计算机科学与探索
計算機科學與探索
계산궤과학여탐색
JOURNAL OF FRONTIERS OF COMPUTER SCIENCE & TECHNOLOGY
2015年
8期
985-994
,共10页
杨隆浩%蔡芷铃%黄志鑫%何星%傅仰耿
楊隆浩%蔡芷鈴%黃誌鑫%何星%傅仰耿
양륭호%채지령%황지흠%하성%부앙경
概率预测%GPS数据%路网数据%置信规则库%置信规则库推理方法(RIMER)
概率預測%GPS數據%路網數據%置信規則庫%置信規則庫推理方法(RIMER)
개솔예측%GPS수거%로망수거%치신규칙고%치신규칙고추리방법(RIMER)
probability prediction%GPS data%road network data%belief rule-base%belief rule-base inference method-ology using evidential reasoning (RIMER)
出租车乘车概率预测中存在数据量级大,底层属性类型多,预测信息不确定的问题。鉴于此,整合大规模轨迹数据范畴中现有的挖掘算法对出租车GPS数据和路网数据进行离线处理;将多类型的不确定性数据转换为具有置信结构的规则形式,并以此构建置信规则库;通过置信规则库推理方法(belief rule-base infer-ence methodology using evidential reasoning,RIMER)在线预测路网道路上各个地点的乘车概率。以北京市2012年11月某天的出租车GPS数据为例说明该在线预测方法的应用。实验结果表明,该预测方法具有较高的实时性和准确性。
齣租車乘車概率預測中存在數據量級大,底層屬性類型多,預測信息不確定的問題。鑒于此,整閤大規模軌跡數據範疇中現有的挖掘算法對齣租車GPS數據和路網數據進行離線處理;將多類型的不確定性數據轉換為具有置信結構的規則形式,併以此構建置信規則庫;通過置信規則庫推理方法(belief rule-base infer-ence methodology using evidential reasoning,RIMER)在線預測路網道路上各箇地點的乘車概率。以北京市2012年11月某天的齣租車GPS數據為例說明該在線預測方法的應用。實驗結果錶明,該預測方法具有較高的實時性和準確性。
출조차승차개솔예측중존재수거량급대,저층속성류형다,예측신식불학정적문제。감우차,정합대규모궤적수거범주중현유적알굴산법대출조차GPS수거화로망수거진행리선처리;장다류형적불학정성수거전환위구유치신결구적규칙형식,병이차구건치신규칙고;통과치신규칙고추리방법(belief rule-base infer-ence methodology using evidential reasoning,RIMER)재선예측로망도로상각개지점적승차개솔。이북경시2012년11월모천적출조차GPS수거위례설명해재선예측방법적응용。실험결과표명,해예측방법구유교고적실시성화준학성。
Large scale of data, various types of low-level attributes and uncertainty of prediction information exist in probability prediction of taking taxi. To solve these problems, this paper offline deals with the GPS data of taxi and road network data by using mining algorithms in the large-scale trajectory data domain, then builds a belief rule-base by transforming various types of information with uncertainty into rules which are in form of the belief structure, after that uses RIMER (belief rule-base inference methodology using evidential reasoning) to get the final probability of any points on the road network. Finally, the GPS data of Beijing’s taxi in November of 2012 are taken as an example to illustrate the usage of the online prediction method, and the results show the real-time and accuracy of the proposed method.