Footfall Seismic Identification for Imposter Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing biometric systems struggle to accurately identify individuals whose data are not present in the database and require direct line of sight or physical contact, and are resource-intensive due to processing entire seismic signals.

Innovation Solution

A biometric system using unsupervised learning-based event detection and extraction (USLEEM) to identify individuals and detect imposters through footfall-generated seismic signals, employing smart devices with sensing modules, analog-to-digital converters, and identification modules to segment and cluster seismic signals for feature extraction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If existing biometric systems use footfall-generated seismic signals for identification, then person identification capability is provided, but accuracy is insufficient when individuals have no prior data in the database

Engineering Contradiction:

Improveidentification accuracyVSAvoidability to detect imposters without prior data

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The seismic signal is divided into multiple segments or windows, and features are extracted from each segment. This segmentation allows the system to analyze different portions of the footfall signal independently, improving the ability to detect imposters even with limited prior data by focusing on distinctive local characteristics.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Instead of trying to match test data against stored templates (traditional approach), the system inverts the approach by learning the characteristics of registered users and then detecting deviations from these learned patterns. This inversion enables effective imposter detection without requiring complete prior knowledge of all possible imposters.

Inventive Principle:

Principle #13The other way round (Inversion)

2Reliability

If existing systems require multiple consecutive footsteps for identification, then reliability is improved, but processing time and resource consumption increase

Engineering Contradiction:

Improveidentification reliabilityVSAvoidprocessing time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system replaces traditional mechanical signal processing methods with machine learning-based feature extraction and classification. This substitution enables more efficient processing of footfall signals, achieving reliable identification with fewer footsteps by leveraging intelligent pattern recognition rather than conventional threshold-based methods.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system changes the parameters used for signal analysis by extracting multiple types of features (time-domain, frequency-domain, and time-frequency domain features) and using sophisticated classification algorithms. This parameter transformation allows the system to achieve high reliability with reduced data requirements compared to traditional single-parameter methods.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If high sensor density is used to improve detection accuracy, then measurement precision is improved, but device complexity and infrastructure needs increase

Engineering Contradiction:

Improvedetection accuracyVSAvoidsensor density requirements

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system transitions from spatial dimension analysis (relying on multiple sensors) to temporal and frequency dimension analysis (using sophisticated signal processing on data from fewer sensors). By analyzing signals in the time-frequency domain and extracting multiple feature types, the system achieves high detection accuracy without requiring high sensor density, thus reducing device complexity.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The system introduces feature extraction and machine learning classification as intermediary processing steps between the raw seismic signal and the final identification result. This intermediary layer enables the system to derive rich information from limited sensor inputs, achieving high accuracy without increasing sensor density or infrastructure complexity.

Inventive Principle:

Principle #24Intermediary (Mediator)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Achieves high accuracy in identifying registered users and detecting imposters with reduced computational resources by effectively extracting footfall events from seismic signals, suitable for applications where prior information on imposters is unavailable.

Implementation Method 1

seismic signals generated due to the vibration of the floor as an individual's heel and toe touches the ground

Methodology Applied

Scientific EffectSeismic signal generation through footfall-induced vibration: Vibration

Data Source

PatentUS12618991B2Person identification and imposter detection using footfall generated seismic signals

Publication Date: 2026.05.05 INDIAN INSTITUTE OF TECHNOLOGY

AI summary

A smart device, biometric authentication system and a corresponding method thereof for person identification and imposter detection has been disclosed. The method comprises detection and extraction of seismic signals generated from corresponding footfalls, by means of unsupervised learning based detection and extraction module (USLEEM) and detection and identification of imposter and/or registered users respectively by means of an identification module.