Extracting Maritime Traffic Networks from AIS Data Using Evolutionary Algorithm

2020 | Business & Information Systems Engineering | Citations: 0

Authors: Filipiak, Dominik; Węcel, Krzysztof; Stróżyna, Milena; Michalak, Michał; Abramowicz, Witold

Abstract: The presented method reconstructs a network (a graph) from AIS data, which refle ... Expand

Abstract: The presented method reconstructs a network (a graph) from AIS data, which reflects vessel traffic and can be used for route planning. The approach consists of three main steps: maneuvering points detection, waypoints discovery, and edge construction. The maneuvering points detection uses the CUSUM method and reduces the amount of data for further processing. The genetic algorithm with spatial partitioning is used for waypoints discovery. Finally, edges connecting these waypoints form the final maritime traffic network. The approach aims at advancing the practice of maritime voyage planning, which is typically done manually by a ship’s navigation officer. The authors demonstrate the results of the implementation using Apache Spark, a popular distributed and parallel computing framework. The method is evaluated by comparing the results with an on-line voyage planning application. The evaluation shows that the approach has the capacity to generate a graph which resembles the real-world maritime traffic network. Collapse

Topics: Apache Spark parallel computing computer hardware

Methods: computational algorithm cumulative sum control chart experiment machine learning optimization model

Theories: graph theory

Using a Heuristic-Systematic Model to assess the Twitter user profile’s impact on disaster tweet credibility

2020 | International Journal of Information Management | Citations: 0

Authors: Son, Jaebong; Lee, Jintae; Oh, Onook; Lee, Hyung Koo; Woo, Jiyoung

Abstract: Journalists, emergency responders, and the general public use Twitter during dis ... Expand

Abstract: Journalists, emergency responders, and the general public use Twitter during disasters as an effective means to disseminate emergency information. However, there is a growing concern about the credibility of disaster tweets. This concern negatively influences Twitter users’ decisions about whether to retweet information, which can delay the dissemination of accurate—and sometimes essential—communications during a crisis. Although verifying information credibility is often a time-consuming task requiring considerable cognitive effort, researchers have yet to explore how people manage this task while using Twitter during disaster situations. Collapse

Topics: Twitter social presence information management social media accounting

Methods: topic model statistical hypothesis test latent dirichlet allocation design artifact logistic regression

Content features of tweets for effective communication during disasters: A media synchronicity theory perspective

2019 | International Journal of Information Management | Citations: 20

Authors: Son, Jaebong; Lee, Hyung Koo; Jin, Sung; Lee, Jintae

Abstract: Users’ ability to retweet information has made Twitter one of the most prominent ... Expand

Abstract: Users’ ability to retweet information has made Twitter one of the most prominent social media platforms for disseminating emergency information during disasters. However, few studies have examined how Twitter’s features can support the different communication patterns that occur during different phases of disaster events. Based on the literature of disaster communication and Media Synchronicity Theory, we identify distinct disaster phases and the two communication types—crisis communication and risk communication—that occur during those phases. We investigate how Twitter’s representational features, including words, URLs, hashtags, and hashtag importance, influence the average retweet time—that is, the average time it takes for retweet to occur—as well as how such effects differ depending on the type of disaster communication. Our analysis of tweets from the 2013 Colorado floods found that adding more URLs to tweets increases the average retweet time more in riskrelated tweets than it does in crisis-related tweets. Further, including key disaster-related hashtags in tweets contributed to faster retweets in crisis-related tweets than in risk-related tweets. Our findings suggest that the influence of Twitter’s media capabilities on rapid tweet propagation during disasters may differ based on the communication processes. Collapse

Topics: Twitter situational awareness accounting sensemaking tsunami

Methods: topic model statistical hypothesis test natural language processing regression analysis method descriptive statistic

Theories: media synchronicity theory

Automated Anomaly Detection in Distribution Grids Using µPMU Measurements

2017 | HICSS | Citations: 0

Authors: Jamei, Mahdi; Scaglione, Anna; Roberts, Ciaran; Stewart, Emma; Peisert, Sean; McParland, Chuck; McEachern, Alex

Abstract: The impact of Phasor Measurement Units (PMUs) for providing situational awarenes ... Expand

Abstract: The impact of Phasor Measurement Units (PMUs) for providing situational awareness to transmission system operators has been widely documented. Micro-PMUs (µPMUs) are an emerging sensing technology that can provide similar benefits to Distribution System Operators (DSOs), enabling a level of visibility into the distribution grid that was previously unattainable. In order to support the deployment of these high resolution sensors, the automation of data analysis and prioritizing communication to the DSO becomes crucial. In this paper, we explore the use of µPMUs to detect anomalies on the distribution grid. Our methodology is motivated by growing concern about failures and attacks to distribution automation equipment. The effectiveness of our approach is demonstrated through both real and simulated data. Collapse

Topics: physical security intrusion detection system

Methods: simulation anomaly detection computational algorithm cumulative sum control chart descriptive statistic

Blind to Time? Temporal Trends in Effect Sizes in IS Research

2016 | International Conference on Information Systems | Citations: 0

Authors: Agogo, David; Hess, Traci

Abstract: This research-in-progress paper describes cumulative meta-analysis, or meta-tren ... Expand

Abstract: This research-in-progress paper describes cumulative meta-analysis, or meta-trend analysis, a form of meta-analysis that considers temporal trends in effect sizes. While this method is common in medical sciences, it is just starting to gain traction in behavioral research, and temporal trends have typically not been addressed in IS research. A review of 64 meta-analysis papers from 15 IS journals confirms that IS research is generally blind to time. No IS paper has employed meta-trend analysis to test for temporal trends, and less than a quarter of the papers reviewed have any treatment or mention of the possible impact of time. Support from ecological systems theory, in particular the idea of proximal processes, is used to explain why IS researchers may expect temporal trends in effect sizes. To illustrate this, meta-trend analysis is conducted on several frequently examined relationships between IS constructs. Preliminary evidence of temporal trends is observed. Collapse

Topics: information system use perceived ease of use perceived usefulness user satisfaction behavioral intention

Methods: meta analysis descriptive statistic literature study cumulative sum control chart

Theories: technology acceptance model general systems theory

Application of Fuzzy Risk Analysis for Selecting Critical Processes in Implementation of SPC with a Case Study

2016 | Group Decision and Negotiation | Citations: 0

Authors: Khorshidi, Hadi Akbarzade; Gunawan, Indra; Nikfalazar, Sanaz

Abstract: Fuzzy risk analysis is widely used in risk assessment of components by linguisti ... Expand

Abstract: Fuzzy risk analysis is widely used in risk assessment of components by linguistic terms. Fuzzy numbers are used to quantify the associated uncertainty. This study employs fuzzy risk analysis to evaluate processes for implementing statistical process control (SPC) in a specified manufacturing system. To reach this goal, fuzzy risk analysis has been applied based on both ranking and similarity of generalized trapezoidal fuzzy numbers in a stepwise procedure. Therefore, a new approach has been introduced for fuzzy risk analysis of processes to overcome the shortcomings of previous fuzzy risk analysis approaches. As a result, fuzzy risk analysis is used as a decision making technique to select critical processes under uncertainty. Also, the application of the proposed SPC implementation algorithm is illustrated in the manufacturing line of a car battery factory. Collapse

Topics: manufacturing information system decision making innovation management statistical process control

Methods: computational algorithm case study trade-off analysis method TOPSIS cumulative sum control chart

Modeling Supply-Side Dynamics of IT Components, Products, and Infrastructure: An Empirical Analysis Using Vector Autoregression

2012 | Information Systems Research | Citations: 0

Authors: Adomavicius, Gediminas; Bockstedt, Jesse; Gupta, Alok

Abstract: Prior IS research on technological change has focused primarily on organizationa ... Expand

Abstract: Prior IS research on technological change has focused primarily on organizational information systems and technology innovation; however, there is a growing need to understand the dynamics of supply-side forces in the introduction of new technologies. In this paper we investigate how the interdependencies among information technology components, products, and infrastructure affect the release of new technologies. Going beyond the ad hoc heuristic approaches applied in previous studies, we empirically validate the existence of several patterns of supply-side technology relationships in the context of wireless networking. We use vector autoregression (VAR) to model the comovements of new component, product, and infrastructure introductions and provide evidence of strong Granger-causal interdependencies. We also demonstrate that substantial improvements in forecasting can be gained by incorporating these cross-level effects into models of technological change. This paper provides some of the first research that empirically demonstrates these cross-level effects and also provides an exposition of VAR methodology for both analysis and forecasting in IS research. Collapse

Topics: wireless computer network technological change wireless LAN computer hardware video game console

Methods: longitudinal research Granger causality time series analysis vector autoregression design artifact

Theories: co-evolution theory

On Quality and Communication: The Relevance of Critical Theory to Health Informatics

2011 | Journal of the Association for Information Systems | Citations: 9

Authors: Shaw, Mark Christopher; Stahl, Bernd Carsten

Abstract: Health information systems require long-term investment before they provide a so ... Expand

Abstract: Health information systems require long-term investment before they provide a socio-economic return, yet their implementation remains problematic, possibly because the claims made about them appear not to sit well with healthcare professionals' practice. Health informatics should address these issues from a sound conceptual base, such as might be provided by critical theory, which seeks to identify hidden assumptions and ideologies. This discipline can provide a better understanding of the inner workings of socio-technical systems, with a view to improving them through the promotion of emancipation (allowing people to fulfill their potential). Critical theory can also shed light on the problems with health information systems and offer insight into remedies, for example, by relating Habermas' theories about communication to feedback, a concept central to quality assurance (QA). Such analysis finds that QA's principal practices can be interpreted as emancipatory but requires organizations to substantially change their behavior. An alternate approach is to install health information systems designed to support QA. Applying critical theory to these systems shows that they could become an active part of service delivery rather than static repositories of data, because they may encourage standardized conversations between all stakeholders about the important features of health care. Success will depend on access for all participants to data entry and analysis tools, integration with work practice, and use by staff and management in QA. These ideas offer new directions for research into and the development of health information systems. The next step will be to implement them and observe their technical and emancipatory properties. Collapse

Topics: health information system research and development societal evaluation criteria

Methods: cumulative sum control chart

Theories: theory of communicative action

A stack-based prospective spatio-temporal data analysis approach

2008 | Decision Support Systems | Citations: 0

Authors: Chang, Wei; Zeng, Daniel; Chen, Hsinchun

Abstract: Spatio-temporal data analysis has recently gained considerable attention from bo ... Expand

Abstract: Spatio-temporal data analysis has recently gained considerable attention from both the research and practitioner communities because of the increasing availability of datasets with prominent spatial and temporal data elements. In this paper, we develop a new spatio-temporal data analysis approach aimed at discovering abnormal spatio-temporal clustering patterns. We also propose a quantitative evaluation framework and compare our approach against a widely used space–time scan statistic-based method under this framework. Our approach is based on a robust clustering engine using support vector machines and incorporates ideas from existing online surveillance methods to track incremental changes over time. Initial experimental results using both simulated and real-world datasets indicate that our approach is able to detect abnormal areas with irregular shapes more accurately than the space–time scan statistic-based method. Collapse

Topics: criminality health information system information retrieval electronic surveillance

Methods: computational algorithm experiment cluster analysis longitudinal research machine learning

Time Changes Everything: An Examination and Application of Time-Varying Coefficients in Information Systems Research

2006 | International Conference on Information Systems | Citations: 0

Authors: Overby, Eric; Konsynski, Benn

Abstract: The Information Systems research field is inherently dynamic. New technologies, ... Expand

Abstract: The Information Systems research field is inherently dynamic. New technologies, new standards, new legislation, and changing user expectations are some of the reasons why topics of interest to the IS field remain in flux. As researchers, we seek to uncover and explain relationships among variables, but due to the dynamism of IS phenomena, these relationships are apt to change over time. For example, the effect of informational features such as product diagnosticity or seller reputation on the price of an electronic commerce transaction is likely to change over time as users become more comfortable with online trading. This paper describes several statistical methods to model these changes in relationships. Specifically, we discuss methods to investigate time-varying coefficients in regression models, including rolling regression, “parameterizing” the coefficients using process functions, and testing for structural change. Importantly, we describe how the structure of many of the data sets used in IS research differs from that of data sets often used in other fields such as finance, economics, or marketing. This has implications for the investigation of time-based effects. We illustrate each method using a data set gathered from the wholesale automotive market, which not only helps us explain the methods, but also allows us to investigate the evolution of market practice in one empirical context. Thus, we address both methodological and substantive issues. Given that our field is inherently dynamic, an understanding of how effects change over time should be central to the overall IS research agenda. This paper is designed to familiarize IS researchers with methods available for this purpose. Collapse

Topics: electronic market electronic commerce marketing management IT investment information system use

Methods: longitudinal research regression analysis method cross sectional research time series analysis cumulative sum control chart