Beruflich Dokumente
Kultur Dokumente
Abstract: Modern life is becoming more linked to our devices and work is being done
in a more regulated way. As life became more complicated, it is becoming challenging
to keep track of one’s health and fitness which may lead to unexpected illness and
diseases. Moreover, lack of activity monitoring and corresponding reminders is
preventing the adoption of a healthier lifestyle. This research provides an effective
approach for identifying Human Activity by using accelerometer data obtained from
wearable devices. The model automatically finds pattern among 33 different physical
exercises such as running, rowing, cycling, jogging etc. and correctly identifies them.
Principal component Analysis was used on the statistical features in order to make the
system more robust. Classification of the physical exercise was performed on the
reduced features using WEKA. An overall accuracy of 85.51% was obtained using 10-
Fold Cross Validation method and K nearest Neighbor Algorithm while 84% accuracy
for Random Forest. The accuracy obtained was better than previous models and could
improve recognition systems in monitoring user activity more precisely.
Instead of using a regular fixed sized window, 90.5% for 10 daily activities. In [11] the task of
adaptive segment was used which ensures more inferring activities when travelling by metro was
likely to detect an activity in those respective explored. It showed when two features could be
segments. Reduction Algorithm makes the selected based on feature selection method the
system computational efficient and robust in model can obtain good accuracy.
many scenarios. Finally, 2 classifiers, one of
Our model improves the existing system by
them is Lazy Algorithm while the other
using adaptive sliding window on preprocessed
Ensemble Tree was used to evaluate
accelerometer signals and then normalizing
performance.
those features. Next using pca the reduced
This research can be pointed down to six features were classified using Machine Learning
sections. Section 2 reviews the previous models.
research related works. Section 3 introduces our
3. PROPOSED METHODOLOGY
proposed model and discusses the experimental
steps that were involved. Section 4 portrays the
findings of our study. Lastly, Section 5 gives the
conclusion of the study and addresses future
works.
2. LITERATURE REVIEW
In order to track and count human activity there
are two approach: The wearable sensor
approach and the other one is the smartphone
based. Vu Ngoc in [5] collected five activities
data from smartphone and was recognized
where they obtained an accuracy of 74% for
kNN and 75.3% for ANN respectively. Activity
and sensor was limited and there were some
ambiguity in the data collected. In [6] Rui
proposed a modified full CNN based algorithm
which predicted human activity sequences on
the self-collected opportunist and hospital An adaptive time series technique [12] of
dataset. In [7], CNN was applied directly on 16 segment length 200 was used on each of the
lower limb activities using 5 sensors and it sensor magnitude for all the subjects from which
showed comparison to using 1 single sensor. feature were extracted.
The Researchers in [8] used a tenfold random-
partitioning cross-validation evaluation to 3.1 Datasets
evaluate the system performance and the
number of features were only limited to 3. For To conduct our experiment, we have collected
capturing repeated periods in activities Banos et REALDISP Activity Recognition dataset [8]
al used a time window to segment the discrete from UCI Machine Learning Repository. The
signal. The model failed to demonstrate reliable dataset consists recordings from 17 subjects, ten
accuracy for accelerometer data when many males and seven females. The recordings
activities were involved. The obtained accuracy include 13 inertial signals obtained from sensors
was a little more than 80%. Tuan Le in [9] located at different part of the body. A
extracted related feature from raw data of 30 multivariate time series were obtained from the
volunteer performing 6 activity and finally used accelerometer sensors which are sampled at
IB3 method to improve accuracy by reducing regular intervals. The experiment consisted of
dimension. 15% improved accuracy was subjects performing 33 physical Activities in 3
obtained through Naïve Bayes (91.85%) and scenarios. The exercise lasted about 15-20 min.
Decision Tree (96%). In [10] Yu-Liang Hsu It is important to note that there are about 1900
used NWFE algorithm on two sensor data instances where the user weren’t moving The
located at two places which are wrist and ankle. count rate of each of the activity after removing
Moreover, the model ensured an accuracy of the irrelevant null activity is as follows
Computer Science and Engineering Research Journal
(6)
Where,
√ ∑ (𝑥 ) (7)
Y = XA (11)
3.3 Z score- normalization
REFERENCES