FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384938310> ?p ?o ?g. }

• W4384938310 abstract "Machine learning (ML) is well suited for the prediction of high-complexity, high-dimensional problems such as those encountered in terminal ballistics. We evaluate the performance of four popular ML-based regression models, extreme gradient boosting (XGBoost), artificial neural network (ANN), support vector regression (SVR), and Gaussian process regression (GP), on two common terminal ballistics’ problems: (a) predicting the V50 ballistic limit of monolithic metallic armour impacted by small and medium calibre projectiles and fragments, and (b) predicting the depth to which a projectile will penetrate a target of semi-infinite thickness. To achieve this we utilise two datasets, each consisting of approximately 1000 samples, collated from public release sources. We demonstrate that all four model types provide similarly excellent agreement when interpolating within the training data and diverge when extrapolating outside this range. Although extrapolation is not advisable for ML-based regression models, for applications such as lethality/survivability analysis, such capability is required. To circumvent this, we implement expert knowledge and physics-based models via enforced monotonicity, as a Gaussian prior mean, and through a modified loss function. The physics-informed models demonstrate improved performance over both classical physics-based models and the basic ML regression models, providing an ability to accurately fit experimental data when it is available and then revert to the physics-based model when not. The resulting models demonstrate high levels of predictive accuracy over a very wide range of projectile types, target materials and thicknesses, and impact conditions significantly more diverse than that achievable from any existing analytical approach. Compared with numerical analysis tools such as finite element solvers the ML models run orders of magnitude faster. We provide some general guidelines throughout for the development, application, and reporting of ML models in terminal ballistics problems." @default.
• W4384938310 created "2023-07-22" @default.
• W4384938310 creator A5008034514 @default.
• W4384938310 creator A5024215125 @default.
• W4384938310 creator A5027946728 @default.
• W4384938310 creator A5040916912 @default.
• W4384938310 creator A5045540854 @default.
• W4384938310 creator A5074891964 @default.
• W4384938310 creator A5078701018 @default.
• W4384938310 date "2023-07-01" @default.
• W4384938310 modified "2023-09-27" @default.
• W4384938310 title "Machine learning for predicting the outcome of terminal ballistics events" @default.
• W4384938310 cites W1845526003 @default.
• W4384938310 cites W1966369198 @default.
• W4384938310 cites W1988760359 @default.
• W4384938310 cites W1991202512 @default.
• W4384938310 cites W2021786390 @default.
• W4384938310 cites W2022070267 @default.
• W4384938310 cites W2026471682 @default.
• W4384938310 cites W2031522376 @default.
• W4384938310 cites W2073137590 @default.
• W4384938310 cites W2078508424 @default.
• W4384938310 cites W2083078919 @default.
• W4384938310 cites W2123098122 @default.
• W4384938310 cites W2161233693 @default.
• W4384938310 cites W2792034161 @default.
• W4384938310 cites W2944442229 @default.
• W4384938310 cites W3026141768 @default.
• W4384938310 cites W3136098705 @default.
• W4384938310 cites W3163993681 @default.
• W4384938310 cites W3192444476 @default.
• W4384938310 cites W3203245760 @default.
• W4384938310 cites W3214876293 @default.
• W4384938310 cites W3216660278 @default.
• W4384938310 cites W4284989568 @default.
• W4384938310 cites W4289526005 @default.
• W4384938310 cites W4310290792 @default.
• W4384938310 cites W4310713697 @default.
• W4384938310 doi "https://doi.org/10.1016/j.dt.2023.07.010" @default.
• W4384938310 hasPublicationYear "2023" @default.
• W4384938310 type Work @default.
• W4384938310 citedByCount "0" @default.
• W4384938310 crossrefType "journal-article" @default.
• W4384938310 hasAuthorship W4384938310A5008034514 @default.
• W4384938310 hasAuthorship W4384938310A5024215125 @default.
• W4384938310 hasAuthorship W4384938310A5027946728 @default.
• W4384938310 hasAuthorship W4384938310A5040916912 @default.
• W4384938310 hasAuthorship W4384938310A5045540854 @default.
• W4384938310 hasAuthorship W4384938310A5074891964 @default.
• W4384938310 hasAuthorship W4384938310A5078701018 @default.
• W4384938310 hasBestOaLocation W43849383101 @default.
• W4384938310 hasConcept C105795698 @default.
• W4384938310 hasConcept C119857082 @default.
• W4384938310 hasConcept C121332964 @default.
• W4384938310 hasConcept C12267149 @default.
• W4384938310 hasConcept C127413603 @default.
• W4384938310 hasConcept C132459708 @default.
• W4384938310 hasConcept C146978453 @default.
• W4384938310 hasConcept C154945302 @default.
• W4384938310 hasConcept C163716315 @default.
• W4384938310 hasConcept C204323151 @default.
• W4384938310 hasConcept C33923547 @default.
• W4384938310 hasConcept C41008148 @default.
• W4384938310 hasConcept C49304495 @default.
• W4384938310 hasConcept C50644808 @default.
• W4384938310 hasConcept C61326573 @default.
• W4384938310 hasConcept C62520636 @default.
• W4384938310 hasConcept C71480407 @default.
• W4384938310 hasConcept C81692654 @default.
• W4384938310 hasConcept C83546350 @default.
• W4384938310 hasConceptScore W4384938310C105795698 @default.
• W4384938310 hasConceptScore W4384938310C119857082 @default.
• W4384938310 hasConceptScore W4384938310C121332964 @default.
• W4384938310 hasConceptScore W4384938310C12267149 @default.
• W4384938310 hasConceptScore W4384938310C127413603 @default.
• W4384938310 hasConceptScore W4384938310C132459708 @default.
• W4384938310 hasConceptScore W4384938310C146978453 @default.
• W4384938310 hasConceptScore W4384938310C154945302 @default.
• W4384938310 hasConceptScore W4384938310C163716315 @default.
• W4384938310 hasConceptScore W4384938310C204323151 @default.
• W4384938310 hasConceptScore W4384938310C33923547 @default.
• W4384938310 hasConceptScore W4384938310C41008148 @default.
• W4384938310 hasConceptScore W4384938310C49304495 @default.
• W4384938310 hasConceptScore W4384938310C50644808 @default.
• W4384938310 hasConceptScore W4384938310C61326573 @default.
• W4384938310 hasConceptScore W4384938310C62520636 @default.
• W4384938310 hasConceptScore W4384938310C71480407 @default.
• W4384938310 hasConceptScore W4384938310C81692654 @default.
• W4384938310 hasConceptScore W4384938310C83546350 @default.
• W4384938310 hasLocation W43849383101 @default.
• W4384938310 hasOpenAccess W4384938310 @default.
• W4384938310 hasPrimaryLocation W43849383101 @default.
• W4384938310 hasRelatedWork W1993966230 @default.
• W4384938310 hasRelatedWork W1996541855 @default.
• W4384938310 hasRelatedWork W2063381173 @default.
• W4384938310 hasRelatedWork W2081545345 @default.
• W4384938310 hasRelatedWork W2318821300 @default.
• W4384938310 hasRelatedWork W2348754292 @default.
• W4384938310 hasRelatedWork W2390299251 @default.
• W4384938310 hasRelatedWork W2914576772 @default.

• next