1 / 26

SurroundSense : Mobile Phone Localization via Ambience Fingerprinting

SurroundSense : Mobile Phone Localization via Ambience Fingerprinting. MARTIN AZIZYAN, IONUT CONSTANDACHE, ROMIT ROY CHOUDHURY Presented by Lingfei Wu. Outline. Introduction SurroundSense Architecture System Design Implementation Evaluation Conclusion. Introduction.

arien
Download Presentation

SurroundSense : Mobile Phone Localization via Ambience Fingerprinting

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. SurroundSense: Mobile Phone Localization via Ambience Fingerprinting MARTIN AZIZYAN, IONUT CONSTANDACHE, ROMIT ROY CHOUDHURY Presented by Lingfei Wu

  2. Outline • Introduction • SurroundSense Architecture • System Design • Implementation • Evaluation • Conclusion

  3. Introduction Application of logical localization • Notion of location • Physical coordinates(latitude/longitude) • Logical labels(like Starbucks, Mcdonalds) • Many applications based on logical location

  4. Introduction Physical coordinate can be reversed to logical location. However, it often causes error ! Why not compute logical location directly?

  5. Relative work 1. Lack accuracy 2. Need pre-installed infrastructure • Active RF • Install special hardware • Ultrasound, Bluetooth • Passive RF • GPS, GSM or WIFI based • Behavior Sensing • Imaging matching

  6. Motivation Starbucks Bookstore Wal-Mart McDonald’s • Combine effect of ambient sound, light, color, user motion • Sound (microphone) • Starbucks VS Bookstore • Light / Color (camera) • Different thematic light, colors and floors. • Human movement (accelerometer) • Wal-Mart VS McDonald • Place may not be unique based on any one attribute • The combination can be unique enough for localization • In this paper, we propose SurroundSense for logical localization.

  7. SurroundSense Architecture Candidate list 1.Xxx 2.Yyy 3.zzz 1.Xxx 2.Yyy 1.Xxx 2.Yyy 1.Xxx 2.Yyy 1.Xxx

  8. System Design • Fingerprint generation • Fingerprinting sound • Fingerprinting motion using accelerometers • Fingerprinting color/light using cameras • Fingerprinting Wi-Fi • Fingerprint matching • Wi-Fi filter • Sound filter • Motion filter • Color/light Match

  9. Fingerprinting sound Normalized occurrence count amplitude value 50 0 -50 time time Normalized amplitude value • Convert signals to time domain • 100 normalized values as feature of sound • Similarity of fingerprints • Compute 100 pair-wise distance between test fingerprint and all candidate fingerprint

  10. Fingerprinting Sound • Unreliable to be a matching scheme • Sound from the same place can vary over time. • Only use as a filter • If distance > threshold τthen discard from the candidate list

  11. Fingerprinting Motion Raw data SVM 1 moving -1 stationary • Use support vector machine(SVM) as classifier • Sequence of states as user’s moving pattern • Movement is prone to fluctuation • In a clothing store, Some users browse for a long time while others purchase clothes in haste. • Only use as a filter

  12. Fingerprinting Motion Sitting Browsing Walking • Compute motion fingerprint: Ratio = tmoving / tstatic • Bucket 1: 0.0 <= Ratio <= 0.2 Sitting (cafe) • Bucket 2: 0.2 <= Ratio <= 2.0 Browsing (clothing) • Bucket 3: 2.0 <= Ratio <= ∞ Walking (grocery)

  13. Fingerprinting Color / Light too much noise • Thematic color and lighting in different stores • Where to capture the picture? • random picture of surrounding • floor • Advantages of taking floor pictures • Privacy concern • Less noisy • Rich diversity in floor color • Easy to obtain

  14. Fingerprinting Color / Light too much noise k=2 sk: the sum of distance from all pixels to their (own cluster’s) centroid. t: convergence threshold k-mean clustering k++ sk-sk-1 < t no yes Bean Trader’s Coffee shop < c1, c2 …, ck > • How to extract colors and light intensity? • RGB • HSL(Hue-Saturation-Lightness) • Find color cluster and its size using K-means clustering algorithm

  15. Fingerprinting Color / Light Total size in C1 or C2 distance of centroid • Similarity of fingerprints • Assume C1 = {c11, c12, …, c1n}; C2 = {c21, c22, …, c2m} • Fingerprint matching • The candidate list with maximum similarity is declared to the matching fingerprint

  16. Fingerprinting Wi-Fi Fingerprint tuple: <{AP1_MAC_Addr, AP1_fraction_time}, {AP2_MAC_Addr, AP2_fraction_time}, {AP3_MAC_Addr, AP3_fraction_time}> • Wi-Fi fingerprint • Record MAC address from APs every 5 second

  17. Fingerprinting Wi-Fi fraction of time M: union of MAC address of fingerprints f1 and f2 • Similarity of fingerprints • Use as filter/matching module • In the absence of light/color, we use it as matching module. • Accuracy depend on location of shops.

  18. Implementation • Client and server • Client: Nokia 95 phones using Python as client • Server: Matlab and Python code and some data mining tools for fingerprinting algorithms. • Fingerprint database • Labor-intensive war-sensing at 51 stores • Store location: 46 business location in university town, 5 location in India

  19. Implementation

  20. Evaluation • SurroundSense(SS) test environment • War-sensed 51 shops organized in 10 clusters • 4 students visited the first nine clusters in university town, while 2 students visited the tenth cluster in India. • 4 localization models: • Wi-Fi only (Wi-Fi) • Sound, Accelerometer, Light and color ( Snd-Acc-Lt-Clr) • Sound, Accelerometer, Wi-Fi (Snd-Acc-Wi-Fi) • SurroundSense (SS)

  21. Evaluation – Per-Cluster Accuracy Similar hardwood floor in strip mall No Wi-Fi Best represented Same AP False negative Snd and Acc Restaurant

  22. Evaluation – Per-Shop Accuracy 30% shops 47% shops SS: 92% Snd-Acc-WiFi: 92% Snd-Acc-Lt-Clr: 75% WiFi: 75% To understand the localization accuracy on a per-shop basis

  23. Evaluation – Per-User Accuracy Simulate 100 virtual user, each assign 4~8 stores from cluster 1~9

  24. Evaluation – Per-Sensor Accuracy false negative Percentage localized using special sensors Number of shops left after special filter Hand-picked 6 samples to exhibit the merits and demerits of each sensor

  25. Conclusion Presented SurroundSense, a non-conventional approach for logical localization. Created fingerprints about ambient sound, light, color, movement and Wi-Fi and match them with fingerprint database to realize accurate logical localization. The evaluation achieved an average location accuracy of over 85% using all sensors.

  26. Discussion • The GPS 10 m, Wi-Fi and GSM 40m and 400m respectively. Why not use Wi-Fi to get initial location instead of using GSM? • Support vector machines (SVM), K-means clustering algorithm are used in paper, do you have any better machine learning methods? Such as Kalman filter, Particlefilter, and Wavelet Transform? • Can other sensors help? Such as compass and Bluetooth? • Energy consideration? Non-business location?

More Related