This book provides a comprehensive overview of the research on anomaly detection with respect to context and situational awareness that aim to get a better understanding of how context information influences anomaly detection. In each chapter, it identifies advanced anomaly detection and key assumptions, which are used by the model to differentiate between normal and anomalous behavior. When applying a given model to a particular application, the assumptions can be used as guidelines to assess the effectiveness of the model in that domain. Each chapter provides an advanced deep content understanding and anomaly detection algorithm, and then shows how the proposed approach is deviating of the basic techniques. Further, for each chapter, it describes the advantages and disadvantages of the algorithm. The final chapters provide a discussion on the computational complexity of the models and graph computational frameworks such as Google Tensorflow and H2O because it is an important issue in real application domains. This book provides a better understanding of the different directions in which research has been done on deep semantic analysis and situational assessment using deep learning for anomalous detection, and how methods developed in one area can be applied in applications in other domains. This book seeks to provide both cyber analytics practitioners and researchers an up-to-date and advanced knowledge in cloud based frameworks for deep semantic analysis and advanced anomaly detection using cognitive and artificial intelligence (AI) models.
Table of Contents
1 Large-Scale Video Event Detection Using Deep Neural Networks 2 Leveraging Selectional Preferences for Anomaly Detection in Newswire Events 3 Abnormal Event Recognition in Crowd Environments 4 Cognitive Sensing: Adaptive Anomalies Detection with Deep Networks 5 Language-Guided Visual Recognition 6 Deep Learning for Font Recognition and Retrieval 7 A Distributed Secure Machine-Learning Cloud Architecture for Semantic Analysis 8 A Practical Look at Anomaly Detection Using Autoencoders with H2O and the R Programming Language
Dr. Mehdi Roopaei has strong background on dynamic systems and control with experience in advance cloud machine learning. He is a Research Assistant Professor in Open Cloud Institute at University of Texas at San Antonio. He has several peer publications with more than 850 citations and serves as program committee member in many conferences. He is the pioneer in feedback image processing and deep learning control.
Paul Rad, Ph.D. is the co-founder and assistant director of Open Cloud Institute (OCI), at the University of Texas at San Antonio (UTSA). Dr. Rad’s research interests relate to data analytics, deep learning, cybersecurity, and cloud computing with applications to spam and malware threat detection and analysis, network intrusion detection and prevention, machine vision and sensing, Internet of Things and Machine to Machine de-centralized decision making and security. He holds 11 US patents on cyber infrastructure, virtualization, cloud computing and big data analytics. Dr. Rad has advised over 200 companies on cyber infrastructure and cloud computing with over 70 industry and academic keynote presentations and peer-reviewed publications that have been cited over 300 times.