Deep Learning for Spatio-Temporal Data Mining: A Survey

ABSTARCT :

With the fast development of various positioning techniques such as Global Position System (GPS), mobile devices and remote sensing, spatio -temporal data has become increasingly available nowadays.Mining valuable knowledge from spatio - temporal data is critically important to many real-world applications including human mobility understanding, smart transportation, urban planning, public safety, health care and environmental management. As the number, volume and resolution of spatio -temporal data increase rapidly, traditional data mining methods, especially statistics-based methods for dealing with such data are becoming overwhelmed. . Recently deep learning models such as recurrent neural network (RNN) and convolutional neural network (CNN) have achieved remarkable success in many domains due to the powerful ability in automatic feature representation learning, and are also widely applied in various spatio-temporal data mining (STDM) tasks such as predictive learning, anomaly detection and classification.In this paper, we provide a comprehensive review of recent progress in applying deep learning techniques for STDM.we conclude the limitations of current research and point out future research directions.

EXISTING SYSTEM :

? Large volumes of spatio-temporal data are increasingly collected and studied in diverse domains, including climate science, social sciences, neuroscience, epidemiology, transportation, mobile health, and Earth sciences. ? Spatio-temporal data differ from relational data for which computational approaches are developed in the data-mining community for multiple decades in that both spatial and temporal attributes are available in addition to the actual measurements/attributes. ? Approaches for mining spatio-temporal data have been studied for over a decade in the data-mining community.

DISADVANTAGE :

? It can highlight the similarities, differences and general frameworks of adopting deep learning models for addressing STDM problems. ? This enables the cross-pollination of methodologies and ideas across the research problems of different application domains. ? The problems that are addressed by traditional methods and deep learning methods in the two surveys are different. ? Except for some general problems like predictive learning and anomaly detection,

PROPOSED SYSTEM :

? We present a broad survey of this relatively young field of spatio-temporal data mining. ? We discuss different types of spatio-temporal data and the relevant data-mining questions that arise in the context of analyzing each of these datasets. ? Based on the nature of the data-mining problem studied, we classify literature on spatio-temporal data mining into six major categories: clustering, predictive learning, change detection, frequent pattern mining, anomaly detection, and relationship mining. We discuss the various forms of spatio-temporal data-mining problems in each of these categories.

ADVANTAGE :

? The deep leaning models such as recurrent neural network (RNN) and convolutional neural network(CNN) have achieved remarkable performance gains in various machine learning tasks due to the powerful ability in automatic feature representation learning. ? The trade-off between efficiency and effectiveness needs to be carefully considered in deep learning model selection and design in a real application scenario. ? In light of the rising number of related studies in recent years, we first categorize the ST data types, and then present the popular deeplearning models that are widely used in STDM