Presentation is loading. Please wait.

Presentation is loading. Please wait.

19. 06. 2014 Automatization of the Stream Mining Process Lovro Šubelj, Zoran Bosnić, Matjaž Kukar, Marko Bajec CAiSE 2014, Thessaloniki, Greece Laboratory.

Similar presentations


Presentation on theme: "19. 06. 2014 Automatization of the Stream Mining Process Lovro Šubelj, Zoran Bosnić, Matjaž Kukar, Marko Bajec CAiSE 2014, Thessaloniki, Greece Laboratory."— Presentation transcript:

1 19. 06. 2014 Automatization of the Stream Mining Process Lovro Šubelj, Zoran Bosnić, Matjaž Kukar, Marko Bajec CAiSE 2014, Thessaloniki, Greece Laboratory for Data Technologies

2 Laboratory for Data Tehnologies 2 Industry specific adoption layer Occapi TM RR3 – Open Intelligent Communication Platform Smart House/ Building/ City Smart Energy/ Grid Smart Traffic/ Lights/ Transport eTolling eHealth RR1 – Intelligent Infrastructure Telecom Operators RR2 - Services and Things management SME Asset & Time mgmt Motivation

3 Laboratory for Data Tehnologies 3  BigData  Real Time Processing  CEP  Prediction  Open connectors  BAM, Dashboards IoT Platforms

4 Laboratory for Data Tehnologies 4

5 + 5 Copyright (c) 2013 FRI-LPT, FE-LTFE 00 01 02 03 04 05 06 07 08 09 10 11 12 13 14 15 16 0.010% 0.008% 0.006% 0.004% 0.002% 0.000% Real time Future

6 Laboratory for Data Tehnologies Objective  To capture expert knowledge  To computerize the stream mining process 6

7 Laboratory for Data Tehnologies Approach  Observe experts at work;  Identify the main activities in the stream mining process – focus on the activities where the experts’ knowledge is crucial;  Acquire expert knowledge;  Prototype an expert system;  Evaluate on different datasets; 7

8 Laboratory for Data Tehnologies Process 8

9 Laboratory for Data Tehnologies Prototype 9

10 Laboratory for Data Tehnologies Prototype 10

11 Laboratory for Data Tehnologies Evaluation  Experimental framework: –Standard statistics (classification: CA, Kappa, F, Rand index; regression: MAE, MAPE, RMSE, Pearson); –Performance comparison: Q-statistics  Datasets: –Flight delay prediction (USA, 1987-2008); –Electricity market price (New South Wales, Australia) –Electric energy consumption (Portugal); –Solar energy forecast (USA, Oclahoma) 11

12 Laboratory for Data Tehnologies Flight delay prediction 12

13 Laboratory for Data Tehnologies Electricity marketplace 13

14 Laboratory for Data Tehnologies Electric energy consumption 14

15 Laboratory for Data Tehnologies Solar energy forecast 15

16 Laboratory for Data Tehnologies Conclusions  For stream mining expert knowledge is required;  The expert knowledge is sufficiently routinized and can be captured as explicit knowledge and computerized;  Important finding for the development of IS on the field of big data, IoT and similar.  Further work: –Full deployment of the meta learner (different learning techniques possible); –Evaluation on more datasets; –Testing in real settings (time complexity, required resources, problem scalability…); 16


Download ppt "19. 06. 2014 Automatization of the Stream Mining Process Lovro Šubelj, Zoran Bosnić, Matjaž Kukar, Marko Bajec CAiSE 2014, Thessaloniki, Greece Laboratory."

Similar presentations


Ads by Google