Data Set Information:

该数据集被用于几个与anuran物种识别挑战相关的分类任务中。它是一个包含三列标签的多标签数据集。这个数据集是通过分割60个音频记录创建的，这些音频记录属于4个不同的科、8个属和10个种。每个音频对应一个样本（单个青蛙），记录ID也包含在一个额外的列中。我们使用谱熵和二元聚类方法来检测属于每个音节的音频帧。在Matlab中进行了图像分割和特征提取。分割后得到7195个音节，作为训练和测试分类器的实例。这些记录是在真实噪声条件下（背景声）就地收集的。有些物种来自马瑙斯亚马逊大学的校园，还有马塔尔的其他大学。￠巴西恩蒂卡，其中一人来自阿根廷科尔多瓦。记录以wav格式存储，采样频率为44.1kHz，分辨率为32位，这使我们能够分析高达22kHz的信号。从每个提取的音节中，使用44个三角形滤波器计算22个MFCC。这些系数在-1 a‰mfcc a‰1之间标准化。每个类的实例数为：

Families:
Bufonidae              68
    Dendrobatidae         542
    Hylidae              2165
    Leptodactylidae      4420

Genus:
    Adenomera          4150
    Ameerega            542
    Dendropsophus       310
    Hypsiboas          1593
    Leptodactylus       270
    Osteocephalus       114
    Rhinella             68
    Scinax              148

Species:
    AdenomeraAndre             672
    AdenomeraHylaedacta€|       3478
    Ameeregatrivittata         542
    HylaMinuta                 310
    HypsiboasCinerascens       472
    HypsiboasCordobae         1121
    LeptodactylusFuscus        270
    OsteocephalusOophaa€|        114
    Rhinellagranulosa           68
    ScinaxRuber                148

Attribute Information:

Mel-frequency cepstral coefficients (MFCCs) are coefficients that collectively make up an mel-frequency cepstrum (MFC). Due to each syllable has different length, every row (i) was normalized acording to MFCCs_i/(max(abs(MFCCs_i))).

Relevant Papers:

1) colonNA, J. G.; CRISTO, M.; SALVATIERRA, M.; NAKAMURA, E. F.
An Incremental Technique for Real-Time Bioacoustic Signal Segmentation.
Expert Systems with Applications, v. 42, p. 7367-7374, 2015.

2) colonNA, J. G.; GAMA, J.; NAKAMURA, E. F.
How to Correctly evaluate an Automatic Bioacoustics Classification Method.
In: 17th Conference of the Spanish Association for Artificial Intelligence (CAEPIA).
Lecture Notes in Computer Science. 986ed.: Springer International Publishing, 2016, v. , p. 37-47.

3) colonNA, J. G.; GAMA, J.; NAKAMURA, E. F.
Recognizing Family, Genus, and Species of Anuran Using a Hierarchical Classification Approach.
Lecture Notes in Computer Science. 995ed.: Springer International Publishing, 2016, v. 9956, p. 198-212.

4) colonNA, J. G.; RIBAS, A. D.; SANTOS, E. M.; NAKAMURA, E. F.
Feature Subset Selection for Automatically Classifying Anuran Calls Using Sensor Networks.
In: International Joint Conference on Neural Networks, 2012, Brisbane.
Proceedings of the International Joint Conference on Neural Networks (IJCNN 2012), 2012. p. 1-8. IEEE

5) colonNA, J. G.; PEET, T.; FERREIRA, C. A.; JORGE, A. M.; GOMES, E. F.; GAMA, J. (2016, July).
Automatic Classification of Anuran Sounds Using Convolutional Neural Networks.
In Proceedings of the Ninth International C* Conference on Computer Science & Software Engineering (No. C3S2E '16, pp. 73-78). ACM.

6) colonNA, J. G.; CRISTO, M.; NAKAMURA, E. F. (2014, August).
A Distributed Approach for Classifying Anuran Species based on Their Calls.
In Pattern Recognition (ICPR), 2014 22nd International Conference on (pp. 1242-1247). IEEE.

7) RIBAS, A. D.; colonNA, J. G.; FIGUEIREDO, C. M. S.; NAKAMURA, E. F.
Similarity clustering for data fusion in wireless sensor networks using k-means
The 2012 International Joint Conference on Neural Networks (IJCNN 2012), p. 1-7. IEEE

8) DIAZ, J. M.; colonNA, J. G.; SOARES, R. B.; FIGUEREIDO, C. M. S.; NAKAMURA, E. F.
Compressive sensing for efficiently collecting wildlife sounds with wireless sensor networks
21st International Conference on Computer Communications and Networks (ICCCN 2012), p. 1-7. IEEE

Citation Request:

Please refer to the Machine Learning Repository's citation policy