Motion Classification for Continuous User Identity Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current security systems, including passwords and biometrics, fail to effectively validate a user's identity and are prone to compromise, as they do not account for unique movement patterns and habits, leading to security vulnerabilities.
Innovation Solution
A user identification system that utilizes motion data from various sources, such as accelerometers and gyroscopes, to generate a unique signature or identifier by analyzing specific movements and habits, employing machine-learning models to classify and verify user identities through a combination of sensors and edge devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If motion sensors and machine learning models are integrated for continuous user verification, then security reliability is improved, but device complexity increases
Solution Approach 1:
The system divides user verification into discrete motion segments that are individually analyzed. Motion data is segmented into discrete actions (e.g., walking, typing, gesturing) that can be independently classified and evaluated, allowing complex verification to be broken into manageable parts that reduce overall system complexity while maintaining high reliability
Solution Approach 2:
Machine learning models serve as intermediaries between raw motion sensor data and security verification decisions. These models process and interpret complex motion patterns, transforming raw sensor inputs into meaningful behavioral classifications that can be reliably used for authentication without requiring direct complex rule-based processing
2Measurement precision
If multiple motion sensors are used to capture comprehensive movement data, then measurement precision is improved, but device complexity increases
Solution Approach 1:
Multiple motion sensors (accelerometers, gyroscopes, magnetometers) are merged into a unified motion analysis system. The sensors work together to capture comprehensive three-dimensional motion data, combining their individual measurements into a cohesive set of motion vectors that provide precise spatial and temporal characterization of user movements without requiring separate processing systems for each sensor
Solution Approach 2:
The motion sensor system is designed to serve multiple functions simultaneously: authentication verification, behavioral analysis, and motion tracking. The same sensor array that captures fine-grained motion patterns for security verification also provides broader motion context, reducing the need for additional dedicated sensors and thereby managing complexity while maintaining measurement precision
Data Source
AI summary
A system and method are disclosed for identifying a user based on the classification of user movement data. An identity verification system receives a sequence of motion data characterizing movements performed by a target user. The sequence of motion data is received as a point cloud of the motion data. The point cloud is input a machine-learned model trained based on manually labeled point clusters of a training set of motion data that each represent a movement. The machine-learned model identifies a movement represented by the point cloud of the motion data and assigns a label describing the movement the point cloud. The system generates a labeled representation of the sequence of motion data comprising the label identifying a portion of the sequence of motion data corresponding to the identified movement.