English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This paper develops a novel two-layer hierarchical classifier that increasesthe accuracy of traditional transportation mode classification algorithms. Thispaper also enhances classification accuracy by extracting new frequency domainfeatures. Many researchers have obtained these features from global positioningsystem data; however, this data was excluded in this paper, as the system usemight deplete the smartphone's battery and signals may be lost in some areas.Our proposed two-layer framework differs from previous classification attemptsin three distinct ways: 1) the outputs of the two layers are combined usingBayes' rule to choose the transportation mode with the largest posteriorprobability; 2) the proposed framework combines the new extracted features withtraditionally used time domain features to create a pool of features; and 3) adifferent subset of extracted features is used in each layer based on theclassified modes. Several machine learning techniques were used, includingk-nearest neighbor, classification and regression tree, support vector machine,random forest, and a heterogeneous framework of random forest and supportvector machine. Results show that the classification accuracy of the proposedframework outperforms traditional approaches. Transforming the time domainfeatures to the frequency domain also adds new features in a new space andprovides more control on the loss of information. Consequently, combining thetime domain and the frequency domain features in a large pool and then choosingthe best subset results in higher accuracy than using either domain alone. Theproposed two-layer classifier obtained a maximum classification accuracy of97.02%.

Smartphone Transportation Mode Recognition Using a Hierarchical Machine Learning Classifier and Pooled Features From Time and Frequency Domains