پردازش سیگنال‌های صوتی خروس به‌منظور تشخیص بلوغ جنسی و پیوبرتی

پرندگان نابالغ با گذر از دوران پیوبرتی به بلوغ جنسی می‌رسند که با تغییرات صوتی صدا همراه است و بعد از دوران بلوغ، ساختار صوتی تکامل می‌یابد. هدف اصلی این پژوهش تشخیص پیوبرتی و بلوغ جنسی خروس‌های مادر از روی سیگنال‌های صوتی می‌باشد. برای انجام این کار خروس‌ها به سه دسته خروس‌های نابالغ، خروس‌های در دوران پیوبرتی و خروس‌های بالغ تقسیم شدند. معیارهای نخستین انزال و غلظت اسپرم به‌ترتیب برای پیوبرتی و بلوغ جنسی استفاده شدند. پس از ضبط سیگنال‌های صوتی، ضرایب کد پیش‌بینی خطی (lpc) از حوزه فرکانس به‌عنوان ویژگی‌های صوتی استخراج شدند. این ویژگی‌های صوتی به‌عنوان ورودی‌های طبقه‌بند k نزدیک‌ترین همسایه (knn) استفاده شدند و خروجی طبقه‌بند سه دسته‌ی خروس‌های نابالغ، خروس‌های در دوران پیوبرتی و خروس‌های بالغ می‌باشد. نتایج مقادیر درستی، حساسیت و دقت به‌ترتیب 98.7%، 98.3% و 98.8% را برای طبقه‌بندی خروس‌ها نشان می‌دهد.

Sound Signals Processing of Roosters for Sexual Maturity and Puberty Diagnosis

Introduction;Immature birds, like humans and many animals, pass through the puberty period to sexual maturity that is accompanied by sound changes and after the sexual maturity, the sound structure evolves. The puberty period is one of the most important periods in the breeder chicken farms. Because the feeding of roosters at this age can delay or accelerate the time of sexual maturity. On the other hand, the diagnosis of mature roosters to mating with chickens increases egg production in early adulthood. Sexual maturity is a summary of the morphological and physiological changes its peak in the roosters from the age of 16 to 24 weeks. In female birds, the beginning of the first laying is considered to be sexual maturity, while the exact timing of sexual maturity in a male bird cannot be determined. The puberty term means the age at which reproduction is possible for the first time, but reproductive processes have not yet evolved. Therefore, the chance of pregnancy at this age is very low and fertility will not be optimal. Puberty can be likened to teenage years in humans. Bird sounds are generated mainly by the syrinx and humans speak with the stimulation of the vocal cords. The sound produced by the bird is similar to how human speech is produced. Therefore, techniques used to recognize human speech are also likely to be useful for classifying bird sounds.;Material and Methods;Variation in an animal’s vocalizations can provide clues about how the animal uses sound, as well as qualities of the individual that is vocalizing. Bioacoustics research depends heavily on the ability to characterize these variations. The main goal of this study is to diagnosis puberty and the sexual maturity in bred roosters based on sound signals. To do this, the number of roosters with the first ejaculation for puberty and sperm concentration criterion for sexual maturity was divided into three groups of immature males, roosters during the puberty period and adult roosters and the rooster 's acoustic signals were recorded by a microphone in a doublesided glass box (50x50x60 cm). The main purpose of using the box is to prevent the effects of noise in the environment on acoustic signals because otherwise, the sound signal of the rooster is unreliable due to the characteristics of the normal sound. Linear predictive coding (LPC) coefficients from the frequency domain were extracted as sound features. The sound features were used to classify k nearest neighbors (KNN) inputs for network training.;Results and Discussion;The results of accuracy, recall and precision values are, respectively, 97.7%, 98.3%, and 98.8% for the classification of roosters. Immature roosters had similar sound structures that with start the puberty and Leakage testosterone hormone, the rooster 's syrinx, which is part of the secondary sexual feature, also begins to change. After sexual maturity, the syrinx has grown and this evolution also makes the sound structure of the mature rooster very similar. Therefore, according to the similarity of the sound of the mature rooster and immature one, as well as the syrinx continuous changes during the puberty period, the KNN classifier with the LPC coefficients can show a high degree of accuracy in the classification of roosters. Because a feature of the kNN algorithm is that it is sensitive to the data local structure.;Conclusions;The main objective of the present study is to detect sexual and puberty of roosters using acoustic signals. The LPC coefficients as KNN classification inputs show accuracy, recall, and precision values of 98.7%, 98.3%, and 98.8%, respectively. These results indicate high accuracy of KNN classification to identify and categorize immature roosters, rooster during puberty period, and mature roosters.