Browse Prior Art Database

Personal Safety Management Application Based on Environment Cognition

IP.com Disclosure Number: IPCOM000247898D
Publication Date: 2016-Oct-10
Document File: 3 page(s) / 55K

Publishing Venue

The IP.com Prior Art Database

Abstract

Disclosed is a personal safety management application (app) based on environment cognition. The purpose is to alert a user that is focused on a mobile device (i.e., looking at the screen) and is not paying attention to surroundings in an unsafe or complex environment.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 51% of the total text.

Page 01 of 3

Personal Safety Management Application Based on Environment Cognition

Users often become fixated on a mobile device and do not pay attention to the surroundings while in motion (e.g., walking

down the street). This behavior is a potential safety hazard to both the device holders and the public.

The novel contribution is a personal safety management application (app) based on environment cognition. The purpose is to alert a user that is focused on a mobile device (i.e., looking at the screen) and is not paying attention to surroundings in an unsafe or complex environment. This application can remind the user of potential harmful events, thus making life safer.

This application is aware of the environmental risk factors when activated with other commonly used mobile apps. The environment scene is one of (but is not limited to) the following: indoor, walking in street, getting off a bus or subway, wild, on a vehicle, etc. When the app recognizes the scene, it calculates a risk score (based on the scene) and activates the mobile app. A risk score exceeding a predefined threshold triggers an alert, reminding the user to be mindful of the surroundings.

This application is composed of three modules: 1) environment cognition, 2) alerting level management, 3) captivity management.

Environment Cognition

This module is the most important part of this application. It is responsible for the cognition and recognition of different environment scenes. An environment scene is defined as a location together with a particular action of the user. For example, the "indoor" scene is defined when the user is inside the room and is not vigorously exercising. The sound sensor and acceleration sensor of the mobile device can be used to collect required information of the scene, such as sound clips and motion patterns. The parameters from the sound clips and motion patterns, such as the distribution of the frequency and the strength of the vibration, are extracted for the cognition of the scene. Some predefined scenes are given in Table1. The user can update the parameters of the predefined scenes with new input or define new scenes. Each scene is tagged with a risk level. The recognition of a scene is accomplished by the real time input from sound sensor and acceleration sensor. The application extracts the same set of parameters and compares those with the existing one to find out the best match of a particular scene, thus a scene is recognized. The methods of comparison may be (but are not limited to) the maximum likelihood method, the least squares method, neutral network, or support vector machine. The system also uses position information from a Global Positioning System (GPS) and map data to better determine a sc...