Machine Learning Classification of Seasonal Feeding Strategies in Urban Macaques

Abstract

Urbanization has been recognized as an ecological factor impacting the behaviour of wildlife by transforming natural habitats, resource availability, and interaction of species. Feeding behaviors of urban macaques have been observed to be continuously impacted by environmental changes and thus, impact the feeding habits of the monkeys. Seasonal variations play a role in shaping the food availability, vegetation, and human-associated foods and thus, shape the feeding behavior of the macaques. Seasonal feeding strategies of the macaques can be useful in understanding the adaptability and effectiveness of urban wildlife management strategies. This research focus on the development of a machine learning-based approach for the automated classification of feeding behaviors in urban macaques in varying seasonal settings. This research aims to incorporate behavioral observation of the macaques along with the use of ecological features to identify and classify the feeding strategies of macaques in various seasons. Data preprocessing techniques are used to prepare the data while feature extraction techniques are used to extract important features. The suggested framework addresses the limitations of the conventional approaches to manual observation, such as the dependency on the observer, time limits, and limited observation capabilities. The classification system allows conducting a quick analysis of the big behavioral datasets and gaining better insight into the adaptation of the macaques in the urban environment. The findings have proved the applicability of machine learning algorithms in the classification of the seasonal feeding behavior and identification of behavioral patterns depending on the environmental changes.