Multi-scale habitat modeling framework for predicting the potential distribution of sheep gastrointestinal nematodes across Iran's three distinct climatic zones: a MaxEnt machine-learning algorithm.

Ecological niche models (ENMs) serve as valuable tools in assessing the potential species distribution, identifying crucial habitat components for species associations, and facilitating conservation efforts. The current study aimed to investigate the gastrointestinal nematodes (GINs) infection in sheep, predict and analyze their ecological niches and ranges, and identify the key bioclimatic variables influencing their distribution across three distinct climatic regions in Iran. In a cross-sectional study, a total of 2140 fecal samples were collected from semi-arid (n = 800), arid (n = 500), and humid-subtropical (n = 840) climates in East Azerbaijan, Kerman, and Guilan provinces, respectively. The flotation method was employed to assess stool samples, whereby the fecal egg count (the number of parasite eggs per gram [EPG]) was ascertained for each individual specimen. Employing a presence-only approach, the multi-scale maximum entropy (MaxEnt) method was used to model GINs' habitat suitability using 93 selected points/locations. The findings revealed that Guilan (34.2%) and East Azerbaijan (19.62%) exhibited the utmost proportion of Strongyle-type eggs. East Azerbaijan province also displayed the highest proportion of Marshallagia and Nematodirus, respectively (approximately 40% and 27%), followed by Guilan and Kerman provinces, while Kerman province had the highest proportion of Trichuris (approximately 15%). Ecological niche modeling revealed that the precipitation of the driest quarter (Bio17) exerted the most significant influence on Marshallagia, Nematodirus, Trichuris, and ُSُُُtrongyle-type eggs' presence in East Azerbaijan and Kerman provinces. For Guilan province, the most influential factor defining habitat suitability for Strongyle-type eggs, Marshallagia, and Nematodirus was increasing slope. Additionally, the distribution of Trichuris was most affected by the variable Bio2 in Guilan province. The study highlights the response of GINs to climate drivers in highly suitable regions, providing insights into ecologically favorable areas for GINs. In conclusion, this study provides a better understanding of GINs and the environmental factors influencing their transmission dynamics.

Constructing a meta-tracker using Dropout to imitate the behavior of an arbitrary black-box tracker.

Imitating the behaviors of an arbitrary visual tracking algorithm enables many higher level tasks such as tracker identification and efficient tracker-fusion. It is also useful for discovering the features essential in a black-box tracker or learning from several trackers to form a super-tracker. In this study, we propose a non-linear feature fusion framework, "MIMIC" that imitates many popular trackers by mixing a pool of heterogeneous features. The MIMIC framework consists of two subtasks, feature selection and feature weight tuning. These subtasks, however, tended to suffer from an overfitting problem when the number of videos available for training is limited. To address this issue, we incorporated Dropout algorithm into the training, which grants the trained MIMIC tracker a high degree of generalization. Extensive experiments testified the effectiveness of the proposed framework so that its applications would be promoted into different related tasks in visual tracking.