Improving Accelerometer Based Activity Recognition
نویسندگان
چکیده
This paper presents the findings of a research on how to improve activity recognition from data captured with chest mounted accelerometer. Several methods were applied to achieve this purpose, including: simple smoothing technique, hidden Markov models (HMM), extraction of frequency domain features, principal component analysis (PCA) and dynamic time warping (DTW). The paper describes each of the methods and presents the achieved results of our research. The results indicate that these techniques, used separately or in combination, can increase recognition accuracy.
منابع مشابه
Improving Accelerometer-Based Activity Recognition by Using Ensemble of Classifiers
In line with the increasing use of sensors and health application, there are huge efforts on processing of collected data to extract valuable information such as accelerometer data. This study will propose activity recognition model aim to detect the activities by employing ensemble of classifiers techniques using the Wireless Sensor Data Mining (WISDM). The model will recognize six activities ...
متن کاملReducing Uncertainty in User-independent Activity Recognition - A Sensor Fusion-based Approach
In this study, a novel user-independent method to recognize activities accurately in situations where traditional accelerometer based classification contains a lot of uncertainty is presented. The method uses two recognition models: one using only accelerometer data and other based on sensor fusion. However, as a sensor fusionbased method is known to consume more battery than an accelerometer-b...
متن کاملVideo Annotation Framework for Accelerometer Placement in Worker Activityrecognition Studies
Automated recognition of worker activities has the potential in aiding quick assessment of labour productivity on construction sites. A novel method called accelerometer based activity recognition has been investigated and preliminary results show that it has good potential for deployment in construction environment. The major decisive factor influencing the performance of the activity recognit...
متن کاملImproving physical security with machine learning and sensor-based human activity recognition
With current maturity and wide accessibility of low-cost sensor technologies, sensor-based human activity recognition is becoming more and more popular in various domains and novel innovative applications. Huge amount of research in this area is driven by smart-home assistive living applications, many of them mostly focused on the development of efficient methods and applications that can help ...
متن کاملCorrelation between new activity-based balance index with accelerometer data and postural balance in elderly woman
Stability and balance in the elderly are measured using several methods. The purpose of this study was to introduce a new activity based balance index using accelerometer and determine the relationship between this index and postural stability in older woman. Materials and Methods: Ninty-two elderly women were selected and participated in this study. For measuring balanace, One Leg Stance, Berg...
متن کاملذخیره 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 2013