scholarly journals Analysis of Feature Dimension Reduction Techniques Applied on the Prediction of Impact Force in Sports Climbing Based on IMU Data

AI ◽  
2021 ◽  
Vol 2 (4) ◽  
pp. 662-683
Author(s):  
Heiko Oppel ◽  
Michael Munz
Keyword(s):  
Dimension Reduction ◽  
Impact Force ◽  
Measurement Unit ◽  
Severe Injuries ◽  
Reduction Techniques ◽  
Median Error ◽  
Feature Dimension ◽  
The Impact ◽  
Dimension Reduction Techniques ◽  
Feature Dimension Reduction

Sports climbing has grown as a competitive sport over the last decades. This has leading to an increasing interest in guaranteeing the safety of the climber. In particular, operational errors, caused by the belayer, are one of the major issues leading to severe injuries. The objective of this study is to analyze and predict the severity of a pendulum fall based on the movement information from the belayer alone. Therefore, the impact force served as a reference. It was extracted using an Inertial Measurement Unit (IMU) on the climber. Additionally, another IMU was attached to the belayer, from which several hand-crafted features were explored. As this led to a high dimensional feature space, dimension reduction techniques were required to improve the performance. We were able to predict the impact force with a median error of about 4.96%. Pre-defined windows as well as the applied feature dimension reduction techniques allowed for a meaningful interpretation of the results. The belayer was able to reduce the impact force, which is acting onto the climber, by over 30%. So, a monitoring system in a training center could improve the skills of a belayer and hence alleviate the severity of the injuries.

Dimension Reduction Using Image Transform for Content-Based Feature Extraction

2018 ◽  
pp. 26-40
Author(s):  
Sourav De ◽  
Madhumita Singha ◽  
Komal Kumari ◽  
Ritika Selot ◽  
Akshat Gupta
Keyword(s):  
Feature Extraction ◽  
Dimension Reduction ◽  
Image Feature ◽  
Extraction Technique ◽  
Image Transform ◽  
Improved Performance ◽  
Different Color ◽  
Feature Dimension ◽  
Feature Extraction Technique ◽  
Feature Dimension Reduction

Technological advancements in the field of machine learning have attempted classification of the images of gigantic datasets. Classification with content-based image feature extraction categorizes the images based on the image content in contrast to conventional text-based annotation. The chapter has presented a feature extraction technique based on application of image transform. The method has extracted meaningful features and facilitated feature dimension reduction. A technique, known as fractional coefficient of transforms, is adopted to facilitate feature dimension reduction. Two different color spaces, namely RGB and YUV, are considered to compare the classification metrics to figure out the best possible reduced feature dimension. Further, the results are compared to state-of-the-art techniques which have revealed improved performance for the proposed feature extraction technique.

scholarly journals Feature Dimension Reduction Using Stacked Sparse Auto-Encoders for Crop Classification with Multi-Temporal, Quad-Pol SAR Data

2020 ◽  
Vol 12 (2) ◽  
pp. 321
Author(s):  
Jiao Guo ◽  
Henghui Li ◽  
Jifeng Ning ◽  
Wenting Han ◽  
Weitao Zhang ◽  
...  
Keyword(s):  
Dimension Reduction ◽  
Classification Accuracy ◽  
Short Term Memory ◽  
European Space Agency ◽  
Agricultural Crop ◽  
Temporal Data ◽  
Multi Temporal ◽  
Crop Classification ◽  
Feature Dimension ◽  
Feature Dimension Reduction

Crop classification in agriculture is one of important applications for polarimetric synthetic aperture radar (PolSAR) data. For agricultural crop discrimination, compared with single-temporal data, multi-temporal data can dramatically increase crop classification accuracies since the same crop shows different external phenomena as it grows up. In practice, the utilization of multi-temporal data encounters a serious problem known as a “dimension disaster”. Aiming to solve this problem and raise the classification accuracy, this study developed a feature dimension reduction method using stacked sparse auto-encoders (S-SAEs) for crop classification. First, various incoherent scattering decomposition algorithms were employed to extract a variety of detailed and quantitative parameters from multi-temporal PolSAR data. Second, based on analyzing the configuration and main parameters for constructing an S-SAE, a three-hidden-layer S-SAE network was built to reduce the dimensionality and extract effective features to manage the “dimension disaster” caused by excessive scattering parameters, especially for multi-temporal, quad-pol SAR images. Third, a convolutional neural network (CNN) was constructed and employed to further enhance the crop classification performance. Finally, the performances of the proposed strategy were assessed with the simulated multi-temporal Sentinel-1 data for two experimental sites established by the European Space Agency (ESA). The experimental results showed that the overall accuracy with the proposed method was raised by at least 17% compared with the long short-term memory (LSTM) method in the case of a 1% training ratio. Meanwhile, for a CNN classifier, the overall accuracy was almost 4% higher than those of the principle component analysis (PCA) and locally linear embedded (LLE) methods. The comparison studies clearly demonstrated the advantage of the proposed multi-temporal crop classification methodology in terms of classification accuracy, even with small training ratios.

Sign in / Sign up

Export Citation Format

Share Document