Matches in SemOpenAlex for { <https://semopenalex.org/work/W2971137647> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2971137647 endingPage "3484" @default.
- W2971137647 startingPage "3484" @default.
- W2971137647 abstract "Hammering rocks of different strengths can make different sounds. Geological engineers often use this method to approximate the strengths of rocks in geology surveys. This method is quick and convenient but subjective. Inspired by this problem, we present a new, non-destructive method for measuring the surface strengths of rocks based on deep neural network (DNN) and spectrogram analysis. All the hammering sounds are transformed into spectrograms firstly, and a clustering algorithm is presented to filter out the outliers of the spectrograms automatically. One of the most advanced image classification DNN, the Inception-ResNet-v2, is then re-trained with the spectrograms. The results show that the training accurate is up to 94.5%. Following this, three regression algorithms, including Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Random Forest (RF) are adopted to fit the relationship between the outputs of the DNN and the strength values. The tests show that KNN has the highest fitting accuracy, and SVM has the strongest generalization ability. The strengths (represented by rebound values) of almost all the samples can be predicted within an error of [−5, 5]. Overall, the proposed method has great potential in supporting the implementation of efficient rock strength measurement methods in the field." @default.
- W2971137647 created "2019-09-05" @default.
- W2971137647 creator A5040016209 @default.
- W2971137647 creator A5045127642 @default.
- W2971137647 creator A5079183779 @default.
- W2971137647 creator A5089269062 @default.
- W2971137647 date "2019-08-23" @default.
- W2971137647 modified "2023-10-18" @default.
- W2971137647 title "A Deep Learning Based Method for the Non-Destructive Measuring of Rock Strength through Hammering Sound" @default.
- W2971137647 cites W1985207154 @default.
- W2971137647 cites W1993695189 @default.
- W2971137647 cites W2001780956 @default.
- W2971137647 cites W2008056655 @default.
- W2971137647 cites W2020997493 @default.
- W2971137647 cites W2036178323 @default.
- W2971137647 cites W2039037503 @default.
- W2971137647 cites W2040698615 @default.
- W2971137647 cites W2083933878 @default.
- W2971137647 cites W2090347238 @default.
- W2971137647 cites W2133059825 @default.
- W2971137647 cites W2167598218 @default.
- W2971137647 cites W2462985469 @default.
- W2971137647 cites W2576938664 @default.
- W2971137647 cites W2589006519 @default.
- W2971137647 cites W2589085805 @default.
- W2971137647 cites W2594159434 @default.
- W2971137647 cites W2597243853 @default.
- W2971137647 cites W2727098128 @default.
- W2971137647 cites W2729902770 @default.
- W2971137647 cites W2735666957 @default.
- W2971137647 cites W2911964244 @default.
- W2971137647 cites W2961384925 @default.
- W2971137647 doi "https://doi.org/10.3390/app9173484" @default.
- W2971137647 hasPublicationYear "2019" @default.
- W2971137647 type Work @default.
- W2971137647 sameAs 2971137647 @default.
- W2971137647 citedByCount "9" @default.
- W2971137647 countsByYear W29711376472021 @default.
- W2971137647 countsByYear W29711376472022 @default.
- W2971137647 countsByYear W29711376472023 @default.
- W2971137647 crossrefType "journal-article" @default.
- W2971137647 hasAuthorship W2971137647A5040016209 @default.
- W2971137647 hasAuthorship W2971137647A5045127642 @default.
- W2971137647 hasAuthorship W2971137647A5079183779 @default.
- W2971137647 hasAuthorship W2971137647A5089269062 @default.
- W2971137647 hasBestOaLocation W29711376471 @default.
- W2971137647 hasConcept C12267149 @default.
- W2971137647 hasConcept C134306372 @default.
- W2971137647 hasConcept C153180895 @default.
- W2971137647 hasConcept C154945302 @default.
- W2971137647 hasConcept C177148314 @default.
- W2971137647 hasConcept C33923547 @default.
- W2971137647 hasConcept C41008148 @default.
- W2971137647 hasConcept C45273575 @default.
- W2971137647 hasConcept C50644808 @default.
- W2971137647 hasConcept C73555534 @default.
- W2971137647 hasConcept C79337645 @default.
- W2971137647 hasConceptScore W2971137647C12267149 @default.
- W2971137647 hasConceptScore W2971137647C134306372 @default.
- W2971137647 hasConceptScore W2971137647C153180895 @default.
- W2971137647 hasConceptScore W2971137647C154945302 @default.
- W2971137647 hasConceptScore W2971137647C177148314 @default.
- W2971137647 hasConceptScore W2971137647C33923547 @default.
- W2971137647 hasConceptScore W2971137647C41008148 @default.
- W2971137647 hasConceptScore W2971137647C45273575 @default.
- W2971137647 hasConceptScore W2971137647C50644808 @default.
- W2971137647 hasConceptScore W2971137647C73555534 @default.
- W2971137647 hasConceptScore W2971137647C79337645 @default.
- W2971137647 hasIssue "17" @default.
- W2971137647 hasLocation W29711376471 @default.
- W2971137647 hasLocation W29711376472 @default.
- W2971137647 hasLocation W29711376473 @default.
- W2971137647 hasLocation W29711376474 @default.
- W2971137647 hasOpenAccess W2971137647 @default.
- W2971137647 hasPrimaryLocation W29711376471 @default.
- W2971137647 hasRelatedWork W2041399278 @default.
- W2971137647 hasRelatedWork W2056016498 @default.
- W2971137647 hasRelatedWork W2128276860 @default.
- W2971137647 hasRelatedWork W2136184105 @default.
- W2971137647 hasRelatedWork W2336974148 @default.
- W2971137647 hasRelatedWork W2382626645 @default.
- W2971137647 hasRelatedWork W2389470892 @default.
- W2971137647 hasRelatedWork W3013515612 @default.
- W2971137647 hasRelatedWork W2187500075 @default.
- W2971137647 hasRelatedWork W2345184372 @default.
- W2971137647 hasVolume "9" @default.
- W2971137647 isParatext "false" @default.
- W2971137647 isRetracted "false" @default.
- W2971137647 magId "2971137647" @default.
- W2971137647 workType "article" @default.