Every vehicle or truck manufacturer maintains databases regarding the service information oftheir vehicles. In this thesis, two vehicle databases: Vehicle Specification Database andMaintenance Service Database are analyzed and compared. The purpose is to explore theconnection between vehicle specification and vehicle maintenance needs. The approach is touse different clustering algorithms(Hierarchical, K-means, Spectral), distance measures (PositiveMatching Index and a modified Positive Matching Index), cluster validity measures(Rand Index,Jaccard Index) and data representations(Binary, Frequency) on these databases to determinethe important maintenance related specification attributes and their relation to differentservice problems (e.g. engine, brake, clutch) The clustering results indicate that there is arelation between vehicle specification and vehicle maintenance profiles. Different data miningrules that connect vehicle specification with vehicle maintenance needs are derived from theclustering results.
| Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:hh-24586 |
| Date | January 2014 |
| Creators | Krishnamaraja, Magesh |
| Publisher | Högskolan i Halmstad, Sektionen för Informationsvetenskap, Data– och Elektroteknik (IDE) |
| Source Sets | DiVA Archive at Upsalla University |
| Language | English |
| Detected Language | English |
| Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
| Format | application/pdf |
| Rights | info:eu-repo/semantics/openAccess |
| Relation | Technical report ; IDE1220 |
Page generated in 0.0021 seconds