蛋鸡发声与机械噪声特征提取及分类识别

规模化蛋鸡舍中不同机械设备运行所产生的噪声会干扰蛋鸡声音提取。为了分析分类识别蛋鸡发声与机械噪声的可行性,该研究以蛋鸡产蛋发声、鸣唱声和规模化蛋鸡舍中通风系统、饲喂系统、清粪系统、集蛋系统单独运行时的噪声为研究对象,运用LabVIEW软件提取了蛋鸡发声和机械噪声的功率谱密度,以子带功率比为特征向量,在数据挖掘平台Weka上应用J48决策树算法构建声音分类识别器。结果表明,蛋鸡产蛋发声和鸣唱声的最大功率比位于频率范围689~1 378 Hz内,通风系统噪声和饲喂系统噪声的最大功率比位于频率范围0~689 Hz内,清粪系统噪声和集蛋系统噪声的最大功率比位于频率范围1 378~2 756 Hz内;该声音分类识别模型的平均识别率为93.4%,其中蛋鸡鸣唱声和产蛋发声的识别率分别为85.9%和92.5%,机械噪声的分类识别率更高,说明基于子带功率比的声音识别方法具有较好的识别效果,该结果为规模化蛋鸡养殖舍复杂声音环境中检测蛋鸡声音提供了参考。

Feature extraction and classification of laying hens' vocalization and mechanical noise

Abstract: Vocalizations of farm animals may accompany with particular states of animals' mood or emotion. Based on these vocalizations we can judge animals' current need and impaired welfare, so they could be regarded as indicators of animals' state of welfare. However, noise made by different mechanical systems in the commercial poultry house can interfere with the detection of laying hens' vocalization. The purpose of this study is to analyze and classify vocalizations of laying hens and mechanical noises. The analysis and classification were based on time domain and frequency domain characteristics of the signals. Vocalization of egg laying process and song were two kinds of typical laying hens' vocalizations. Mechanical noises in farm mainly include ventilation system noise, manure removal system noise, egg collection system noise and feeding system noise. The power spectral density and sub-band power ratio of laying hens' vocalizations and mechanical noises were extracted by using a sound analysis system based on the program development environment LabVIEW, J48 decision tree algorithm was used to classify and identify laying hens' vocalization and mechanical noise on the data mining platform of Weka. The results showed that the frequency ranges of vocalization of egg laying process and song were mainly distributed within 400-2 500 Hz, the frequency ranges of ventilation system noise and feeding system noise were mainly distributed below 1 500 Hz, the frequency ranges of manure removal system noise and egg collection system noise were located within 100-3 000 Hz, which was wider than the frequency ranges of other sounds. The max power ratios of vocalization of egg laying process and song were (83.4±9.9)% and 76.7%±18.8%, which were within the frequency range >689-1 378 Hz, the power ratios of vocalization of egg laying process and song were higher than that of mechanical noises in the frequency range >689-1 378 Hz; The max power ratios of ventilation system noise and feeding system noise were 68.1%±2.1% and 74.5%±9.7%, which were within the frequency range 0-689 Hz, the power ratios of ventilation system noise and feeding system noise were higher than that of others in the frequency range 0-689 Hz; The power ratio of manure removal system noise and egg collection system noise were relatively uniform, the maximum power ratios were just 37.2%±4.1% and 40.9%±3.4%, which were within the frequency range >1 378-2 756 Hz, the power ratios of manure removal system noise and egg collection system noise were higher than that of others in the frequency range >1 378- 2 756 Hz. The sound recognition model based on sub-band power ratio had an average correct classification rate of 93.4%, 92.5% of vocalizations of egg laying process and 85.9% of songs were correctly identified, and the correct classification ratios of ventilation system noise, feeding system noise, manure removal system noise and egg collection system noise were 97.7%, 96.2%, 97.8%, and 94.4%, which were higher than that of laying hens' vocalizations. The method based on sub-band power ratio has a good recognition effect, which can provide a reference for detecting vocalizations of animals from complex noise environment in the commercial farm.