ETD

Archivio digitale delle tesi discusse presso l'Università di Pisa

Tesi etd-06292018-170021


Tipo di tesi
Tesi di laurea magistrale
Autore
POLLINA, GIOVANNI
URN
etd-06292018-170021
Titolo
A multilayered stigmergic architecture fed by sensorized footwears providing anomaly detection over human's habits
Dipartimento
INGEGNERIA DELL'INFORMAZIONE
Corso di studi
COMPUTER ENGINEERING
Relatori
relatore Prof. Cimino, Mario Giovanni Cosimo Antonio
relatore Prof.ssa Vaglini, Gigliola
Parole chiave
  • machine learning
  • FCM
  • Activities of daily living
  • Behaviour monitoring
  • Stigmergy
  • sensorized footwears
  • Gait Analysis
Data inizio appello
20/07/2018
Consultabilità
Non consultabile
Data di rilascio
20/07/2088
Riassunto
Monitoring the activities of daily living (ADLs) and detection of deviations from previous patterns is crucial to assessing the quality of daily living without disorders. Footwear is one of the most and common used medium to obtain this information.
Footwear in fact acts as the interface between the ground and the wearer’s foot. Lots of information can be gleaned from observing this interaction, for this reason a smart shoe is useful devices for monitoring purpose.
In this regard, we present an adaptive, reliable, and innovative anomaly detection method based on multi-layered stigmergic fed by sensorized footwears.
We exploit pressure sensor data, gathered via footwear, in order to identify subject’s behavioral
Pattern over human's habits.
More specifically pressures sensor samples are processed via computational stigmergy, a bio-inspired scalar and temporal aggregation of samples.
Stigmergy associates each sample to a digital pheromone deposit (mark) defined in a mono-dimensional space and characterized by evaporation over time. As a consequence, samples close in terms of time and intensity are aggregated into functional structures called trails. The stigmergic trails allow to compute the similarity between time series on different temporal scales, to support classification or clustering processes.
The outcome is a similarity between days of the same subject, to generate clusters of different behavioural patterns, at the end an anomaly index ranks the anomaly level of new day or series of days.
File