Researchers are developing a system that helps smart devices find their locations
https://newsstechh.blogspot.com/2019/10/researchers-are-developing-system-that.html
Researchers are developing a system that helps smart devices find their locations
A new system developed by researchers at MIT and elsewhere helps smart device networks find their location in environments where GPS is usually down
Today, the “Internet of Things” concept is somewhat known: billions of interconnected sensors around the world - embedded in everyday objects, equipment, vehicles, or worn by humans or animals - collect and share data for a range of applications.
An emerging concept known as “localization of things” enables these devices to sense their location and communicate with them. This concept can be useful in supply chain control, independent navigation, high-link smart cities, and even the formation of a real-time 'live map' of the world. Experts predict that the localization market will grow to $ 128 billion by 2027.
The concept depends on precise translation techniques. Traditional methods make use of GPS satellites or wireless signals shared by devices to determine their relative distances and positions from each other. But there is an obstacle: accuracy in places with reflective surfaces, obstructions or interfering signals, such as indoor buildings, underground tunnels, or "city valleys" where high-rise buildings surround both sides of the street, suffers greatly.
Researchers from the Massachusetts Institute of Technology, the University of Ferrara, the Basque Center for Applied Mathematics (BCAM), and the University of Southern California have developed a system that captures location information even in these noisy areas that deny GPS.
When devices in a network, called “nodes”, communicate wirelessly in a signal-blocking or “harsh” environment, the system integrates different types of spot information from the evasive radio signals exchanged between nodes as well as digital maps. In doing so, each node takes into account the information associated with all possible locations - called "easy information" - regarding that property to all other nodes.
The system takes advantage of machine learning techniques and techniques that minimize the dimensions of processed data to identify potential placements from measurements and contextual data. Using this information, it locates the node.
Researchers are now designing ways to use less computational power to work with resource-poor nodes that cannot transfer or calculate all the necessary information. Researchers will use information about how signals are scattered about these nodes, so that other nodes know their existence and location.
A new system developed by researchers at MIT and elsewhere helps smart device networks find their location in environments where GPS is usually down
Today, the “Internet of Things” concept is somewhat known: billions of interconnected sensors around the world - embedded in everyday objects, equipment, vehicles, or worn by humans or animals - collect and share data for a range of applications.
An emerging concept known as “localization of things” enables these devices to sense their location and communicate with them. This concept can be useful in supply chain control, independent navigation, high-link smart cities, and even the formation of a real-time 'live map' of the world. Experts predict that the localization market will grow to $ 128 billion by 2027.
The concept depends on precise translation techniques. Traditional methods make use of GPS satellites or wireless signals shared by devices to determine their relative distances and positions from each other. But there is an obstacle: accuracy in places with reflective surfaces, obstructions or interfering signals, such as indoor buildings, underground tunnels, or "city valleys" where high-rise buildings surround both sides of the street, suffers greatly.
Researchers from the Massachusetts Institute of Technology, the University of Ferrara, the Basque Center for Applied Mathematics (BCAM), and the University of Southern California have developed a system that captures location information even in these noisy areas that deny GPS.
When devices in a network, called “nodes”, communicate wirelessly in a signal-blocking or “harsh” environment, the system integrates different types of spot information from the evasive radio signals exchanged between nodes as well as digital maps. In doing so, each node takes into account the information associated with all possible locations - called "easy information" - regarding that property to all other nodes.
The system takes advantage of machine learning techniques and techniques that minimize the dimensions of processed data to identify potential placements from measurements and contextual data. Using this information, it locates the node.
Researchers are now designing ways to use less computational power to work with resource-poor nodes that cannot transfer or calculate all the necessary information. Researchers will use information about how signals are scattered about these nodes, so that other nodes know their existence and location.
