![LITERATURE REVIEW
6/25
Authors Aspects Remarks
Uslu et
al. [3]
Human activity monitoring with
wearable sensors and hybrid
classifiers.
1.How to effectively
use Accelerometer
sensor.
Asim et
al. [4]
Context-Aware Human Activity
Recognition (CAHAR) in-the-Wild
using Smartphone Accelerometer.
1. Related with the
mathematical
Calculations.
S. Bosch
et al. [2]
Keep on moving! activity
monitoring and stimulation using
wireless sensor networks.
1. Stimulation using
wireless network.
2. Different types of the
proposed algorithm.
4/6/2020](https://image.slidesharecdn.com/endsempresentation-210909163830/85/Human-Activity-Monitoring-System-Using-Wearable-Sensors-presentation-6-320.jpg)
Human Activity Monitoring System Using Wearable Sensors presentation
- 1. Presented By:- Amrit Raj (B16CS013) Arun Kumar Verma (B16CS021) Guided by :- Dr Soumen Moulik Assistant Professor Human Activity Monitoring Using Wearable Sensors 1/25
- 2. CONTENTS ⮚ OBJECTIVE ⮚ INTRODUCTION ⮚ MOTIVATION ⮚ LITERATURE REVIEW ⮚ USED COMPONENT ⮚ ARDUINO UNO ⮚ NODE-MCU ⮚ ANALOG TO DIGITAL CONVERTER ⮚ ACCELEROMETER ⮚ CIRCUIT DIAGRAM ⮚ WORKING PROCEDURE ⮚ RESULTS AND DISCUSSION ⮚ FUTURE SCOPE ⮚ REFERENCES 4/6/2020 2/25
- 3. ⮚ Activity Monitoring of Human with Wearable Sensors using Accelerometer. ⮚ Monitoring over old/elderly people at home using sensor. ⮚ Using Google Excel sheet and Web App we can see the status of the old person/patients. ⮚ To provide an objective indication of the activity levels or restrictions experienced by patients or the elderly. 3/25 OBJECTIVE 4/6/2020
- 4. INTRODUCTION ⮚ Real-time activity monitoring using wearable sensors and hybrid classifiers. ⮚ Recognizing activities such as standing, walking, running, or sitting. ⮚ Patients with dementia and other mental pathologies could be monitored to detect abnormal activities and thereby prevent undesirable consequences. ⮚ 50% of the old age(70+) group hospitalized due to injuries by falling down. 4/25 4/6/2020
- 5. MOTIVATION ⮚ The emphasis is given on the monitoring of the elderly people. An example of that includes the continuous monitoring of elderly people. ⮚ Integration of cheap and replaceable components makes it feasible for public. ⮚ Authorise person can monitor using Internet from anywhere. ⮚ The devices which do not intrude into the privacy of the person to be monitored can have an advantage over the devices like camera. 5/25 4/6/2020
- 6. LITERATURE REVIEW 6/25 Authors Aspects Remarks Uslu et al. [3] Human activity monitoring with wearable sensors and hybrid classifiers. 1.How to effectively use Accelerometer sensor. Asim et al. [4] Context-Aware Human Activity Recognition (CAHAR) in-the-Wild using Smartphone Accelerometer. 1. Related with the mathematical Calculations. S. Bosch et al. [2] Keep on moving! activity monitoring and stimulation using wireless sensor networks. 1. Stimulation using wireless network. 2. Different types of the proposed algorithm. 4/6/2020
- 7. USED COMPONENTS ⮚ Accelerometer ⮚ Arduino Uno ⮚ ESP8266 Wi-Fi Module(Node MCU) ⮚ Analog to Digital Converter (ADS1115) ⮚ Breadboard ⮚ Connecting Wires ⮚ Power Supply (5 V) 7/25 4/6/2020
- 8. ARDUINO UNO ⮚ Arduino Uno is a microcontroller board based on the ATmega328P. ⮚ It consists of other components such as serial communication, crystal oscillator, voltage regulator, etc. to support the microcontroller ⮚ Arduino Uno has 6 analog input pins, 14 digital input/output pins, a USB connection, ⮚ A Power barrel jack, an ICSP header and a reset button. 4/6/2020 8/25
- 9. NODEMCU (ESP8266 Wi-Fi Module) ⮚ Microcontroller: Tensilica 32-bit RISC CPU Xtensa LX106 ⮚ Integrated support for Wi-Fi network ⮚ It supports serial communication protocols ⮚ Low cost and Low energy consumption (3.3V) ⮚ Even Programmable with Arduino IDE ⮚ Small in Size 9/25 4/6/2020
- 10. ADS11150 ⮚Ultra-Small X2QFN Package: 2 mm × 1.5 mm × 0.4 mm Consists of both a physical and programmable circuit board ⮚Wide Supply Ranges between 2.0V to 5.5V ⮚Low Current Consumption (150 µA) ⮚Operating Temperature Ranges in –40°C to +125°C 10/25 4/6/2020
- 11. ACCELEROMETER ⮚An electromechanical device ⮚It measures proper acceleration ⮚by sensing the amount of dynamic acceleration ⮚Uses piezoelectric effect or changes in capacitance ⮚Test vibrations or Musical Instruments ⮚Power supply ( +3.5 v) 11/25 4/6/2020
- 12. CIRCUIT DIAGRAM 12/25 Figure 01 : Connection with NodeMCU 4/6/2020
- 13. CIRCUIT DIAGRAM 13/25 Figure 02 : Connection with Arduino Uno 4/6/2020
- 14. For Module 1(Arduino UNO): ⮚Arduino is connected through USB ⮚The accelerometer measures orientation ⮚The data is captured using serial monitor ⮚PLX-DAQ Data Acquisition for Excel ⮚Data is being analyzed using mean algorithm 14/25 WORKING PROCEDURE 4/6/2020
- 15. WORKING PROCEDURE For Module 2(NodeMCU): ⮚Wi-Fi module connects to the personal hotspot/Wi-Fi ⮚The accelerometer measured orientation ⮚The data is sent through an internet ⮚Data is being collected in a Google sheet ⮚Data is being analyzed using Standard deviation, mean absolute value and Energy 15/25 4/6/2020
- 16. 16/25 WORKING PROCEDURE ⮚ Data stored in excel sheet as training data ⮚ All calculations are automatic ⮚ 25 data test for each activity is being tested ⮚ Calculating different characteristics for test data ⮚ According to 25 test data predicts activity ⮚ Shows activity in summary sheet 4/6/2020
- 17. USED FORMULA ⮚ Maximum Value = ⮚ Minimum Value = ⮚ Average Value = ⮚ Standard Deviation = ⮚ MAVFD = ⮚ MAVSD = ⮚ Energy = ⮚ Where s(n) represents the acceleration signal along x, y, or z-axis of the accelerometer,N is the length of sequence s(n) 17/25 4/6/2020
- 18. 18/25 RESULT AND DISCUSSION ⮚Our hardware module detects the different activities ● Walking Plane ● Sitting ● Standing ● Jogging ● Running ● Walking Up ● Walking Down 4/6/2020
- 21. Average Efficiency = Average Efficiency =(80+100+85+100+90+80+90)/7= 89.29% 21/25 RESULT AND DISCUSSION 4/6/2020
- 22. FUTURE SCOPE ⮚Other human physical analysis like heartbeat, pressure, specific disease like asthma and other medical issues. ⮚A clear distinction between almost similar types of activities like Staircase Down-and-Walking and Jogging-and-Running ⮚The incorporation of multiple human subjects would also lead to a new direction of research that would study the interaction between people and help to analyze group behaviour. ⮚The application domains are as broad as from healthcare to security services and fitness monitoring. 22/25 4/6/2020
- 23. REFERENCES 1. A. Czabke, S. Marsch, and T. Lueth, “Accelerometer based real- time activity analysis on a microcontroller,” in Pervasive Computing Technologies for Healthcare (Pervasive Health), 2011 5th IEEE International Conference on, may 2011, pp. 40 –46. 2. S. Bosch, M. Marin-Perianu, R. Marin-Perianu, P. Havinga, and H. Hermens, “Keep on moving! activity monitoring and stimulation using wireless sensor networks,” Proceedings of EuroSSC’09, the 4th European conference on Smart sensing and context, pp. 11– 23, ACM, 2009. 3. Uslu, Gamze, H. Ibrahim Dursunoglu, Ozgur Altun, and Sebnem Baydere. "Human activity monitoring with wearable sensors and hybrid classifiers." International Journal of Computer Information Systems and Industrial Management Applications 5 (2013): 345- 353. 23/25 4/6/2020
- 24. 4. Asim, Y., Azam, M. A., Ehatisham-ul-Haq, M., Naeem, U., & Khalid, A. (2020). “Context-Aware Human Activity Recognition (CAHAR) in-the-Wild using Smartphone Accelerometer.” IEEE Sensors Journal,pp.1–1,2020. 5. M. Espinilla, J. Medina, J. Hallberg, and C. Nugent,“A new approach based on temporal sub-windows for online sensor- based activity recognition,” Journal of Ambient Intelligence and Humanized Computing, pp.1–13, 2018. 24/25 REFERENCES 4/6/2020
- 25. 25/25