University of South Florida

Miguel A Labrador

Philip L Winters

Rafael Perez

Sean J Barbeau

Nevine Georggi

Alfredo Perez

Sudeep Sarkar

Ravichandran Subramanian

Edgar A Banguero

Narin Persad

Dmytro Bilov

Sasha Dos Santos

Sasha dos-Santos

Sivakumar Bakthavachalu

Kevin Kerrigan

Venkatesh Ramarathinam

Aspects of gait matching are described herein. In one embodiment, a method of gait matching includes identifying a gait cycle timing in a data sequence captured by an inertial sensor, splitting the data sequence into a gait cycle segment, resampling the gait cycle segment, and estimating a rotation matrix for the resampled gait cycle segment. The rotation matrix, in one embodiment, can be estimated by minimizing a root mean squared deviation between the resampled gait cycle segment and a reference gait cycle segment. The method further includes calculating an aligned gait cycle segment from the resampled gait cycle segment using the rotation matrix, and generating a similarity measure between the aligned gait cycle segment and the reference gait cycle segment.

Orientation invariant gait matching

Accuracy of data collected from comprehensive travel surveys is a key to studying and analyzing human travel behavior. Better understanding of travel behavior enhances the ability of transportation professionals to utilize resources available in designing appropriate solutions to existing problems. In the past, this data has been obtained through paper or phone-based surveys of individuals and households. These surveys are subject to problems, including inaccurate data due to user error, apathy, and intentional or unintentional omissions, and must often be limited to one or two days due to the amount of effort required from the participant. The present invention describes a system and method that improves both quality and quantity of data gathered on individual travel behavior across multiple modes of transportation, including non-motorized travel, and submits the data from any location. By combining Personal Digital Assistants (PDAs) and Global Positioning System (GPS) devices the proposed system automates the collection of much of the data needed to measure individual travel behavior.

System and method for transportation demand management

Aspects of gait matching are described herein. In one embodiment, a method of gait matching includes identifying a gait cycle timing in a data sequence captured by an inertial sensor, splitting the data sequence into a gait cycle segment, resampling the gait cycle segment, and estimating a rotation matrix for the resampled gait cycle segment. The rotation matrix, in one embodiment, can be estimated by minimizing a root mean squared deviation between the resampled gait cycle segment and a reference gait cycle segment using the Kabsch algorithm, for example. The method further includes calculating an aligned gait cycle segment from the resampled gait cycle segment using the rotation matrix, and generating a similarity measure between the aligned gait cycle segment and the reference gait cycle segment. The Kabsch algorithm can be used to minimize error and reduce identity authentication errors.

Provided is a distributed and decentralized location-aware system. The system includes a number of peers, each in communication with other peers and adapted to communicate PING, PONG, and ALERT messages. Each of the messages has a header that includes location information. Also provided is a method of communication between two peers in the system. In addition, the present invention includes a method of rendering the system. In the method, a communication link between an electronic map and a number of peers is provided. The location information and the covering distance of each of the peers is obtained and used to plot the location and render the covering distance of each peer on the electric map. A communication link between an electronic control device and the electronic map is also provided.

System and method for rendering a distributed location-aware system

Disclosed is an automated trip-purpose detection method that utilizes GPS Data collected by GPS-enabled devices. The GPS data is compared against a GIS map to obtain various spatial and location characteristics of the surrounding area. This information is then used to derive a traveler's trip purpose. In a preferred embodiment, the inventive method is implemented automatically without any needed manipulation of GIS data. Additionally, the method integrates location information as defined by the user for critical locations such as home and work. These personalized locations allow the method to immediately identify the two most common types of trips: work-related trips and trips returning home.

System and method for automatically determining purpose information for travel behavior

Distributed and decentralized location aware architecture

This present invention is a spatial data processing system and method that allows the automatic, rapid, scalable analysis and transformation of large amounts of travel behavior data (e.g., tracking data points) into individual 'points-of-interest' and discrete trips stored in a spatial database. Each trip has a point-of-interest as a starting and ending location, and contains multiple positions (e.g. latitude and longitudes) which define the travel path of the user/device during that time period.

System and method for spatial point-of-interest generation and automated trip segmentation using location data

A prediction method that estimates the real-time position of a mobile device based on previously observed data is provided. The present invention can be used in real-time navigation, including providing real-time alerts of an upcoming destination and notifications of emergency events in close geographic proximity. The prediction method utilizes neural networks and/or functions generated using genetic algorithms in estimating the mobile device's real-time position. The prediction method provides reliable Location-Based Services (LBS) in events where traditional positioning technologies become unreliable. It is also seamless, as the user remains unaware of any interruption in accessing the positioning technology.

System for pattern recognition in real-time location-based services applications

A two-layer communication protocol that supports efficient real-time location-aware application on multiple mobile devices that must communicate with each other and/or a centralized server. The two-layer protocol includes a method of communicating data between a first mobile device and a second mobile device using a server to facilitate the communication of the data. The two-layer communication protocol also includes a method of communicating data between a first mobile device and a second mobile device using a server to facilitate the connection between the two devices. The communication of data occurs directly between the two mobile devices. Each method uses reliable, connection-oriented protocols to exchange application-level information and control signals while utilizing unreliable, connection-less protocols to communicate real-time location data. Also provided are architectures implementing these methods.

Architecture and two-layered protocol for real-time location-aware applications

A method of buffering location data on a mobile device. The method transmits location data packets via an unreliable protocol to a receiving device and buffers a copy of the location data packet. Periodically, the method also transmits a location data packet via a reliable protocol to the receiving device. When no acknowledgement is received from the receiving device, the location data sent via the reliable protocol is buffered to memory. Once an acknowledgement is received from the receiving device, all of the buffered location data is sent to the receiving device via an unreliable protocol.

Adaptive location data buffering for location-aware applications

Using pattern recognition in real-time LBS applications

A path prediction method that uses a commuter's travel patterns to predict their route and destination, and transmit road advisories via a GPS-enabled device. Once the user's location data is transmitted via a GPS-enabled device it is then catalogued and stored in a GIS database. The user's current travel path is then compared to their path history and statistics and a destination is determined based on related spatial and time properties. A warning is then automatically delivered to the user if there is an accident along their predicted path, without requiring any request or input form the user.

System and method for real-time travel path prediction and automatic incident alerts

Provided is a critical point method used to determine the points of a real-time stream of location data, such as Global Positioning System (GPS) data, that should be retained based on their importance in reconstructing the travel path of a mobile device. The method may run on a mobile device or on a server. When run on a mobile device, the method reduces the amount of data transferred between mediums by only transferring points that are critical to reconstructing the path of travel of the mobile device. This reduction saves power used in the wireless transmission and reception of the non-critical data and the bandwidth used while transmitting non-critical data. The method may be run every time a new position is calculated. When a new position is determined to be a critical point, the point is transmitted. If the new position is not a critical point, then the point is discarded.

Method for determining critical points in location data generated by location-based applications

Provided is a detection method used to alert a rider of a transit system that his or her upcoming destination location is approaching. The method detects upcoming transit stops and alerts the transit rider to prepare to depart the transit vehicle. Another alert to request a stop at the appropriate time may also be given. The detection method detects a destination location when the transit vehicle is not going to stop and service the second-to-last, or triggering, stop and when the transit vehicle stops at the triggering location and then resumes travel towards the destination location. The detection method establishes a triggering location, two regions about the triggering location, a destination location, a destination region about the destination location, and a current location and speed from available location data. The method then triggers alerts based on the current speed and the current location's position within or without the established regions.

Method of providing a destination alert to a transit system rider

Provided is an emergency locator system adapted for GPS-enabled wireless devices. Global Positioning System (GPS) technology is and Location Based Services (LBS) are used to determine the exact location of a user and communicate information relating to the emergency status of that location. The user initiates the locator application via a wireless device and their physical location information is automatically transferred to a server. The server then compares the user's location with Geographic Information System (GIS) maps to identify the emergency status associated with their location. Once the server has calculated the current emergency status, the information is automatically returned to the user, along with emergency instructions.

Growing community of inventors

Tampa, FL, United States of America

Miguel A Labrador