Feature‐selection ability of the decision‐tree algorithm and the impact of feature‐selection/extraction on decision‐tree results based on hyperspectral data

2008 ◽  
Vol 29 (10) ◽  
pp. 2993-3010 ◽  
Author(s):  
Y. Y. Wang ◽  
J. Li
Author(s):  
Shahadat Iqbal ◽  
Taraneh Ardalan ◽  
Mohammed Hadi ◽  
Evangelos Kaisar

Transit signal priority (TSP) and freight signal priority (FSP) allow transportation agencies to prioritize signal service allocations considering the priority of vehicles and, potentially, decrease the impact signal control has on them. However, there have been no studies to develop guidelines for implementing signal control considering both TSP and FSP. This paper reports on a study conducted to provide such guidelines that employed a literature review, a simulation study, and a decision tree algorithm based on the simulation results. The guideline developed provides recommendations in accordance with the signal timing slack time, the proportion of major to minor street hourly volume, hourly truck volume per lane for the major street, hourly truck volume per lane for the minor street, the proportion of major to minor street hourly truck volume, the proportion of major to minor street hourly bus volume, the volume-to-capacity ratio for the major street, and the volume-to-capacity ratio for the minor street. The guideline developed was validated by implementing it for a case study facility. The validation result showed that the guideline works correctly for both high and low traffic demand.


2021 ◽  
Author(s):  
Simón Marín Giraldo ◽  
Miguel Fernando Ramos García ◽  
Mauricio Toro

Coffee is one of the most important products for colombianeconomy because it represents 6.9% of our exportations,contributing $2.7 billion dollars to our country each year.Coffee rust is a plague that affects plants leavingdevastating loss in agricultural industry around the world.Coffee industry loses more than 30% of the productionbecause of rust.It is necessary to create a solution to reduce the impact ofthis plague and returning greater profits (or smaller loss) tocolombian coffee industry. We proposed a decision treedata structure which determines if a coffee crop has coffeeleaf rust. A decision tree algorithm learns from the data itanalyzes and it determines the existence of rust with moreease each time you pass it new data.


Author(s):  
GUOLIANG QIAN ◽  
DANIEL YEUNG ◽  
ERIC C. C. TSANG ◽  
WENHAO SHU

Feature selection is a difficult but important issue in the field of machine learning and pattern recognition. In this paper, features for Chinese character recognition are selected by using inductive learning algorithms. The existing inductive learning method based on extension matrix requires precise consistency between positive example and negative example sets, which is very difficult to maintain in most practical cases. The traditional decision tree algorithm ID3 considers only the performance of the discriminating power while selecting features. However, in actual practice the consideration of the associated cost of feature extraction may become a significant concern. In addressing these problems we propose a modified extension matrix approach to select feature subset from the training example set with noises. A decision tree algorithm based on information gain and cost evaluation is also proposed to facilitate cost consideration. The comparative experiments show that the proposed algorithms perform better than the existing inductive learning algorithms to a certain extent.


2021 ◽  
Vol 1869 (1) ◽  
pp. 012082
Author(s):  
B A C Permana ◽  
R Ahmad ◽  
H Bahtiar ◽  
A Sudianto ◽  
I Gunawan

Sign in / Sign up

Export Citation Format

Share Document