Development of 12V Battery Replacement Interval Prediction Model by Self-Organizing Map Using Connected Car Data

コネクティッドカーデータを用いたSelf-Organizing Map による12V バッテリ交換インターバル予測モデルの開発

12V battery replacement interval prediction model is presented. This prediction model mainly consists of two parts. One is training part, and the other is prediction part. In the training part, clustering procedures are carried out by Self-Organizing Map (SOM) which is one of the unsupervised machine learning techniques. On the other hand, in the prediction part, pattern matching between clustering results and observed connected car data is performed. In this paper, the effectiveness of prediction model has been verified using car dealers’ actual maintenance data and connected car data.12Vバッテリ交換インターバル予測モデルを開発した. 開発したモデルは主に学習部分と予測部分で構成される. 学習部分では, SOMでクラスタリングを実施し, 予測部分では, コネクティッドカーデータとSOMとのマッチングにより交換インターバルを予測する. 実データを用いて本モデルの有効性を確認した.


  • English
  • Japanese

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01689607
  • Record Type: Publication
  • Source Agency: Japan Science and Technology Agency (JST)
  • Files: TRIS, JSTAGE
  • Created Date: Nov 26 2018 3:02PM