Fiber-Optic Gunshot Classification for False-Alarm Reduction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing gunshot detection systems in public areas suffer from high installation costs, privacy concerns, and high rates of false alarms, particularly from fireworks and mechanical noises, which divert first responders from actual emergencies.

Innovation Solution

A distributed fiber optic sensing (DFOS) system integrated with machine learning and deep learning techniques processes acoustic data into a small set of features using Mel-frequency cepstral coefficients (MFCCs) and convolutional neural networks to accurately distinguish gunshots from other acoustic events while preserving privacy, reducing false alarms.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional gunshot detection systems are deployed in public areas, then gunshot detection capability is provided, but installation costs increase and privacy concerns arise

Engineering Contradiction:

Improvegunshot detection capabilityVSAvoidinstallation costs and system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies universality by utilizing existing optical fiber infrastructure for multiple purposes - both for communication and for gunshot detection. The distributed acoustic sensing system repurposes the optical fiber network already deployed in public areas, eliminating the need for separate detection infrastructure and reducing installation costs while maintaining detection capability

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent replaces traditional mechanical acoustic sensors (microphones) with optical sensing based on distributed acoustic sensing technology. This substitution uses optical properties of the fiber to detect acoustic events, providing more reliable gunshot detection while reducing privacy concerns since the system processes optical signals rather than recording audible sound

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If traditional acoustic detection systems are used, then gunshot detection is attempted, but false alarm rates increase due to fireworks and mechanical noises

Engineering Contradiction:

Improvegunshot detection accuracyVSAvoidfalse alarm rate

Core Design Contradiction:

ReliabilityVSObject-generated harmful factors

Solution Approach 1:

The patent changes the detection parameter from acoustic pressure (microphone-based) to optical properties of the fiber (DAS-based). By measuring strain and vibration along the optical fiber, the system captures different physical characteristics of gunshot events versus fireworks or mechanical noises, enabling more accurate classification and reducing false alarms

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent introduces an intermediary classification system that analyzes the characteristics of detected acoustic events. The system uses the optical fiber to detect events and then applies signal processing and pattern recognition to distinguish gunshots from other sources like fireworks or mechanical noises, acting as a mediator between raw detection data and final classification

Inventive Principle:

Principle #24Intermediary (Mediator)

3Loss of information

If comprehensive acoustic monitoring is implemented, then all acoustic events are captured, but privacy of individuals is compromised

Engineering Contradiction:

Improveacoustic event informationVSAvoidprivacy concerns

Core Design Contradiction:

Loss of informationVSObject-affected harmful factors

Solution Approach 1:

The patent extracts only the necessary information for gunshot detection from the acoustic environment. By using distributed acoustic sensing on optical fiber, the system detects vibration and strain patterns indicative of gunshots without capturing or storing recordable audio that would reveal private conversations or identifiable sounds, thus extracting detection capability while leaving privacy-preserving information out

Inventive Principle:

Principle #2Taking out (Extraction)

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

The system achieves high accuracy (>99%) in gunshot detection and localization with reduced false alarms, utilizing existing optical fibers and limited computing resources, enabling real-time monitoring and effective response to actual threats.

Implementation Method 1

Distributed fiber optic sensing (DFOS) technologies including Distributed Acoustic Sensing (DAS), Distributed Vibration Sensing (DVS), and Distributed Temperature Sensing (DTS) are known to be quite useful for sensing acoustic events, vibrational events, and temperatures

Methodology Applied

Scientific EffectDistributed Acoustic Sensing (DAS):

Implementation Method 2

Methodology Applied

Scientific EffectDistributed Vibration Sensing (DVS):

Implementation Method 3

Methodology Applied

Scientific EffectDistributed Temperature Sensing (DTS):

Data Source

PatentUS12460963B2Gunshot detection via classification using deep learning and fiber sensing technologies

Publication Date: 2025.11.04 NEC CORP

AI summary

A machine learning (ML)/artificial intelligence (AI) based distributed fiber optic sensing (DFOS) system and method providing detection and localization of gunshot events. In addition to the ML/AI DFOS, a signal processing pipeline that compresses an audible distributed acoustic sensing (DAS) waveform data into a small set of features that protects privacy of individuals while preserving the utility of acoustic events to detect the gunshot events and discriminate same from other events. A data-driven deep learning approach automatically predicts acoustic event types with higher accuracy that realized by prior art methods.