Presentation is loading. Please wait.

Presentation is loading. Please wait.

Gary M. Weiss & Jeffrey W. Lockhart Fordham University

Similar presentations


Presentation on theme: "Gary M. Weiss & Jeffrey W. Lockhart Fordham University"— Presentation transcript:

1 Gary M. Weiss & Jeffrey W. Lockhart Fordham University {gweiss,lockhart}@cis.fordham.edu

2  Biometrics concerns unique identification based on physical or behavioral traits  Hard biometrics relies on uniquely identifying traits ▪ Fingerprints, DNA, iris, etc.  Soft biometric traits are not distinctive enough for unique identification, but may help ▪ Physical traits: Sex, age, height, weight, etc. ▪ Behavioral traits: gait, clothes, travel patterns, etc. 8/21/2011Gary M. Weiss SensorKDD 20112

3  In earlier work 1 we showed that for 36 users we were able to identify the correct user using only accelerometer data:  With a single 10 second walking sample: 84% - 91%  With a 5-10 minute walking sample: 100%  So if we can identify a user based on their movements, maybe we can identify user traits 8/21/2011Gary M. Weiss SensorKDD 2011 1 Jennifer R. Kwapisz, Gary M. Weiss and Samuel A. Moore. Cell Phone-Based Biometric Identification, Proceedings of the IEEE Fourth International Conference on Biometrics: Theory, Applications and Systems (BTAS-10), Washington DC. 3

4  To help identify a person (soft biometrics)  But do we have better uses for these “soft” traits than for identification?  As data miners, of course we do!  We want to know everything we possibly can about a person. Somehow we will exploit this. 8/21/2011Gary M. Weiss SensorKDD 20114

5  Normally think about traits as being:  Unchanging: race, skin color, eye color, etc.  Slow changing: Height, weight, etc.  But want to know everything about a person:  What they wear, how they feel, if they are tired, etc.  Our goal is to predict these too  We have not seen this goal stated in context of mobile sensor data mining. 8/21/2011Gary M. Weiss SensorKDD 20115

6  Very little explicit work on this topic  Some work related to biometrics but incidental ▪ Work on gait recognition mentions factors that influence recognition, like weight of footwear & sex  Other communities work in related areas  Ergonomics & kinesiology study factors that impact gait ▪ Texture of footwear, type of shoe, sex, age, heel height 8/21/2011Gary M. Weiss SensorKDD 20116

7  Data collected from ~70 people  Accelerometer data while walking  Survey data includes anything we could think of that might somehow be predictable: ▪ Sex, height, weight, age, race, handedness, disability ▪ Type of area grew up in {rural, suburban, urban} ▪ Shoe size, footwear type, size of heels, type of clothing ▪ # hours academic work, # hours exercise  Too few subjects investigate all factors ▪ Many were not predictable (maybe with more data) 8/21/2011Gary M. Weiss SensorKDD 20117

8 Accuracy 71.2% MaleFemale Male317 Female1216 8/21/2011Gary M. Weiss SensorKDD 2011 Accuracy 83.3% ShortTall Short155 Tall220 Accuracy 78.9% LightHeavy Light137 Heavy217 Results for IB3 classifier. For height and weight middle categories removed. 8

9 8/21/2011Gary M. Weiss SensorKDD 20119

10  A wide open area for data mining research  A marketers dream  Clear privacy issues  Room for creativity & insight for finding traits  Probably many interesting commercial and research applications  Imagine diagnosing back problems via your mobile phone via gait analysis … 8/21/2011Gary M. Weiss SensorKDD 201110

11  Will collect data from hundreds of users  Getting a diverse sample a bit difficult (on campus)  Try to construct more useful features  Evaluate the ability to predict the dozens of user traits that we track  Have begun to track shoe type and heel size 8/21/2011Gary M. Weiss SensorKDD 201111


Download ppt "Gary M. Weiss & Jeffrey W. Lockhart Fordham University"

Similar presentations


Ads by Google