Analysis of Operation Performance of Blast Furnace With Machine Learning Methods

Although its theoretical foundation is well understood by researchers, a blast furnace is like a black box in practice because its behavior is not always as expected. It is a complex reactor where multiple reactions and multiple phases are involved, and the operation heavily relies on the operators' experience. In order to help the operators gain insights into the operation, the authors do not use traditional metallurgy models but instead use machine learning methods to analyze the data associated with the operation performance of a blast furnace. They analyze the variables that are connected to the economic and technical performance indices by combining domain knowledge and results obtained from two fundamental feature selection methods, and they propose a classification algorithm to train classifiers for the prediction of the operation performance. The findings could assist the operators in reviewing as well as improving the guideline for the operation.

Privacy and Security in Data-Driven Urban Mobility

A wide range of smart mobility technologies are being deployed within urban environment. These technologies generate huge quantities of data, much of them in real-time and at a highly granular scale. Such data about mobility, transport, and citizens can be put to many beneficial uses and, if shared, for uses beyond the system and purposes for which they were generated. Jointly, these data create the evidence base to run mobility services more efficiently, effectively, and sustainably. However, generating, processing, analyzing, sharing, and storing vast amounts of actionable data also raises several concerns and challenges. For example, data privacy, data protection, and data security issues arise from the creation of smart mobility. This chapter highlights the various privacy and security concerns and harms related to the deployment and use of smart mobility technologies and initiatives, and makes suggestions for addressing apprehensions about and harms arising from data privacy, protection, and security issues.

Exploring Multiple Dynamic Social Networks in Computer-Mediated Communications

This chapter discusses concepts and tools for the exploration and visualization of computer-mediated communication (CMC), especially communication involving multiple users and taking place asynchronously. The work presented here is based on experimentally validated social networks (SN) extraction methods and consists of a diverse number of techniques for conveying the data to a business analyst. The chapter explores a large number of contexts ranging from direct social network graphs to more complex geographical, hierarchical, and conversation-centric approaches. User validation studies were conducted for the most representative techniques, centered both on extracting and on conveying of CMC data. The chapter examines methods for automatically extracting social networks, which is determining who is communicating with whom across different CMC channels. Beyond the network, the chapter focuses on the end-user discovery of topics and on integrating those with geographical, hierarchical, and user data. User-centric, interactive visualizations are presented from a functional perspective.

Large Multivariate Time Series Forecasting

Research on the analysis of time series has gained momentum in recent years, as knowledge derived from time series analysis can improve the decision-making process for industrial and scientific fields. Furthermore, time series analysis is often an essential part of business intelligence systems. With the growing interest in this topic, a novel set of challenges emerges. Utilizing forecasting models that can handle a large number of predictors is a popular approach that can improve results compared to univariate models. However, issues arise for high dimensional data. Not all variables will have direct impact on the target variable and adding unrelated variables may make the forecasts less accurate. Thus, the authors explore methods that can effectively deal with time series with many predictors. The authors discuss state-of-the-art methods for optimizing the selection, dimension reduction, and shrinkage of predictors. While similar research exists, it exclusively targets small and medium datasets, and thus, the research aims to fill the knowledge gap in the context of big data applications.

Applications of Artificial Intelligence in the Realm of Business Intelligence

The objective of this chapter is to discuss the integration of advancements made in the field of artificial intelligence into the existing business intelligence tools. Specifically, it discusses how the business intelligence tool can integrate time series analysis, supervised and unsupervised machine learning techniques and natural language processing in it and unlock deeper insights, make predictions, and execute strategic business action from within the tool itself. This chapter also provides a high-level overview of current state of the art AI techniques and provides examples in the realm of business intelligence. The eventual goal of this chapter is to leave readers thinking about what the future of business intelligence would look like and how enterprise can benefit by integrating AI in it.

A Big Data Platform for Enhancing Life Imaging Activities

The field of life imaging spans a large spectrum of scientific study from mathematics and computer science to medical, passing by physics, biology, etc. The challenge of IDV project is to enrich a multi-parametrized, quantitative, qualitative, integrative, and correlative life imaging in health. It deals with linking the current research developments and applications of life imaging in medicine and biology to develop computational models and methods for imaging and quantitative image analysis and validate the added diagnostic and therapeutic value of new imaging methods and biomarkers.

C-Idea

Discovering trend reversals between two data cubes provides users with novel and interesting knowledge when the real-world context fluctuates: What is new? Which trends appear or emerge? With the concept of emerging cube, the authors capture such trend reversals by enforcing an emergence constraint. In a big data context, trend reversal predictions promote a just-in-time reaction to these strategic phenomena. In addition to prediction, a business intelligence approach aids to understand observed phenomena origins. In order to exhibit them, the proposal must be as fast as possible, without redundancy but with ideally an incremental computation. Moreover, the authors propose an algorithm called C-Idea to compute reduced and lossless representations of the emerging cube by using the concept of cube closure. This approach aims to improve efficiency and scalability while preserving integration capability. The C-Idea algorithm works à la Buc and takes the specific features of emerging cubes into account. The proposals are validated by various experiments for which we measure the size of representations.

A Survey of Parallel Indexing Techniques for Large-Scale Moving Object Databases

A moving object database is a database that tracks the movements of objects. As such, these databases have business intelligence applications in areas like trajectory-based advertising, disease control and prediction, hurricane path prediction, and drunk-driver detection. However, in order to extract knowledge from these objects, it is necessary to efficiently query these databases. To this end, databases incorporate special data structures called indexes. Multiple indexing techniques for moving object databases have been proposed. Nonetheless, indexing large sets of objects poses significant computational challenges. To cope with these challenges, some moving object indexes are designed to work with parallel architectures, such as multicore CPUs and GPUs (graphics processing units), which can execute multiple instructions simultaneously. This chapter discusses business intelligence applications of parallel moving object indexes, identifies issues and features of these techniques, surveys existing parallel indexes, and concludes with possible future research directions.