ICACT20220120 Question.1
Questioner: liumengup@126.com 2022-02-15 오전 5:04:09 |
ICACT20220120 Answer.1
Answer by Auhor lehonglam@vnu.edu.vn 2022-02-15 오전 5:04:09
Chrome  Click!! |
| This paper investigates different classifiers using the wearable device’s accelerometer data only, which is publicly available at http://sites.google.com/up.edu.mx/har-up/.
1. what dose overlap rates mean in paper? is it the overlap ratio of the window and the signal? To get the best result, a algorithm is used or not to get the 90% overlap rates? |
Thank you very much for your interest in our article,
On behalf of the research team, I would like to answer your questions as follows:
In this paper, overlap ratio means: Overlapping is a way of retrieving some data point of the previous window as a component of the current window. This technique is used in many published studies on activities and behavior recognition through sensor data.
It is the overlapping ratio between adjacent data windows.
In this paper, we use the 80% overlapping ratio to compare the results with previous studies.
Best regards, |
ICACT20220120 Question.2
Questioner: tomayoon@ieee.org 2022-02-15 오전 4:23:09 |
ICACT20220120 Answer.2
Answer by Auhor lehonglam@vnu.edu.vn 2022-02-15 오전 4:23:09
Chrome Click!! |
| First of all, thank you for the good research paper and presentation contents. I would like to know more about the research environment used in this study, and also in detail about the equipment & operating systems, development languages and software libraries you used. |
Thank you very much for your interest in our article,
On behalf of the research team, I would like to answer your questions as follows:
We use computers running on Windows operating system.
We use java language and weka tool to build models.
Best regards, |
ICACT20220120 Question.3
Questioner: tomayoon@ieee.org 2022-02-15 오후 12:10:32 |
ICACT20220120 Answer.3
Answer by Auhor lehonglam@vnu.edu.vn 2022-02-15 오후 12:10:32
Chrome Click!! |
| Will you tell us what is the major achievement of this paper, and also what is further study issue from this? Thanks in advance!! |
In this paper, we proposed a novel method for improving classifiers using Particle Swarm Optimization to deal with wearable sensor data. The wearable sensor data was preprocessed and transformed into Time, Frequency, and Hjorth domains, and then, the PSO optimization algorithm has been applied to find the optimal set of parameters for the RF algorithm to improve its detection rate.
In the future, we will expand our research towards building a feature set from many sensors to improve and enhance the stability of the fall detection system. |
ICACT20220120 Question.4
Questioner: sean9887@naver.com 2022-02-15 오후 12:26:49 |
ICACT20220120 Answer.4
Answer by Auhor lehonglam@vnu.edu.vn 2022-02-15 오후 12:26:49
Chrome Click!! |
| Will you tell me more details about the sensor data used in the experiment? |
In this research, we have been used data collected from an IMU 3-axis accelerometer placed in the right trouser pocket. |
ICACT20220120 Question.5
Questioner: namacabale@gmail.com 2022-02-16 오후 12:21:04 |
ICACT20220120 Answer.5
Answer by Auhor lehonglam@vnu.edu.vn 2022-02-16 오후 12:21:04
Chrome Click!! |
| Dear Author, you have a very good research. Is there an existing technology almost similar to your proposal that has been deployed in real world environment? What does it lack that your work specifically addressed? Thank you and stay safe.
|
|
