Limits...
Plant classification from bat-like echolocation signals.

Yovel Y, Franz MO, Stilz P, Schnitzler HU - PLoS Comput. Biol. (2008)

Bottom Line: We used a standard machine learning algorithm (SVM) to automatically extract suitable linear combinations of time and frequency cues from the spectrograms such that classification with high accuracy is enabled.This demonstrates that ultrasonic echoes are highly informative about the species membership of an ensonified plant, and that this information can be extracted with rather simple, biologically plausible analysis.Thus, our findings provide a new explanatory basis for the poorly understood observed abilities of bats in classifying vegetation and other complex objects.

View Article: PubMed Central - PubMed

Affiliation: Animal Physiology, Zoological Institute, University of Tuebingen, Tuebingen, Germany.

ABSTRACT
Classification of plants according to their echoes is an elementary component of bat behavior that plays an important role in spatial orientation and food acquisition. Vegetation echoes are, however, highly complex stochastic signals: from an acoustical point of view, a plant can be thought of as a three-dimensional array of leaves reflecting the emitted bat call. The received echo is therefore a superposition of many reflections. In this work we suggest that the classification of these echoes might not be such a troublesome routine for bats as formerly thought. We present a rather simple approach to classifying signals from a large database of plant echoes that were created by ensonifying plants with a frequency-modulated bat-like ultrasonic pulse. Our algorithm uses the spectrogram of a single echo from which it only uses features that are undoubtedly accessible to bats. We used a standard machine learning algorithm (SVM) to automatically extract suitable linear combinations of time and frequency cues from the spectrograms such that classification with high accuracy is enabled. This demonstrates that ultrasonic echoes are highly informative about the species membership of an ensonified plant, and that this information can be extracted with rather simple, biologically plausible analysis. Thus, our findings provide a new explanatory basis for the poorly understood observed abilities of bats in classifying vegetation and other complex objects.

Show MeSH

Related in: MedlinePlus

Effect of the DFT window length on classification performance.(A) The area under the ROC curve (AUC) for four different window lengths ranging from 250–2000 µs. Average results are presented together with the blackthorn classification case, in which the effect was most clear. The difference between a 2000 µs window length and the other lengths is significant (P<0.05), whereas the difference between the three other lengths is not. (B) Average spectrograms for a window length of 2000 µs (first row) and a 250 µs one (second row) for the classification task of blackthorn vs. the rest. It can be seen how time information is decreased (i.e. smeared) for the 2000 µs window (first row). This makes separation between the two classes easier with the 250 µs window (second row) even when only examining them visually.
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC2267002&req=5

pcbi-1000032-g006: Effect of the DFT window length on classification performance.(A) The area under the ROC curve (AUC) for four different window lengths ranging from 250–2000 µs. Average results are presented together with the blackthorn classification case, in which the effect was most clear. The difference between a 2000 µs window length and the other lengths is significant (P<0.05), whereas the difference between the three other lengths is not. (B) Average spectrograms for a window length of 2000 µs (first row) and a 250 µs one (second row) for the classification task of blackthorn vs. the rest. It can be seen how time information is decreased (i.e. smeared) for the 2000 µs window (first row). This makes separation between the two classes easier with the 250 µs window (second row) even when only examining them visually.

Mentions: To determine the effect of the DFT window length we varied it and kept the percentage of the overlap between sequential windows constant (Figure 6). The extent of the spectrograms in the temporal direction decreased with window length whereas the extent in frequency increased such that the overall information remained constant. Up to a certain window length (1000), representing a time bin of 1ms (with 80% overlap) the window length had no significant influence on classification performance. Above this length however, for the 2000 window, there was an overall significant decrease (0.07 on average) in classification performance (2-way ANOVA, F3,80>18.5, P<0.0001). This decrease mainly affected the three classification tasks blackthorn vs. rest (0.25 on average, 1-way ANOVA, F3,16>24.8, P<3−6), beech vs. rest (0.13 on average, 1-way ANOVA, F3,16>6.5, P<0.005) and corn vs. rest (0.03 by average, 1-way ANOVA, F3,16>2.85, P<0.07) while the performance of the other two tasks did not change. The decrease is probably a result of the loss of time information due to excessive smoothing. In general, the most suitable window length depends on the specific classification task.


Plant classification from bat-like echolocation signals.

Yovel Y, Franz MO, Stilz P, Schnitzler HU - PLoS Comput. Biol. (2008)

Effect of the DFT window length on classification performance.(A) The area under the ROC curve (AUC) for four different window lengths ranging from 250–2000 µs. Average results are presented together with the blackthorn classification case, in which the effect was most clear. The difference between a 2000 µs window length and the other lengths is significant (P<0.05), whereas the difference between the three other lengths is not. (B) Average spectrograms for a window length of 2000 µs (first row) and a 250 µs one (second row) for the classification task of blackthorn vs. the rest. It can be seen how time information is decreased (i.e. smeared) for the 2000 µs window (first row). This makes separation between the two classes easier with the 250 µs window (second row) even when only examining them visually.
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC2267002&req=5

pcbi-1000032-g006: Effect of the DFT window length on classification performance.(A) The area under the ROC curve (AUC) for four different window lengths ranging from 250–2000 µs. Average results are presented together with the blackthorn classification case, in which the effect was most clear. The difference between a 2000 µs window length and the other lengths is significant (P<0.05), whereas the difference between the three other lengths is not. (B) Average spectrograms for a window length of 2000 µs (first row) and a 250 µs one (second row) for the classification task of blackthorn vs. the rest. It can be seen how time information is decreased (i.e. smeared) for the 2000 µs window (first row). This makes separation between the two classes easier with the 250 µs window (second row) even when only examining them visually.
Mentions: To determine the effect of the DFT window length we varied it and kept the percentage of the overlap between sequential windows constant (Figure 6). The extent of the spectrograms in the temporal direction decreased with window length whereas the extent in frequency increased such that the overall information remained constant. Up to a certain window length (1000), representing a time bin of 1ms (with 80% overlap) the window length had no significant influence on classification performance. Above this length however, for the 2000 window, there was an overall significant decrease (0.07 on average) in classification performance (2-way ANOVA, F3,80>18.5, P<0.0001). This decrease mainly affected the three classification tasks blackthorn vs. rest (0.25 on average, 1-way ANOVA, F3,16>24.8, P<3−6), beech vs. rest (0.13 on average, 1-way ANOVA, F3,16>6.5, P<0.005) and corn vs. rest (0.03 by average, 1-way ANOVA, F3,16>2.85, P<0.07) while the performance of the other two tasks did not change. The decrease is probably a result of the loss of time information due to excessive smoothing. In general, the most suitable window length depends on the specific classification task.

Bottom Line: We used a standard machine learning algorithm (SVM) to automatically extract suitable linear combinations of time and frequency cues from the spectrograms such that classification with high accuracy is enabled.This demonstrates that ultrasonic echoes are highly informative about the species membership of an ensonified plant, and that this information can be extracted with rather simple, biologically plausible analysis.Thus, our findings provide a new explanatory basis for the poorly understood observed abilities of bats in classifying vegetation and other complex objects.

View Article: PubMed Central - PubMed

Affiliation: Animal Physiology, Zoological Institute, University of Tuebingen, Tuebingen, Germany.

ABSTRACT
Classification of plants according to their echoes is an elementary component of bat behavior that plays an important role in spatial orientation and food acquisition. Vegetation echoes are, however, highly complex stochastic signals: from an acoustical point of view, a plant can be thought of as a three-dimensional array of leaves reflecting the emitted bat call. The received echo is therefore a superposition of many reflections. In this work we suggest that the classification of these echoes might not be such a troublesome routine for bats as formerly thought. We present a rather simple approach to classifying signals from a large database of plant echoes that were created by ensonifying plants with a frequency-modulated bat-like ultrasonic pulse. Our algorithm uses the spectrogram of a single echo from which it only uses features that are undoubtedly accessible to bats. We used a standard machine learning algorithm (SVM) to automatically extract suitable linear combinations of time and frequency cues from the spectrograms such that classification with high accuracy is enabled. This demonstrates that ultrasonic echoes are highly informative about the species membership of an ensonified plant, and that this information can be extracted with rather simple, biologically plausible analysis. Thus, our findings provide a new explanatory basis for the poorly understood observed abilities of bats in classifying vegetation and other complex objects.

Show MeSH
Related in: MedlinePlus