Advertisement

Neural Computing and Applications

, Volume 25, Issue 3–4, pp 793–806 | Cite as

Feature selection using swarm-based relative reduct technique for fetal heart rate

  • H. Hannah Inbarani
  • P. K. Nizar Banu
  • Ahmad Taher AzarEmail author
Original Article

Abstract

Fetal heart rate helps in diagnosing the well-being and also the distress of fetal. Cardiotocograph (CTG) monitors the fetal heart activity to estimate the fetal tachogram based on the evaluation of ultrasound pulses reflected from the fetal heart. It consists in a simultaneous recording and analysis of fetal heart rate signal, uterine contraction activity and fetal movements. Generally CTG comprises more number of features. Feature selection also called as attribute selection is a process of selecting a subset of highly relevant features which is responsible for future analysis. In general, medical datasets require more number of features to predict an activity. This paper aims at identifying the relevant and ignores the redundant features, consequently reducing the number of features to assess the fetal heart rate. The features are selected by using unsupervised particle swarm optimization (PSO)-based relative reduct (US-PSO-RR) and compared with unsupervised relative reduct and principal component analysis. The proposed method is then tested by applying various classification algorithms such as single decision tree, multilayer perceptron neural network, probabilistic neural network and random forest for maximum number of classes and clustering accuracies like root mean square error, mean absolute error, Davies–Bouldin index and Xie–Beni index for minimum number of classes. Empirical results show that the US-PSO-RR feature selection technique outperforms the existing methods by producing sensitivity of 72.72 %, specificity of 97.66 %, F-measure of 74.19 % which is remarkable, and clustering results demonstrate error rate produced by US-PSO-RR is less as well.

Keywords

Unsupervised PSO Feature selection Relative reduct Fetal heart rate Cardiotocogram 

References

  1. 1.
    Geijn HP (1996) Developments in CTG analysis. Bailliere’s Clin. Obstet. Gynaecol. 10(2):185–209CrossRefGoogle Scholar
  2. 2.
    Steer PJ (2008) Has electronic fetal heart rate monitoring made a difference. Semin. Fetal Neonat. Med. 13:2–7CrossRefGoogle Scholar
  3. 3.
    FIGO (1986) Guidelines for the use of fetal monitoring. Int. J. Gynecol. Obstet. 25:159–167Google Scholar
  4. 4.
    Gonçalves H, Rocha AP, De Campos DA, Bernardes J (2006) Linear and nonlinear fetal heart rate analysis of normal and acidemic fetuses in the minutes preceding delivery. Med. Biol. Eng. Comput. 44(10):847–855CrossRefGoogle Scholar
  5. 5.
    Magenes G, Signorini MG, Arduini D (2000) Classification of cardiotocographic records by neural networks. In: Proceedings of the IEEE-INNS-ENNS international joint conference on neural networks IJCNN, vol 3, pp 637–641Google Scholar
  6. 6.
    Salamalekis E, Thomopoulos P, Giannaris D, Salloum I, Vasios G, Prentza A, Koutsouris D (2002) Computerised intrapartum diagnosis of fetal hypoxia based on fetal heart rate monitoring and fetal pulse oximetry recordings utilising wavelet analysis and neural networks. BJOG 109(10):1137–1142CrossRefGoogle Scholar
  7. 7.
    Georgoulas G, Stylios C, Groumpos P (2005). Classification of fetal heart rate using scale dependent features and support vector machines. In: Proceedings of 16th IFAC world congressGoogle Scholar
  8. 8.
    Leski J (2003) Neuro-fuzzy system with learning tolerant to imprecision. Fuzzy Sets Syst 138:427–439MathSciNetCrossRefGoogle Scholar
  9. 9.
    Czabanski R, Jezewski M, Wrobel J, Horoba K, Jezewski J (2008). A neurofuzzy approach to the classification of fetal cardiotocograms. In: Proceedings of 14th international conference NBC2008, vol 20, pp 446–449Google Scholar
  10. 10.
    Czabanski R, Jezewski M, Wrobel J, Jezewski J, Horoba K (2010) Predicting the risk of low-fetal birth weight from cardiotocographic signals using ANBLIR system with deterministic annealing and e-insensitive learning. IEEE Trans Inf Technol Biomed 14:1062–1074CrossRefGoogle Scholar
  11. 11.
    Vapnik V (1998) Statistical learning theory. Wiley, New YorkzbMATHGoogle Scholar
  12. 12.
    Vapnik V (1999) An overview of statistical learning theory. IEEE Trans Neural Netw 10:988–999CrossRefGoogle Scholar
  13. 13.
    Magenes G, Signorini MG, Arduini D (2000) Classification of cardiotocographic records by neural networks. In: Proceedings of the IEEE-INNSENNS international joint conference on neural networks (IJCNN’00), vol 3, pp 637–641Google Scholar
  14. 14.
    Magenes G, Signorini MG, Sassi R, Arduini D (2001) Multiparametric analysis of fetal heart rate: comparison of neural and statistical classifiers. In: 9th mediterranean conference on medical and biological engineering and computing (MEDICON 2001), IFMBE Proceedings, 12–15 June 2001, Pula, Croatia, vol 1, pp 360–363Google Scholar
  15. 15.
    Georgoulas G, Stylios C, Bernardes J, Groumpos PP (2004) Classification of cardiotocograms using Support Vector Machines. In: Proceedings 10th IFAC symposium on large scale systems: theory and applications (LSS’04), 26–28 July 2004, Osaka, JapanGoogle Scholar
  16. 16.
    Pawlak Z (1982) Rough sets. Int J Comput Inform Sci 11(5):341–356zbMATHMathSciNetCrossRefGoogle Scholar
  17. 17.
    Nizar Banu PK, Hannah Inbarani H (2012) Performance evaluation of hybridized rough set based unsupervised approaches for gene selection. Int J Comput Intell Inf 2(2):132–141Google Scholar
  18. 18.
    Costa A, Ayres-de-Campos D, Costa F, Santos C, Bernardes J (2009) Prediction of neonatal acidemia by computer analysis of fetal heart rate and ST event signals. Am J Obstet Gynecol 201(5):464.e1–464.e6CrossRefGoogle Scholar
  19. 19.
    Georgoulas G, Stylios CD, Groumpos PP (2006) Feature extraction and classification of fetal heart rate using wavelet analysis and support vector machines. Int J Artif Intell Tools 15(3):411–432CrossRefGoogle Scholar
  20. 20.
    Georgoulas G, Stylios C, Groumpos P (2006) Predicting the risk of metabolic acidosis for newborns based on fetal heart rate signal classification using support vector machines. IEEE Trans Biomed Eng 53(5):875–884CrossRefGoogle Scholar
  21. 21.
    Warrick P, Hamilton E, Precup D, Kearney R (2010) Classification of normal and hypoxic fetuses from systems modeling of intrapartum cardiotocography. IEEE Trans Biomed Eng 57(4):771–779CrossRefGoogle Scholar
  22. 22.
    Chaffin DG, Goldberg CC, Reed KL (1991) The dimension of chaos in the fetal heart rate. Am J Obstet Gynecol 165(4):1425–1429CrossRefGoogle Scholar
  23. 23.
    Gough NA (1993) Fractal analysis of foetal heart rate variability. Physiol Meas 14(3):309–315CrossRefGoogle Scholar
  24. 24.
    Felgueiras CS, Marques de Sá JP, Bernardes J, Gama S (1998) Classification of foetal heart rate sequences based on fractal features. Med Biol Eng Comput 36(2):197–201CrossRefGoogle Scholar
  25. 25.
    Kikuchi A, Unno N, Horikoshi T, Shimizu T, Kozuma S, Taketani Y (2005) Changes in fractal features of fetal heart rate during pregnancy. Early Hum Dev 81(8):655–661CrossRefGoogle Scholar
  26. 26.
    Georgoulas G, Gavrilis D, Tsoulos IG, Stylios C, Bernardes J, Groumpos PP (2007) Novel approach for fetal heart rate classification introducing grammatical evolution. Biomed Signal Process Control 2(2):69–79CrossRefGoogle Scholar
  27. 27.
    Van Laar J, Porath M, Peters C, Oei S (2008) Spectral analysis of fetal heart rate variability for fetal surveillance: review of the literature. Acta Obstet Gynecol Scand 87(3):300–306CrossRefGoogle Scholar
  28. 28.
    Van Laar J, Peters CHL, Houterman S, Wijn PFF, Kwee A, Oei SG (2011) Normalized spectral power of fetal heart rate variability is associated with fetal scalp blood pH. Early Hum Dev 87(4):259–263CrossRefGoogle Scholar
  29. 29.
    Hopkins P, Outram N, Zofgren N, Ifeachor EC, Rosen KG (2006) A comparative study of fetal heart rate variability analysis techniques. In: Proceedings of the 28th annual international conference of the ieee engineering in medicine and biology society, pp 1784–1787Google Scholar
  30. 30.
    Pincus SM, Viscarello RR (1992) Approximate entropy: a regularity measure for fetal heart rate analysis. Obstet Gynecol 79(2):249–255Google Scholar
  31. 31.
    Ferrario M, Signorini MG, Magenes G, Cerutti S (2006) Comparison of entropy based regularity estimators: application to the fetal heart rate signal for the identification of fetal distress. IEEE Trans Biomed Eng 53(1):119–125CrossRefGoogle Scholar
  32. 32.
    Gonçalves H, Bernardes J, Rocha AP, Ayres-de-Campos D (2007) Linear and nonlinear analysis of heart rate patterns associated with fetal behavioral states in the antepartum period. Early Hum Dev 83(9):585–591CrossRefGoogle Scholar
  33. 33.
    Ferrario M, Signorini M, Magenes G (2009) Complexity analysis of the fetal heart rate variability: early identification of severe intrauterine growth-restricted fetuses. Med Biol Eng Comput 47(9):911–919CrossRefGoogle Scholar
  34. 34.
    Spilka J, Chudáček V, Koucký M, Lhotská L, Huptych M, Janku P, Georgoulas G, Stylios C (2012) Using nonlinear features for fetal heart rate classification. Biomed Signal Process Control 7(4):350–357CrossRefGoogle Scholar
  35. 35.
    Questier F, Rollier IA, Walczak B, Massart DL (2002) Application of rough set theory to feature selection for unsupervised clustering. Chemometr Intell Lab Syst 63(2):155–167CrossRefGoogle Scholar
  36. 36.
    Zhang J, Wang J, Li D, He H, Sun J (2003) A new heuristic reduct algorithm base on rough sets theory. LNCS, vol 2762, pp 247–253. Springer, BerlinGoogle Scholar
  37. 37.
    Swiniarski RW, Skowron A (2003) Rough set methods in feature selection and recognition. Pattern Recognit Lett 24(6):833–849zbMATHCrossRefGoogle Scholar
  38. 38.
    Thangavel K, Pethalakshmi A (2009) Dimensionality reduction based on rough set theory: a review. Appl Soft Comput 9(1):1–12CrossRefGoogle Scholar
  39. 39.
    Echeverría JC, Άlvarez-Ramírez J, Pena MA, Rodríguez E, Gaitán MJ, González-Camarena R (2012) Fractal and nonlinear changes in the long-term baseline fluctuations of fetal heart rate. Med Eng Phys 34(4):466–471CrossRefGoogle Scholar
  40. 40.
    Skinner J, Garibaldi J, Ifeachor E (1999) A fuzzy system for fetal heart rate assessment. In: Reusch B (ed) Computational intelligence. Lecture notes in computer science, vol 1625. Springer, Berlin, pp 20–29Google Scholar
  41. 41.
    Skinner J, Garibaldi J, Curnow J, Ifeachor E (2000) Intelligent fetal heart rate analysis. In: 1st International conference on advances in medical signal and information processing, pp 14–21Google Scholar
  42. 42.
    Keith R, Beckley S, Garibaldi J (1995) A multicentre comparative study of 17 experts and an intelligent computer system for managing labour using the cardiotocogram. Br J Obstet Gynaecol 102(9):688–700CrossRefGoogle Scholar
  43. 43.
    Signorini M, de Angelis A, Magenes G, Sassi R, Arduini D, Cerutti S (2000). Classification of fetal pathologies through fuzzy inference systems based on a multiparametric analysis of fetal heart rate. In: Computers in cardiology, pp 435–438. Cambridge, MAGoogle Scholar
  44. 44.
    Arduini D, Giannini F, Magnes G, Signorini MG, Meloni P (2001). Fuzzy logic in the management of new prenatal variables. In: Proceedings of 5th world congress of perinatal medicine, Barcelona, vol 1, pp 1211–1216Google Scholar
  45. 45.
    Huang YP, Huang YH, Sandnes FE (2006) A fuzzy inference method-based fetal distress monitoring system. In: IEEE international symposium on industrial electronics, vol 1, pp 55–60, 9–13 July 2006, Montreal, QueGoogle Scholar
  46. 46.
    Hasbargen U (1994) Application of neural networks for intrapartum surveillance. In: van Geijn H, Copray F (eds) A critical appraisal of fetal surveillance. Elsevier Science (Excerpta Medica), Amsterdam, New York, pp 363–367Google Scholar
  47. 47.
    Beksac M, Ozdemir K, Erkmen A, Karakas U (1994) Assessment of antepartum fetal heart rate tracings using neural networks. In: van Geijn H, Copray F (eds) A critical appraisal of fetal surveillance. Elsevier Science (Excerpta Medica), Amsterdam, New York, pp 354–362Google Scholar
  48. 48.
    Magenes G, Signorini M G, Arduini D (2000) Classification of cardiotocographic records by neural networks. In: Proceedings IEEE-INNS-ENNS international joint conference on neural networks IJCNN, vol 3, pp 637–641Google Scholar
  49. 49.
    Magenes G, Signorini M, Sassi R, Arduini D (2001). Multiparametric analysis of fetal heart rate: comparison of neural and statistical classifiers. In: IFMBE proceedings of MEDICON, vol 1, pp 360–363Google Scholar
  50. 50.
    Noguchi Y, Matsumoto F, Maed K, Nagasawa T (2009) Neural network analysis and evaluation of the fetal heart rate. Algorithms 2:19–30CrossRefGoogle Scholar
  51. 51.
    Jezewski M, Wrobel J, Horoba K, Gacek A, Henzel N, Leski J (2007) The prediction of fetal outcome by applying neural network for evaluation of CTG records. In: Kurzynski M, Puchala E, Wozniak M, Zolnierek A (eds) Computer recognition systems 2. Advances in intelligent and soft computing, vol 45. Springer, Berlin, pp 532–541Google Scholar
  52. 52.
    Jezewski M, Czabanski R, Wrobel J, Horoba K (2010) Analysis of extracted cardiotocographic signal features to improve automated prediction of fetal outcome. Biocybernetics and Biomedical Engineering 30:39–47Google Scholar
  53. 53.
    Frize M, Ibrahim D, Seker H, Walker R, Odetayo M, Petrovic D, Naguib R (2004) Predicting clinical outcomes for newborns using two artificial intelligence approaches. In: Engineering in medicine and biology society, IEMBS’04. Proceedings of 26th annual international conference of the IEEE, vol 2, pp 3202–3205Google Scholar
  54. 54.
    Azar AT, Nizar Banu PK, Hannah Inbarani H (2013) PSORR—An unsupervised feature selection technique for fetal heart rate. In: Proceedings of the 5th international conference on modelling, Identification and control (ICMIC 2013), Aug 31–Sept 2 2013. Cairo, Egypt, pp 60–65Google Scholar
  55. 55.
    Komorowski J, Pawlak Z, Polkowski L, Skowron A (1999) Rough sets: a tutorial. In: Pal SK, Skowron A (eds) Rough fuzzy hybridization: a new trend in decision making. Springer, Berlin, pp 3–98Google Scholar
  56. 56.
    Kalyani P, Karnan M (2011) A new implementation of attribute reduction using quick relative reduct algorithm. Int J Internet Comput 1(1):99–102Google Scholar
  57. 57.
    Lin TY, Cercone N (1997) Rough sets and data mining: analysis of imprecise data. Kluwer Academic Publishers, DordrechtzbMATHGoogle Scholar
  58. 58.
    Hu XT, Lin TY, Han J (2003) A new rough sets model based on database systems. In: Rough sets, fuzzy sets, data mining, and granular computing. Lecture notes in computer science, vol 2639, pp 114–121. doi: 10.1007/3-540-39205-X_15
  59. 59.
    Hannah Inbarani H, Nizar Banu PK (2012) Unsupervised hybrid PSO—relative reduct approach for feature reduction. In: Proceedings of the international conference on pattern recognition, informatics and medical engineering (PRIME), pp 103–108. doi: 10.1109/ICPRIME.2012.6208295
  60. 60.
    Velayutham C, Thangavel K (2011) Unsupervised feature selection using rough sets. In: Proceedings of the international conference-emerging trends in computing, pp 307–314Google Scholar
  61. 61.
    Velayutham C, Thangavel K (2011) Unsupervised quick reduct algorithm using rough set theory. J Electron Sci Technol 9(3):193–201Google Scholar
  62. 62.
    Bache K, Lichman M (2013) UCI machine learning repository. http://archive.ics.uci.edu/ml. University of California, School of Information and Computer Science, Irvine, CA
  63. 63.
    Davis JC (2002) Statistics and data analysis in geology, 3rd edn. Wiley, NewYorkGoogle Scholar
  64. 64.
    Breiman L, Friedman J, Olshen R, Stone C (1984) Classification and regression trees. Wadsworth, Belmont, CAzbMATHGoogle Scholar
  65. 65.
    Bridle JS (1989) Probabilistic interpretation of feedforward classification network outputs, with relationships to statistical pattern recognition. In: Fougelman-Soulie F (ed) Neurocomputing: algorithms, architectures and applications. Springer, Berlin, pp 227–236Google Scholar
  66. 66.
    Specht DF (1990) Probabilistic neural networks. Neural Netw 3(1):109–118CrossRefGoogle Scholar
  67. 67.
    Breiman L (2001) Random forests. Mach Learn 45(1):5–32zbMATHCrossRefGoogle Scholar
  68. 68.
    De Franca OF, Ferreira HM, Von Zuben FJ (2007) Applying biclustering to perform collaborative filtering. In: Proceedings of the seventh internationalGoogle Scholar
  69. 69.
    Xi XL, Beni G (1991) A validity measure for fuzzy clustering. IEEE Trans Pattern Anal Mach Intell 13(8):841–847CrossRefGoogle Scholar
  70. 70.
    Davies DL, Bouldin DW (1979) A cluster separation measure. IEEE Trans Pattern Anal Mach Intell 1(2):224–227CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London 2014

Authors and Affiliations

  • H. Hannah Inbarani
    • 1
  • P. K. Nizar Banu
    • 2
  • Ahmad Taher Azar
    • 3
    Email author
  1. 1.Department of Computer SciencePeriyar UniversitySalemIndia
  2. 2.Department of Computer ApplicationsB.S. Abdur Rahman UniversityChennaiIndia
  3. 3.Faculty of Computers and InformationBenha UniversityBenhaEgypt

Personalised recommendations