EAS System Neural Network Reducing False Alarms via Dynamic Criteria

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing electronic article surveillance (EAS) systems experience false alarms due to improperly deactivated tags and other non-tag objects, leading to unnecessary alerts and disruptions.

Innovation Solution

The system adjusts its alarm trigger sensitivity by modifying detection criteria, including frequency and energy level thresholds, to differentiate between valid and improperly deactivated tags, reducing the range of valid alarm trigger frequencies and minimizing false alarms.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the alarm trigger sensitivity is increased to detect all valid tags, then the detection capability is improved, but false alarms increase due to improperly deactivated tags and non-tag objects

Engineering Contradiction:
Improvedetection capabilityVSAvoidfalse alarms
Core Design Contradiction:
ReliabilityVSObject-generated harmful factors

Solution Approach 1:

The detection process is segmented into multiple independent criteria: frequency threshold evaluation, energy level ratio evaluation, and alarm trigger evaluation. Each criterion processes a specific aspect of the tag signal independently, allowing the system to filter out false alarms by requiring all criteria to be satisfied simultaneously rather than relying on a single sensitive detector

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system dynamically adjusts detection parameters including frequency thresholds and energy level ratios based on the specific characteristics of detected tags. By changing these parameters adaptively, the system maintains high detection sensitivity for valid tags while automatically raising the threshold for detecting improperly deactivated tags and non-tag objects

Inventive Principle:
Principle #35Parameter changes

2Adaptability or versatility

If the frequency range for valid alarm triggers is wide to accommodate variations, then more valid tags are detected, but improperly deactivated tags also trigger false alarms

Engineering Contradiction:
Improvefrequency toleranceVSAvoidtag deactivation detection
Core Design Contradiction:
Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The system transitions from single-dimension frequency detection to two-dimensional detection by introducing energy level ratio as an additional evaluation dimension. A tag must satisfy both frequency criteria and energy level ratio criteria to trigger an alarm, creating a more precise detection boundary that accommodates frequency variations while excluding improperly deactivated tags

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The frequency threshold and energy level ratio are not fixed values but dynamic parameters that adjust based on the detected tag characteristics. This dynamic adjustment allows the system to adapt to different valid tag frequency variations while maintaining precise discrimination against false alarms

Inventive Principle:
Principle #15Dynamics

3Measurement precision

If the energy level threshold is lowered to detect weak tag signals, then detection sensitivity is improved, but noise and ambient signals cause false alarms

Engineering Contradiction:
Improvesignal detection sensitivityVSAvoidnoise interference
Core Design Contradiction:
Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The energy level ratio serves as an intermediary evaluation criterion between the raw signal detection and the final alarm trigger. Rather than directly using absolute energy levels which are susceptible to noise, the system evaluates the ratio of energy levels at different frequencies, which cancels out common noise components and provides a more reliable detection metric

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

This approach effectively reduces false alarms and failures to deactivate by accurately distinguishing between active and inactive tags, enhancing the reliability of EAS systems in high-traffic areas.

Implementation Method 1

The transmitter produces a predetermined excitation signal in a tag detection zone

Methodology Applied
Scientific EffectElectromagnetic radiation: Electromagnetic Induction

Implementation Method 2

When activated, AM tags resonate and transmit a signal at a resonant frequency when stimulated by an interrogation signal at a particular frequency

Methodology Applied
Scientific EffectResonance: Resonance

Data Source

PatentEP2243124B1Electronic article surveillance system neural network minimizing false alarms and failures to deactivate
Publication Date: 2014.03.05 TYCO FIRE & SECURITY GMBH
  • EP2243124B1 patent drawingFigure 1
  • EP2243124B1 patent drawingFigure 2
  • EP2243124B1 patent drawingFigure 3

AI summary

A method, system and computer program product for managing false alarms in a security system. A detection zone is established. An alarm event is triggered based on the detection of a tag in the detection zone using an initial alarm trigger sensitivity. The initial alarm trigger sensitivity is based on an initial set of one or more detection criteria. The set of detection criteria is modified to adjust the alarm trigger sensitivity of the security system.