ImpSlidingWindow: A New Model to Improve the Performance of the Sliding Window Based Streaming Data Summarization Method

Öz

Sliding window based data summarization which is a quantity based summarization is commonly used in data stream clustering area in which the recent data is more important. In this data summarization method, w which is a predefined variable, of the most recent data is taken as the summary each time a new data arrives and the window slides one by one. This means that the model processes all the data in the data window each time a new data arrives. This approach causes the performance to reduce. Therefore, there is a need of new studies to be proposed in this area. In this study, a new sliding window model named ImpSlidingWindow (ISW) is proposed as a solution to the mentioned problem. In the proposed model, we propose that clustering model to work whenever a certain number of data accumulates instead of each data entry. With this new model, the sliding window width is divided into four equal parts and the clustering model works at the end of each part. As a result, a significant increase in the performance is achieved by enabling the clustering model to run four times instead of working as much as the number of data in the window width. When the proposed model applied to KD-AR Stream algorithm which is a proposed algorithm in the data stream clustering area, it has been found that up to 80% improvement obtained in run-time complexity.

Anahtar Kelimeler

• Data stream clustering
• data summarization
• sliding window

ImpSlidingWindow: Kayan Pencere Tabanlı Akan Veri Özetleme Yönteminin Performansını Arttırmaya Yönelik Yeni Bir Model

Öz

Kayan pencere tabanlı veri özetleme, akan veri kümeleme alanında son gelen verilerin daha önemli olduğu uygulamalarda sıkça kullanılan miktar tabanlı bir veri özetleme yaklaşımıdır. Bu veri özetleme yaklaşımında, her yeni veri gelişinde ön tanımlı bir değişken olan en son gelen w tane veri özet olarak alınır ve pencere birer birer kaymaktadır. Yani model her yeni veri girişinde veri penceresinde bulunan tüm verileri işler. Bu da performansı olumsuz etkilemektedir. Bu nedenle bu probleme çözüm üretecek çalışmalara ihtiyaç duyulmaktadır. Bu çalışmada sözü edilen probleme çözüm olarak ImpSlidingWindow (ISW) isimli yeni bir kayan pencere modeli önerilmektedir. Önerilen modelde her veri girişinde kümeleme modelinin çalışması yerine belirli sayıda veri biriktikçe kümeleme modelinin çalışması önerilmektedir. Bu yeni model ile kayan pencere genişliği dört eşit parçaya bölünmekte ve her parçanın sonunda kümeleme modelinin çalışması sağlanmaktadır. Sonuç olarak pencere genişliğinde bulunan veri sayısı kadar kümeleme modelinin çalışması yerine dört defa çalışması sağlanarak performansta çok önemli bir artış sağlanmaktadır. Önerilen model akan veri kümeleme alanında önerilmiş bir algoritma olan KD-AR Stream algoritmasına uygulandığında çalışma zamanında %80’lara varan iyileştirmeler elde edilmiştir.

Anahtar Kelimeler

• Akan veri kümeleme
• veri özetleme
• kayan pencereler

Kaynakça

1. Ackermann, M. R., Martens, M., Raupach, C., Swierkot, K., Lammersen, C. ve Sohler, C. (2012). StreamKM++: A clustering algorithm for data streams. J. Exp. Algorithmics, 17, 2.1-2.30. doi:10.1145/2133803.2184450
2. Aggarwal, C. C. (2010). Data Streams: An Overview and Scientific Applications. In M. M. Gaber (Ed.), Scientific Data Mining and Knowledge Discovery: Principles and Foundations (pp. 377-397). Berlin, Heidelberg: Springer Berlin Heidelberg.
3. Aggarwal, C. C., Han, J., Wang, J. ve Yu, P. S. (2003). A framework for clustering evolving data streams. Paper presented at the Proceedings of the 29th international conference on Very large data bases - Volume 29, Berlin, Germany.
4. Ahmed, M. (2019). Buffer-based Online Clustering for Evolving Data Stream. Information Sciences. doi:https://doi.org/10.1016/j.ins.2019.03.022
5. AlNuaimi, N., Masud, M. M., Serhani, M. A. ve Zaki, N. (2019). Streaming feature selection algorithms for big data: A survey. Applied Computing and Informatics. doi:https://doi.org/10.1016/j.aci.2019.01.001
6. Amini, A. ve Wah, T. Y. (2013). LeaDen-Stream: A Leader Density-Based Clustering Algorithm over Evolving Data Stream. Journal of Computer and Communications, 1, 26-31. doi:10.4236/jcc.2013.15005
7. Ankleshwaria, T. B. ve Dhobi, J. S. (2014). Mining Data Streams: A Survey. International Journal of Advance Research in Computer Science and Management Studies, 2(2), 379-386.
8. Antonellis, P., Makris, C. ve Tsirakis, N. (2009). Algorithms for clustering clickstream data. Information Processing Letters, 109(8), 381-385. doi:https://doi.org/10.1016/j.ipl.2008.12.011

9. Badiozamany, S., Orsborn, K. ve Risch, T. (2016). Framework for real-time clustering over sliding windows. Paper presented at the Proceedings of the 28th International Conference on Scientific and Statistical Database Management, Budapest, Hungary.
10. Cao, F., Estert, M., Qian, W. ve Zhou, A. Density-Based Clustering over an Evolving Data Stream with Noise Proceedings of the 2006 SIAM International Conference on Data Mining (pp. 328-339).
11. Chairukwattana, R., Kangkachit, T., Rakthanmanon, T. ve Waiyamai, K. (2013, 4-6 Sept. 2013). Efficient evolution-based clustering of high dimensional data streams with dimension projection. Paper presented at the 2013 International Computer Science and Engineering Conference (ICSEC).
12. Charu, C. A., Jiawei, H., Jianyong, W. ve Philip, S. Y. (2004). A framework for projected clustering of high dimensional data streams Proceedings of the Thirtieth international conference on Very large data bases - Volume 30 %@ 0-12-088469-0 (pp. 852-863). Toronto, Canada: VLDB Endowment.
13. Datar, M., Gionis, A., Indyk, P. ve Motwani, R. (2002). Maintaining stream statistics over sliding windows: (extended abstract). Paper presented at the Proceedings of the thirteenth annual ACM-SIAM symposium on Discrete algorithms, San Francisco, California.
14. Diaz-Rozo, J., Bielza, C. ve Larrañaga, P. (2018). Clustering of Data Streams with Dynamic Gaussian Mixture Models. An IoT Application in Industrial Processes. IEEE Internet of Things Journal, 1-1. doi:10.1109/JIOT.2018.2840129
15. Gao, J., Li, J., Zhang, Z. ve Tan, P.-N. (2005). An Incremental Data Stream Clustering Algorithm Based on Dense Units Detection, Berlin, Heidelberg.
16. Görmüş, S., Aydın, H. ve Ulutaş, G. (2018). Nesnelerin interneti teknolojisi için güvenlik: Var olan mekanizmalar, protokoller ve yaşanılan zorlukların araştırılması. Gazi Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi, 33, 1247-1272.
17. Gravina, R., Alinia, P., Ghasemzadeh, H. ve Fortino, G. (2017). Multi-sensor fusion in body sensor networks: State-of-the-art and research challenges. Information Fusion, 35, 68-80. doi:https://doi.org/10.1016/j.inffus.2016.09.005
18. Guha, S., Rastogi, R. ve Shim, K. (2001). Cure: an efficient clustering algorithm for large databases. Information Systems, 26(1), 35-58. doi:https://doi.org/10.1016/S0306-4379(01)00008-4
19. Hahsler, M. ve Bolaños, M. (2016). Clustering Data Streams Based on Shared Density between Micro-Clusters. IEEE Transactions on Knowledge and Data Engineering, 28(6), 1449-1461. doi:10.1109/TKDE.2016.2522412
20. Hendricks, D. (2017). Using real-time cluster configurations of streaming asynchronous features as online state descriptors in financial markets. Pattern Recognition Letters, 97, 21-28. doi:https://doi.org/10.1016/j.patrec.2017.06.026
21. Hyde, R., Angelov, P. ve MacKenzie, A. R. (2017). Fully online clustering of evolving data streams into arbitrarily shaped clusters. Information Sciences, 382-383, 96-114. doi:https://doi.org/10.1016/j.ins.2016.12.004
22. Ikonomovska, E., Loskovska, S. ve Gjorgjevik, D. (2007). A survey of stream data mining. Paper presented at the Eighth International Conference with International Participation – ETAI 2007, Ohrid, Republic ofMacedonia.
23. Jia, C., Tan, C. ve Yong, A. (2008, 25-26 Sept. 2008). A Grid and Density-Based Clustering Algorithm for Processing Data Stream. Paper presented at the 2008 Second International Conference on Genetic and Evolutionary Computing.
24. Kanmaz, M. ve Aydin, M. A. (2018). Kablosuz Sensör Ağlarda Konumlandırma Yöntemleri ve K-means++ Kümeleme Yöntemi ile Yeni Yaklaşım. Gazi Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi, 2018, 0-0.
25. Keim, D. A. ve Heczko, M. (2001). Wavelets and their Applications in Databases. Paper presented at the 17th International Conference on Data Engineering (ICDE'01), Heidelberg, Germany, 2001.
26. King, R. C., Villeneuve, E., White, R. J., Sherratt, R. S., Holderbaum, W. ve Harwin, W. S. (2017). Application of data fusion techniques and technologies for wearable health monitoring. Medical Engineering & Physics, 42, 1-12. doi:https://doi.org/10.1016/j.medengphy.2016.12.011
27. Kranen, P., Assent, I., Baldauf, C. ve Seidl, T. (2011). The ClusTree: indexing micro-clusters for anytime stream mining. Knowledge and Information Systems, 29(2), 249-272. doi:10.1007/s10115-010-0342-8
28. Laohakiat, S., Phimoltares, S. ve Lursinsap, C. (2017). A clustering algorithm for stream data with LDA-based unsupervised localized dimension reduction. Information Sciences, 381, 104-123. doi:https://doi.org/10.1016/j.ins.2016.11.018
29. Li, Z. Q. (2014). A New Data Stream Clustering Approach about Intrusion Detection. Advanced Materials Research, 926-930, 2898-2901. doi:10.4028/www.scientific.net/AMR.926-930.2898
30. Manzi, A., Dario, P. ve Cavallo, F. (2017). A Human Activity Recognition System Based on Dynamic Clustering of Skeleton Data. Sensors (Basel, Switzerland), 17(5), 1100. doi:10.3390/s17051100
31. Martín, A., Julián, A. B. A. ve Cos-Gayón, F. (2019). Analysis of Twitter messages using big data tools to evaluate and locate the activity in the city of Valencia (Spain). Cities, 86, 37-50. doi:https://doi.org/10.1016/j.cities.2018.12.014
32. Ntoutsi, I., Zimek, A., Palpanas, T., Kröger, P. ve Kriegel, H.-P. (2012). Density-based Projected Clustering over High Dimensional Data Streams. Paper presented at the SIAM International Conference on Data Mining.
33. O'Callaghan, L., Mishra, N., Meyerson, A., Guha, S. ve Motwani, R. (2002, 26 Fe.-1 March 2002). Streaming-data algorithms for high-quality clustering. Paper presented at the Proceedings 1st International Conference on Data Engineering, San Jose, CA, USA, USA.
34. Oussous, A., Benjelloun, F.-Z., Ait Lahcen, A. ve Belfkih, S. (2018). Big Data technologies: A survey. Journal of King Saud University - Computer and Information Sciences, 30(4), 431-448. doi:https://doi.org/10.1016/j.jksuci.2017.06.001
35. Reddy, K. S. S. ve Bindu, C. S. (2018). StreamSW: A Density-based Approach for Clustering Data Streams over Sliding Windows. Measurement. doi:https://doi.org/10.1016/j.measurement.2018.11.041
36. Ren, J. ve Ma, R. (2009, 14-16 Aug. 2009). Density-Based Data Streams Clustering over Sliding Windows. Paper presented at the 2009 Sixth International Conference on Fuzzy Systems and Knowledge Discovery.
37. Silva, J. d. A., Hruschka, E. R. ve Gama, J. (2017). An evolutionary algorithm for clustering data streams with a variable number of clusters. Expert Syst. Appl., 67(C), 228-238. doi:10.1016/j.eswa.2016.09.020
38. Şenol, A. ve Karacan, H. (2018). A Survey on Data Stream Clustering Techniques. European Journal of Science and Technology(13), 17-30.
39. Şenol, A. ve Karacan, H. (2019). K-boyutlu ağaç ve uyarlanabilir yarıçap (KD-AR Stream) tabanlı gerçek zamanlı akan veri kümeleme. Gazi Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi, (Basımda).
40. Tasnim, S., Caldas, J., Pissinou, N., Iyengar, S. S. ve Ding, Z. (2018, 5-8 March 2018). Semantic-Aware Clustering-based Approach of Trajectory Data Stream Mining. Paper presented at the 2018 International Conference on Computing, Networking and Communications (ICNC).
41. Tu, L. ve Chen, Y. (2009). Stream data clustering based on grid density and attraction. ACM Trans. Knowl. Discov. Data, 3(3), 1-27. doi:10.1145/1552303.1552305 Udommanetanakit, K., Rakthanmanon, T. ve Waiyamai, K. (2007). E-Stream: Evolution-Based Technique for Stream Clustering, Berlin, Heidelberg.
42. Wan, L., Ng, W. K., Dang, X. H., Yu, P. S. ve Zhang, K. (2009). Density-based clustering of data streams at multiple resolutions. ACM Trans. Knowl. Discov. Data, 3(3), 1-28. doi:10.1145/1552303.1552307
43. Wang, W., Yang, J. ve Muntz, R. R. (1997). STING: A Statistical Information Grid Approach to Spatial Data Mining. Paper presented at the Proceedings of the 23rd International Conference on Very Large Data Bases.
44. Xu, J., Wang, G., Li, T., Deng, W. ve Gou, G. (2017). Fat node leading tree for data stream clustering with density peaks. Knowledge-Based Systems, 120, 99-117. doi:https://doi.org/10.1016/j.knosys.2016.12.025
45. Yin, C., Xia, L. ve Wang, J. (2017, 2017). Application of an Improved Data Stream Clustering Algorithm in Intrusion Detection System. Paper presented at the Advanced Multimedia and Ubiquitous Engineering, Singapore.
46. Yin, C., Xia, L. ve Wang, J. (2018, 2018). Data Stream Clustering Algorithm Based on Bucket Density for Intrusion Detection. Paper presented at the Advances in Computer Science and Ubiquitous Computing, Singapore.