Heterogeneous Data For Alzheimer's Disease Classification, P. S. Pillai, Tze-Yun Leong

Research Collection School Of Computing and Information Systems

In multi-view learning, multimodal representations of a real world object or situation are integrated to learn its overall picture. Feature sets from distinct data sources carry different, yet complementary, information which, if analysed together, usually yield better insights and more accurate results. Neuro-degenerative disorders such as dementia are characterized by changes in multiple biomarkers. This work combines the features from neuroimaging and cerebrospinal fluid studies to distinguish Alzheimer's disease patients from healthy subjects. We apply statistical data fusion techniques on 101 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. We examine whether fusion of biomarkers helps to improve diagnostic …

Faitcrowd: Fine Grained Truth Discovery For Crowdsourced Data Aggregation, Fenglong Ma, Yaliang Li, Qi Li, Minghui Qiu, Jing Gao, Shi Zhi, Lu Su, Bo Zhao, Jiawei Han

Research Collection School Of Computing and Information Systems

In crowdsourced data aggregation task, there exist conflicts in the answers provided by large numbers of sources on the same set of questions. The most important challenge for this task is to estimate source reliability and select answers that are provided by high-quality sources. Existing work solves this problem by simultaneously estimating sources' reliability and inferring questions' true answers (i.e., the truths). However, these methods assume that a source has the same reliability degree on all the questions, but ignore the fact that sources' reliability may vary significantly among different topics. To capture various expertise levels on different topics, we …

Efficacy Of Social Media Utilization By Public Accounting Firms: Findings And Directions For Future Research, B. Eschenbrenner, Fiona Fui-Hoon Nah, V. Telaprolu

Research Collection School Of Computing and Information Systems

Social media presents a new platform for businesses to communicate and interact with others, both internally and externally. Social media may be utilized for activities such as sharing success stories and providing industry updates. Although a plethora of opportunities to achieve business objectives with social media usage exists, the efficacy of its use by public accounting firms is unclear. This article identifies the business objectives that Big 4 and second-tier firms are pursuing with social media. Primary business objectives being fulfilled by social media include Knowledge Sharing, Branding and Marketing, and Socialization and Onboarding. The findings suggest that Big 4 …

Facilitating Image Search With A Scalable And Compact Semantic Mapping, Meng Wang, Weisheng Li, Dong Liu, Bingbing Ni, Jialie Shen, Shuicheng Yan

Research Collection School Of Computing and Information Systems

This paper introduces a novel approach to facilitating image search based on a compact semantic embedding. A novel method is developed to explicitly map concepts and image contents into a unified latent semantic space for the representation of semantic concept prototypes. Then, a linear embedding matrix is learned that maps images into the semantic space, such that each image is closer to its relevant concept prototype than other prototypes. In our approach, the semantic concepts equated with query keywords and the images mapped into the vicinity of the prototype are retrieved by our scheme. In addition, a computationally efficient method …

Event Detection: Exploiting Socio-Physical Interactions In Physical Spaces, Kasthuri Jayarajah, Archan Misra, Xiao-Wen Ruan, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

This paper investigates how digital traces of people's movements and activities in the physical world (e.g., at college campuses and commutes) may be used to detect local, short-lived events in various urban spaces. Past work that use occupancy-related features can only identify high-intensity events (those that cause large-scale disruption in visit patterns). In this paper, we first show how longitudinal traces of the coordinated and group-based movement episodes obtained from individual-level movement data can be used to create a socio-physical network (with edges representing tie strengths among individuals based on their physical world movement & collocation behavior). We then investigate …

On Mining Lifestyles From User Trip Data, Meng-Fen Chiang, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Large cities today are facing major challenges in planning and policy formulation to keep their growth sustainable. In this paper, we aim to gain useful insights about people living in a city by developing novel models to mine user lifestyles represented by the users' activity centers. Two models, namely ACMM and ACHMM, have been developed to learn the activity centers of each user using a large dataset of bus and subway train trips performed by passengers in Singapore. We show that ACHMM and ACMM yield similar accuracies in location prediction task. We also propose methods to automatically predict "home", "work" …

Topic Modeling With Document Relative Similarities, Jianguang Du, Jing Jiang, Dandan Song, Lejian Liao

Research Collection School Of Computing and Information Systems

Topic modeling has been widely used in text mining. Previous topic models such as Latent Dirichlet Allocation (LDA) are successful in learning hidden topics but they do not take into account metadata of documents. To tackle this problem, many augmented topic models have been proposed to jointly model text and metadata. But most existing models handle only categorical and numerical types of metadata. We identify another type of metadata that can be more natural to obtain in some scenarios. These are relative similarities among documents. In this paper, we propose a general model that links LDA with constraints derived from …

Business Intelligence, Data And Analytics, Singapore Management University

Perspectives@SMU

Data can be used to predict outcomes but quality data is essential

Scalable Euclidean Embedding For Big Data, Zohreh S. Alavi, Sagar Sharma, Lu Zhou, Keke Chen

Kno.e.sis Publications

Euclidean embedding algorithms transform data defined in an arbitrary metric space to the Euclidean space, which is critical to many visualization techniques. At big-data scale, these algorithms need to be scalable to massive dataparallel infrastructures. Designing such scalable algorithms and understanding the factors affecting the algorithms are important research problems for visually analyzing big data. We propose a framework that extends the existing Euclidean embedding algorithms to scalable ones. Specifically, it decomposes an existing algorithm into naturally parallel components and non-parallelizable components. Then, data parallel implementations such as MapReduce and data reduction techniques are applied to the two categories of …

Informing And Performing: A Study Comparingadaptive Learning To Traditional Learning, Meg Coffin Murray, Jorge Perez

Faculty Articles

Technology has transformed education, perhaps most evidently in course delivery options. However, compelling questions remain about how technology impacts learning. Adaptive learning tools are technology-based artifacts that interact with learners and vary presentation based upon that interaction. This study examines completion rates and exercise scores for students assigned adaptive learning exercises and compares them to completion rates and quiz scores for students assigned objective-type quizzes in a university digital literacy course. Current research explores the hypothesis that adapting instruction to an individual’s learning style results in better learning outcomes. Computer technology has long been seen as an answer to the …

Evaluating A Potential Commercial Tool For Healthcare Application For People With Dementia, Tanvi Banerjee, Pramod Anantharam, William L. Romine, Larry Wayne Lawhorne

Kno.e.sis Publications

The widespread use of smartphones and sensors has made physiology, environment, and public health notifications amenable to continuous monitoring. Personalized digital health and patient empowerment can become a reality only if the complex multisensory and multimodal data is processed within the patient context, converting relevant medical knowledge into actionable information for better and timely decisions. We apply these principles in the healthcare domain of dementia. Specifically, in this study we validate one of our sensor platforms to ascertain whether it will be suitable for detecting physiological changes that may help us detect changes in people with dementia. This study shows …

Hotel Management System, Yimin Jin

All Capstone Projects

With the development of social service industries, using software to manage the hotel business requirements are gradually warming, conditional hotel before going to the relevant hotel management through, resolved depends on the original manual records management, inefficient, error-prone flaws, the hotel industry itself to provide the quality of service and the ability to have it higher requirements, hotel information management system is therefore increasingly attention.

Hotel information management system to achieve the hotel rooms management, customer information management, customer management add , modify customer management, customer management function.so the whole hotel information management system is divided into two parts, room …

State Preserving Extreme Learning Machine For Face Recognition, Md. Zahangir Alom, Paheding Sidike, Vijayan K. Asari, Tarek M. Taha

Electrical and Computer Engineering Faculty Publications

Extreme Learning Machine (ELM) has been introduced as a new algorithm for training single hidden layer feed-forward neural networks (SLFNs) instead of the classical gradient-based algorithms. Based on the consistency property of data, which enforce similar samples to share similar properties, ELM is a biologically inspired learning algorithm with SLFNs that learns much faster with good generalization and performs well in classification applications. However, the random generation of the weight matrix in current ELM based techniques leads to the possibility of unstable outputs in the learning and testing phases. Therefore, we present a novel approach for computing the weight matrix …

Automatic Video Self Modeling For Voice Disorder, Ju Shen, Changpeng Ti, Anusha Raghunathan, Sen-Ching S. Cheung, Rita Patel

Computer Science Faculty Publications

Video self modeling (VSM) is a behavioral intervention technique in which a learner models a target behavior by watching a video of him- or herself. In the field of speech language pathology, the approach of VSM has been successfully used for treatment of language in children with Autism and in individuals with fluency disorder of stuttering. Technical challenges remain in creating VSM contents that depict previously unseen behaviors. In this paper, we propose a novel system that synthesizes new video sequences for VSM treatment of patients with voice disorders. Starting with a video recording of a voice-disorder patient, the proposed …

Domain Specific Document Retrieval Framework For Real-Time Social Health Data, Swapnil Soni

Kno.e.sis Publications

With the advent of the web search and microblogging, the percentage of Online Health Information Seekers (OHIS) using these online services to share and seek health real-time information has in- creased exponentially. OHIS use web search engines or microblogging search services to seek out latest, relevant as well as reliable health in- formation. When OHIS turn to microblogging search services to search real-time content, trends and breaking news, etc. the search results are not promising. Two major challenges exist in the current microblogging search engines are keyword based techniques and results do not contain real-time information. To address these challenges, …

Log-Euclidean Metric Learning On Symmetric Positive Definite Manifold With Application To Image Set Classification, Zhiwu Huang, R. Wang, S. Shan, X. Li, X. Chen

Research Collection School Of Computing and Information Systems

The manifold of Symmetric Positive Definite (SPD) matrices has been successfully used for data representation in image set classification. By endowing the SPD manifold with Log-Euclidean Metric, existing methods typically work on vector-forms of SPD matrix logarithms. This however not only inevitably distorts the geometrical structure of the space of SPD matrix logarithms but also brings low efficiency especially when the dimensionality of SPD matrix is high. To overcome this limitation, we propose a novel metric learning approach to work directly on logarithms of SPD matrices. Specifically, our method aims to learn a tangent map that can directly transform the …

Fast Optimal Aggregate Point Search For A Merged Set On Road Networks, Weiwei Sun, Chong Chen, Baihua Zheng, Chunan Chen, Liang Zhu, Weimo Liu, Yan Huang

Research Collection School Of Computing and Information Systems

Aggregate nearest neighbor query, which returns an optimal target point that minimizes the aggregate distance for a given query point set, is one of the most important operations in spatial databases and their application domains. This paper addresses the problem of finding the aggregate nearest neighbor for a merged set that consists of the given query point set and multiple points needed to be selected from a candidate set, which we name as merged aggregate nearest neighbor(MANN) query. This paper proposes two algorithms to process MANN query on road networks when aggregate function is max. Then, we extend the algorithms …

A Convolution Kernel Approach To Identifying Comparisons In Text, Maksim Tkachenko, Hady W. Lauw

Research Collection School Of Computing and Information Systems

Comparisons in text, such as in online reviews, serve as useful decision aids. In this paper, we focus on the task of identifying whether a comparison exists between a specific pair of entity mentions in a sentence. This formulation is transformative, as previous work only seeks to determine whether a sentence is comparative, which is presumptuous in the event the sentence mentions multiple entities and is comparing only some, not all, of them. Our approach leverages not only lexical features such as salient words, but also structural features expressing the relationships among words and entity mentions. To model these features …

Online Learning To Rank For Content-Based Image Retrieval, Ji Wan, Pengcheng Wu, Steven C. H. Hoi, Peilin Zhao, Xingyu Gao, Dayong Wang, Yongdong. Zhang, Jintao Li

Research Collection School Of Computing and Information Systems

A major challenge in Content-Based Image Retrieval (CBIR) is to bridge the semantic gap between low-level image contents and high-level semantic concepts. Although researchers have investigated a variety of retrieval techniques using different types of features and distance functions, no single best retrieval solution can fully tackle this challenge. In a real-world CBIR task, it is often highly desired to combine multiple types of different feature representations and diverse distance measures in order to close the semantic gap. In this paper, we investigate a new framework of learning to rank for CBIR, which aims to seek the optimal combination of …