Skip to main content
SpringerLink
Log in

Performance comparison of artificial neural networks learning algorithms and activation functions in predicting severity of autism

  • Original Article
  • Published:
Network Modeling Analysis in Health Informatics and Bioinformatics Aims and scope Submit manuscript

Abstract

Artificial neural networks are one of the most efficient methods for pattern recognition and have a vast range of applications for aiding medical decision making. The proposed study applies feed-forward back-propagation neural networks as a classifier and compares the combination of nine learning algorithms and three activation functions to build a knowledge-based system with the best network architecture for predicting the severity of autism. The performances of the derived models were evaluated based on statistical criteria such as mean squared error (MSE), mean absolute percentage error (MAPE), root mean squared error (RMSE), regression (R value), training time and number of epochs. The study findings showed that the optimal performance was achieved by model MLP_LM_104 trained on Levenberg–Marquardt (LM) back-propagation algorithm having network topology of 40-10-4 with purelin and tansig activation functions in hidden and output layers. The regression coefficients for training, validation and test datasets were 0.996, 0.996 and 0.994, respectively. The MSE, RMSE and MAPE were \( 2.26 \times 10^{ - 4} \), \( 1.50 \times 10^{ - 2} \) and \( 1.13 \), respectively. Furthermore, BFGS quasi-Newton (BFG), conjugate gradient, gradient descent and resilient back-propagation (RP) algorithms did not perform well. Models trained with BFG algorithms required longer training time, whereas the performance of models trained on RP algorithm got worse as the numbers of hidden neurons were increased.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  • Ahmed FE (2005) Artificial neural networks for diagnosis and survival prediction in colon cancer. Mol Cancer 4:29. doi:10.1186/1476-4598-4-29

    Article  Google Scholar 

  • Ayat S, Farahani HA, Aghamohamadi M, Alian M, Aghamohamadi S, Kazemi Z (2013) A comparison of artificial neural networks learning algorithms in predicting tendency for suicide. Neural Comput Appl 23:1381–1386. doi:10.1007/s00521-012-1086-z

    Article  Google Scholar 

  • Bai VT, Srivatsa SK (2006) Wireless tele care system for intensive care unit of hospitals using bluetooth and embedded technology. Inform Technol J 5:1106–1112. doi:10.3923/itj.2006.1106.1112

    Article  Google Scholar 

  • Bailey A, Le Couteur A, Gottesman I, Bolton P, Simonoff E, Yuzda E, Rutter M (1995) Autism as a strongly genetic disorder: evidence from a British twin study. Psychol Med 25:63–77. doi:10.1017/s0033291700028099

    Article  Google Scholar 

  • Baird G, Charman T, Cox A, Baron-Cohen S, Swettenham J, Wheelwright S, Drew A (2001) Current topic: screening and surveillance for autism and pervasive developmental disorders. Arch Dis Child 84:468–475. doi:10.1136/adc.84.6.468

    Article  Google Scholar 

  • Bartosch-Härlid A, Andersson B, Aho U, Nilsson J, Andersson R (2008) Artificial neural networks in pancreatic disease. Br J Surg 95:817–826. doi:10.1002/bjs.6239

    Article  Google Scholar 

  • Basheer IA, Hajmeer M (2000) Artificial neural networks: fundamentals, computing, design and application. J Microbiol Meth 43:3–31. doi:10.1016/S0167-7012(00)00201-3

    Article  Google Scholar 

  • Belmonte MK, Cook EH, Anderson GM, Rubenstein JLR, Greenough WT, Beckel-Mitchener A, Courchesne E, Boulanger LM, Powell SB, Levitt PR, Perry EK, Jiang YH, DeLorey TM, Tierney E (2004) Autism as a disorder of neural information processing: directions for research and targets for therapy. Mol Psychiatry 9:646–663. doi:10.1038/sj.mp.4001499

    Google Scholar 

  • Bhatt A (2002) Reservoir properties from well logs using neural networks. Dissertation, Norwegian University of Science and Technology

  • Bishop CM (1995) Neural networks for pattern recognition. Clarendon Press, Oxford

    Google Scholar 

  • Bouabaz M, Hamami M (2008) A cost estimation model for repair bridges based on artificial neural network. Am J Appl Sci 5:334–339. doi:10.3844/ajassp.2008.334.339

    Article  Google Scholar 

  • Bradley BP (2012) Finding biomarkers is getting easier. Ecotoxicology 21:631–636. doi:10.1007/s10646-011-0848-1

    Article  Google Scholar 

  • Broyden CG (1970) The convergence of a class of double-rank minimization algorithms. IMA J Appl Math 6:222–231. doi:10.1093/imamat/6.3.222

    Article  MathSciNet  MATH  Google Scholar 

  • Bryson SE, Rogers SJ, Fombonne E (2003) Autism spectrum disorders: early detection, intervention, education, and psychopharmacological management. Can J Psychiatry 48:506–516

    Google Scholar 

  • Caruana R, Lawrence S, Giles CL (2001) Overfitting in neural networks: backpropagation, conjugate gradient and early stopping. In: Leen TK, Dietterich TG, Tresp V (eds) Advances in neural information processing systems 13. MIT Press, Cambridge

    Google Scholar 

  • Caudill M, Butler C (1992) Understanding neural networks, volume 1: basic networks. The MIT Press, Cambridge

    Google Scholar 

  • Charman T, Taylor E, Drew A, Cockerill H, Brown JA, Baird G (2005) Outcome at 7 years of children diagnosed with autism at age 2: predictive validity of assessments conducted at 2 and 3 years of age and pattern of symptom change over time. J Child Psychol Psychiatry 46:500–513. doi:10.1111/j.1469-7610.2004.00377.x

    Article  Google Scholar 

  • Cheng B, Titterington DM (1994) Neural networks: a review from a statistical perspective. Stat Sci 9:2–30. doi:10.1214/ss/1177010638

    Article  MathSciNet  MATH  Google Scholar 

  • Cuccaro ML, Wright HH, Rownd CV, Abramson RK, Waller J, Fender D (1996) Professional perceptions of children with developmental difficulties: the influence of race and socioeconomic status. J Autism Dev Disord 26:461–469. doi:10.1007/bf02172830

    Article  Google Scholar 

  • Daliakopoulos NI, Couliblay P, Tsanis HK (2005) Ground water level forcasting using artificial neural networks. J Hydrol 309:229–240

    Article  Google Scholar 

  • Dearlove J, Kearney D (1990) How good is general practice developmental screening? BMJ 300:1177–1180. doi:10.1136/bmj.300.6733.1177

    Article  Google Scholar 

  • Dee GL, Bakhary N, Rahman AA, Ahmad BH (2011) A comparison of artificial neural network learning algorithms for vibration-based damage detection. J Adv Mater Res 163–167:2756–2760. doi:10.4028/www.scientific.net/AMR.163-167.2756

    Google Scholar 

  • Demuth H, Beale M, Hagan M (2008) Neural network toolbox™ 6. User’s guide

  • Dobos AE, Dworkin PH, Bernstein BA (1994) Pediatricians’ approaches to developmental problems: has the gap been narrowed? J Dev Behav Pediatr 15:34–38. doi:10.1097/00004703-199402000-00006

    Article  Google Scholar 

  • Dorofki M, Elshafie AH, Jaafar O, Karim OA, Mastura S (2012) Comparison of artificial neural network transfer functions abilities to simulate extreme runoff data. Int Proc Chem Biol Environ Eng 33:39–44

    Google Scholar 

  • Elveren E, Yumuşak N (2011) Tuberculosis disease diagnosis using artificial neural network trained with genetic algorithm. J Med Syst 35:329–332. doi:10.1007/s10916-009-9369-3

    Article  Google Scholar 

  • Er O, Temurtas F, Tanrikulu AC (2010) Tuberculosis disease diagnosis using artificial neural networks. J Med Syst 34:299–302. doi:10.1007/s10916-008-9241-x

    Article  Google Scholar 

  • Erzin Y, Gul TO (2014) The use of neural networks for the prediction of the settlement of one-way footings on cohesionless soils based on standard penetration test. Neural Comput Appl 24:891–900. doi:10.1007/s00521-012-1302-x

    Article  Google Scholar 

  • Farahani HA, Kazemi Z, Aghamohamadi S, Ansari M, Aghamohamadi M (2011) Predicting tendency for suicide based on risk factors and ontological identity using artificial neural network. Psychol Res 1:227–238

    Google Scholar 

  • Fletcher R, Reeves CM (1964) Function minimization by conjugate gradients. Comput J 7:149–154. doi:10.1093/comjnl/7.2.149

    Article  MathSciNet  MATH  Google Scholar 

  • Fombonne E (2005) Epidemiology of autistic disorder and other pervasive developmental disorders. J Clin Psychiatry 10:3–8

    Google Scholar 

  • Ghaffari A, Abdollahi H, Khoshayand MR, Bozchalooi IS, Dadgar A, Rafiee-Tehrani M (2006) Performance comparison of neural network training algorithms in modeling of bimodal drug delivery. Int J Pharm 327:126–138. doi:10.1016/j.ijpharm.2006.07.056

    Article  Google Scholar 

  • Gill PE, Murray W, Wright MH (1981) Practical optimization. Academic Press, New York

    MATH  Google Scholar 

  • Glascoe FP (1997) Parents’ concerns about children’s development: prescreening technique or screening test? Pediatrics 99:522–528. doi:10.1542/peds.99.4.522

    Article  Google Scholar 

  • Gupta MK, Agarwal K, Prakash N, Singh DB, Misra K (2012) Prediction of miRNA in HIV-1 genome and its targets through artificial neural network: a bioinformatics approach. Netw Model Anal Health Inform Bioinform 1:141–151. doi:10.1007/s13721-012-0017-3

    Article  Google Scholar 

  • Hagan MT, Menhaj MB (1994) Training feedforward networks with the Marquardt algorithm. IEEE Trans Neural Netw 5:989–993. doi:10.1109/72.329697

    Article  Google Scholar 

  • Hager WW, Zhang H (2006) A survey of nonlinear conjugate gradient methods. Pacific J Optim 2:35–58

    MathSciNet  MATH  Google Scholar 

  • Heidgerken AD, Geffken G, Modi A, Frakey L (2005) A survey of autism knowledge in a health care setting. J Autism Dev Disord 35:323–330. doi:10.1007/s10803-005-3298-x

    Article  Google Scholar 

  • Howlin P (1998) Children with autism and asperger syndrome. A guide for practitioners and carers. John Wiley & Sons, Chichester

    Google Scholar 

  • Ince R (2004) Prediction of fracture parameters of concrete by artificial neural networks. Eng Fract Mech 71:2143–2159. doi:10.1016/j.engfracmech.2003.12.004

    Article  Google Scholar 

  • Iranmanesh S, Mahdavi MA (2009) A differential adaptive learning rate method for back-propagation neural networks. World Acad Sci Eng Technol 50:285–288

    Google Scholar 

  • Kermani BG, Schiffman SS, Nagle HT (2005) Performance of the Levenberg–Marquardt neural network training method in electronic nose applications. Sens Actuators B Chem 110:13–22. doi:10.1016/j.snb.2005.01.008

    Article  Google Scholar 

  • Lahmiri S (2011) A comparative study of backpropagation algorithms in financial prediction. Int J Comput Sci Eng Appl. doi:10.5121/ijcsea.2011.1402

    Google Scholar 

  • Lawrence J (1994) Introduction to neural networks: design, theory and applications. California Scientific Software Press, California

    Google Scholar 

  • Lin RH (2009) An intelligent model for liver disease diagnosis. Artif Intell Med 47:53–62. doi:10.1016/j.artmed.2009.05.005

    Article  Google Scholar 

  • Lord C, Risi S, DiLavore PS, Shulman C, Thurm A, Pickles A (2006) Autism from 2 to 9 years of age. Arch Gen Psychiatry 63:694–701. doi:10.1001/archpsyc.63.6.694

    Article  Google Scholar 

  • Lord C, Petkova E, Hus V, Gan W, Lu F, Martin DM, Ousley O, Guy L, Bernier R, Gerdts J, Algermissen M, Whitaker A, Sutcliffe JS, Warren Z, Klin A, Saulnier C, Hanson E, Hundley R, Piggot J, Fombonne E, Steiman M, Miles J, Kanne SM, Goin-Kochel RP, Peters SU, Cook EH, Guter S, Tjernagel J, Green-Snyder LA, Bishop S, Esler A, Gotham K, Luyster R, Miller F, Olson J, Richler J, Risi S (2012) A multisite study of the clinical diagnosis of different autism spectrum disorders. Arch Gen Psychiatry 69:306–313. doi:10.1001/archgenpsychiatry.2011.148

    Article  Google Scholar 

  • Magoulas GD, Vrahatis MN, Androulakis GS (1999) Improving the convergence of the backpropagation algorithm using learning rate adaptation methods. Neural Comput 11:1769–1796. doi:10.1162/089976699300016223

    Article  Google Scholar 

  • Mandell DS, Novak MM, Zubritsky CD (2005) Factors associated with age of diagnosis among children with autism spectrum disorders. Pediatrics 116:1480–1486. doi:10.1542/peds.2005-0185

    Article  Google Scholar 

  • Maria PRF (2002) An intelligent, interactive, web-based platform for effective clinical education through VR and distance learning modules. Inform Technol J 1:126–131. doi:10.3923/itj.2002.126.131

    Article  Google Scholar 

  • Mazurowski MA, Habas PA, Zurada JM, Lo JY, Baker JA, Tourassi GD (2008) Training neural network classifiers for medical decision making: the effects of imbalanced datasets on classification performance. Neural Netw 21:427–436. doi:10.1016/j.neunet.2007.12.031

    Article  Google Scholar 

  • Modai I, Saban NI, Stoler M, Valevski A, Saban N (1995) Sensitivity profile of 41 psychiatric parameters determined by neural network in relation to 8-week outcome. Comput Hum Behav 11:181–190. doi:10.1016/0747-5632(94)00022-a

    Article  Google Scholar 

  • Moller MF (1993) A scaled conjugate gradient algorithm for fast supervised learning. Neural Networks 6:525–533. doi:10.1016/S0893-6080(05)80056-5

    Article  Google Scholar 

  • Nair J, Nair S, Kashani J, Reid J, Mistry S, Vargas V (1999) Analysis of the symptoms of depression—a neural network approach. J Psychiatry Res 87:193–201. doi:10.1016/s0165-1781(99)00054-2

    Article  Google Scholar 

  • Nocedal J, Wright SJ (2000) In: Mikosch TV, Resnich SI, Robinson SM (eds) Limited-memory quasi-Newton methods: numerical optimization, 2nd edn. Springer, New York

    Google Scholar 

  • Nordahl CW, Dierker D, Mostafavi I, Schumann CM, Rivera SM, Amaral DG, Van Essen DC (2007) Cortical folding abnormalities in autism revealed by surface-based morphometry. J Neurosci 27:11725–11735. doi:10.1523/jneurosci.0777-07.2007

    Article  Google Scholar 

  • Noterdaeme M, Amorosa H, Mildenberger K, Sitter S, Minow F (2001) Evaluation of attention problems in children with autism and children with a specific language disorder. Eur Child Adolesc Psychiatry 10:58–66. doi:10.1007/s007870170048

    Article  Google Scholar 

  • Ohta M, Nagai Y, Hara H, Sasaki M (1987) Parental perception of behavioral symptoms in Japanese autistic children. J Autism Dev Disord 17:549–563. doi:10.1007/bf01486970

    Article  Google Scholar 

  • Pace F, Savarino V (2007) The use of artificial neural network in gastroenterology: the experience of the first 10 years. Eur J Gastroenterol Hepatol 19:1043–1045. doi:10.1097/MEG.0b013e3282f198e5

    Article  Google Scholar 

  • Pinto-Martin JA, Young LM, Mandell DS, Poghosyan L, Giarelli E, Levy SE (2008) Screening strategies for autism spectrum disorders in pediatric primary care. J Dev Behav Pediatr 29:345–350. doi:10.1097/dbp.0b013e31818914cf

    Article  Google Scholar 

  • Powell MJD (1977) Restart procedures for the conjugate gradient method. Math Program 12:241–254. doi:10.1007/BF01593790

    Article  MATH  Google Scholar 

  • Raju KS, Kumar DN, Duckstein L (2006) Artificial neural networks and multicriterion analysis for sustainable irrigation planning. Comput Oper Res 33:1138–1153. doi:10.1016/j.cor.2004.09.010

    Article  MATH  Google Scholar 

  • Rapin I (1997) Autism. N Engl J Med 337:97–104. doi:10.1056/nejm199707103370206

    Article  Google Scholar 

  • Riedmiller (1993) Proceedings of the IEEE International Conference on Neural Networks (ICNN). San Francisco pp 586–591

  • Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323:533–536. doi:10.1038/323533a0

    Article  Google Scholar 

  • Saini LM, Soni MK (2002) Artificial neural network based peak load forecasting using Levenberg-Marquardt and quasi-Newton methods. IEEE Proc Gener Transm Dist 149:578–584. doi:10.1049/ip-gtd:20020462

    Article  Google Scholar 

  • Scales LE (1985) Introduction to non-linear optimization. Springer, Berlin

    Book  Google Scholar 

  • Setiono R, Hui LCK (1995) Use of a quasi-Newton method in a feedforward neural network construction algorithm. IEEE Trans Neural Netw 6:273–277. doi:10.1109/72.363426

    Article  Google Scholar 

  • Shah K (2001) What do medical students know about autism? Autism 5:127–133. doi:10.1177/1362361301005002003

    Article  Google Scholar 

  • Shankaracharya Odedra D, Samanta S, Vidyarthi AS (2010) Computational intelligence in early diabetes diagnosis: a review. Rev Diabet Stud 7:252–262. doi:10.1900/RDS.2010.7.252

    Article  Google Scholar 

  • Shevell MI, Majnemer A, Rosenbaum P, Abrahamowicz M (2001) Profile of referrals for early childhood developmental delay to ambulatory subspecialty clinics. J Child Neurol 16:645–650. doi:10.1177/088307380101600904

    Article  Google Scholar 

  • Sices L, Feudtner C, McLaughlin J, Drotar D, Williams M (2003) How do primary care physicians identify young children with developmental delays? A national survey. J Dev Behav Pediatr 24:409–417. doi:10.1542/peds.113.2.274

    Article  Google Scholar 

  • Siristatidis CS, Chrelias C, Pouliakis A, Katsimanis E, Kassanos D (2010) Artificial neural networks in gynaecological diseases: current and potential future applications. Med Sci Monit 16:231–236

    Google Scholar 

  • Spelt L, Andersson B, Nilsson J, Andersson R (2012) Prognostic models for outcome following liver resection for colorectal cancer metastases: a systematic review. Eur J Surg Oncol 38:16–24. doi:10.1016/j.ejso.2011.10.013

    Article  Google Scholar 

  • Stevens R, Ikeda J, Casillas A, Palacio-Cayetano J, Clyman S (1999) Artificial neural network-based performance assessments. Comput Hum Behav 15(3–4):295–313. doi:10.1016/s0747-5632(99)00025-4

    Article  Google Scholar 

  • Talaee PH (2014) Multilayer perceptron with different training algorithms for streamflow forecasting. Neural Comput Appl 24:695–703. doi:10.1007/s00521-012-1287-5

    Article  Google Scholar 

  • Temurtas H, Yumusak N, Temurtas F (2009) A comparative study on diabetes disease diagnosis using neural networks. Expert Syst Appl 36:8610–8615. doi:10.1016/j.eswa.2008.10.032

    Article  Google Scholar 

  • Thakur A, Mishra V, Jain S (2011) Feed forward artificial neural network: tool for early detection of ovarian cancer. Sci Pharm 79:493–505. doi:10.3797/scipharm.1105-11

    Article  Google Scholar 

  • Uğuz H (2012) A biomedical system based on artificial neural network and principal component analysis for diagnosis of the heart valve diseases. J Med Syst 36:61–72. doi:10.1007/s10916-010-9446-7

    Article  Google Scholar 

  • Wassink TH, Brzustowicz LM, Bartlett CW, Szatmari P (2004) The search for autism disease genes. Ment Retard Dev Disabil Res Rev 10:272–283. doi:10.1002/mrdd.20041

    Article  Google Scholar 

  • Weigend A (1993) On overfitting and the effective number of hidden units. In: Mozer A, Smolensky P, Touretzky DS, Elman JL, Weigend AS (eds) Proceedings of the 1993 connectionist models summer school Hillsdale. Lawrence Erlbaum Associates, NJ, pp 335–342

    Google Scholar 

  • Wiggins LD, Baio J, Rice C (2006) Examination of the time between first evaluation and first autism spectrum diagnosis in a population-based sample. J Dev Behav Pediatr 27:79–87. doi:10.1097/00004703-200604002-00005

    Article  Google Scholar 

  • Wilding P, Morgan M, Grygotis A, Shoffner M, Rosato E (1994) Application of backpropagation neural networks to diagnosis of breast and ovarian cancer. Cancer Lett 77:145–155. doi:10.1016/0304-3835(94)90097-3

    Article  Google Scholar 

  • Yeargin-Allsopp M, Rice C, Karapurkar T, Doernberg N, Boyle C, Murphy C (2003) Prevalence of autism in a US metropolitan area. J Am Med Assoc 289:49–55. doi:10.1001/jama.289.1.49

    Article  Google Scholar 

Download references

Acknowledgments

The authors wish to thank National Institute for the Mentally Handicapped (NIMH) for providing the autistic patients’ data and to the Dept. of Bioinformatics, Karunya University for their constant support and motivation.

Conflict of interest

The authors declare that they have no conflict of interest.

Author information

Authors and Affiliations

  1. Department of Bioinformatics, School of Biotechnology and Health Sciences, Karunya University, Karunya Nagar, Coimbatore, Tamil Nadu, India

    Yamini Chand & Md. Afroz Alam

  2. Vasavi Medical and Research Centre, Khairatabad, Hyderabad, Andhra Pradesh, India

    Y. R. S. N. Tejaswini

Authors
  1. Yamini Chand
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Md. Afroz Alam
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Y. R. S. N. Tejaswini
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yamini Chand.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chand, Y., Alam, M.A. & Tejaswini, Y.R.S.N. Performance comparison of artificial neural networks learning algorithms and activation functions in predicting severity of autism. Netw Model Anal Health Inform Bioinforma 4, 2 (2015). https://doi.org/10.1007/s13721-014-0073-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s13721-014-0073-y

Keywords

Search

Navigation