scholarly journals Evaluation of Inertial Sensor-Based Pre-Impact Fall Detection Algorithms Using Public Dataset

Sensors ◽  
2019 ◽  
Vol 19 (4) ◽  
pp. 774 ◽  
Author(s):  
Soonjae Ahn ◽  
Jongman Kim ◽  
Bummo Koo ◽  
Youngho Kim
Keyword(s):  
Angular Velocity ◽  
Inertial Sensor ◽  
Fall Detection ◽  
Measurement Unit ◽  
Elderly Subjects ◽  
Blind Test ◽  
Detection Algorithms ◽  
Trunk Inclination ◽  
Custom Made ◽  
Public Dataset

In this study, pre-impact fall detection algorithms were developed based on data gathered by a custom-made inertial measurement unit (IMU). Four types of simulated falls were performed by 40 healthy subjects (age: 23.4 ± 4.4 years). The IMU recorded acceleration and angular velocity during all activities. Acceleration, angular velocity, and trunk inclination thresholds were set to 0.9 g, 47.3°/s, and 24.7°, respectively, for a pre-impact fall detection algorithm using vertical angles (VA algorithm); and 0.9 g, 47.3°/s, and 0.19, respectively, for an algorithm using the triangle feature (TF algorithm). The algorithms were validated by the results of a blind test using four types of simulated falls and six types of activities of daily living (ADL). VA and TF algorithms resulted in lead times of 401 ± 46.9 ms and 427 ± 45.9 ms, respectively. Both algorithms were able to detect falls with 100% accuracy. The performance of the algorithms was evaluated using a public dataset. Both algorithms detected every fall in the SisFall dataset with 100% sensitivity). The VA algorithm had a specificity of 78.3%, and TF algorithm had a specificity of 83.9%. The algorithms had higher specificity when interpreting data from elderly subjects. This study showed that algorithms using angles could more accurately detect falls. Public datasets are needed to improve the accuracy of the algorithms.

scholarly journals Accelerometer-Based Fall Detection Using Machine Learning: Training and Testing on Real-World Falls

Sensors ◽  
2020 ◽  
Vol 20 (22) ◽  
pp. 6479
Author(s):  
Luca Palmerini ◽  
Jochen Klenk ◽  
Clemens Becker ◽  
Lorenzo Chiari
Keyword(s):  
Machine Learning ◽  
Real World ◽  
Inertial Sensor ◽  
Fall Detection ◽  
Medical Attention ◽  
Support Vector ◽  
Detection Algorithms ◽  
Detection Systems ◽  
Machine Learning Approach ◽  
Extensive Collection

Falling is a significant health problem. Fall detection, to alert for medical attention, has been gaining increasing attention. Still, most of the existing studies use falls simulated in a laboratory environment to test the obtained performance. We analyzed the acceleration signals recorded by an inertial sensor on the lower back during 143 real-world falls (the most extensive collection to date) from the FARSEEING repository. Such data were obtained from continuous real-world monitoring of subjects with a moderate-to-high risk of falling. We designed and tested fall detection algorithms using features inspired by a multiphase fall model and a machine learning approach. The obtained results suggest that algorithms can learn effectively from features extracted from a multiphase fall model, consistently overperforming more conventional features. The most promising method (support vector machines and features from the multiphase fall model) obtained a sensitivity higher than 80%, a false alarm rate per hour of 0.56, and an F-measure of 64.6%. The reported results and methodologies represent an advancement of knowledge on real-world fall detection and suggest useful metrics for characterizing fall detection systems for real-world use.

scholarly journals Trunk Inclination Estimate During the Sprint Start Using an Inertial Measurement Unit: A Validation Study

2013 ◽  
Vol 29 (5) ◽  
pp. 622-627 ◽  
Author(s):  
Elena Bergamini ◽  
Pélagie Guillon ◽  
Valentina Camomilla ◽  
Hélène Pillet ◽  
Wafa Skalli ◽  
...  
Keyword(s):  
Angular Velocity ◽  
Inertial Measurement Unit ◽  
Sagittal Plane ◽  
Measurement Unit ◽  
Mean Values ◽  
Inertial Measurement ◽  
Trunk Inclination ◽  
Time Histories ◽  
Mean Square Difference ◽  
Curve Similarity

The proper execution of the sprint start is crucial in determining the performance during a sprint race. In this respect, when moving from the crouch to the upright position, trunk kinematics is a key element. The purpose of this study was to validate the use of a trunk-mounted inertial measurement unit (IMU) in estimating the trunk inclination and angular velocity in the sagittal plane during the sprint start. In-laboratory sprint starts were performed by five sprinters. The local acceleration and angular velocity components provided by the IMU were processed using an adaptive Kalman filter. The accuracy of the IMU inclination estimate and its consistency with trunk inclination were assessed using reference stereophotogrammetric measurements. A Bland-Altman analysis, carried out using parameters (minimum, maximum, and mean values) extracted from the time histories of the estimated variables, and curve similarity analysis (correlation coefficient > 0.99, root mean square difference < 7 deg) indicated the agreement between reference and IMU estimates, opening a promising scenario for an accurate in-field use of IMUs for sprint start performance assessment.

scholarly journals Identification of Gait Motion Patterns Using Wearable Inertial Sensor Network

Sensors ◽  
2019 ◽  
Vol 19 (22) ◽  
pp. 5024 ◽  
Author(s):  
Kee S. Moon ◽  
Sung Q Lee ◽  
Yusuf Ozturk ◽  
Apoorva Gaidhani ◽  
Jeremiah A. Cox
Keyword(s):  
Sensor Network ◽  
Inertial Sensor ◽  
Three Dimensional ◽  
Gait Pattern ◽  
Health Condition ◽  
Knee Joints ◽  
Measurement Unit ◽  
Abnormal Gait ◽  
Custom Made ◽  
The Individual

Gait signifies the walking pattern of an individual. It may be normal or abnormal, depending on the health condition of the individual. This paper considers the development of a gait sensor network system that uses a pair of wireless inertial measurement unit (IMU) sensors to monitor the gait cycle of a user. The sensor information is used for determining the normality of movement of the leg. The sensor system places the IMU sensors on one of the legs to extract the three-dimensional angular motions of the hip and knee joints while walking. The wearable sensor is custom-made at San Diego State University with wireless data transmission capability. The system enables the user to collect gait data at any site, including in a non-laboratory environment. The paper also presents the mathematical calculations to decompose movements experienced by a pair of IMUs into individual and relative three directional hip and knee joint motions. Further, a new approach of gait pattern classification based on the phase difference angles between hip and knee joints is presented. The experimental results show a potential application of the classification method in the areas of smart detection of abnormal gait patterns.

scholarly journals Machine Learning to Improve Orientation Estimation in Sports Situations Challenging for Inertial Sensor Use

2021 ◽  
Vol 3 ◽  
Author(s):  
Marit P. van Dijk ◽  
Manon Kok ◽  
Monique A. M. Berger ◽  
Marco J. M. Hoozemans ◽  
DirkJan H. E. J. Veeger
Keyword(s):  
Machine Learning ◽  
Mean Squared Error ◽  
Learning Algorithm ◽  
Inertial Sensor ◽  
Measurement Unit ◽  
Body Segment ◽  
Inertial Measurement ◽  
Wheelchair Sports ◽  
Trunk Inclination ◽  
Better Than

In sports, inertial measurement units are often used to measure the orientation of human body segments. A Madgwick (MW) filter can be used to obtain accurate inertial measurement unit (IMU) orientation estimates. This filter combines two different orientation estimates by applying a correction of the (1) gyroscope-based estimate in the direction of the (2) earth frame-based estimate. However, in sports situations that are characterized by relatively large linear accelerations and/or close magnetic sources, such as wheelchair sports, obtaining accurate IMU orientation estimates is challenging. In these situations, applying the MW filter in the regular way, i.e., with the same magnitude of correction at all time frames, may lead to estimation errors. Therefore, in this study, the MW filter was extended with machine learning to distinguish instances in which a small correction magnitude is beneficial from instances in which a large correction magnitude is beneficial, to eventually arrive at accurate body segment orientations in IMU-challenging sports situations. A machine learning algorithm was trained to make this distinction based on raw IMU data. Experiments on wheelchair sports were performed to assess the validity of the extended MW filter, and to compare the extended MW filter with the original MW filter based on comparisons with a motion capture-based reference system. Results indicate that the extended MW filter performs better than the original MW filter in assessing instantaneous trunk inclination (7.6 vs. 11.7° root-mean-squared error, RMSE), especially during the dynamic, IMU-challenging situations with moving athlete and wheelchair. Improvements of up to 45% RMSE were obtained for the extended MW filter compared with the original MW filter. To conclude, the machine learning-based extended MW filter has an acceptable accuracy and performs better than the original MW filter for the assessment of body segment orientation in IMU-challenging sports situations.

scholarly journals The Performance of Post-Fall Detection Using the Cross-Dataset: Feature Vectors, Classifiers and Processing Conditions

Sensors ◽  
2021 ◽  
Vol 21 (14) ◽  
pp. 4638
Author(s):  
Bummo Koo ◽  
Jongman Kim ◽  
Yejin Nam ◽  
Youngho Kim
Keyword(s):  
Time Series ◽  
Fall Detection ◽  
Discrete Data ◽  
Classification Performance ◽  
Training Data ◽  
Processing Conditions ◽  
Feature Vectors ◽  
External Data ◽  
Public Dataset ◽  
The Cross

In this study, algorithms to detect post-falls were evaluated using the cross-dataset according to feature vectors (time-series and discrete data), classifiers (ANN and SVM), and four different processing conditions (normalization, equalization, increase in the number of training data, and additional training with external data). Three-axis acceleration and angular velocity data were obtained from 30 healthy male subjects by attaching an IMU to the middle of the left and right anterior superior iliac spines (ASIS). Internal and external tests were performed using our lab dataset and SisFall public dataset, respectively. The results showed that ANN and SVM were suitable for the time-series and discrete data, respectively. The classification performance generally decreased, and thus, specific feature vectors from the raw data were necessary when untrained motions were tested using a public dataset. Normalization made SVM and ANN more and less effective, respectively. Equalization increased the sensitivity, even though it did not improve the overall performance. The increase in the number of training data also improved the classification performance. Machine learning was vulnerable to untrained motions, and data of various movements were needed for the training.

An Improved and Efficient Algorithm for SINS/GPS/Doppler Integrated Navigation Systems

2012 ◽  
Vol 245 ◽  
pp. 323-329 ◽  
Author(s):  
Muhammad Ushaq ◽  
Jian Cheng Fang
Keyword(s):  
Kalman Filter ◽  
Navigation System ◽  
Inertial Navigation System ◽  
Inertial Sensor ◽  
Inertial Navigation ◽  
Measurement Unit ◽  
Navigation Systems ◽  
Integrated Navigation ◽  
Efficient Manner ◽  
Position Errors

Inertial navigation systems exhibit position errors that tend to grow with time in an unbounded mode. This degradation is due, in part, to errors in the initialization of the inertial measurement unit and inertial sensor imperfections such as accelerometer biases and gyroscope drifts. Mitigation to this growth and bounding the errors is to update the inertial navigation system periodically with external position (and/or velocity, attitude) fixes. The synergistic effect is obtained through external measurements updating the inertial navigation system using Kalman filter algorithm. It is a natural requirement that the inertial data and data from the external aids be combined in an optimal and efficient manner. In this paper an efficient method for integration of Strapdown Inertia Navigation System (SINS), Global Positioning System (GPS) and Doppler radar is presented using a centralized linear Kalman filter by treating vector measurements with uncorrelated errors as scalars. Two main advantages have been obtained with this improved scheme. First is the reduced computation time as the number of arithmetic computation required for processing a vector as successive scalar measurements is significantly less than the corresponding number of operations for vector measurement processing. Second advantage is the improved numerical accuracy as avoiding matrix inversion in the implementation of covariance equations improves the robustness of the covariance computations against round off errors.

scholarly journals Re-Enactment as a Method to Reproduce Real-World Fall Events Using Inertial Sensor Data: Development and Usability Study

10.2196/13961 ◽  
2020 ◽  
Vol 22 (4) ◽  
pp. e13961
Author(s):  
Kim Sarah Sczuka ◽  
Lars Schwickert ◽  
Clemens Becker ◽  
Jochen Klenk
Keyword(s):  
Real World ◽  
Independent Living ◽  
Inertial Sensors ◽  
Inertial Sensor ◽  
Center Of Mass ◽  
Fall Detection ◽  
Video Data ◽  
Sensor Data ◽  
Movement Behavior ◽  
The Real

Background Falls are a common health problem, which in the worst cases can lead to death. To develop reliable fall detection algorithms as well as suitable prevention interventions, it is important to understand circumstances and characteristics of real-world fall events. Although falls are common, they are seldom observed, and reports are often biased. Wearable inertial sensors provide an objective approach to capture real-world fall signals. However, it is difficult to directly derive visualization and interpretation of body movements from the fall signals, and corresponding video data is rarely available. Objective The re-enactment method uses available information from inertial sensors to simulate fall events, replicate the data, validate the simulation, and thereby enable a more precise description of the fall event. The aim of this paper is to describe this method and demonstrate the validity of the re-enactment approach. Methods Real-world fall data, measured by inertial sensors attached to the lower back, were selected from the Fall Repository for the Design of Smart and Self-Adaptive Environments Prolonging Independent Living (FARSEEING) database. We focused on well-described fall events such as stumbling to be re-enacted under safe conditions in a laboratory setting. For the purposes of exemplification, we selected the acceleration signal of one fall event to establish a detailed simulation protocol based on identified postures and trunk movement sequences. The subsequent re-enactment experiments were recorded with comparable inertial sensor configurations as well as synchronized video cameras to analyze the movement behavior in detail. The re-enacted sensor signals were then compared with the real-world signals to adapt the protocol and repeat the re-enactment method if necessary. The similarity between the simulated and the real-world fall signals was analyzed with a dynamic time warping algorithm, which enables the comparison of two temporal sequences varying in speed and timing. Results A fall example from the FARSEEING database was used to show the feasibility of producing a similar sensor signal with the re-enactment method. Although fall events were heterogeneous concerning chronological sequence and curve progression, it was possible to reproduce a good approximation of the motion of a person’s center of mass during fall events based on the available sensor information. Conclusions Re-enactment is a promising method to understand and visualize the biomechanics of inertial sensor-recorded real-world falls when performed in a suitable setup, especially if video data is not available.

scholarly journals A Hard Example Mining Approach for Concealed Multi-Object Detection of Active Terahertz Image

2021 ◽  
Vol 11 (23) ◽  
pp. 11241
Author(s):  
Ling Li ◽  
Fei Xue ◽  
Dong Liang ◽  
Xiaofei Chen
Keyword(s):  
Computer Vision ◽  
Object Detection ◽  
State Of The Art ◽  
Terahertz Imaging ◽  
Public Security ◽  
Counter Terrorism ◽  
Detection Algorithms ◽  
Public Dataset ◽  
The One ◽  
Objects Detection

Concealed objects detection in terahertz imaging is an urgent need for public security and counter-terrorism. So far, there is no public terahertz imaging dataset for the evaluation of objects detection algorithms. This paper provides a public dataset for evaluating multi-object detection algorithms in active terahertz imaging. Due to high sample similarity and poor imaging quality, object detection on this dataset is much more difficult than on those commonly used public object detection datasets in the computer vision field. Since the traditional hard example mining approach is designed based on the two-stage detector and cannot be directly applied to the one-stage detector, this paper designs an image-based Hard Example Mining (HEM) scheme based on RetinaNet. Several state-of-the-art detectors, including YOLOv3, YOLOv4, FRCN-OHEM, and RetinaNet, are evaluated on this dataset. Experimental results show that the RetinaNet achieves the best mAP and HEM further enhances the performance of the model. The parameters affecting the detection metrics of individual images are summarized and analyzed in the experiments.

scholarly journals Semi-supervised near-miss fall detection for ironworkers with a wearable inertial measurement unit

2016 ◽  
Vol 68 ◽  
pp. 194-202 ◽  
Author(s):  
Kanghyeok Yang ◽  
Changbum R. Ahn ◽  
Mehmet C. Vuran ◽  
Sepideh S. Aria
Keyword(s):  
Inertial Measurement Unit ◽  
Fall Detection ◽  
Near Miss ◽  
Measurement Unit ◽  
Inertial Measurement

A new method to reduce the noise of the miniaturised inertial sensors disposed in redundant linear configurations

2013 ◽  
Vol 117 (1188) ◽  
pp. 111-132 ◽  
Author(s):  
T. L. Grigorie ◽  
R. M. Botez
Keyword(s):  
Inertial Sensors ◽  
Inertial Sensor ◽  
Low Frequency ◽  
Minimum Variance ◽  
Measurement Unit ◽  
Time Step ◽  
Accelerometer Sensor ◽  
Sensor Model ◽  
Input Acceleration

Abstract This paper presents a new adaptive algorithm for the statistical filtering of miniaturised inertial sensor noise. The algorithm uses the minimum variance method to perform a best estimate calculation of the accelerations or angular speeds on each of the three axes of an Inertial Measurement Unit (IMU) by using the information from some accelerometers and gyros arrays placed along the IMU axes. Also, the proposed algorithm allows the reduction of both components of the sensors’ noise (long term and short term) by using redundant linear configurations for the sensors dispositions. A numerical simulation is performed to illustrate how the algorithm works, using an accelerometer sensor model and a four-sensor array (unbiased and with different noise densities). Three cases of ideal input acceleration are considered: 1) a null signal; 2) a step signal with a no-null time step; and 3) a low frequency sinusoidal signal. To experimentally validate the proposed algorithm, some bench tests are performed. In this way, two sensors configurations are used: 1) one accelerometers array with four miniaturised sensors (n = 4); and 2) one accelerometers array with nine miniaturised sensors (n = 9). Each of the two configurations are tested for three cases of input accelerations: 0ms−1, 9·80655m/s2 and 9·80655m/s2.

Sign in / Sign up

Export Citation Format

Share Document