Meishan pig estrus monitoring method based on acoustic information

An acoustic and acoustic signal technology, applied in the field of estrus monitoring of Meishan pigs based on acoustic information, can solve weak problems, achieve the effects of reducing labor costs, improving the level of informatization, and improving monitoring efficiency

Inactive Publication Date: 2019-03-19
HUAZHONG AGRI UNIV +1
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the research on sow estrus monitoring based on sound information is still very weak. The research on pig sounds mainly focuses on pig coughing and suck

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Meishan pig estrus monitoring method based on acoustic information
  • Meishan pig estrus monitoring method based on acoustic information
  • Meishan pig estrus monitoring method based on acoustic information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] A method for monitoring Meishan pig estrus based on acoustic information, said method comprising the following steps:

[0039] Step 1: Collect the sound signals produced by Meishan pigs when they are in estrus through the recording equipment placed in the pigsty, and at the same time collect the sound signals of sneezing, eating, screaming, humming and ear shaking of Meishan pigs and Landrace pigs in the pig farm environment ;

[0040] Step 2: The Wiener speech enhancement algorithm based on wavelet threshold multi-window spectrum preprocesses the pig sound signal collected in step 1, realizes denoising of the pig sound signal, and obtains the pig sound signal after denoising;

[0041] Step 3: Using the double-threshold endpoint detection method based on short-term energy to extract the effective signal from the denoised pig sound signal in step 2 to obtain an effective pig sound signal;

[0042] Step 4: Analyze the time-frequency characteristics of the effective pig s...

Embodiment 2

[0055] 1 Pig sound collection and preprocessing

[0056] 1.1 Pig sound collection

[0057] The sound collection of pigs was completed in the boutique pig breeding farm of Huazhong Agricultural University. The acquisition device is Meibo-M66 recording pen, the sampling frequency is 48kHz, the sampling accuracy is 16 bits, two-channel continuous acquisition, and the maximum working time is 24h. The pigs are distributed in three adjacent pens, with 5 Meishan pigs in the middle pen and 5 Landrace pigs in the other two pens. The experienced manager of the pig farm confirmed that there were only 3 Meishan pigs in estrus. The sound signal in the pig farm environment is complex and diverse, mixed with a variety of noises and the sounds of multiple pigs. The collected pig sounds were classified, marked and screened, and 500 Meishan pig estrous sound samples and 500 non-estrous sound samples were selected, among which the non-estrous sound samples included 100 sneezing samples, 110 e...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention belongs to the technical field of animal estrus monitoring, and particularly relates to a meishan pig estrus monitoring method based on acoustic information. The method comprises the steps that a meishan pig estrus acoustic signal and the sound made by the sniffling, eating, screaming, mumbling and ear moving of other pigs in a pig farm environment are firstly collected, pre-processing is conducted on the pig acoustic signal through multi-window spectrum Wiener speech enhancement based on wavelet thresholding and double-threshold end-point detection based on short-time energy, and the denoising and effective signal detection of pig acoustic signal are achieved; the time-and-frequency domain features of the pig acoustic signal are analyzed by using a time-and-frequency analyzing method and a short-time analyzing technology, 1352-dimension of meishan pig acoustic features in total of 300-dimension short-time energy, 300-dimension short-time zero crossing rate, 32-dimensionsub band frequency range energy ratio based on six-layer wavelet decomposing and 720-dimension Vermeer cepstral coefficients which are standardized by a time wrapping algorithm are extracted; the recognition of meishan pig estrus sound performed by a depth belief network (DBN) is constructed. The method has the advantages that the estrus period of the meishan pig is accurately judged to help the timely conception of sows, achieve the propagation potential of the sows and improve economical benefits.

Description

technical field [0001] The invention belongs to the technical field of animal estrus monitoring, and in particular relates to a method for monitoring Meishan pig estrus based on acoustic information. Background technique [0002] In recent years, with the adjustment of the industrial structure of live pigs and sows, the aquaculture industry has rapidly moved towards large-scale, high-efficiency, intelligent, and intensified directions, which put forward higher requirements for the timely monitoring of sow estrus. Estrus monitoring plays an important role in pig farm management. Insemination during estrus can greatly increase the chances of conception, thereby exerting the reproductive potential of animals and improving economic benefits. Estrus monitoring in sows can generally be divided into two categories. One is the traditional method, which mainly includes external observation method, vaginal mucus inspection method, standing reflex inspection method, and boar test meth...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): A01K29/00
CPCA01K29/005
Inventor 黎煊端木凡昌刘望宏高云雷明刚杨迪朱望武赵建曹唪粒郭继亮明志伟马伟王文凯
Owner HUAZHONG AGRI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap