Pattern recognition neural classifier for fall detection in rock climbing

Abstract

From an athlete’s perspective, the identification of falls during rock climbing is of major importance. It constitutes a solid performance indicator, but more importantly, it could be used to trigger an instantaneous alarm to rescue teams, thus reducing the negative health consequences for the climber. In this context, an artificial neural network–based technique for fall detection during rock climbing is presented in this study. The output of this tool could be used for safety and performance monitoring purposes. The proposed method exploits a neural network for binary pattern recognition. This network is fed with a set of features extracted in real time from the acceleration and altitude signals acquired by means of a wearable device. The classifier is trained and validated with experimental datasets recorded during real climbing sessions of eight athletes through different route grades and conditions. This article illustrates the architecture of the proposed algorithm, feature extraction process, and evaluation of its accuracy. In addition, an analysis of the severity level of the detected falls is conducted. The method is able to identify real fall events with a high success rate, while yielding very few false positive indications of a fall.

Fatigue monitoring of climbing ropes

“…As presented in previous works, the combination of triaxial acceleration and altimetry measurements allows the detection of climbing falls through different post-processing algorithms with the possibility of working in real time. 24,25 Assuming the implementation of such techniques, one can find the acceleration peak due to a fall impact. Therefore, the force acting on the rope in a fall event is given by equation (1)…”

“…Recently, the authors also applied a pattern recognition neural network trained to detect the fall event from the same data set. 25 Because of its adaptive learning ability, this method does not require any fixed threshold on the studied variables. A frequency characterization of the data logger 24 demonstrates that the device has a linear sensitivity behavior up to 15g, that is, 10kN considering a user of 68kg.…”

“…Previous works have shown that it is possible to detect climbing falls with a reasonable level of accuracy by means of wearable data logging devices equipped with off-the-shelf motion sensors. 24,25 A further simple enhancement of the fall detection algorithm would allow for the extraction of the acceleration peak at the instant of impact. This information is useful to calculate the force amplitude acting on the rope; a subsequent correlation of this information to a fatigue curve could lead to an estimate of the rope damage.…”

A Data-Driven Method for Vehicle Speed Estimation

“…The road condition identification is performed by the two-layered (one hidden and one output layer) feed forward pattern recognition ANN. This architecture connects an input feature space to an output space of multiple pattern classes and it has been already presented in the literature to solve classification problems in different engineering fields [38][39]. After a trial and error procedure, the hidden layer has been designed with a size of 50 neurons.…”

Tracing Mechanism of Sports Competition Pressure Based on Backpropagation Neural Network

“…Its purpose is to use a certain simple mathematical model to describe the structure of the biological neural network. To a certain extent, the intelligent behavior of the quasibiological neural network solves the problem of intelligent information that cannot be handled by traditional algorithms [7,8]. It is the basis of massive information parallel processing and large-scale parallel computing.…”