Advanced

Analysis of Activity Recognition and the Influence of Feature Extraction and Selection in an Android Based Device

Holgersson, Philip LU and Åkerberg, Fredrik LU (2015) In Master's Theses in Mathematical Sciences FMA820 20152
Mathematics (Faculty of Engineering)
Abstract
Tracking activities have lately been very popular in smartphones, which requires that the devices are able to classify activities correctly. Since this type of devices has limitations in both power consumption and computational performance, it is important to keep these factors to a minimum. Therefore, the low cost of the accelerometer sensor is a good platform to build a classification on. Although classifications that only use the accelerometer sensor is far from perfected, as far as accuracy is concerned.
To obtain a more accurate classification, it would be necessary to dissect
the different parts of the classification process, and investigate if any of the parts can be improved. Many studies have been focusing on the different... (More)
Tracking activities have lately been very popular in smartphones, which requires that the devices are able to classify activities correctly. Since this type of devices has limitations in both power consumption and computational performance, it is important to keep these factors to a minimum. Therefore, the low cost of the accelerometer sensor is a good platform to build a classification on. Although classifications that only use the accelerometer sensor is far from perfected, as far as accuracy is concerned.
To obtain a more accurate classification, it would be necessary to dissect
the different parts of the classification process, and investigate if any of the parts can be improved. Many studies have been focusing on the different methods of calculating the classification, leading to many different well tested methods. However, very few have investigated the impact features may have on the classification, using the approach ”more is better”. Therefore this work focuses on feature selection combined with modified evaluation methods. Here we show that more features are not necessarily the best solution and that a modified naive evaluation method in most cases are better than a more recognized one. This can affect classifications in the future, especially since fewer features takes less power to compute. This is only the beginning, more studies are needed. We anticipate that our study will be used as a starting point for more in-depth studies in this field. (Less)
Please use this url to cite or link to this publication:
author
Holgersson, Philip LU and Åkerberg, Fredrik LU
supervisor
organization
course
FMA820 20152
year
type
H2 - Master's Degree (Two Years)
subject
keywords
activity analysis, confusion matrix, data analysis, classification, least squares, features selection, feature extraction, accelerometer
publication/series
Master's Theses in Mathematical Sciences
report number
LUTFMA-3284-2015
ISSN
1404-6342
other publication id
2015:E50
language
English
id
8233311
date added to LUP
2016-11-16 10:40:12
date last changed
2016-11-16 10:40:12
@misc{8233311,
  abstract     = {Tracking activities have lately been very popular in smartphones, which requires that the devices are able to classify activities correctly. Since this type of devices has limitations in both power consumption and computational performance, it is important to keep these factors to a minimum. Therefore, the low cost of the accelerometer sensor is a good platform to build a classification on. Although classifications that only use the accelerometer sensor is far from perfected, as far as accuracy is concerned.
To obtain a more accurate classification, it would be necessary to dissect
the different parts of the classification process, and investigate if any of the parts can be improved. Many studies have been focusing on the different methods of calculating the classification, leading to many different well tested methods. However, very few have investigated the impact features may have on the classification, using the approach ”more is better”. Therefore this work focuses on feature selection combined with modified evaluation methods. Here we show that more features are not necessarily the best solution and that a modified naive evaluation method in most cases are better than a more recognized one. This can affect classifications in the future, especially since fewer features takes less power to compute. This is only the beginning, more studies are needed. We anticipate that our study will be used as a starting point for more in-depth studies in this field.},
  author       = {Holgersson, Philip and Åkerberg, Fredrik},
  issn         = {1404-6342},
  keyword      = {activity analysis,confusion matrix,data analysis,classification,least squares,features selection,feature extraction,accelerometer},
  language     = {eng},
  note         = {Student Paper},
  series       = {Master's Theses in Mathematical Sciences},
  title        = {Analysis of Activity Recognition and the Influence of Feature Extraction and Selection in an Android Based Device},
  year         = {2015},
}