Sains Malaysiana 49(4)(2020): 963-970

http://dx.doi.org/10.17576/jsm-2020-4904-25

Pendekatan Baharu untuk Mengelompok Stesen Pengawasan Kualiti Udara menggunakan Homologi Gigih

(A New Approach to Cluster Air Quality Monitoring Stations using Persistent Homology)

NUR FARIHA SYAQINA ZULKEPLI*, MOHD SALMI MD NOORANI, FATIMAH ABDUL RAZAK, MUNIRA ISMAIL & MOHD ALMIE ALIAS

Fakulti Sains dan Teknologi, Universiti Kebangsaan Malaysia, 43600 UKM Bangi, Selangor Darul Ehsan, Malaysia

Diserahkan: 28 Ogos 2019/Diterima: 14 Disember 2019

ABSTRAK

Isu pencemaran udara merupakan masalah global yang terus dibincangkan sehingga kini. Seringkali penggunaan pendekatan kuantitatif seperti analisis kelompok, analisis korelasi dan analisis komponen prinsipal digunakan untuk menganalisis keserupaan pencemaran udara antara stesen. Walau bagaimanapun, kajian berkaitan dengan pendekatan kualitatif khususnya pendekatan topologi untuk menganalisis keserupaan pencemaran udara tidak lagi dipelopori dengan meluas di Malaysia. Oleh itu, penyelidikan ini adalah kajian rintis yang dijalankan untuk mengkaji keserupaan pencemaran udara antara beberapa stesen di Malaysia menggunakan teknik dalam analisis data bertopologi yang dikenali sebagai homologi gigih. Sifat topologi pencemaran udara diperihalkan oleh ciri-ciri topologi seperti komponen berkait, lubang dan lompong. Habuk halus (PM₁₀) yang diketahui sebagai pencemar utama digunakan untuk memperihalkan perilaku pencemaran udara di stesen pengawasan kualiti udara Klang, Petaling Jaya dan Shah Alam. Ciri-ciri topologi yang diperoleh daripada PM₁₀ dianalisis menggunakan ukuran jarak (jarak Wasserstein) untuk mendapatkan keserupaan topologi. Darjah keserupaan dicirikan oleh nilai jarak yang kecil dan sebaliknya. Hasil daripada ukuran jarak menunjukkan Petaling Jaya dan Shah Alam adalah stesen yang paling serupa dan Klang adalah stesen yang paling tak serupa. Penentusahan untuk hasil tersebut dijalankan melalui analisis kelompok agglomeratif berhierarki yang mengelompokkan stesen mengikut jarak ketakserupaan dan hasilnya adalah konsisten dengan keputusan kajian ini. Melalui penemuan ini, kajian yang lebih mendalam dengan menggunakan jentera lain dalam bidang analisis data bertopologi boleh dilakukan sebagai kaedah alternatif dalam menganalisis masalah pencemaran udara di Malaysia.

Kata kunci: Analisis data bertopologi; homologi gigih; jarak Wasserstein; keserupaan topologi; PM₁₀

ABSTRACT

The issue of air pollution is a global problem that continues to be discussed today. Often, the use of quantitative approaches such as cluster analysis, correlation analysis and principal component analysis is used to analyze the similarity of air pollution between stations. However, studies related to qualitative approaches, especially topological approaches to analyzing the similarity of air pollution, have not been widely popularized in Malaysia. Therefore, this study is a pilot study conducted to investigate the similarity of air pollution between several stations in Malaysia using a technique in the topological data analysis known as persistent homology. The topological properties of air pollution are described by topological features such as connected components, holes, and void. The particulate matter (PM₁₀) known as the main pollutant is used to describe the air pollution behavior at Klang, Petaling Jaya and Shah Alam air quality monitoring stations. The topological features obtained from the PM₁₀ is analyzed using distance measure (Wasserstein distance) to obtain topological similarity. The degree of similarity is characterized by a small distance value and vice versa. Results of distance measure show that Petaling Jaya and Shah Alam are the most similar stations and Klang is the most dissimilar station. The validation of these results was carried out by analysis of hierarchical agglomerative cluster analysis that grouped the stations according to their dissimilarity distance and the results are consistent with the findings of this study. From this finding, a more in-depth study using other machinery in the field of topological data analysis can be done as an alternative method for analyzing air pollution problems in Malaysia.

Keywords: Persistent homology; PM₁₀; topological data analysis; topological similarity; Wasserstein distance

RUJUKAN

Abdullah, A.M., Samah, M.A. & Jun, T.Y. 2012. An overview of the air pollution trend in Klang Valley, Malaysia. Open Environmental Sciences 6(1): 13-19.

Adenan, N.H. & Noorani, M.S.M. 2016. Multiple time-scales nonlinear prediction of river flow using chaos approach. Jurnal Teknologi 78: 1-7.

Afroz, R., Hassan, M.N. & Ibrahim, N.A. 2003. Review of air pollution and health impacts in Malaysia. Environmental Research 92(2): 71-77.

Austin, E., Coull, B.A., Zanobetti, A. & Koutrakis, P. 2013. A framework to spatially cluster air pollution monitoring sites in US based on the PM_2.5 composition. Environment International 59: 244-254.

Azid, A., Juahir, H., Ezani, E., Toriman, M.E., Endut, A., Rahman, M.N.A., Yunus, K., Kamarudin, M.K.A., Hasnam, C.N.C., Saudi, A.S. & Umar, M.R. 2015. Identification source of variation on regional impact of air quality pattern using chemometric. Aerosol and Air Quality Research 15: 1545-1558.

Azmi, S.Z., Latif, M.T., Ismail, A.S., Juneng, L. & Jemain, A.A. 2010. Trend and status of air quality at three different monitoring stations in the Klang Valley, Malaysia. Air Quality, Atmosphere & Health 3(1): 53-64.

Cohen, A.J., Brauer, M., Burnett, R., Anderson, H.R., Frostad, J., Estep, K., Balakrishnan, K., Brunekreef, B., Dandona, L., Dandona, R. & Feigin, V. 2017. Estimates and 25-year trends of the global burden of disease attributable to ambient air pollution: An analysis of data from the Global Burden of Diseases Study 2015. The Lancet 389(10082): 1907-1918.

Edelsbrunner, H. & Harer, J. 2010. Computational Topology: An Introduction. Applied Math Textbook.

Everitt, B.S., Landau, S., Leese, M. & Stahl, D. 2011. Cluster Analysis. 5th ed. Chichester, UK: John Wiley & Sons.

Fasy, B.T., Kim, J., Lecci, F., Maria, C. & Rouvreau, V. 2017. Statistical tools for topological data analysis. https://cran.r project.org/web/packages/TDA/TDA.pdf. Diakses pada 2 Februari 2018.

Ghrist, R. 2008. Barcodes: The persistent topology of data. Bulletin of the American Mathematical Society 45(1): 61-75.

Gidea, M. & Katz, Y. 2018. Topological data analysis of financial time series: Landscapes of crashes. Physica A: Statistical Mechanics and its Applications 491: 820-834.

Hajij, M., Wang, B., Scheidegger, C. & Rosen, P. 2018. Visual detection of structural changes in time-varying graphs using persistent homology. 2018 IEEE Pacific Visualization Symposium (PacificVis). hlm. 125-134.

Hamid, N.Z.A. & Noorani, M.S.M. 2017. Aplikasi model baharu penambahbaikan pendekatan kalut ke atas peramalan siri masa kepekatan ozon. Sains Malaysiana 46(8): 1333-1339. 

Hatcher, A. 2002. Algebraic Topology. Cambridge: Cambridge University Press.

Hua, A.K. 2018. Applied chemometric approach in identification sources of air quality pattern in Selangor, Malaysia. Sains Malaysiana 47(3): 471-479.

Iizuka, A., Shirato, S., Mizukoshi, A., Noguchi, M., Yamasaki, A. & Yanagisawa, Y. 2014. A cluster analysis of constant ambient air monitoring data from the Kanto Region of Japan. International Journal of Environmental Research and Public Health 11(7): 6844-6855.

Isiyaka, H.A. & Azid, A. 2015. Air quality pattern assessment in Malaysia using multivariate techniques. Malaysian Journal of Analytical Sciences 19(5): 966-978.

Jamalani, M.A., Abdullah, A.M., Azid, A., Ramli, M.F., Baharudin, M.R., Bose, M. MElhadi, R.E., Youssef, K.A.A.B., Gnadimzadeh, A. & Gumel, D.Y. 2016. Monthly analysis of PM₁₀ in ambient air of Klang Valley, Malaysia. Malaysian Journal of Analytical Sciences 20(5): 1159-1170.

JASM. 2019a. Laporan Kualiti Alam Sekeliling 2015. https://enviro.doe.gov.my/. Diakses pada 24 Februari 2019.

JASM. 2019b. Laporan Kualiti Alam Sekeliling 2013. https://enviro.doe.gov.my/. Diakses pada 24 Februari 2019. 

Kerber, M., Morozov, D. & Nigmetov, A. 2017. Geometry helps to compare persistence diagrams. Journal of Experimental Algorithmics 22: 1-4.

Khasawneh, F.A. & Munch, E. 2014. Stability determination in turning using persistent homology and time series analysis. Prosiding ASME 2014 International Mechanical Engineering Congress and Exposition, November 14-20, Montreal, Canada.

Khasawneh, F.A., Munch, E. & Perea, J.A. 2018. Chatter classification in turning using machine learning and topological data analysis. IFAC-PapersOnLine 51(14): 195-200.

Kramár, M., Levanger, R., Tithof, J., Suri, B., Xu, M., Paul, M., Schatz, M.F. & Mischaikow, K. 2016. Analysis of Kolmogorov flow and Rayleigh-Bénard convection using persistent homology. Physica D: Nonlinear Phenomena 334: 82-98.

Ling, O.H.L., Siti Nur, A.M. & Noralizawati, M. 2014. Air quality and land use in urban region of Petaling Jaya, Shah Alam and Klang, Malaysia. Environment Asia 7(1): 134-144.

Lu, W.Z., He, H.D. & Dong, L.Y. 2011. Performance assessment of air quality monitoring networks using principal component analysis and cluster analysis. Building and Environment 46(3): 577-583.

Maletić, S., Zhao, Y. & Rajković, M. 2016. Persistent topological features of dynamical systems. Chaos: An Interdisciplinary Journal of Nonlinear Science 26(5): 053105.

Nicolau, M., Levine, A.J. & Carlsson, G. 2011. Topology based data analysis identifies a subgroup of breast cancers with a unique mutational profile and excellent survival. Proceedings of the National Academy of Sciences 108(17): 7265-7270.

Otter, N., Porter, M.A., Tillmann, U., Grindrod, P. & Harrington, H.A. 2017. A roadmap for the computation of persistent homology. EPJ Data Science 6(1): 17.

Pereira, C.M. & Mello, R.F.D. 2015. Persistent homology for time series and spatial data clustering. Expert Systems with Applications 42(15-16): 6026-6038.

Petri, G., Expert, P., Turkheimer, F., Carhart-Harris, R., Nutt, D., Hellyer, P.J. & Vaccarino, F. 2014. Homological scaffolds of brain functional networks. Journal of the Royal Society Interface 11(101): 20140873.

Rahman, S.R.A., Ismail, S.N.S., Raml, M.F., Latif, M.T., Abidin, E.Z. & Praveena, S.M. 2015. The assessment of ambient air pollution trend in Klang Valley, Malaysia. World Environment 5(1): 1-11.

Seversky, L.M., Davis, S. & Berger, M. 2016. On time-series topological data analysis: New data and opportunities. Prosiding IEEE Conference on Computer Vision and Pattern Recognition Workshops. hlm. 59-67.

Spangl, W., Schneider, J., Moosmann, L. & Nagl, C. 2007. Representativeness and classification of air quality monitoring stations. Final Report: Umweltbundesamt.

Takens, F. 1981. Detecting strange attractors in turbulence. Lecture Notes in Mathematics Dynamical Systems and Turbulence, Warwick 1980: 366-381.

Umeda, Y. 2017. Time series classification via topological data analysis. Information and Media Technologies 12: 228-239.

Zainordin, N.S., Ramli, N.A. & Elbayoumi, M. 2017. Distribution and temporal behaviour of O₃ and NO₂ near selected schools in Seberang Perai, Pulau Pinang and Parit Buntar, Perak, Malaysia. Sains Malaysiana 46(2): 197-207.

Zulkepli, N.F.S., Noorani, M.S.M., Razak, F.A., Ismail, M. & Alias, M.A. 2019a. Topological characterization of haze episodes using persistent homology. Aerosol and Air Quality Research 19: 1614-1624.

Zulkepli, N.F.S., Noorani, M.S.M., Razak, F.A., Ismail, M. & Alias, M.A. 2019b. Haze detection using persistent homology. AIP Conference Proceedings 2111: 020012.

*Pengarang untuk surat-menyurat; email: farihasyaqina@yahoo.com