Motion Sensor User Recognition via Feature Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile device authentication methods, such as PINs, fingerprints, and continuous authentication using motion sensors, face challenges with accuracy, flexibility, and vulnerability to guessing, spoofing, and presentation attacks, requiring improved security and accuracy in user recognition.
Innovation Solution
A system and method for user recognition using motion sensor data from mobile devices, which involves collecting motion signals, extracting features using various algorithms like statistical analysis, Mel Frequency Cepstral Coefficients, and deep embeddings with Convolutional Neural Networks, selecting discriminative features, and classifying users using a stacked generalization technique with classifiers like Naïve Bayes and Support Vector Machines.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional authentication methods (PINs, fingerprints) are used, then implementation simplicity is maintained, but security accuracy deteriorates and is vulnerable to guessing and spoofing attacks
Solution Approach 1:
The patent replaces conventional mechanical/biometric authentication systems (fingerprints, PINs) with a motion sensor-based authentication system that uses accelerometers and gyroscopes to detect user interaction patterns. This substitution enables continuous authentication through behavioral biometric signals without requiring explicit user interaction, thereby improving security accuracy while reducing the need for complex dedicated hardware
Solution Approach 2:
The patent makes the motion sensor system universal by using existing sensors already present in mobile devices for authentication purposes. The same accelerometers and gyroscopes used for motion tracking are now employed for continuous user verification, eliminating the need for separate authentication hardware and reducing overall system complexity
2Adaptability or versatility
If explicit user interaction is required for authentication, then implementation simplicity is maintained, but flexibility deteriorates and cannot prevent post-login access by adversaries
Solution Approach 1:
The authentication system performs self-service by continuously monitoring user behavior patterns through motion sensors without requiring explicit user action. The system automatically verifies user identity based on detected interaction patterns, enabling continuous authentication that adapts to user behavior while maintaining ease of operation
Solution Approach 2:
The patent implements continuous authentication by maintaining ongoing verification of user identity through motion sensor data collection during device usage. This continuous action replaces one-time authentication, providing constant security verification without interrupting user interaction or requiring additional explicit user input
3Adaptability or versatility
If motion sensor data is collected for continuous authentication, then authentication flexibility is improved, but measurement precision deteriorates due to lower accuracy rates compared to conventional methods
Solution Approach 1:
The patent segments the authentication process into multiple independent modules: motion signal collection, feature extraction, feature selection, and classification. This segmentation allows each component to be optimized independently, improving overall measurement precision by refining how motion data is processed and analyzed for user recognition
Solution Approach 2:
The patent changes the parameters of motion signal processing by applying multiple feature extraction algorithms (statistical features, MFCC, HOG, Markov transition matrix) and using ensemble classification methods. These parameter transformations enhance the discriminative power of motion data, improving accuracy rates while maintaining continuous authentication flexibility
Data Source
AI summary
Technologies are presented herein in support of system and methods for user recognition using motion sensor data. Embodiments of the present invention concern a system and method for capturing motion sensor data using motion sensors of a mobile device and characterizing the motion sensor data into features for user recognition. The motion sensor data of a user is collected by the motion sensors of a mobile device in the form of a motion signal. One or more sets of features are extracted from the motion signal and a subset of discriminative features are then selected. The subset of features is analyzed, and a classification score is generated to classify the user as a genuine user or an imposter user.