Anomaly Detection and Complex Event Processing Over IoT Data Streams

Anomaly Detection and Complex Event Processing over IoT Data Streams: With Application to Electrocardiogram (ECG) Patient Data Monitoring presents the advanced processing techniques for IoT data streams, with a case study in the field of eHealth, namely, a classification scenario over an Electrocardiogram (ECG) stream. Bio-metric signals, such as the massive amount of raw ECG signals from the sensors are processed dynamically across the data pipeline and classified with modern machine learning approaches based on the Hierarchical Temporal Memory (HTM) and Convolutional Neural Network (CNN) algorithms. Discusses adaptive solutions that can be extended to other use cases to enable a complex analysis of patient data in a historical, predictive, and even prescriptive application scenario will be discussed. The book brings new advances and generalized techniques for processing an IoT data streams, semantic data enrichment with contextual information at Edge, Fog, and Cloud as well as complex event processing in IoT applications from health domain. Provides the state-of-the-art in IoT Data Stream Processing, Semantic Data Enrichment, Reasoning and KnowledgeExtraction (Anomaly Detection)Illustrates new scalable and reliable processing techniques based on IoT stream technologiesOffers application to new real-time anomaly detection scenarios in the health domain. · Development of data-driven reasoning software systems in eHealth