scholarly journals Splitting Choice and Computational Complexity Analysis of Decision Trees

Entropy ◽  
2021 ◽  
Vol 23 (10) ◽  
pp. 1241
Author(s):  
Xin Zhao ◽  
Xiaokai Nie
Keyword(s):  
Computational Complexity ◽  
Decision Trees ◽  
Missing Values ◽  
Complexity Analysis ◽  
Original Data ◽  
Theoretical Support ◽  
Entropy Information ◽  
Building Process ◽  
Tree Building ◽  
Complexity Increase

Some theories are explored in this research about decision trees which give theoretical support to the applications based on decision trees. The first is that there are many splitting criteria to choose in the tree growing process. The splitting bias that influences the criterion chosen due to missing values and variables with many possible values has been studied. Results show that the Gini index is superior to entropy information as it has less bias regarding influences. The second is that noise variables with more missing values have a better chance to be chosen while informative variables do not. The third is that when there are many noise variables involved in the tree building process, it influences the corresponding computational complexity. Results show that the computational complexity increase is linear to the number of noise variables. So methods that decompose more information from the original data but increase the variable dimension can also be considered in real applications.

Complexity Issues within Eigenvalue-Based Multi-Antenna Spectrum Sensing

2015 ◽  
pp. 603-617 ◽  
Author(s):  
Ines Elleuch ◽  
Fatma Abdelkefi ◽  
Mohamed Siala
Keyword(s):  
Computational Complexity ◽  
False Alarm ◽  
Spectrum Sensing ◽  
Complexity Analysis ◽  
Floating Point ◽  
Beam Forming ◽  
Multiple Antenna ◽  
Deep Insight ◽  
Minimum Eigenvalue ◽  
Insight Into

This chapter provides a deep insight into multiple antenna eigenvalue-based spectrum sensing algorithms from a complexity perspective. A review of eigenvalue-based spectrum-sensing algorithms is provided. The chapter presents a finite computational complexity analysis in terms of Floating Point Operations (flop) and a comparison of the Maximum-to-Minimum Eigenvalue (MME) detector and a simplified variant of the Multiple Beam forming detector as well as the Approximated MME method. Constant False Alarm Performances (CFAR) are presented to emphasize the complexity-reliability tradeoff within the spectrum-sensing problem, given the strong requirements on the sensing duration and the detection performance.

Building a Search Tree for a Pilot System of a Rescue Search Robot in a Discretized Random Step Environment

2011 ◽  
Vol 23 (4) ◽  
pp. 567-581 ◽  
Author(s):  
Evgeni Magid ◽  
◽  
Takashi Tsubouchi ◽  
Eiji Koyanagi ◽  
Tomoaki Yoshida ◽  
...  
Keyword(s):  
Search Algorithm ◽  
Search Space ◽  
Search Tree ◽  
Quality Estimation ◽  
Dynamic Path Planning ◽  
Building Process ◽  
Path Search ◽  
Tree Building ◽  
Random Step ◽  
Real State

Rescue robotics applies search and rescue robots to expand rescue capabilities while increasing safety. Mobile robots working at a disaster site are monitored remotely by operators who may not be able to see the site well and select work paths appropriately. Our goal is to provide a “pilot system” that can propose options for traversing 3D debris environments. This requires a special debris path search algorithm and an appropriately defined search tree ensuring smooth exploration. To make a path search feasible in huge real state space we discretize search space and robot movement before a search. In this paper we present path quality estimation and search tree branching functionF, which defines search tree building process online through node opening and branching. Well-defined functionFremoves unsuitable search directions from the search tree and enables dynamic path planning accounting for debris. Exhaustive simulation was used to structure and analyze data. Experiments confirmed the feasibility of our approach.

Computational Complexity Analysis of Selective Breeding Algorithm

2014 ◽  
Vol 591 ◽  
pp. 172-175
Author(s):  
M. Chandrasekaran ◽  
P. Sriramya ◽  
B. Parvathavarthini ◽  
M. Saravanamanikandan
Keyword(s):  
Computational Complexity ◽  
Selective Breeding ◽  
Heuristic Algorithms ◽  
Complexity Analysis ◽  
Optimization Problems ◽  
Optimal Solution ◽  
Approximate Solutions ◽  
Problem Size ◽  
Combinatorial Optimization Problems ◽  
Complete Problems

In modern years, there has been growing importance in the design, analysis and to resolve extremely complex problems. Because of the complexity of problem variants and the difficult nature of the problems they deal with, it is arguably impracticable in the majority time to build appropriate guarantees about the number of fitness evaluations needed for an algorithm to and an optimal solution. In such situations, heuristic algorithms can solve approximate solutions; however suitable time and space complication take part an important role. In present, all recognized algorithms for NP-complete problems are requiring time that's exponential within the problem size. The acknowledged NP-hardness results imply that for several combinatorial optimization problems there are no efficient algorithms that realize a best resolution, or maybe a close to best resolution, on each instance. The study Computational Complexity Analysis of Selective Breeding algorithm involves both an algorithmic issue and a theoretical challenge and the excellence of a heuristic.

Sign in / Sign up

Export Citation Format

Share Document