scholarly journals Pavement slipperiness detection using wheel speed and acceleration sensor data

2021 ◽  
Vol 11 ◽  
pp. 100431
Author(s):  
Jinhwan Jang
Keyword(s):  
Wheel Speed ◽  
Sensor Data ◽  
Acceleration Sensor

P 120 A machine learning approach to detecting sleep and sleep disorders in acceleration sensor data

2017 ◽  
Vol 128 (10) ◽  
pp. e388
Author(s):  
R. Leenings ◽  
C. Glatz ◽  
A. Heidbreder ◽  
M. Boentert ◽  
G. Pipa ◽  
...  
Keyword(s):  
Machine Learning ◽  
Sleep Disorders ◽  
Sensor Data ◽  
Learning Approach ◽  
Acceleration Sensor ◽  
Machine Learning Approach

scholarly journals Public Transport Driver Identification System Using Histogram of Acceleration Data

2019 ◽  
Vol 2019 ◽  
pp. 1-15 ◽  
Author(s):  
Nuttun Virojboonkiate ◽  
Adsadawut Chanakitkarnchok ◽  
Peerapon Vateekul ◽  
Kultida Rojviboonchai
Keyword(s):  
Public Transport ◽  
System Architecture ◽  
Detection System ◽  
Window Size ◽  
Data Preprocessing ◽  
Sensor Data ◽  
Identification System ◽  
Acceleration Sensor ◽  
Collection Data ◽  
Driver Identification

This paper introduces a driver identification system architecture for public transport which utilizes only acceleration sensor data. The system architecture consists of three main modules which are the data collection, data preprocessing, and driver identification module. Data were collected from real operation of campus shuttle buses. In the data preprocessing module, a filtering module is proposed to remove the inactive period of the public transport data. To extract the unique behavior of the driver, a histogram of acceleration sensor data is proposed as a main feature of driver identification. The performance of our system is evaluated in many important aspects, considering axis of acceleration, sliding window size, number of drivers, classifier algorithms, and driving period. Additionally, the case study of impostor detection is implemented by modifying the driver identification module to identify a car thief or carjacking. Our driver identification system can achieve up to 99% accuracy and the impostor detection system can achieve the F1 score of 0.87. As a result, our system architecture can be used as a guideline for implementing the real driver identification system and further driver identification researches.

Abstract 240: Smartphone Application to Provide Real-Time Cardiopulmonary Resuscitation Quality Feedback

Circulation ◽  
2019 ◽  
Vol 140 (Suppl_2) ◽  
Author(s):  
Emily Stumpf ◽  
Ravi Ambati ◽  
Raj Shekhar ◽  
Steven Staffa ◽  
David Zurakowski ◽  
...  
Keyword(s):  
Cardiopulmonary Resuscitation ◽  
Real Time ◽  
Mobile Application ◽  
Sensor Data ◽  
Smart Device ◽  
Compression Rate ◽  
Acceleration Sensor ◽  
Compression Depth ◽  
Quality Feedback ◽  
Cpr Quality

Introduction: Quality of cardiopulmonary resuscitation (CPR) contributes significantly to morbidity and mortality in both in-hospital and out-of-hospital cardiac arrest. Key parameters that determine the CPR quality are compression rate, compression depth, duration of interruptions, chest recoil factor and respiratory rate. Several studies have demonstrated that real-time audiovisual feedback improves CPR quality in both bystanders and hospital staff. This study aims to develop and validate a smart device (phones and wearable technology) application to provide real-time audiovisual and haptic feedback to optimize CPR quality, by calculating aforementioned chest compression parameters. Hypothesis: A mobile application using acceleration sensor data from smart devices can provide accurate real time CPR quality feedback. Methods: A mobile application was developed to track the compression depth, compression rate and pause duration in real time using the data captured from the on-device accelerometer. The mobile device was placed on an adult manikin’s chest along the midline close to the point of compressions. Data from the application was compared directly to data obtained from a validated clinical standard CPR quality tool. Results: CPR quality parameters were obtained from the app and the standard for 60, 10-second-long sessions. Bland-Altman plot analysis for compression depth showed agreement between the app measurements and standard within +/-3.5mm (Figure 1). The intraclass correlation for agreement in the measurement of compression count was 0.92 (95% CI: 0.88-0.95), indicative of very strong agreement. Conclusions: Smart device (phones and wearable technology) applications using acceleration sensor data can accurately provide real-time CPR quality feedback. With further development and validation they can provide a ubiquitous CPR feedback tool valuable for out of hospital arrests and in under-privileged areas worldwide.

scholarly journals Classification of cow’s behaviors based on 3-DoF accelerations from cow’s movements

2019 ◽  
Vol 9 (3) ◽  
pp. 1656
Author(s):  
Phung Cong Phi Khanh ◽  
Kieu Thi Nguyen ◽  
Nguyen Dinh-Chinh ◽  
Tran Duc-Nghia ◽  
Hoang Quang Trung ◽  
...  
Keyword(s):  
Decision Tree ◽  
Data Acquisition ◽  
Real Time ◽  
Wireless Transmission ◽  
Sensor Data ◽  
Test Results ◽  
Acceleration Sensor

Cow’s behavior classification helps people to monitor cow activities, thus the health and physiological periods of cows can be well tracked. To classify the behavior of cows, the data from the 3-axis acceleration sensor mounted on their neck is often used. Data acquisition and preprocessing of sensor data is required in this device. We acquire data from the 3-axis acceleration sensor mounted on the cows’neck and send to the microcontrollter. At the microcontroller, a proposed decision tree is applied in real-time manner to classify four important activities of the cows (standing, lying, feeding, and walking). Finally, the results can be sent to the server through the wireless transmission module. The test results confirm the reliability of the proposed device.

Sign in / Sign up

Export Citation Format

Share Document