Mathematical Problems in Engineering / 2017 / Article / Tab 1

Research Article

A New Terrain Classification Framework Using Proprioceptive Sensors for Mobile Robots

Table 1

Accuracies with individual data source and handcrafted feature vector at 2 m/s.

Data sourceFeature vectorSVMRFkNNNB

Acoustics MMFCC89.6%87.1%80.8%77.9%
FFT82.9%70%56.7%55.4%
Gianna and shape58.8%67.9%53.8%64.2%

Wheel vibration Temporal68.3%62.5%62.1%56.3%
FFT90.4%89.2%75.4%84.6%
Frequency characteristics59.6%64.2%62.5%51.7%

Centroid vibration
-Axes
Temporal41.7%52.9%51.3%47.5%
FFT94.2%92.9%72.1%88.3%
Frequency characteristics46.7%54.2%47.1%44.2%

Centroid vibration
-Axes
Temporal42.5%44.2%50%46.7%
FFT92.1%93%91.3%88.2%
Frequency characteristics44.6%44.6%46.7%45.1%

Centroid vibration
-Axes
Temporal44.2%46.3%50%45.5%
FFT93.3%92.9%91.3%90.8%
Frequency characteristics42.5%48.3%46.7%42.5%

We are committed to sharing findings related to COVID-19 as quickly and safely as possible. Any author submitting a COVID-19 paper should notify us at help@hindawi.com to ensure their research is fast-tracked and made available on a preprint server as soon as possible. We will be providing unlimited waivers of publication charges for accepted articles related to COVID-19. Sign up here as a reviewer to help fast-track new submissions.