Long term monitoring of the reproductive behavior of wild Chinese pangolin (Manis pentadactyla)

Sun, Nick Ching‐Min; Pei, Kurtis Jai-Chyi; Wu, Li-Yue

doi:10.1038/s41598-021-97618-4

Cited by 5 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Early cameras were employed to capture animal behavior for human understanding. For instance, Sun used cameras to document pangolin behavior [6], while Ina and Irene manually observed cows' and pigs' crawling and jumping behavior [7,8]. However, manual observation is time-consuming, labor-intensive, inefficient, and error-prone.…”

Section: Introductionmentioning

confidence: 99%

Automatic Identification of Pangolin Behavior Using Deep Learning Based on Temporal Relative Attention Mechanism

Wang,

Hou,

et al. 2024

Animals

View full text Add to dashboard Cite

With declining populations in the wild, captive rescue and breeding have become one of the most important ways to protect pangolins from extinction. At present, the success rate of artificial breeding is low, due to the insufficient understanding of the breeding behavior characteristics of pangolins. The automatic recognition method based on machine vision not only monitors for 24 h but also reduces the stress response of pangolins. This paper aimed to establish a temporal relation and attention mechanism network (Pangolin breeding attention and transfer network, PBATn) to monitor and recognize pangolin behaviors, including breeding and daily behavior. There were 11,476 videos including breeding behavior and daily behavior that were divided into training, validation, and test sets. For the training set and validation set, the PBATn network model had an accuracy of 98.95% and 96.11%, and a loss function value of 0.1531 and 0.1852. The model is suitable for a 2.40 m × 2.20 m (length × width) pangolin cage area, with a nest box measuring 40 cm × 30 cm × 30 cm (length × width × height) positioned either on the left or right side inside the cage. A spherical night-vision monitoring camera was installed on the cage wall at a height of 2.50 m above the ground. For the test set, the mean Average Precision (mAP), average accuracy, average recall, average specificity, and average F1 score were found to be higher than SlowFast, X3D, TANet, TSN, etc., with values of 97.50%, 99.17%, 97.55%, 99.53%, and 97.48%, respectively. The recognition accuracies of PBATn were 94.00% and 98.50% for the chasing and mounting breeding behaviors, respectively. The results showed that PBATn outperformed the baseline methods in all aspects. This study shows that the deep learning system can accurately observe pangolin breeding behavior and it will be useful for analyzing the behavior of these animals.

show abstract

Section: Introductionmentioning

confidence: 99%

Automatic Identification of Pangolin Behavior Using Deep Learning Based on Temporal Relative Attention Mechanism

Wang,

Hou,

et al. 2024

Animals

View full text Add to dashboard Cite

show abstract

Inconsistent reproductive cycles and postnatal growth between captive and wild Chinese pangolins and its conservation implications

Sun,

Lo,

Chan

et al. 2024

Global Ecology and Conservation

View full text Add to dashboard Cite

New horizons in the reproductive biology of Chinese pangolin (Manis pentadactyla) using the gonadal hormonal profile

Arora,

Pei,

Chin

2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

The reproductive uniqueness of pangolins has been documented through diverse biological reports with discernible data discrepancies in gestation, copulation, and pregnancy. These mechanistic reproductive differences have yet to be endocrinologically quantified, which could assist in optimizing natural breeding in zoos to recover endangered species. The present research characterizes the Chinese pangolin's annual seasonal reproductive pattern by measuring immunoreactive estrogens and progestagens in 34 captive females and testosterone in 29 captive males. Our results showed that Chinese pangolins are seasonal breeders, with most births witnessed during Sept–Dec, overlapping with the field records. Females exhibited spontaneous ovulation and post-partum ovulation. Pregnant females exhibited a higher P4 level for ~ 9 months (Jan–Sept) and decreased before parturition (Oct–Dec). The circulating E2 is maintained at the baseline in pregnant females year-round. Contrastingly, in non-pregnant females, P4 is maintained at the baseline, apart from a slight elevation in January, and E2 demonstrates a sudden hike from November and remains elevated until February, suggesting the onset of ovulation. The serum testosterone concentration in males peaked during October, which is in sync with the female ovulation period. As a result that their major reproductive events, ovulation, mating, and parturition, all transpire in November-March. Evidence also supports that Chinese pangolins exhibit signs of postimplantation (pregnancy) ranging only from 5 to 6 months (May–Oct), preceded by possible facultative delay implantation triggered by lactation. The provided data not only fill in the knowledge gap for this critically endangered species but can also assist in making informed decisions, which can directly affect the successful breeding of this species in captivity.

show abstract

Long term monitoring of the reproductive behavior of wild Chinese pangolin (Manis pentadactyla)

Cited by 5 publications

References 34 publications

Automatic Identification of Pangolin Behavior Using Deep Learning Based on Temporal Relative Attention Mechanism

Automatic Identification of Pangolin Behavior Using Deep Learning Based on Temporal Relative Attention Mechanism

Inconsistent reproductive cycles and postnatal growth between captive and wild Chinese pangolins and its conservation implications

New horizons in the reproductive biology of Chinese pangolin (Manis pentadactyla) using the gonadal hormonal profile

Contact Info

Product

Resources

About