IoT Big Data Aggregation
US20140297826 illustrates a system for big data aggregation in a sensor network. The most important part of the Internet of Things (IoT) big data analytics is collecting data before storing the data. The Hadoop big data platform supports collecting data in Hadoop Distributed File System (HDFS). HDFS is an open source for storing big data dispersedly, that is, a technology for storing collected data reliably. The big data aggregation system includes a sensor network which comprises many sensor nodes connected to each other over a wired/wireless network and is configured to transfer sensor data generated by each of sensor nodes to a big data management unit by setting a destination address in the sensor data as an address of a big data management unit. The big data management unit configured to distribute and dispersedly store the sensor data based on the set destination address of the sensor data.
IoT Big Data Platform
The Hadoop big data platform is based on the MapReduce framework. US7650331 describes the MapReduce framework. US20110313973 illustrates the MapReduce framework including the shuffle function using the DFS. US20150012502 illustrates a big data central intelligence system for managing, analyzing, and maintaining large scale, connected information systems such as the IoT device networks.
IoT Big Data Real Time Processing
US20150134704 illustrates a system for processing large scale unstructured data in real time. The interconnected IoT sensing devices continuously generate massive information at a very high speed. Thus a technology for effectively processing a huge amount of information in the form of a data stream in real time is very important. The real time big data analysis system includes a receiver for receiving streamed input data from live data sources, a pattern generator for deriving emergent patterns in data subsets, a pattern identifier for identifying a repeating pattern and corresponding data subset within the emergent patterns, a compressor for reducing the identified data subset and identified pattern to a compressed signature and a repository for storing the streamed input data with the compressed signature and without the identified data subset in which the data subset can be rebuilt if necessary using the compressed signature.
IoT Big Data Cloud
US20130227569 illustrates the system that can gather data from thousands of the IoT sensors/devices and analyze the data in the cloud without the massive amount of investment in the server and big data analytics infrastructure. The cloud based IoT big data system provides a virtual IoT sensors/devices cloud as an Infrastructure as a Service (IaaS) and a service cloud as a Software as a Service (SaaS), to provide a flexible and scalable system. The IaaS provides flexibility by handling heterogeneous IoT sensors/devices. The SaaS provides scalability by relieving end users of computational overheads, and enabling on-demand sharing of IoT sensors/devices data to requesting end users. The SaaS also relieves end users from specifying IoT sensors/devices characteristics, locating physical IoT sensors/devices, and provisioning for the physical IoT sensors/devices. The end user, via a device (e.g., smartphone), requests and receives services provided by the system.
IoT Big Data Analytics
US20150179079 illustrates a system and for real time monitoring a patient’s cognitive and motor response to a stimulus. The big data analysis of massive data obtained by the IoT healthcare/medical devices can provide many value-added healthcare services. US20150186972 illustrate a big data analytics system for the business IoT applications. The business IoT devices can collects a large amount of data regarding products, product attributes, prices, and price attributes. To be understood by a person, this large amount of data and analytic output must be summarized, personalized, and organized in relevant terms. The summarization and personalization of such a large and complex set of data presents challenges in the selection and refinement of information as well as with respect to identification of patterns and arrangement of information in a user interface. The big data analytics system provides a user interface to summarize and personalize a large amount of price and product information, to identify patterns therein, and to generate recommendations in relation to the information.
Artificial Intelligence for IoT
Artificial Intelligence (AI) is essential to provide value added IoT services by finding the patterns, correlations and anomalies in user behaviors for autonomous context-aware actions of the IoT system surrounding the user. US20150039105 illustrates the smart home intelligence system to fulfill the special needs of each family member exploiting AI. US20140073486 illustrates a heart rate monitoring system by providing the best type of sensor to use at a given time determined by AI based on the level of motion (e.g., via an accelerometer) and whether the user is asleep (e.g., based on movement input, skin temperature and heart rate). US20140108307 illustrates the AI exploitation in the connected car applications. Base on the profile information and/or contextual information, AI system provides suggestions to the driver. US20140340236 illustrates the AI application for securing the distributed power distribution networks in the IoT smart grids.
IoT+ Big Data + Cloud + AI Integration
US20150227118 illustrates the IoT Cloud Big Data AI system for facilitating automatic control of the smart home devices based on past device behavior, current device events, sensor data, and server-sourced data. Cloud-based big data analytics is accessible via a server system for analyzing data associated with persons or buildings in a geographic region about the building, such as local news and weather information and data pertaining to appliances within the geographic region, such as a neighborhood, zip code, and so on. The analyzed data is used to develop the control rules to control smart home devices automatically.
The automatic control of the smart home devices enable various benefits, such as triggering lights to automatically turn on when a user enters a particular room at a particular time; activating a sprinkler system when server-side data indicates that a fire is nearby; automatically turning on a heater in advance of a home owner’s return at a particular time when the home temperature is below a predetermined level; turning off a sound system and lights in various rooms after data indicates that a user is preparing to sleep; turning off lower priority devices that may conflict with higher priority devices, and so on.
Cloud-based big data analytics also can be used to make a prediction about the future device usage and/or device behavior and/or user behavior exploiting AI. The device usage and/or device behavior and/or user behavior predictions can be used to generate control rules. The prediction can be derived by comparing collected data with a sample table of data to determine whether a correlation exists between the collected data and data in the sample table of data. The prediction can be generated based on a correlation between the collected data and data in the sample table of data. The prediction also can be based on a frequency of occurrence of an instance of data in the collected data (and timing information associated with occurrences of the instances of data) to generate a probability estimate. The probability estimate is employed to determine the prediction.
Weebit Nano is at the Epicenter of the ReRAM Revolution