Using Random Forest for Opportunistic Human Activity Recognition: a complete study on Opportunity dataset

نویسندگان

  • Luis Gioanni
  • Christel Dartigues-Pallez
  • Stéphane Lavirotte
  • Jean-Yves Tigli
چکیده

RÉSUMÉ Un grand nombre de recherches existent pour la reconnaissance d’activité humaine. Cependant, la plupart d’entre elles utilisent un ensemble statique et immuable de capteurs connus par avance. Cette approche ne fonctionne pas lorsqu’elle est appliquée à un système ubiquitaire, car nous ne connaissons alors pas par avance quels capteurs seront disponibles dans l’environnement de l’utilisateur. C’est pourquoi nous considérons ici une approche opportuniste où chaque capteur est entrainé individuellement et capable d’apporter sa propre connaissance. Nous considérons toutes les étapes de la chaîne de reconnaissance d’activité et nous montrons comment ce processus peut être amélioré à chacune de ces étapes. Plus précisément, nous prenons en compte les étapes telles que le prétraitement, la segmentation, l’extraction de caractéristiques et l’apprentissage. Nous proposons également d’évaluer à la fois l’efficacité des Random Forests (RF) pour entrainer des capteurs et la robustesse de la fusion des résultats basée sur le vote à la majorité en comparant les résultats obtenus à ceux du projet Opportunity. Nous montrons ainsi que les RF donnent de meilleurs résultats plus robustes que les algorithmes d’apprentissage testés par Opportunity.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Feature integration with random forests for real-time human activity recognition

This paper presents an approach for real-time human activity recognition. Three different kinds of features (flow, shape, and a keypoint-based feature) are applied in activity recognition. We use random forests for feature integration and activity classification. A forest is created at each feature that performs as a weak classifier. The international classification of functioning, disability a...

متن کامل

Gesture Recognition Using Template Based Random Forest Classifiers

This paper presents a framework for spotting and recognizing continuous human gestures. Skeleton based features are extracted from normalized human body coordinates to represent gestures. These features are then used to construct spatio-temporal template based Random Decision Forest models. Finally, predictions from different models are fused at score level to improve overall recognition perfor...

متن کامل

Comparing random forest approaches to segmenting and classifying gestures

A complete gesture recognition system should localize and classify each gesture from a given gesture vocabulary, within a continuous video stream. In this work, we compare two approaches: a method that performs the tasks of temporal segmentation and classification simultaneously with another that performs the tasks sequentially. The first method trains a single random forest model to recognize ...

متن کامل

3D Detection of Power-Transmission Lines in Point Clouds Using Random Forest Method

Inspection of power transmission lines using classic experts based methods suffers from disadvantages such as highel level of time and money consumption. Advent of UAVs and their application in aerial data gathering help to decrease the time and cost promenantly. The purpose of this research is to present an efficient automated method for inspection of power transmission lines based on point c...

متن کامل

Facial Recognition using Modified Local Binary Pattern and Random Forest

This paper presents an efficient algorithm for face recognition using the local binary pattern (LBP) and random forest (RF). The novelty of this research effort is that a modified local binary pattern (MLBP), which combines both the sign and magnitude features for the improvement of facial texture classification performance, is applied. Furthermore, RF is used to select the most important featu...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2016