Presentation is loading. Please wait.

Presentation is loading. Please wait.

SenMinCom: Pervasive Distributed Dynamic Sensor Data Mining for Effective Commerce.

Similar presentations

Presentation on theme: "SenMinCom: Pervasive Distributed Dynamic Sensor Data Mining for Effective Commerce."— Presentation transcript:

1 SenMinCom: Pervasive Distributed Dynamic Sensor Data Mining for Effective Commerce

2 Outline 1. What is SenMinCom ? 2. Past Works & Why SenMinCom ? 3. How SenMinCom ? 4. SenMinCom’s Contributions 5. Current Methods v/s SenMinCom 6. SenMinCom’s Simulations 1. Shopping Model 2. Mobile Device Usage Model 7. Conclusion 8. References 9. Acknowledgements

3 What is SenMinCom [24] ?  Independent units that receive and respond to signals  Unobtrusive  Cheaply available computer Sensing

4 contd…  Process of sorting through heap of data and picking out relevant gems  Mostly on data that have not been previously discovered Mining

5 contd…  Mobile commerce or U commerce is the ability to conduct commerce using a cellular device  U-commerce because of its Ubiquitous-ness mobile Commer ce

6 contd… unobtrusive Sensing live Mining mobile Commer ce

7 Past Works & Why SenMinCom [24] ? Sensors restricted to defense, environmental tracking, etc. Cellular phones limited to entertainment, commerce, etc.

8 contd… Enormous potential over the traditional invasive methods Environmental monitoring [1-7] Self-organizing, adaptive systems Smart environments [8] Discusses frameworks, applications Mobile Commerce [9-10]

9 contd… Location service management GypSii [11-12] Share photos, send invitations, etc. Mobile social networking [12-13]

10 contd… Sensors Cellular phones

11 contd… Keeps track of runs, heart pulse, mini body fat calculator NTT DoCoMo’s Wellness Phone [14-15] Register an earthquake & relays warning messages to the people in affected area Tsunami warning system [16] Set of non-invasive physiological sensors that monitors a patient’s health HealthGear [17]

12 contd… Wirelessly record sales, issue receipts and track inventory Schwan’s for route sale drivers [18]

13 contd… sensors cellular phones mining

14 contd… Shopping Scenario No method to get the real time shopping pattern No way to know about shoppers’ preference for products No effective way to lure shoppers’ before they leave store No system that benefits retail and consumer

15 contd… Mobile Usage Scenario Companies rely on quarterly surveys No method to get real-time mobile usage

16 contd… automate the task of market surveys up-to-the- minute information effective progress

17 How SenMinCom [24] ? Centralized static data mining Distributed dynamic data mining

18 contd… Centralized static data mining Off-line data mining Time & resource intensive Sink processes & analyzes Sensor tracks & forwards

19 contd… Formed by code & data Clone & migrate Reduce network load Overcome network latency Mobile agent Reveal patterns Easy to perceive, interpret, manipulate Mining accomplished on real time data rather than on a snapshot Data mining Achieves unobtrusive sensing Gathers +Processes +Communicates Sensor

20 contd… SenMinCom [24] Sensed data Mobile agent Data mining

21 SenMinCom’s Contributions [24]

22 contd… Centralized location Regional server Mobile Information Server Network Store1…nInternet Cellular tower Sensor-ized area CustomerProductSink

23 contd… Aggregator nodes Sensor-ized area

24 contd… Distributed Dynamic Mining System (DDMS) Reduces communication effort [19] Dimensionality reduction of data mining Mining on fresh data Less resource intensive

25 contd…  A DDMS is a set of transactions where 'T' is a purchase or product information event and 't' represents the time and date of the occurrence of T.  DDMS M = {... } where M is the recorded Mac Id of the customer's cell phone.  System will have pre-defined rule base from which the distinction of customers is achieved.

26 contd… i.Define Rules and corresponding parameters for each Rule ii.for shopper (Mac Id) m=1 to M i.Identify DDMS m from set of DDMS ii.for segment r=1 to R i.Select Rule r from the set of Rules, R ii.If(Rule r ⊆ DDMS m ) add shopper m to group r iii.The R groups of shoppers are the segments

27 contd… If(thisNode = = firstAggregator) MA migrates toward firstAggregator Else if( (thisNode = = nextAggregator) && (nextAggregator != lastAggregator) ) MA collects sensed raw data and does local mining Set nextAggregator in the MA packet MA migrates towards next aggregator Else if(thisNode = = lastAggregator) MA collects sensed data MA migrates back to sink

28 Current Methods v/s SenMinCom [24] Communicating messages consume far more energy than processing it [21] Mining done at aggregator Mined results don’t affect real-world situation [22] Mining takes place on fresh data Link bandwidth of wireless sensor network very less [20] Agent carries only the result set

29 contd… Central mining costly in terms of communication and storage [23] Task of mining distributed on all aggregators Sensor nodes passive Sensor made an active device

30 SenMinCom’s Simulations Shopping Model Mobile Device Usage Model

31 Shopping Model [24]  Random shoppers have no strong intention to purchase something, and just wander among aisles a.k.a. window shoppers  Rational shoppers visiting a store, know clearly what they need a.k.a prompt shoppers  Recurrent or regular customers are customers who visit the store often. They can be further divided into  Customers with higher purchasing power  Customers with lower purchasing power

32 contd…  Example  Book store company e.g. Barnes & Nobles  Store modeled on SenMinCom architecture  Result  Customers shopping & checkout patterns dynamically tracked

33 contd… Features 1. Aisle wise real time products distribution 2. Reveals aisle popularity Consequences 1. Restacking products 2. Maximize selling

34 contd… Features 1. Aisle wise real time products distribution at separate time intervals 2. Aisle popularity Consequences 1. Restacking products according to different hours of a day, days in a week, etc.

35 contd… Features 1. Reveals customers purchasing power 2. Categorize customers Consequences 1. Directed products promotion

36 contd… Feature 1. Products lifted to checked out Consequences 1. With shopping history product promotion offers 2. Customer

37 contd… Feature 1. Products lifted to checked out customer level Consequences 1. Shopping history leads product promotion offers 2. Products picked to checked out share 3. Aisle movement pattern

38 Mobile Device Usage Model  Popular cellular phone cravings  Brand popularity where the people are attracted or loyal towards a company  For a cell phone company, popularity of a given model or total volume of their models  Cellular phone usage among an age group  Educational period is a stage among the age group of 18-28, generally students attending schools, colleges, and universities.  Working period, among the age group 28-60

39 contd…  Example  Georgia State University Campus  Area modeled on SenMinCom architecture  Result  Students real time device usage scenario  Manual device survey avoided

40 contd… Mobile Devices GSU Plaza

41 contd… Mobile Devices GSU Student Center

42 contd… Popular Mobile GSU

43 contd… Features 1. Area wide popular mobile models 2. Total mobile device usage scenario Consequences 1. Real time mobile popularity 2. Brand consideration leads to streamlining promotions

44 contd… Feature 1. Various mobile models of a brand Consequences 1. Popularity of models 2. Reasons like cost, intriguing features, etc. revealed

45 contd… Motorola Volume UsagePopular Mobile Devices

46 contd… Feature 1. Market share of cell phone models Consequences 1. Timeline based share of model 2. Provide insight for a newly released model

47 contd… Feature 1. Mobile usage of new cell phone models Consequences 1. Crosscheck their marketing campaign 2. Peoples’ current mobile preferences

48 Conclusion SenMinCom [24] Sensors extended to retail Real time pervasive system Data centric Real time analysis of business

49 References 1. Mainwaring, A., Polastre, J., Szewczyk, R., Culler, D., Anderson, J.,“Wireless Sensor Networks for Habitat Monitoring”, Proceedings of the 1 st ACM International Workshop on Wireless Sensor Networks and Applications, 2002, pp Warrior, J., “Smart Sensor Networks of the Future”, Sensors Magazine, March Pottie, G.J., Kaiser, W.J., “Wireless Integrated Network Sensors”, Communications of the ACM, vol. 43, no. 5, pp , May Cerpa, A., Elson, J., Estrin, D., Girod, L., Hamilton M., Zhao, J., “Habitat monitoring: Application driver for wireless communications technology”, 2001 ACM SIGCOMM Workshop on data Communications in Latin America and the Caribbean, Costa Rica, April Werner-Allen, G., Johnson, J., Ruiz, M., Lees, J., Welsh, M., “Monitoring volcanic eruptions with a wireless sensor network”, Wireless Sensor Networks, Proceedings of the second European Workshop, 2005, pp Intel Research Sensor Network Operation, 7. Shih, E., Cho, S., Ickes, N., Min, R., Sinha, A., Wang, A., Chandrakasan, A., “Physical layer driven protocol and algorithm design for energy-efficient wireless sensor networks”, Proceedings of ACM MobiCom’01, Rome, Italy, July 2001, pp

50 contd… 8. Herring, C., Kaplan, S., “Component-based software systems for smart environments, IEEE Personal Communications, October 2000, pp Varshney, U., Vetter, R., “Framework, Applications, and Networking Support for M- commerce”, ACM/Kluwer Journal on Mobile Network and Applications (MONET), June Varshney, U., Vetter, R., Kalakota, R.,”Mobile Commerce: A New Frontier”, IEEE Computer, 2000, 22(10), pp GyPSii Webtop, 12. Social Networking moves to the cell phone, Social Network Zingku, Zingku-mobile-social-networking-service_1.html Zingku-mobile-social-networking-service_1.html 14. NTT DoCoMo Newsletter, Mobility, Adding the Human Touch to Communication, New Cell phone doubles as personal trainer and shrink,

51 contd… 16. MedDay has Breakthrough solution for Tsunami Warning System based on disease detection and management system, Oliver, N., Flores-Mangas, F., HealthGear: A Real-time Wearable System for Monitoring and Analyzing Physiological Signals, Proceedings of the International Workshop on Wearable and Implantable Body Sensor Networks (BSN ’06), Schwan’s, B1D7291A275D/0/schwans.pdf B1D7291A275D/0/schwans.pdf 19. Goel, S., and Imielinski, T., “Prediction-based monitoring in sensor networks: Taking lessons from mpeg”, ACM Computer Communication Review, 31(5), Chen M., Kwon, T., Choi, Y., “Data Dissemination based on Mobile Agent in Wireless Sensor Networks”, Proceedings of the IEEE Conference on Local Computer Networks 30th anniversary (LCN '05). 21. Chen M., Kwon, T., Yuan, Y., Leung V.C.M., “Mobile Agent Based Wireless Sensor Networks”, Journal of Computers, Vol 1, No. 1., April 2006

52 contd… 22. Ong, K., Zhang, Z., Ng, W., Lim, E., “Agents and Stream Data Mining: A New Perspective”, IEEE Intelligent Systems, June Bontempi, G., Borgne, Y., “An Adaptive Modular Approach to the mining of Sensor Network Data”, 2005 SIAM International Conference on Data Mining, April Hiremath, N., Zhang, Y., “SenMinCom: Pervasive Distributed Dynamic Sensor Data Mining for Effective Commerce,” Proceedings of 2008 IEEE International Conference on Granular Computing (GrC 2008), Aug 2008

Download ppt "SenMinCom: Pervasive Distributed Dynamic Sensor Data Mining for Effective Commerce."

Similar presentations

Ads by Google