This article examines machine learning analysis of gunshot recognition.
This paper investigates the efficiency of various machine learning models for gunshot recognition. The ability to recognize a gunshot has significance in reinforcing public safety, assisting in crime scene investigations, and preventing gun violence. The authors present a model to identify the type of pistol or rifle discharged by analyzing only an audio signal of the gunshot. Among the array of methods explored, AdaBoost performed the best achieving an accuracy of 99.9% and sustaining over 80% accuracy with 40 dB conditions. Additionally, the researchers experimented with the importance level of the features to identify the most relevant variables that boost the performance of the algorithms. (Published Abstract Provided)
Downloads
Similar Publications
- Observing Variation of Acoustical Characteristics of Several Common Firearms in a Quasi Anechoic Environment at a High Sampling Rate
- "I'm Not Gonna Let My Daughter Be Ashamed of Who Her Father Is": Assessing the Complex Relationship Between Fatherhood, Recovery, and Desistance
- Mock Jurors’ Evaluations of Eyewitness Identification Evidence Based on Appearance Change and Associated Instructions