Databases and Information Systems Commons^™

Using A Data Warehouse As Part Of A General Business Process Data Analysis System, Amit Maor

CMC Senior Theses

Data analytics queries often involve aggregating over massive amounts of data, in order to detect trends in the data, make predictions about future data, and make business decisions as a result. As such, it is important that a database management system (DBMS) handling data analytics queries perform well when those queries involve massive amounts of data. A data warehouse is a DBMS which is designed specifically to handle data analytics queries.

This thesis describes the data warehouse Amazon Redshift, and how it was used to design a data analysis system for Laserfiche. Laserfiche is a software company that provides each …

Evaluating Distributed Word Representations For Predicting Missing Words In Sentences, Saniya Saifee

Dissertations and Theses

In recent years, the distributed representation of words in vector space or word embeddings have become very popular as they have shown significant improvements in many statistical natural language processing (NLP) tasks as compared to traditional language models like Ngram. In this thesis, we explored various state-of-the-art methods like Latent Semantic Analysis, word2vec, and GloVe to learn the distributed representation of words. Their performance was compared based on the accuracy achieved when tasked with selecting the right missing word in the sentence, given five possible options. For this NLP task we trained each of these methods using a training corpus …

A Tool-Free Calibration Method For Turntable-Based 3d Scanning Systems, Xufang Pang, Rynson W.H. Lau, Zhan Song, Shengfeng He, Shengfeng He

Research Collection School Of Computing and Information Systems

Turntable-based 3D scanners are popular but require calibration of the turntable axis. Existing methods for turntable calibration typically make use of specially designed tools, such as a chessboard or criterion sphere, which users must manually install and dismount. In this article, the authors propose an automatic method to calibrate the turntable axis without any calibration tools. Given a scan sequence of the input object, they first recover the initial rotation axis from an automatic registration step. Then they apply an iterative procedure to obtain the optimized turntable axis. This iterative procedure alternates between two steps: refining the initial pose of …

Posting Topics ≠ Reading Topics: On Discovering Posting And Reading Topics In Social Media, Wei Gong, Ee-Peng Lim, Feida Zhu

Research Collection School Of Computing and Information Systems

Social media users make decisions about what content to post and read. As posted content is often visible to others, users are likely to impose self-censorship when deciding what content to post. On the other hand, such a concern may not apply to reading social media content. As a result, the topics of content that a user posted and read can be different and this has major implications to the applications that require personalization. To better determine and profile social media users’ topic interests, we conduct a user survey in Twitter. In this survey, participants chose the topics they like …

On Analyzing Geotagged Tweets For Location-Based Patterns, Philips Kokoh Prasetyo, Palakorn Achananuparp, Ee Peng Lim

Research Collection School Of Computing and Information Systems

Geotagged social media is becoming highly popular as social media access is now made very easy through a wide range of mobile apps which automatically detect and augment social media posts with geo-locations. In this paper, we analyze two kinds of location-based patterns. The first is the association between location attributes and the locations of user tweets. The second is location association pattern which comprises a pair of locations that are co-visited by users. We demonstrate that through tracking the Twitter data of Singapore-based users, we are able to reveal association between users tweeting from school locations and the school …

Insights From Machine-Learned Diet Success Prediction, Ingmar Weber, Palakorn Achananuparp

Research Collection School Of Computing and Information Systems

To support people trying to lose weight and stay healthy, more and more fitness apps have sprung up including the ability to track both calories intake and expenditure. Users of such apps are part of a wider “quantified self“ movement and many opt-in to publicly share their logged data. In this paper, we use public food diaries of more than 4,000 long-term active MyFitnessPal users to study the characteristics of a (un-)successful diet. Concretely, we train a machine learning model to predict repeatedly being over or under self-set daily calories goals and then look at which features contribute to the …

A Comparison Of Fundamental Network Formation Principles Between Offline And Online Friends On Twitter, Felicia Natali, Feida Zhu

Research Collection School Of Computing and Information Systems

We investigate the differences between how some of the fundamental principles of network formation apply among offline friends and how they apply among online friends on Twitter. We consider three fundamental principles of network formation proposed by Schaefer et al.: reciprocity, popularity, and triadic closure. Overall, we discover that these principles mainly apply to offline friends on Twitter. Based on how these principles apply to offline versus online friends, we formulate rules to predict offline friendship on Twitter. We compare our algorithm with popular machine learning algorithms and Xiewei’s random walk algorithm. Our algorithm beats the machine learning algorithms on …

Information Source Detection Via Maximum A Posteriori Estimation, Biao Chang, Feida Zhu, Enhong Chen, Qi. Liu

Research Collection School Of Computing and Information Systems

The problem of information source detection, whose goal is to identify the source of a piece of information from a diffusion process (e.g., computer virus, rumor, epidemic, and so on), has attracted ever-increasing attention from research community in recent years. Although various methods have been proposed, such as those based on centrality, spectral and belief propagation, the existing solutions still suffer from high time complexity and inadequate effectiveness. To this end, we revisit this problem in the paper and present a comprehensive study from the perspective of likelihood approximation. Different from many previous works, we consider both infected and uninfected …

Data Analytics On Consumer Behavior In Omni-Channel Retail Banking, Card And Payment Services, Geng Dan

Research Collection School Of Computing and Information Systems

Innovations in financial services have created challenges for banks that Information Systems (IS) research can address. My interests involve transaction cost theory, substitution and complementarity theory, and consumer informedness theory to understand consumer behavior and firm performance in the omni-channel world of digital banking. At a high level, my research inquiry asks: How can financial institutions take advantage of the deep insights that data analytics and management science modeling create on consumer behavior and channel management decision-making? And how can changes in payments and services in retail banking be understood in spatial and temporal terms? I am working on three …

An Evaluation Of Robotics In Nursing Homes To Reduce Adverse Drug Events, Ozell Ueal Jr.

Walden Dissertations and Doctoral Studies

Adverse drug events (ADE) cause many deaths annually in addition to affecting the quality of life of many others. The descriptive mixed methods approach, specifically exploratory case study and experimental design that guided this research utilized the survey and focus group methods to evaluate perceptions about robotic technology (RT) to reduce the rate of ADEs in U.S. nursing homes (NH). There is a lack of scholarly research into whether a conceptual approach rooted in RT can be implemented to assist with drug administrations in NHs. The purpose of this study was twofold. The first purpose was to evaluate the causes …

The Impact Of Transportation Infrastructure On Nigeria's Economic Developmeny, William A. Agbigbe

Walden Dissertations and Doctoral Studies

The United Nations Development Programme (UNDP) described Nigeria's road networks as one of the poorest and deadliest transportation infrastructural systems in the world. Data from the UNDP and the World Bank (WB) show that Nigeria has suffered transportation infrastructure deficits; these data also illustrate Nigeria as one of the lowest indices in economic development in the last decade. This qualitative case study addressed the impact of a lack of investment in transportation infrastructure in the form of road networks on Nigeria's economic development. The purpose of the study was to understand the relationship between the investment in road networks and …

Strategies To Control Internal Factors Affecting Information Systems Projects In Puerto Rico, Annie Luz Roman Acevedo

Walden Dissertations and Doctoral Studies

Many project managers and business leaders lack effective strategies to control internal factors that affect information systems (IS) projects, which may impede leadership's ability to respond to market changes. The purpose of this multiple case study was to explore strategies used by 6 purposefully selected project managers who successfully implemented information system development (ISD) projects by controlling the internal factors that affected different ISD project phases in Puerto Rico's telecommunication service industry. The framework that guided this study was coordination theory. The data collection process included semistructured interviews and project documentation including business requirements, project charters, project plans, and lessons …

Mitigation Strategies Of Technostress On Supply Chain Management, Robert Lewis Penn

Walden Dissertations and Doctoral Studies

Logistics managers work to create practices that reduce technostress, which is associated with diminished productivity in supply chain management. The purpose of this multiple case study was to explore the mitigation strategies that logistics managers at distribution centers used to reduce technostress with their employees in the Los Angeles County, California area. The conceptual framework included in this study was the sociotechnical systems theory. Semistructured interviews were conducted with 6 logistics managers from large distribution centers who implemented mitigation strategies that demonstrably reduced technostress with their employees. Public documents and physical artifacts reviewed in this study included productivity assessment tools, …

Unexpected Events In Nigerian Construction Projects: A Case Of Four Construction Companies, Gabriel Baritulem Pidomson

Walden Dissertations and Doctoral Studies

In Nigeria, 50% to 70% of construction projects are delayed due to unexpected events that are linked to lapses in performance, near misses, and surprises. While researchers have theorized on the impact of mindfulness and information systems management (ISM) on unexpected events, information is lacking on how project teams can combine ISM and mindfulness in response to unexpected events in construction projects. The purpose of this case study was to examine how project teams can combine mindfulness with ISM in response to unexpected events during the execution phase of Nigerian construction projects. The framework of High Reliability Theory revealed that …

Meeting Meaningful-Use Requirements With Electronic Medical Records In A Community Health Clinic, Tony Andrew Richardson

Walden Dissertations and Doctoral Studies

Small nonprofit medical practices lack the technical expertise to implement electronic medical records (EMRs) that are consistent with federal meaningful-use requirements. Failure to comply with meaningful-use EMR requirements affects nonprofit community health care leaders' ability to receive reimbursement for care. Complexity theory was the conceptual framework used in this exploratory single case study. The purpose of the study was to explore the strategies nonprofit community health care leaders in Washington, DC used to implement EMRs in order to comply with the meaningful-use requirements. Data were collected via in-depth interviews with 7 purposively-selected health care leaders in a nonprofit clinic and …

Information Technology Adoption By Small Businesses Owners, Soha Elaskalani Ragab

Walden Dissertations and Doctoral Studies

Small business owners need effective strategies to increase profitability. One such strategy is the adoption of information technology (IT). The purpose of this multiple case study was to explore the strategies used by small business enterprise (SBE) owners to implement IT solutions for increased profitability within 3 years of opening their business. The population consisted of 3 small business owners in Orange County Southern California who were profitable by their third year of business. The conceptual framework for this study was based upon general systems theory. Data for this study were collected through semistructured interviews and a review of company …

Decision-Making On Technology Deployment For Online Programs At Historically Black Institutions, Shirley M. Mcclellan

Walden Dissertations and Doctoral Studies

Historically Black colleges and universities (HBCUs) lag behind predominantly White institutions in their production of online courses and degree programs because of nonexistent or inadequate technology training for faculty members and limited financial resources. The purpose of this qualitative comparative case study was to obtain insight into how decisions are made on technology deployment and integration of online programs at HBCUs. Guided by Donaldson's contingency theory, this case study addressed how decisions are determined at HBCUs to integrate online learning programs into the curriculum and how the individuals who make these decisions perceive online learning programs. Survey responses were collected …

Strategies For E-Commerce Platform Adoption In The Manufacturing Sector In Western India, Neeraj Parikh

Walden Dissertations and Doctoral Studies

While 95% of Indian SME leaders have not adopted an e-commerce platform, the few SME leaders having adopted such platforms reported 64% higher sales and 65% higher profits. The purpose of this multi-case study, guided by the diffusion of innovation (DOI) theory, was to explore the strategies that Indian SME leaders used to adopt e-commerce platforms to expand their businesses. Data for this study emerged from conducting face-to-face, semistructured interviews with 3 SME leaders who operated in the manufacturing industry in western India. The data analysis process included validating, coding, interpreting, and summarizing data and generating themes. Methodological triangulation of …

Examining Data Privacy Breaches In Healthcare, Tanshanika Turner Smith

Walden Dissertations and Doctoral Studies

Healthcare data can contain sensitive, personal, and confidential information that should remain secure. Despite the efforts to protect patient data, security breaches occur and may result in fraud, identity theft, and other damages. Grounded in the theoretical backdrop of integrated system theory, the purpose of this study was to determine the association between data privacy breaches, data storage locations, business associates, covered entities, and number of individuals affected. Study data consisted of secondary breach information retrieved from the Department of Health and Human Services Office of Civil Rights. Loglinear analytical procedures were used to examine U.S. healthcare breach incidents and …

Adoption Of Information And Communication Technology In Nigerian Small- To Medium-Size Enterprises, Kessington Enaye Okundaye

Walden Dissertations and Doctoral Studies

Small- to medium-size enterprises (SMEs) play a vital role in a dynamic economy through job creation, poverty alleviation, and socioeconomic development in developed and developing countries. The purpose of this multiple case study was to explore how SME leaders in Lagos, Nigeria, adopted information and communication technology (ICT) as a business strategy to increase profitability and compete globally. Organizational leaders have adopted ICT so that their organizations can become more efficient, effective, innovative, and globally competitive. This study involved 4 SMEs that had successfully implemented ICT. The participants included 5 SME leaders from each of the SMEs. The data collection …