Space-Time Analytics for Spatial Dynamics

The so-called Big Data Challenge poses not only issues with massive volumes of data, but issues with the continuing data streams from multiple sources that monitor environmental processes or record social activities. Many statistics tools and data mining methods have been developed to reveal embedded patterns in large data sets. While patterns are critical to data analysis, deep insights will remain buried unless we develop means to associate spatiotemporal patterns to the dynamics of spatial processes that essentially drive the formation of patterns in the data. This chapter reviews the literature with the conceptual foundation for space-time analytics dealing with spatial processes, discusses the types of dynamics that have and have not been addressed in the literature, and identifies needs for new thinking that can systematically advance space-time analytics to reveal dynamics of spatial processes. The discussion is facilitated by an example to highlight potential means of space-time analytics in response to the Big Data Challenge. The example shows the development of new space-time concepts and tools to analyze data from two common General Circulation Models for climate change predictions. Common approaches compare temperature changes at locations from the NCAR CCSM3 and from the CNRM CM3 or animate time series of temperature layers to visualize the climate prediction. Instead, new space-time analytics methods are shown here the ability to decipher the differences in spatial dynamics of the predicted temperature change in the model outputs and apply the concepts of change and movement to reveal warming, cooling, convergence, and divergence in temperature change across the globe.

Pattern Mining for Outbreak Discovery Preparedness

Today, the objective of public health surveillance system is to reduce the impact of outbreaks by enabling appropriate intervention. Commonly used techniques are based on the changes or aberration in health events when compared with normal history to detect an outbreak. The main problem encountered in outbreaks is high rates of false alarm. High false alarm rates can lead to unnecessary interventions, and falsely detected outbreaks will lead to costly investigation. In this chapter, the authors review data mining techniques focusing on frequent and outlier mining to develop generic outbreak detection process model, named as “Frequent-outlier” model. The process model was tested against the real dengue dataset obtained from FSK, UKM, and also tested on the synthetic respiratory dataset obtained from AUTON LAB. The ROC was run to analyze the overall performance of “frequent-outlier” with CUSUM and Moving Average (MA). The results were promising and were evaluated using detection rate, false positive rate, and overall performance. An important outcome of this study is the knowledge rules derived from the notification of the outbreak cases to be used in counter measure assessment for outbreak preparedness.

Research Challenge of Locally Computed Ubiquitous Data Mining

Advances in wireless, sensor, mobile and wearable technologies present new challenges for data mining research on providing mobile applications with intelligence. Autonomy and adaptability requirements are the two most important challenges for data mining in this new environment. In this chapter, in order to encourage the researchers on this area, we analyzed the challenges of designing ubiquitous data mining services by examining the issues and problems while paying special attention to context and resource awareness. We focused on the autonomous execution of a data mining algorithm and analyzed the situational factors that influence the quality of the result. Already existing solutions in this area and future directions of research are also covered in this chapter.

Challenges to Use Recommender Systems to Enhance Meta-Cognitive Functioning in Online Learners

A wealth of research has shown that meta-cognition plays a crucial role in the promotion of effective school learning. In most of the e-learning environment designs, however, meta-cognitive strategies have generally been neglected, and therefore, satisfactory uses of these strategies have rarely been realized. Most learners are not even aware of what they have been studying. If the learning system could automatically guide and intelligently recommend learning activities or strategies to facilitate student monitoring and control of their learning, it would favor and improve their learning process and performance. Unfortunately, nearly no e-learning systems to date have attempted to do so. In this chapter, we first described the need for enhancing meta-cognitive skills in e-learning environment, followed by an outline of major challenges for meta-cognitive activity recommendations. We then proposed to adopt data mining algorithms (i.e., content-based and sequence-based recommendation techniques) to meet the identified issues with a toy example.

Evaluation Challenges for Computer-Aided Diagnostic Characterization

Evaluating the success of computer-aided decision support systems depends upon a reliable reference standard, a ground truth. The ideal gold standard is expected to result from the marking, labeling, and rating by domain experts of the image of interest. However experts often disagree, and this lack of agreement challenges the development and evaluation of image-based feature prediction of expert-defined “truth.” The following discussion addresses the success and limitation of developing computer-aided models to characterize suspicious pulmonary nodules based upon ratings provided by multiple expert radiologists. These prediction models attempt to bridge the semantic gap between images and medically-meaningful, descriptive opinions about visual characteristics of nodules. The resultant computer-aided diagnostic characterizations (CADc) are directly usable for indexing and retrieving in content-based medical image retrieval and supporting computer-aided diagnosis. The predictive performance of CADc models are directly related to the extent of agreement between radiologists; the models better predict radiologists’ opinions when radiologists agree more with each other about the characteristics of nodules.

Financial Early Warning System for Risk Detection and Prevention from Financial Crisis

Risk management has become a vital topic for all enterprises especially in financial crisis periods. All enterprises need systems to warn against risks, detect signs and prevent from financial distress. Before the global financial crisis that began 2008, small and medium-sized enterprises (SMEs) have already fought with important financial issues. The global financial crisis and the ensuring flight away from risk have affected SMEs more than larger enterprises When we consider these effects, besides the issues of poor business performance, insufficient information and insufficiencies of managers in finance education, it is clear that early warning systems (EWS) are vital for SMEs for detection risk and prevention from financial crisis. The aim of this study is to develop and present a financial EWS for risk detection via data mining. For this purpose, data of SMEs listed in Istanbul Stock Exchange (ISE) and Chi-Square Automatic Interaction Detector (CHAID) Decision Tree Algorithm were used. By using EWS, we determined the risk profiles and risk signals for risk detection and road maps for risk prevention from financial crisis.

A Decision Support System for Privacy Compliance

Regulatory compliance in areas such as privacy has become a major challenge for organizations. In large organizations there can be hundreds or thousands of projects that involve personal information. Ensuring that all those projects properly take privacy considerations into account is a complex challenge for accountable privacy management. Accountable privacy management requires that an organization makes sure that all relevant projects are in compliance and that there is evidence and assurance that this actually is the case. To date, there has been no suitable automated, scalable support for accountable privacy management; it is such a tool that the authors describe in this chapter. Specifically, they describe a privacy risk assessment and compliance tool which they are developing and rolling out within a large, global company – called HP Privacy Advisor (HP PA) – and its generalisation and extension. The authors also bring out those security, privacy, risk, and trust-related aspects they have been researching related to this work in particular.

Structuring and Facilitating Online Learning through Learning/Course Management Systems

Online learning—whether it is human-facilitated or automated, hybrid/blended, asynchronopus or synchronous or mixed--often relies on learning/course management systems (L/CMSes). These systems have evolved in the past decade-and-a-half of popular use to integrate powerful tools, third-party software, Web 2.0 functionalities (blogs, wikis, virtual worlds, and tag clouds), and a growing set of capabilities (eportfolios, data management, back-end data mining, information assurance, and other elements). This chapter highlights learning/course management systems, their functionalities and structures (including some integrated technologies), their applied uses in adult e-learning, and extra-curricular applications. A concluding section explores future L/CMSes based on current trends.

Mobile Purchase Decision Support Systems for In-Store Shopping Environments

Purchase decision-making is influenced by product information available in online or in-store shopping environments. In online shopping environments, the use of decision support systems increases the value of product information as information becomes adaptive and thus more relevant to consumers’ information needs. Correspondingly, mobile purchase decision support systems (MP-DSSs) may also increase the value of product information in in-store shopping environments. In this chapter, we investigate the use of a MP-DSS that is bound to a physical product. Based on Theory of Planned Behaviour, Innovation Diffusion Theory, and Technology Acceptance Model, we propose and evaluate a model to better understand MP-DSSs. Results indicate that perceived usefulness influences product purchases and predicts usage intentions and store preferences of consumers. We therefore discuss new business models for retail stores in which MP-DSSs satisfy both the information needs of consumers and the communication needs of retailers.

Knowledge Discovery from Online Communities

This chapter presents an overview of social network features such as user behavior, social models, and user-generated content to highlight the most notable research trends and application systems built over such appealing models and online media data. It first describes the most popular social networks by analyzing the growth trend, the user behaviors, the evolution of social groups and models, and the most relevant types of data continuously generated and updated by the users. Next, the most recent and valuable applications of data mining techniques to social network models and user-generated content are presented. Discussed works address both social model extractions tailored to semantic knowledge inference and automatic understanding of the user-generated content. Finally, prospects of data mining research on social networks are provided as well.