Census and monitoring based on individually identifiable vocalizations: the role of neural networks

Vocal individuality is widely suggested as a method for identifying individuals within a population. But few studies have explored its performance in real or simulated conservation situations. Here we simulated the use of vocal individuality to monitor the calling corncrake ( Crex crex ), a secretive and endangered land rail. Our data set contained 600 calls from 30 individuals and was used to simulate a population of corncrakes being counted and monitored. We tested three different neural network models for their ability to discriminate between and to identify individuals. Neural networks are non-linear classification tools widely applied to both biological and non-biological identification tasks. Backpropagation and probabilistic neural networks were used to simulate the reidentification of members of a known population (monitoring) and a Kohonen network was used to simulate the counting of a population of unknown size (census). We found that both backpropagation and probabilistic networks identified all individuals correctly all the time, irrespective of sample size. Kohonen networks were more variable in performance but estimated population size to within one individual of the actual size. Our results indicate that neural networks can be used effectively together with recordings of vocalizations in census and monitoring tasks.

[1]  M. Ryan,et al.  Neural networks predict response biases of female túngara frogs , 1998, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[2]  H L Roitblat,et al.  The neural network classification of false killer whale (Pseudorca crassidens) vocalizations. , 1998, The Journal of the Acoustical Society of America.

[3]  Donald R. Beightol,et al.  Sonagraphic Analysis of the American Woodcock's "Peent" Call , 1973 .

[4]  Hal Whitehead,et al.  AN ASSESSMENT OF CHANGES WITH TIME IN THE MARKING PATTERNS USED FOR PHOTOIDENTIFICATION OF INDIVIDUAL SPERM WHALES, PHYSETER MACROCEPHALUS , 1995 .

[5]  Stuart Parsons,et al.  Identification of New Zealand bats (Chalinolobus tuberculatus and Mystacina tuberculata) in flight from analysis of echolocation calls by artificial neural networks , 2001 .

[6]  J. Ford,et al.  Vocal traditions among resident killer whales (Orcinus orca) in coastal waters of British Columbia , 1991 .

[7]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[8]  Herbert L. Roitblat,et al.  NEURAL NETWORK MODELING OF A DOLPHIN'S SONAR DISCRIMINATION CAPABILITIES , 1994 .

[9]  M. Ryan,et al.  History influences signal recognition: neural network models of túngara frogs , 2000, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[10]  P Spong,et al.  Dialect change in resident killer whales: implications for vocal learning and cultural transmission , 2000, Animal Behaviour.

[11]  D. Weary,et al.  Use of male blue monkey “Pyow” calls for long‐term individual identification , 1992, American journal of primatology.

[12]  Peter K. McGregor,et al.  Discrimination of individually characteristic electric organ discharges by a weakly electric fish , 1992, Animal Behaviour.

[13]  J Placer,et al.  A fuzzy-neural system for identification of species-specific alarm calls of Gunnison's prairie dogs , 2000, Behavioural Processes.

[14]  Heribert Hofer,et al.  Loud calling in a female-dominated mammalian society: I. Structure and composition of whooping bouts of spotted hyaenas, Crocuta crocuta , 1991, Animal Behaviour.

[15]  V. Janik,et al.  Signature whistle variations in a bottlenosed dolphin, Tursiops truncatus , 1994, Behavioral Ecology and Sociobiology.

[16]  L. May.  INDIVIDUALLY DISTINCTIVE CORNCRAKE CREX CREX CALLS: A PILOT STUDY , 1994 .

[17]  Geoffrey E. Hinton,et al.  How neural networks learn from experience. , 1992, Scientific American.

[18]  K. Cortopassi,et al.  THE COMPARISON OF HARMONICALLY RICH SOUNDS USING SPECTROGRAPHIC CROSS-CORRELATION AND PRINCIPAL COORDINATES ANALYSIS , 2000 .

[19]  S. Lek,et al.  Individuality in the groans of fallow deer ( Dama dama ) bucks , 1998 .

[20]  V B Deecke,et al.  Quantifying complex patterns of bioacoustic variation: use of a neural network to compare killer whale (Orcinus orca) dialects. , 1999, The Journal of the Acoustical Society of America.

[21]  W. Au,et al.  Comparison of sonar discrimination: dolphin and an artificial neural network. , 1994, The Journal of the Acoustical Society of America.

[22]  W. M. Masters,et al.  Sonar signals of big brown bats, Eptesicus fuscus, contain information about individual identity, age and family affiliation , 1995, Animal Behaviour.

[23]  Brian K. Flachs,et al.  DISTINGUISHING INDIVIDUAL MALE WILD TURKEYS BY ANALYZING VOCALIZATIONS USING A PERSONAL COMPUTER , 1990 .

[24]  R. W. Mannan,et al.  Identification of individual breeding bald eagles by voice analysis , 1989 .

[25]  S. Parsons,et al.  Acoustic identification of twelve species of echolocating bat by discriminant function analysis and artificial neural networks. , 2000, The Journal of experimental biology.

[26]  L. May,et al.  INDIVIDUALLY DISTINCTIVE CORNCRAKE CREX CREX CALLS: A FURTHER STUDY , 1998 .

[27]  Leon S. Durbin,et al.  INDIVIDUALITY IN THE WHISTLE CALL OF THE ASIATIC WILD DOG CUON ALPINUS , 1998 .

[28]  Peter K. McGregor,et al.  A COMPARISON OF SOME TECHNIQUES USED TO ASSESS VOCAL INDIVIDUALITY , 2001 .

[29]  A Dhondt,et al.  Individual voice recognition in birds. , 1992, Trends in ecology & evolution.

[30]  W. Mitchell Masters,et al.  The use of neural networks to classify echolocation calls of bats , 1999 .

[31]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[32]  I. Dimopoulos,et al.  Artificial neural networks as a classification method in the behavioural sciences , 1997, Behavioural Processes.

[33]  D. Saunders,et al.  Consistent individuality of voice in birds as a management tool , 1988 .