Accesso libero

Temporal association rules discovery algorithm based on improved index tree

Chen Yuanyuan

Chen Yuanyuan

Department of Management and Economics, Naval University of EngineeringWuhan, China
Cerca questo autore su
Sciendo|Google Scholar
Yuanyuan, Chen
, 
Wang Rui

Wang Rui

Teaching and Research Support Center, Naval University of EngineeringWuhan, China
Cerca questo autore su
Sciendo|Google Scholar
Rui, Wang
, 
Zeng Bin

Zeng Bin

Department of Management and Economics, Naval University of EngineeringWuhan, China
Cerca questo autore su
Sciendo|Google Scholar
Bin, Zeng
 e 
W. S. Griffith

W. S. Griffith

Cerca questo autore su
Sciendo|Google Scholar
Griffith, W. S.
  
19 mar 2021
Temporal association rules discovery algorithm based on improved index tree's Cover Image
INFORMAZIONI SU QUESTO ARTICOLO
Articolo precedente
Articolo Successivo
Cita
Scarica la copertina
Pubblicato online: 19 mar 2021
Pagine: 115 - 128
Ricevuto: 01 dic 2020
Accettato: 31 gen 2021
DOI: https://doi.org/10.2478/amns.2021.1.00016
Parole chiave
© 2020 Chen Yuanyuan et al., published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.

Fig. 1

Discretising the continuous domain.
Discretising the continuous domain.

Fig. 2

Graph representation of transactions in example 1.
Graph representation of transactions in example 1.

Fig. 3

The Apriori-modified algorithm.
The Apriori-modified algorithm.

Fig. 4

Function join.
Function join.

Fig. 5

Steps to find frequent intervals by using the Apriori-modified algorithm.
Steps to find frequent intervals by using the Apriori-modified algorithm.

Fig. 6

An example of an index-tree.
An example of an index-tree.

Fig. 7

Algorithm insert.
Algorithm insert.

Fig. 8

Algorithm index-tree method.
Algorithm index-tree method.

Fig. 9

Function count.
Function count.

Fig. 10

An example of 2-d intervals.
An example of 2-d intervals.

Fig. 11

An example of sub-intervals.
An example of sub-intervals.

Fig. 12

Runtime vs.number of transactions (n = 100, m = 5%, s = 5%).
Runtime vs.number of transactions (n = 100, m = 5%, s = 5%).

Fig. 13

Runtime vs. mean interval length (d = 10k, n = 100, s = 5%).
Runtime vs. mean interval length (d = 10k, n = 100, s = 5%).

Fig. 14

Runtime vs. support threshold (d = 100k, n = 100, m = 5%).
Runtime vs. support threshold (d = 100k, n = 100, m = 5%).

Fig. 15

Runtime vs. number of unit intervals (d = 10K, m = 5%, s = 5%).
Runtime vs. number of unit intervals (d = 10K, m = 5%, s = 5%).

Fig. 16

Runtime vs. number of dimensions (d = 10K, n = 10, m = 40%, s = 30%).
Runtime vs. number of dimensions (d = 10K, n = 10, m = 40%, s = 30%).

Fig. 17

Runtime vs. memory size (d = 10K, n = 100, m = 5%, s = 0.5%).
Runtime vs. memory size (d = 10K, n = 100, m = 5%, s = 0.5%).

All frequent intervals and their supports

ID Starting Ending Support ID Starting Ending Support
1 2 2 2/5 12 5 6 3/5
2 3 3 1/2 13 6 7 7/10
3 4 4 1/2 14 7 8 3/5
4 5 5 3/5 15 8 9 2/5
5 6 6 4/5 16 4 6 2/5
6 7 7 7/10 17 5 7 1/2
7 8 8 3/5 18 6 8 3/5
8 9 9 2/5 19 7 9 2/5
9 2 3 2/5 20 5 8 2/5
10 3 4 2/5 21 6 9 2/5
11 4 5 2/5
Lingua:
Inglese
Frequenza di pubblicazione:
1 volte all'anno
Argomenti della rivista:
Scienze biologiche, Scienze della vita, altro, Matematica, Matematica applicata, Matematica generale, Fisica, Fisica, altro
Feed RSS della rivista