Surface classification using acceleration signals recorded during human freehand movement

2015 ◽  
Author(s):  
Matti Strese ◽  
Clemens Schuwerk ◽  
Eckehard Steinbach
Keyword(s):  
Surface Classification ◽  
Acceleration Signals

scholarly journals Intelligent Tire Sensor-Based Real-Time Road Surface Classification Using an Artificial Neural Network

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 3233
Author(s):  
Dongwook Lee ◽  
Ji-Chul Kim ◽  
Mingeuk Kim ◽  
Hanmin Lee
Keyword(s):  
Neural Network ◽  
Control Systems ◽  
Real Time ◽  
Vertical Axis ◽  
Autonomous Driving ◽  
Classification Algorithm ◽  
Road Surface ◽  
Electronic Control ◽  
Surface Classification ◽  
Acceleration Signals

Vehicles today have many advanced driver assistance control systems that improve vehicle safety and comfort. With the development of more sophisticated vehicle electronic control and autonomous driving technology, the need and effort to estimate road surface conditions is increasing. In this paper, a real-time road surface classification algorithm, based on a deep neural network, is developed using a database collected through an intelligent tire sensor system with a three-axis accelerometer installed inside the tire. Two representative types of network, fully connected neural network (FCNN) and convolutional neural network (CNN), are learned with each of the three-axis acceleration sensor signals, and their performances were compared to obtain an optimal learning network result. The learning results show that the road surface type can be classified in real-time with sufficient accuracy when the longitudinal and vertical axis acceleration signals are trained with the CNN. In order to improve classification accuracy, a CNN with multiple input that can simultaneously learn 2-axis or 3-axis acceleration signals is suggested. In addition, by analyzing how the accuracy of the network is affected by number of classes and length of input data, which is related to delay of classification, the appropriate network can be selected according to the application. The proposed real-time road surface classification algorithm is expected to be utilized with various vehicle electronic control systems and makes a contribution to improving vehicle performance.

scholarly journals Assessment of upper extremity movement performance of patients with obstetric brachial plexus palsy

2017 ◽  
Vol 3 (1) ◽  
pp. 1-5 ◽  
Author(s):  
Ligia C. S. Fonseca ◽  
Annika K. Nelke ◽  
Jörg Bahm ◽  
Catherine Disselhorst-Klug
Keyword(s):  
Brachial Plexus ◽  
Upper Extremity ◽  
Objective Data ◽  
Brachial Plexus Palsy ◽  
Obstetric Brachial Plexus Palsy ◽  
Movement Performance ◽  
Obstetric Brachial Plexus ◽  
The Individual ◽  
Acceleration Signals ◽  
Upper Extremity Movement

Abstract:Coping strategies of patients with obstetric brachial plexus palsy (OBPP) are highly individual. Up to now, individual movement performance is assessed by visual observations of physicians or therapists - a procedure, which is highly subjective and lacks objective data. However, objective data about the individual movement performance are the key to evidence-based and individualized treatment. In this paper, a new approach is presented, which provides objective information about the upper extremity movement performance of patients with OBPP. The approach is based on the use of accelerometers in combination with a classification procedure. The movement performance of 10 healthy volunteers and 41 patients with OBPP has been evaluated by experienced physiotherapists and has been assigned to one of 4 categories representing the Mallet Scale (MS) IV to I. Three triaxial-accelerometers were placed at chest, upper arm and wrist of the affected side of the patient. Acceleration signals have been recorded during repetitive movements with relevance regarding daily life. Here, especially the results from the “hand to mouth” task are presented. From the 9 recorded acceleration signals 13 relevant features were extracted. For each of the 13 features 4 thresholds have been determined distinguishing best between the 4 patient categories of the MS and the healthy subjects. With respect to the thresholds each feature value has been assigned to the discrete numbers 0, 1, 2, 3 or 4. Afterwards, each discrete number has been weighted by a factor regarding the correlation between the feature’s value and the MS score. The resulting weighted discrete numbers of all 13 features have been added resulting in a score, which quantifies the individual upper extremity movement performance. Based on this score the movement performance of each patient has been assigned to the classes “very good”, “good”, “regular” and “bad”. All movements of the 10 healthy volunteers were classified as “very good”. The movement performance of two patients MS IV were classified as “very good” as well and the movements of the other 16 patients as “good”. The movements of the entire group of MS III patients fell into the class “regular”. Just one MS II patient was assigned to the class “regular” while the others were classified as “bad”. It was not possible to classify the movements of MS I patients. This was mainly due to the fact that none of these patients MS I was able to complete the task successfully. The developed approach demonstrated its ability to quantify the movement performance of upper extremity movements based on accelerometers. This provides an easy to use tool to assess patient’s movement strategies during daily tasks for diagnosis and rehabilitation.

Road Surface Classification Based on Radar Imaging Using Convolutional Neural Network

2021 ◽  
pp. 1-1
Author(s):  
Shahrzad Minooee Sabery ◽  
Aleksandr Bystrov ◽  
Peter Gardner ◽  
Ana Stroescu ◽  
Marina Gashinova
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Radar Imaging ◽  
Road Surface ◽  
Surface Classification

scholarly journals Effectiveness of Variable-Gain Kalman Filter Based on Angle Error Calculated from Acceleration Signals in Lower Limb Angle Measurement with Inertial Sensors

2013 ◽  
Vol 2013 ◽  
pp. 1-12 ◽  
Author(s):  
Yuta Teruyama ◽  
Takashi Watanabe
Keyword(s):  
Kalman Filter ◽  
Lower Limb ◽  
Measurement Accuracy ◽  
Inertial Sensors ◽  
Angle Measurement ◽  
Angle Error ◽  
Variable Gain ◽  
Improve Measurement ◽  
Kalman Gain ◽  
Acceleration Signals

The wearable sensor system developed by our group, which measured lower limb angles using Kalman-filtering-based method, was suggested to be useful in evaluation of gait function for rehabilitation support. However, it was expected to reduce variations of measurement errors. In this paper, a variable-Kalman-gain method based on angle error that was calculated from acceleration signals was proposed to improve measurement accuracy. The proposed method was tested comparing to fixed-gain Kalman filter and a variable-Kalman-gain method that was based on acceleration magnitude used in previous studies. First, in angle measurement in treadmill walking, the proposed method measured lower limb angles with the highest measurement accuracy and improved significantly foot inclination angle measurement, while it improved slightly shank and thigh inclination angles. The variable-gain method based on acceleration magnitude was not effective for our Kalman filter system. Then, in angle measurement of a rigid body model, it was shown that the proposed method had measurement accuracy similar to or higher than results seen in other studies that used markers of camera-based motion measurement system fixing on a rigid plate together with a sensor or on the sensor directly. The proposed method was found to be effective in angle measurement with inertial sensors.

Collocated OLCI optical imagery and SAR radar altimetry from Sentinel3 for enhanced sea ice surface classification

2021 ◽  
Author(s):  
Dorsa Nasrollahi Shirazi ◽  
Michel Tsamados ◽  
Isobel Lawrence ◽  
Sanggyun Lee ◽  
Thomas Johnson ◽  
...  
Keyword(s):  
Sea Ice ◽  
Classification Algorithms ◽  
Polar Regions ◽  
Radar Altimetry ◽  
Imaging Spectrometer ◽  
Ice Surface ◽  
Ice Roughness ◽  
Elevation Data ◽  
Optical Imagery ◽  
Surface Classification

<p>The Copernicus operational Sentinel-3A since February 2016 and Sentinel-3B since April 2018 build on the CryoSat-2 legacy in terms of their synthetic aperture radar (SAR) mode altimetry providing high-resolution radar freeboard elevation data over the polar regions up to 81N. This technology combined with the Ocean and Land Colour Instrument (OLCI) imaging spectrometer offers the first space-time collocated optical imagery and radar altimetry dataset. We use these joint datasets for validation of several existing surface classification algorithms based on Sentinel-3 altimeter echo shapes. We also explore the potential for novel AI techniques such as convolutional neural networks (CNN) for winter and summer sea ice surface classification (i.e. melt pond fraction, lead fraction, sea ice roughness). For lead surface classification we analyse the winters of 2018/19 and 2019/20 and for summer sea ice feature classification we focus on the Sentinel-3A &3B tandem phase of the summer 2018. We compare our CNN models with other existing surface classification algorithms.</p>

On-Field Measurements of the Dissipated Vibrational Power of an SUV Car Traditional Viscous Shock Absorber

2018 ◽  
Author(s):  
Mohamed A. A. Abdelkareem ◽  
Lin Xu ◽  
Mohamed Kamal Ahmed Ali ◽  
Mohamed A. Hassan ◽  
Ahmed Elagouz ◽  
...  
Keyword(s):  
Shock Absorber ◽  
Average Power ◽  
Field Measurements ◽  
Velocity Range ◽  
Suspension Systems ◽  
Shock Absorbers ◽  
Road Section ◽  
Speed Range ◽  
System Body ◽  
Acceleration Signals

The current paper provides some on-field measurements regarding the quantification of the dissipated power during the damping process of a traditional viscous shock absorber. In this regard, the HAVAL H8 SUV was driven for several trips on the Nanhu campus arena considering a velocity range of 20–50 km/h. Furthermore, two species of campus road sections were selected during the fabricated tests; straight road section with and without a speed bump. The acceleration signals of the rear-right suspension system (body and wheel) were acquired as the average power dissipation trend could be calculated from the relative suspension velocity. The findings of this investigation indicate that the average dissipated power of a traditional shock absorber can be in a range of 10–90 W for a speed range of 20–50 km/h driving on a campus road section free of speed bumps. Whilst, for another road segment with one speed bump, the shock absorber dissipated a kinetic energy between 40–140 W for a velocity range of 20–50 km/h. Suggesting that an average overall dissipated power of 160–560 W is available by means of the traditional shock absorbers. The results are of strategic interest for the researchers and vehicle manufacturers for further considerations in terms of regenerative suspension systems where a part of this energy could be harvested instead of being wholly dissipated.

Damage Detection in Flexible Propeller Beam Structures by Exploiting Impact-Induced Coupled Acceleration Signals

2011 ◽  
Author(s):  
Ioannis T. Georgiou
Keyword(s):  
Data Driven ◽  
Distributed Information ◽  
Modal Expansion ◽  
Shape Difference ◽  
Spatio Temporal ◽  
Temporal Sample ◽  
High Level ◽  
Proper Orthogonal ◽  
Acceleration Signals

A local damage at the tip of a composite propeller is diagnosed by properly comparing its impact-induced free coupled dynamics to that of a pristine wooden propeller of the same size and shape. This is accomplished by creating indirectly via collocated measurements distributed information for the coupled acceleration field of the propellers. The powerful data-driven modal expansion analysis delivered by the Proper Orthogonal Decomposition (POD) Transform reveals that ensembles of impact-induced collocated coupled experimental acceleration signals are underlined by a high level of spatio-temporal coherence. Thus they furnish a valuable spatio-temporal sample of coupled response induced by a point impulse. In view of this fact, a tri-axial sensor was placed on the propeller hub to collect collocated coupled acceleration signals induced via modal hammer nondestructive impacts and thus obtained a reduced order characterization of the coupled free dynamics. This experimental data-driven analysis reveals that the in-plane unit components of the POD modes for both propellers have similar shapes-nearly identical. For the damaged propeller this POD shape-difference is quite pronounced. The shapes of the POD modes are used to compute indices of difference reflecting directly damage. At the first POD energy level, the shape-difference indices of the damaged composite propeller are quite larger than those of the pristine wooden propeller.

Sign in / Sign up

Export Citation Format

Share Document