Skip to main content

Comparing supervised learning methods for classifying sex, age, context and individual Mudi dogs from barking

Animal Cognition volume 18, pages 405–421 (2015)Cite this article

Abstract

Barking is perhaps the most characteristic form of vocalization in dogs; however, very little is known about its role in the intraspecific communication of this species. Besides the obvious need for ethological research, both in the field and in the laboratory, the possible information content of barks can also be explored by computerized acoustic analyses. This study compares four different supervised learning methods (naive Bayes, classification trees, \(k\)-nearest neighbors and logistic regression) combined with three strategies for selecting variables (all variables, filter and wrapper feature subset selections) to classify Mudi dogs by sex, age, context and individual from their barks. The classification accuracy of the models obtained was estimated by means of \(K\)-fold cross-validation. Percentages of correct classifications were 85.13 % for determining sex, 80.25 % for predicting age (recodified as young, adult and old), 55.50 % for classifying contexts (seven situations) and 67.63 % for recognizing individuals (8 dogs), so the results are encouraging. The best-performing method was \(k\)-nearest neighbors following a wrapper feature selection approach. The results for classifying contexts and recognizing individual dogs were better with this method than they were for other approaches reported in the specialized literature. This is the first time that the sex and age of domestic dogs have been predicted with the help of sound analysis. This study shows that dog barks carry ample information regarding the caller’s indexical features. Our computerized analysis provides indirect proof that barks may serve as an important source of information for dogs as well.

This is a preview of subscription content, access via your institution.

Access options

Buy single article

Instant access to the full article PDF.

USD 39.95

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

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

References

  • Acevedo M, Corrada-Bravo C, Corrada-Bravo H, Villanueva-Rivera L, Aide T (2009) Automated classification of bird and amphibian calls using machine learning: a comparison of methods. Ecol Inform 4(4):206–214

    Article  Google Scholar 

  • Adachi I, Kuwahata H, Fujita K (2007) Dogs recall their owner’s face upon hearing the owner’s voice. Anim Cogn 10:17–21

    PubMed  Article  Google Scholar 

  • Adams M, Law B, Gibson M (2010) Reliable automation of bat call identification for Eastern New South Wales, Australia, using classification trees and AnaScheme software. Acta Chiropterol 12(1):231–245

    Article  Google Scholar 

  • Armitage D, Ober H (2010) A comparison of supervised learning techniques in the classification of bat echolocation calls. Ecol Inform 5(6):465–473

    Article  Google Scholar 

  • Au W, Andersen L, Roitblat ARH, Nachtigall P (1995) Neural network modeling of a dolphin’s sonar discrimination capabilities. J Acoust Soc Am 98:43–50

    CAS  PubMed  Article  Google Scholar 

  • Bálint A, Faragó T, Dóka A, Miklósi A, Pongrácz P (2013) “Beware, I am big and non-dangerous!”—playfully growling dogs are perceived larger than their actual size by their canine audience. Appl Anim Behav Sci 148:128–137

    Article  Google Scholar 

  • Bielza C, Li G, Larrañaga P (2011) Multi-dimensional classification with Bayesian networks. Int J Approx Reason 52:705–727

    Article  Google Scholar 

  • Blumstein D, Munos O (2005) Individual, age and sex-specific information is contained in yellow-bellied marmot alarm calls. Anim Behav 69(2):353–361

    Article  Google Scholar 

  • Borchani H, Bielza C, Martínez-Martín P, Larrañaga P (2012) Markov blanket-based approach for learning multi-dimensional Bayesian network classifiers: an application to predict the European Quality of Life-5 Dimensions (EQ-5D) from the 39-item Parkinson’s Disease Questionnaire (PDQ-39). J Biomed Inform 45:1175–1184

    PubMed  Article  Google Scholar 

  • Britzke E, Duchamp J, Murray K, Swihart R, Robbins L (2011) Acoustic identification of bats in the Eastern United States: a comparison of parametric and nonparametric methods. J Wildl Manage 75(3):660–667

    Article  Google Scholar 

  • Charrier I, Aubin T, Mathevon N (2010) Mother-calf vocal communication in Atlantic walrus: a first field experimental study. Anim Cogn 13(3):471–482

    PubMed  Article  Google Scholar 

  • Cheng J, Sun Y, Ji L (2010) A call-independent and automatic acoustic system for the individual recognition of animals: a novel model using four passerines. Pattern Recogn 43(11):3846–3852

    Article  Google Scholar 

  • Chesmore E (2001) Application of time domain signal coding and artificial neural networks to passive acoustical identification of animals. Appl Acoust 62(12):1359–1374

    Article  Google Scholar 

  • Clemins P (2005) Automatic Classification of Animal Vocalizations. PhD thesis, Marquete University

  • Cohen J, Fox M (1976) Vocalizations in wild canids and possible effects of domestication. Behav Process 1:77–92

  • Coppinger R, Feinstein M (1991) “Hark! Hark! the dogs bark\(ldots\)” and bark and hark. Smithonian 21:119–128

    Google Scholar 

  • Druzhkova A, Thalmann O, Trifonov V, Leonard J, Vorobieva N, Ovodov N, ASGraphodatsky, Wayne R (2013) Ancient DNA analysis affirms the canid from Altai as a primitive dog. PLoS ONE 8(e57):754

    Google Scholar 

  • Duda R, Hart P, Stork D (2001) Pattern classification. Wiley, New York

    Google Scholar 

  • Fant G (1976) Acoustic theory of speech production. Mouton De Gruyter.

  • Faragó T, Pongrácz P, Miklósi A, Huber L, Virányi Z, Range F (2010a) Dogs’ expectation about signalers’ body size by virtue of their growls. PLoS ONE 5(12):e15,175

    Article  Google Scholar 

  • Faragó T, Pongrácz P, Range F, Virányi Z, Miklósi A (2010b) The bone is mine’: affective and referential aspects of dog growls. Anim Behav 79(4):917–925

    Article  Google Scholar 

  • Feddersen-Petersen DU (2000) Vocalization of European wolves (Canis lupus lupus l.) and various dog breeds (Canis lupus f. fam.). Arch Tierz Dummerstorf 43(4):387–397

    Google Scholar 

  • Fix E, Hodges JL (1951) Discriminatory analysis. Nonparametric discrimination: consistency properties. USAF Sch Aviat Med 4:261–279

    Google Scholar 

  • Frommolt KH, Goltsman M, MacDonald D (2003) Barking foxes, Alopex lagopus: field experiments in individual recognition in a territorial mammal. Anim Behav 65:509–518

    Article  Google Scholar 

  • Goodwin M, Gooding KM, Regnier F (1979) Sex pheromone in the dog. Science 203:559–561

    CAS  PubMed  Article  Google Scholar 

  • Gunasekaran S, Revathy K (2011) Automatic recognition and retrieval of wild animal vocalizations. Int J Comput Theor Eng 3(1):136–140

    Article  Google Scholar 

  • Hall M (1999) Correlation-based feature selection for machine learning. PhD thesis, Department of Computer Science, University of Waikato, UK

  • Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten I (2009) The WEKA data mining software: an update. SIGKDD Explor 11(1):10–18

    Article  Google Scholar 

  • Hartwig S (2005) Individual acoustic identification as a non-invasive conservation tool: an approach to the conservation of the African wild dog Lycaon pictus (Temminck, 1820). Bioacoustics 15:35–50

    Article  Google Scholar 

  • Hecht J, Miklósi A, Gácsi M (2012) Behavioral assessment and owner perceptions of behaviors associated with guilt in dogs. Appl Anim Behav Sci 139:134–142

    Article  Google Scholar 

  • Hunag C, Yang Y, Yang D, Chen Y (2009) Frog classification using machine learning techniques. Expert Syst Appl 36(2):3737–3743

    Article  Google Scholar 

  • Jain A, Murty MN, Flynn P (1999) Data clustering: a review. ACM Comput Surv 31(3):264–323

    Article  Google Scholar 

  • Le Cessie S, van Houwelingen JC (1992) Ridge estimators in logistic regression. Appl Stat 41(1):191–201

    Article  Google Scholar 

  • Liu H, Motoda H (1998) Feature selection for knowledge discovery and data mining. Kluwer Academic, Dordrecht

    Book  Google Scholar 

  • Lord K, Feinstein M, Coppinger R (2000) Barking and mobbing. Behav Process 81:358–368

    Article  Google Scholar 

  • Manser M, Seyfarth R, Cheney D (2002) Suricate alarm calls signal predator class and urgency. Trends Cogn Sci 6(2):55–57

    PubMed  Article  Google Scholar 

  • Maros K, Pongrácz P, Bárdos G, Molnár C, Faragó T, Miklósi A (2008) Dogs can discriminate barks from different situations. Appl Anim Behav Sci 114:159–167

    Article  Google Scholar 

  • Mazzini F, Townsend SW, Virányi Z, Range F (2013) Wolf howling is mediated by relationship quality rather than underlying emotional stress. Curr Biol 23:1677–1680

    CAS  PubMed Central  PubMed  Article  Google Scholar 

  • McConnell PB (1990) Acoustic structure and receiver response in domestic dogs, Canis familiaris. Anim Behav 39:897–904

    Article  Google Scholar 

  • McConnell PB, Baylis JR (1985) Interspecific communication in cooperative herding: acoustic and visual signals from human shepherds and herding dogs. Z Tierpsychol 67:302–382

    Article  Google Scholar 

  • Mech LD (1999) Alpha status, dominance and division of labor in wolf packs. Can J Zool 77:1196–1203

    Article  Google Scholar 

  • Meints K, Racca A, Hickey N (2010) Child-dog misunderstandings: children misinterpret dogs’ facial expressions. In: Proceedings of the 2nd Canine Science Forum, p 99

  • Miklósi A, Polgárdi R, Topál J, Csányi V (2000) Intentional behaviour in dog-human communication: an experimental analysis of “showing” behaviour in the dog. Anim Cogn 3:159–166

    Article  Google Scholar 

  • Minsky M (1961) Steps toward artificial intelligence. T Ins Radio Eng 49:8–30

    Google Scholar 

  • Molnár C, Pongrácz P, Dóka A, Miklósi A (2006) Can humans discriminate between dogs on the base of the acoustic parameters of barks? Behav Process 73:76–83

    Article  Google Scholar 

  • Molnár C, Kaplan F, Roy P, Pachet F, Pongrácz P, Dóka A, Moklósi A (2008) Classification of dog barks: a machine learning approach. Anim Cogn 11:389–400

    PubMed  Article  Google Scholar 

  • Molnár C, Pongrácz P, Faragó T, Dóka A, Miklósi A (2009) Dogs discriminate between barks: the effect of context and identity of the caller. Behav Process 82(2):198–201

    Article  Google Scholar 

  • Morton E (1977) On the occurrence and significance of motivation—structural rules in some bird and mammal sounds. Am Nat 111:855–869

    Article  Google Scholar 

  • Netto W, Planta D (1997) Behavioural testing for aggression in the domestic dog. Appl Anim Behav Sci 52:243–263

    Article  Google Scholar 

  • Overall K, Dunham A, Frank D (2001) Frequency of nonspecific clinical signs in dogs with separation anxiety, thunderstorm phobia, and noise phobia, alone or in combination. J Am Vet Med Assoc 219:467–473

    CAS  PubMed  Article  Google Scholar 

  • Parsons S (2001) Identification of New Zeeland bats (Chalinobus tuberculatus and Mystacina tuberculata) in flight from analysis of echolocation calls by artificial neural networks. J Zool 253(4):447–456

    Article  Google Scholar 

  • Parsons S, Jones G (2000) Acoustic identification of twelve species of echolocating bat by discriminant function analysis and artificial neural networks. J Exp Biol 203(17):2641–2656

    CAS  PubMed  Google Scholar 

  • Pongrácz P, Molnár C, Miklósi A, Csányi V (2005) Human listeners are able to classify dog (canis familiaris) barks recorded in different situations. J Comp Psychol 119:136–144

    PubMed  Article  Google Scholar 

  • Pongrácz P, Molnár C, Miklósi A (2006) Acoustic parameters of dog barks carry emotional information for humans. Appl Anim Behav Sci 100:228–240

    Article  Google Scholar 

  • Pongrácz P, Molnár C, Miklósi A (2010) Barking in family dogs: an ethological approach. Vet J 183:141–147

    PubMed  Article  Google Scholar 

  • Pongrácz P, Szabó E, Kis A, Péter A, Miklósi A (2014) More than noise? Field investigations of intraspecific acoustic communication in dogs (Canis familiaris). Appl Anim Behav Sci (in press)

  • Quinlan R (1993) C4.5: programs for machine learning. Morgan Kaufmann

  • Reid P (2009) Adapting to the human world: dogs’ responsiveness to our social cues. Behav Process 80:325–333

    Article  Google Scholar 

  • Roch M, Soldevilla M, Hoenigman R, Wiggins S, Hidebrand J (2008) Comparison of machine learning techniques for the classification of echolocation clicks from three species of odontocetes. Can Acoust 36(1):41–47

    Google Scholar 

  • Root-Gutteridge H, Bencsik M, Chebli M, Gentle L, Terrell-Nield C, Bourit A, Yarnell RW (2013) Improving individual identification in captive Eastern grey wolves (Canis lupus lycaon) using the time course of howl amplitudes. Bioacoustics 23(1):39–53

    Article  Google Scholar 

  • Saeys Y, Inza I, Larrañaga P (2007) A review of feature selection techniques in bioinformatics. Bioinformatics 23(19):2507–2517

    CAS  PubMed  Article  Google Scholar 

  • Serpell J, Hsu Y (2001) Development and validation of a novel method for evaluating behavior and temperament in guide dogs. Appl Anim Behav Sci 72:347–364

    PubMed  Article  Google Scholar 

  • Smith A, Birnie A, Lane K, French J (2009) Production and perception of sex differences in vocalizations of wied’s black-tufted-ear marmosets (callithrix kuhlii). Am J Primatol 71:324–332

    PubMed Central  PubMed  Article  Google Scholar 

  • Stone M (1974) Cross-validatory choice and assessment of statistical predictions. J R Stat Soc B 36(2):111–147

    Google Scholar 

  • Sucar E, Bielza C, Morales E, Hernandez-Leal P, Zaragoza J, Larrañaga P (2014) Multi-label classification with Bayesian network-based chain classifiers. Pattern Recogn Lett 41:14–22

    Article  Google Scholar 

  • Taylor A, Reby D, McComb K (2008) Human listeners attend to size information in domestic dog growls. J Acoust Soc Am 123(5):2903–2909

    PubMed  Article  Google Scholar 

  • Taylor A, Reby D, McComb K (2009) Context-related variation in the vocal growling behaviour of the domestic dog (Canis familiaris). Ethology 115(10):905–915

    Article  Google Scholar 

  • Taylor A, Reby D, McComb K (2010) Size communication in domestic dog, Canis familiaris, growls. Anim Behav 79(1):205–210

    Article  Google Scholar 

  • Téglás E, Gergely A, Kupán K, Miklósi A, Topál J (2012) Dogs’ gaze following is tuned to human communicative signals. Curr Biol 22:1–4

    Article  Google Scholar 

  • Tembrock G (1976) Canid vocalizations. Behav Process 1:57–75

    CAS  Article  Google Scholar 

  • Volodin I, Volodina E, Klenova A, Filatova O (2005) Individual and sexual differences in the calls of the monomorphic white-faced whistling duck dendrocygna viduata. Acta Ornithol 40:43–52

    Article  Google Scholar 

  • Wan M, Bolger N, Champagne F (2012) Human perception of fear in dogs varies according to experience with dogs. PLoS ONE 7(e51):775

    Google Scholar 

  • Yeon SC (2007) The vocal communication of canines. J Vet Behav 2:141–144

    Article  Google Scholar 

  • Yin S (2002) A new perspective on barking in dogs (Canis familiaris). J Comp Psychol 116:189–193

    PubMed  Article  Google Scholar 

  • Yin S, McCowan B (2004) Barking in domestic dogs: context specificity and individual identification. Anim Behav 68:343–355

    Article  Google Scholar 

  • Yovel Y, Au WWL (2010) How can dolphins recognize fish according to their echoes? A statistical analysis of fish echoes. PLoS ONE 5(11):e14,054

    Article  Google Scholar 

Download references

Acknowledgments

This work has been partially supported by the Spanish Ministry of Economy and Competitiveness, projects Cajal Blue Brain (C080020-09; the Spanish partner of the Blue Brain Project initiative from EPFL) and TIN2013-41592-P, by the János Bolyai Research Scholarship from the Hungarian Academy of Sciences, and co-financed by a grant from OTKA K82020. The authors are thankful to Celeste R. Pongrácz for the English proofreading of this manuscript and to Nikolett Czinege for help in preparing the bark databases.

Author information

Authors and Affiliations

  1. Student at the Universidad Alfonso X El Sabio, Av. Universidad, 1, 28691, Villanueva de la Cañada, Madrid, Spain

    Ana Larrañaga

  2. Department of Ethology, Biological Institute, Eötvös Loránd University, 1117 Pázmány Péter sétány 1/c, Budapest, Hungary

    Péter Pongrácz, Tamás Faragó & Anna Bálint

  3. Computational Intelligence Group, Universidad Politecnica de Madrid, Campus de Montegancedo, 28660, Boadilla del Monte, Madrid, Spain

    Concha Bielza & Pedro Larrañaga

Authors
  1. Ana Larrañaga
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Concha Bielza
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Péter Pongrácz
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Tamás Faragó
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Anna Bálint
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Pedro Larrañaga
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Pedro Larrañaga.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 42 KB)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Larrañaga, A., Bielza, C., Pongrácz, P. et al. Comparing supervised learning methods for classifying sex, age, context and individual Mudi dogs from barking. Anim Cogn 18, 405–421 (2015). https://doi.org/10.1007/s10071-014-0811-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10071-014-0811-7

Keywords

  • Mudi dog barks
  • Acoustic communication
  • Feature subset selection
  • Machine learning
  • Supervised classification
  • \(K\)-fold cross-validation