FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2065009246> ?p ?o ?g. }

• W2065009246 abstract "Gunshot recordings have the potential for both tactical detection and forensic evaluation particularly to ascertaininformation about the type of firearm and ammunition used. Perhaps the most significant challenge to such an analysis isthe effect of recording conditions on the audio signature of recorded data. In this paper we present a first study of usingan exemplar embedding approach to automatically detect and classify firearm type across different recording conditions.We demonstrate that a small number of exemplars can span the space of gunshot audio signatures and that this optimalset can be obtained using a wrapper function. By projecting a given gunshot to the subspace spanned by the exemplar seta distance measure/feature vector is obtained that enables comparisons across recording conditions. We also investigatethe use of a hierarchy of gunshot classifications that assists in improving finer level classification by pruning out gunshotlabeling that is inconsistent with its higher level type. The embedding based approach can thus be used both by itself andas a pruning stage for other search techniques.Our dataset includes 20 different gun types captured in a number of different conditions. This data acts as our originalexemplar set. The dataset also includes 12 gun types each with multiple shots recorded in the same conditions as theexemplar set. This second set provides our training and testing sets. We show that we can reduce our exemplar spacefrom 20 to only 4 uniquely different gunshots without significantly limiting the ability of our embedding approach todiscriminate different gunshots in the training and testing sets. The basic hypothesis in the embedding approach is thatthe relationship between the set of exemplars and space of gunshots including the testing/training set would be robust toa change in recording conditions or the environment. That is to say the embedding distance between a particular gunshotand the exemplars would tend to remain the same in changing environments. The implication of this are two-fold; first,unlike other dimensionality reduction approaches we have access to particular instances/examples of entities (theexemplars), which act as bridges to connect different recording conditions. Second, the embedding distances areinvariant across recording conditions, the embedded vector can be used as a feature of similarity between gunshotsrecorded in different conditions.Unlike other dimensionality reduction approaches , our approach generates descriptions that are always in terms of thesame exemplars. In other approaches such as PCA, the data driven nature makes it difficult if not impossible to makecorrespondence in the dimensions in one space to another.We have shown that gunshot classification across different recording conditions can be performed at a reasonable degreeof certainty (60-72%) at a finer level (gunshot to weapon model) and at a high degree of certainty (95-100%) at ahigher degree of abstraction (gunshot to `handgun' or `rifle'). We also investigate the use of simulated recordingconditions and artificial noise to quantitatively evaluate the performance of our approach." @default.
• W2065009246 created "2016-06-24" @default.
• W2065009246 creator A5028124265 @default.
• W2065009246 creator A5049445059 @default.
• W2065009246 creator A5091076182 @default.
• W2065009246 date "2010-04-23" @default.
• W2065009246 modified "2023-09-25" @default.
• W2065009246 title "Weapon identification across varying acoustic conditions using an exemplar embedding approach" @default.
• W2065009246 cites W1519226138 @default.
• W2065009246 cites W1619226191 @default.
• W2065009246 cites W2073889107 @default.
• W2065009246 cites W2118230268 @default.
• W2065009246 cites W2227972867 @default.
• W2065009246 cites W3021898884 @default.
• W2065009246 cites W1583167942 @default.
• W2065009246 doi "https://doi.org/10.1117/12.850185" @default.
• W2065009246 hasPublicationYear "2010" @default.
• W2065009246 type Work @default.
• W2065009246 sameAs 2065009246 @default.
• W2065009246 citedByCount "1" @default.
• W2065009246 countsByYear W20650092462022 @default.
• W2065009246 crossrefType "proceedings-article" @default.
• W2065009246 hasAuthorship W2065009246A5028124265 @default.
• W2065009246 hasAuthorship W2065009246A5049445059 @default.
• W2065009246 hasAuthorship W2065009246A5091076182 @default.
• W2065009246 hasConcept C108010975 @default.
• W2065009246 hasConcept C116834253 @default.
• W2065009246 hasConcept C124101348 @default.
• W2065009246 hasConcept C138885662 @default.
• W2065009246 hasConcept C153180895 @default.
• W2065009246 hasConcept C154945302 @default.
• W2065009246 hasConcept C177264268 @default.
• W2065009246 hasConcept C199360897 @default.
• W2065009246 hasConcept C2524010 @default.
• W2065009246 hasConcept C2776401178 @default.
• W2065009246 hasConcept C2779696439 @default.
• W2065009246 hasConcept C32834561 @default.
• W2065009246 hasConcept C33923547 @default.
• W2065009246 hasConcept C41008148 @default.
• W2065009246 hasConcept C41608201 @default.
• W2065009246 hasConcept C41895202 @default.
• W2065009246 hasConcept C59822182 @default.
• W2065009246 hasConcept C6557445 @default.
• W2065009246 hasConcept C86803240 @default.
• W2065009246 hasConceptScore W2065009246C108010975 @default.
• W2065009246 hasConceptScore W2065009246C116834253 @default.
• W2065009246 hasConceptScore W2065009246C124101348 @default.
• W2065009246 hasConceptScore W2065009246C138885662 @default.
• W2065009246 hasConceptScore W2065009246C153180895 @default.
• W2065009246 hasConceptScore W2065009246C154945302 @default.
• W2065009246 hasConceptScore W2065009246C177264268 @default.
• W2065009246 hasConceptScore W2065009246C199360897 @default.
• W2065009246 hasConceptScore W2065009246C2524010 @default.
• W2065009246 hasConceptScore W2065009246C2776401178 @default.
• W2065009246 hasConceptScore W2065009246C2779696439 @default.
• W2065009246 hasConceptScore W2065009246C32834561 @default.
• W2065009246 hasConceptScore W2065009246C33923547 @default.
• W2065009246 hasConceptScore W2065009246C41008148 @default.
• W2065009246 hasConceptScore W2065009246C41608201 @default.
• W2065009246 hasConceptScore W2065009246C41895202 @default.
• W2065009246 hasConceptScore W2065009246C59822182 @default.
• W2065009246 hasConceptScore W2065009246C6557445 @default.
• W2065009246 hasConceptScore W2065009246C86803240 @default.
• W2065009246 hasLocation W20650092461 @default.
• W2065009246 hasOpenAccess W2065009246 @default.
• W2065009246 hasPrimaryLocation W20650092461 @default.
• W2065009246 hasRelatedWork W1020007573 @default.
• W2065009246 hasRelatedWork W1167987884 @default.
• W2065009246 hasRelatedWork W1572150741 @default.
• W2065009246 hasRelatedWork W1603829220 @default.
• W2065009246 hasRelatedWork W1731063510 @default.
• W2065009246 hasRelatedWork W1856564138 @default.
• W2065009246 hasRelatedWork W1870026203 @default.
• W2065009246 hasRelatedWork W1965756682 @default.
• W2065009246 hasRelatedWork W2001974163 @default.
• W2065009246 hasRelatedWork W2012082634 @default.
• W2065009246 hasRelatedWork W2043625195 @default.
• W2065009246 hasRelatedWork W2053452625 @default.
• W2065009246 hasRelatedWork W2085254150 @default.
• W2065009246 hasRelatedWork W2124698274 @default.
• W2065009246 hasRelatedWork W2155700021 @default.
• W2065009246 hasRelatedWork W2157670092 @default.
• W2065009246 hasRelatedWork W2159498231 @default.
• W2065009246 hasRelatedWork W2194877621 @default.
• W2065009246 hasRelatedWork W2900056051 @default.
• W2065009246 hasRelatedWork W2171160689 @default.
• W2065009246 isParatext "false" @default.
• W2065009246 isRetracted "false" @default.
• W2065009246 magId "2065009246" @default.
• W2065009246 workType "article" @default.