Neural network modeling of a dolphin’s sonar discrimination capabilities

Andersen, Lars Nonboe; Rasmussen, Asbjørn; Au, Whitlow W. L.; Nachtigall, Paul E.; Roitblat, Herbert L.

doi:10.1121/1.413700

Cited by 37 publications

(15 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Because artificial neural networks resemble the organization of biological neural systems, they have been used frequently to model the performance of biological systems. There have been several efforts to model the echolocation performance of dolphins using neural networks ͑e.g., Au et al, 1995;Roitblat et al, 1989͒. The networks in these studies used temporal and/or spectral features of the echoes and performed at times better or worse than the dolphin. The drawback of these studies is that they did not attempt to compare the error patterns of the dolphin and the network, so it is difficult to ascertain whether the network was using the same features as the dolphin.…”

Section: Discussionmentioning

confidence: 96%

Acoustic features of objects matched by an echolocating bottlenose dolphin

DeLong

Lemonds

et al. 2006

The Journal of the Acoustical Society of America

Self Cite

View full text Add to dashboard Cite

The focus of this study was to investigate how dolphins use acoustic features in returning echolocation signals to discriminate among objects. An echolocating dolphin performed a match-to-sample task with objects that varied in size, shape, material, and texture. After the task was completed, the features of the object echoes were measured (e.g., target strength, peak frequency). The dolphin's error patterns were examined in conjunction with the between-object variation in acoustic features to identify the acoustic features that the dolphin used to discriminate among the objects. The present study explored two hypotheses regarding the way dolphins use acoustic information in echoes: (1) use of a single feature, or (2) use of a linear combination of multiple features. The results suggested that dolphins do not use a single feature across all object sets or a linear combination of six echo features. Five features appeared to be important to the dolphin on four or more sets: the echo spectrum shape, the pattern of changes in target strength and number of highlights as a function of object orientation, and peak and center frequency. These data suggest that dolphins use multiple features and integrate information across echoes from a range of object orientations.

show abstract

Section: Discussionmentioning

confidence: 96%

Acoustic features of objects matched by an echolocating bottlenose dolphin

DeLong

Lemonds

et al. 2006

The Journal of the Acoustical Society of America

Self Cite

View full text Add to dashboard Cite

show abstract

“…The humans reported using pitch (potentially TSP) and duration to identify the cylinders and using pitch and timbre to identify the spheres. Neural network models using echoes from the cylinders classifed them using frequency information, although better discrimination resulted from use of both time and frequency information (Au, Andersen, Rasmussen, Roitblat, & Nachtigall, 1995).…”

Section: Echoic Object Discrimination: Echoic Cuesmentioning

confidence: 99%

Echoic Object Recognition by the Bottlenose Dolphin

Harley¹,

DeLong²

2008

CCBR

View full text Add to dashboard Cite

Object recognition, essential to many animals, often occurs underwater and in poor visibility conditions for bottlenose dolphins. Bottlenose dolphins can use sound through their ability to echolocate in order to recognize objects. Echoic object recognition is an unusual faculty that offers rich research opportunities and is the focus of this article. This review begins with a brief overview of the dolphin's echolocation system followed by considerations of echoic object discrimination, echoic object constancy, the use of echo trains versus individual echoes for object recognition, and extraction of object feature information from echoes. The authors present new data relating the acoustic analysis of objects with a dolphin's ability to recognize those objects. The results highlight the potential uses for simultaneous analysis of acoustic and behavioral data in order to understand better which features of echoes and echo trains allow the dolphin to recognize objects across vision and echolocation.

show abstract

“…ArtiWcial neural networks emulate the parallel processing ability and pattern recognition capability of the brain and the use of such methods in dolphin echolocation and other Welds of bioacoustics is worthy (Au et al 1995). Another Weld of behavioral studies where artiWcial intelligence methods were used is image recognition from video recordings for behavioral analysis (Burghardt et al 2004;Burghardt and Calic 2006;Calic et al 2005).…”

Section: Introductionmentioning

confidence: 99%

Classification of dog barks: a machine learning approach

Molnár

Kaplan

Roy³

et al. 2008

Anim Cogn

View full text Add to dashboard Cite

In this study we analyzed the possible contextspeciWc and individual-speciWc features of dog barks using a new machine-learning algorithm. A pool containing more than 6,000 barks, which were recorded in six diVerent communicative situations was used as the sound sample. The algorithm's task was to learn which acoustic features of the barks, which were recorded in diVerent contexts and from diVerent individuals, could be distinguished from another. The program conducted this task by analyzing barks emitted in previously identiWed contexts by identiWed dogs. After the best feature set had been obtained (with which the highest identiWcation rate was achieved), the eYciency of the algorithm was tested in a classiWcation task in which unknown barks were analyzed. The recognition rates we found were highly above chance level: the algorithm could categorize the barks according to their recorded situation with an eYciency of 43% and with an eYciency of 52% of the barking individuals. These Wndings suggest that dog barks have context-speciWc and individual-speciWc acoustic features. In our opinion, this machine learning method may provide an eYcient tool for analyzing acoustic data in various behavioral studies.

show abstract

Neural network modeling of a dolphin’s sonar discrimination capabilities

Cited by 37 publications

References 7 publications

Acoustic features of objects matched by an echolocating bottlenose dolphin

Acoustic features of objects matched by an echolocating bottlenose dolphin

Echoic Object Recognition by the Bottlenose Dolphin

Classification of dog barks: a machine learning approach

Contact Info

Product

Resources

About