Challenges and Methods for Data-Intensive Applications
Description
At present, data-intensive applications are one of the most prominent lines of work in data science. Most of these projects occur in the context of sensor data analytics, in which different devices, equipment, and software applications provide dynamic datasets to be processed and analyzed with machine learning algorithms. Application domains span multiple areas, including smart cities and intelligent transport, economy and finance, energy management, biomedical applications, geographical systems, agriculture, and livestock or cybersecurity.
This volume is centered on emerging challenges, methods, algorithms, and tools that address sensor data analytics, with a special emphasis on approaches that leverage information theory to accomplish projected goals. It includes practical applications following interdisciplinary approaches using real-world data. Articles are focused on new methods applied to a wide range of applications, from electricity markets to healthcare, among others. Practical cases with real or simulated data demonstrate the usefulness of these methods. Outcomes stemming from these works constitute essential inputs for data-driven decision making.
