Criminal investigation plays an important role in
law enforcement agencies while analyzing crimes. This can
help in finding suspects and for better attribution of past
crimes. So the use of pattern based approaches will have the
potential to assist crime analyze experts in discovering new
patterns of criminal activities. So the research is extended in
this area in finding new crime patterns. Since frequent
pattern mining problem has been introduced, researchers
have been developed many ways and also extended to
different useful emerging patterns such as closed, maximal,
cyclic, periodic, and popular patterns. In this paper, we
introduced popular crime patterns which give the popularity
of each crime or incident among the entire crime database.
The process used for mining popular crime patterns is
discussed as PCrime-growth algorithm. The compact data
structure called PCrime-tree is implemented in this
algorithm. Finally our experiment results have been shown
which gives information of compact, space efficient and time
efficient of our proposed algorithm.
B.V.S.Varma : is Associate Professor in the department of Computer
Science & Engineering at Ideal Institute of Technology, India. He
obtained M.Tech degree in CSE from Dr. M.G.R.University and
B.Tech in CSE from Madras University. He has 13 years of Teaching
Experience He research interest includes Data Mining.
V.Valli Kumari : is professor in the department of Computer Science
& Systems Engineering and Director of Computer Center at Andhra
University, India. She has received best Researcher Award from the
same university. She has 17 years of teaching experience and guided
several Ph.Ds. she is an active researcher and executed several
research projects. She has published more than 120 research papers
in international conferences and journals, authored several book
chapters and chaired several international conferences.
Crime Patterns
Popular Patterns
Crime
databases
PCrime-growth
In this paper we introduced a new algorithm called
PCrime-growth algorithm that finds popular crime
patterns from Crime datasets. With the first database scan
it constructs PCrime-tree and also computes support of a
crime, maximum crime transaction length and popularity
of each crime. After that the algorithm performs for
super-pattern popularity for unpopular crimes to prune the
crime database. After second scan its going to compute
length of each crime transaction by eliminates unpopular
crimes and will extracts popular crime patterns from the
crime databases. Our experimental results showed that
our PCrime-tree is time and space efficient for both sparse
and dense datasets. In addition these results are also
affected on crime datasets on construction of PCrime-tree
and mining of popular crime patterns to be time efficient.
[1] N. G. Khan, V. Bhaga, Effective data mining
approach for crime-terrorpattern detection using
clustering algorithm technique, Engineering
Research and Technology International Journal
Vol 2 (4) (2013), pp. 20432048.
[2] H. Chen, W. Chung, J. Xu, G. Wang, Y. Qin, M.
Chau, Crime data mining: A general framework
and some examples, IEEE Computer Journal 37
(4) (2004) 5056.
[3] Mohammad, J. Mohsen, E. Martin, G. Uwe, F.
Richard, Crimewalker: A recommendation
model for suspect investigation, in: Proc. fifth
ACM conference on Recommender systems,
ACM, 2011, pp. 18.
[4] O. Isafiade, A. Bagula, Citisafe: Adaptive spatial
pattern knowledge using fp-growth algorithm for
crime situation recognition, in: Proc. IEEE
International Conference on Ubiquitous
Intelligence and Computing, IEEE, 2013, pp.
551556.
[5] P. Phillips, I. Lee, Mining co-distribution
patterns for large crime datasets, Expert Systems
with Applications International Journal 39 (14)
(2012) 1155611563.
[6] D. Wang, W. Ding, H. Lo, T. Stepinski, J.
Salazar, M. Morabito, Crime hotspot mapping
using the crime related factors- a spatial data
mining approach, Applied Intelligence Journal
39 (4) (2013) 772781.
[7] Agrawal, R., Srikant, R.: Fast algorithms for
mining association rules. In: VLDB, 1994, pp.
487499 (1994).
[8] Han, J., Pei, J., Yin, Y.: Mining frequent
patterns without candidate generation. In: ACM
SIGMOD 2000, pp. 112 (2000).
[9] Lee, Y.-K., Kim, W.-Y., Cai, Y.D., Han, J.:
CoMine: efficient mining of correlated patterns.
In: IEEE ICDM 2003, pp. 581584 (2003).
[10] Rasheed, F., Alshalalfa, M., Alhajj, R.: Efficient
periodicity mining in time series databases using
suffix trees. IEEE TKDE 23(1), 7994 (2011).
[11] Zhang, M., Kao, B., Cheung, D.W., Yip, K.Y.:
Mining periodic patterns with gap requirement
from sequences. ACM TKDD, 1(2), art. 7
(2007).
[12] Lakshmanan,L.V.S., Leung, C.K.-
S.,Ng,R.T.:Efficient dynamic mining of
constrained frequent sets. ACM TODS 28(4),
337389 (2003).
[13] Leung, C.K.-S., Sun, L.: A new class of
constraints for constrained frequent pattern
mining. In: ACM SAC 2012, pp. 199204
(2012).
[14] Xiong, H., Tan, P.-N., Kumar, V.: Hyperclique
pattern discovery. Data Mining and Knowledge
Discovery 13(2), 219242 (2006).
[15] Yao, H., Hamilton, H.J.: Mining itemset utilities
from transaction databases. DKE 59(3), 603626
(2006).
[16] Leung C.K.-S., Tanbeer S.K.: Mining Popular
Patterns from Transactional Databases. Springer
DaWak 2012, 291-302 (2012).
[17] Leung C.K.-S., Tanbeer S.K.: Finding Popular
Friends in Social Networks. IEEE Second
International Conference on Cloud and Green
Computing, 501-508 (2012).
[18] Omowunmi Isafiade, Antoine Bagula, Sonia
Berman.: A Revised Frequenrt Pattern Model for
Crime Situation Recognition Based on Floor-Ceil
Quartile Function. Elsevier Science Direct,
Procedia Computer Science 55 (2015), 251-260.
[19] Brown, D.E. The regional crime analysis
program (RECAP): A frame work for mining
data to catch criminals," in Proceedings of the