International Journal of Environmental Science and Green Technology

Creating an Object Recognition System Based on Computer Vision in Waste Recycling Processes

2025-10-20T10:48:21+00:00

This paper investigates the methods and results of building a computer vision-based object recognition system in waste recycling processes. The study evaluated the performance of a CNN model using a dataset of 19,762 images with 10 classes, including clothing, metal, glass, biological waste, and other recyclable materials. The model was trained for 30 epochs and stopped at the 23rd epoch using the Early Stopping mechanism, achieving a training accuracy of 95.57% and a validation accuracy of 81.68%. The results showed that the model had high training efficiency, but the low validation accuracy limited its generalization ability. The data distribution imbalance and overtraining symptoms indicated the need for additional augmentation and optimization. The study confirmed the potential of computer vision in automating waste sorting, but the model needs further development for real-time application. Future research is recommended to expand the dataset, use hybrid models, and optimize in real time. The results lay the foundation for the development of innovative solutions that contribute to environmental protection and efficient use of resources.

Microbiological Monitoring of Drinking Water in Public Areas of the City of Turkestan

2025-12-21T08:41:30+00:00

Water is an essential resource that directly affects public health. In the context of global change and population growth, water resources face increasing threats of pollution and reduced availability. This issue is particularly relevant for the city of Turkestan in Kazakhstan, where the quality of drinking water is under continuous monitoring. This study focuses on assessing the microbiological parameters of water from public sources in the city, with an emphasis on identifying contamination levels and potential health risks. Special attention is given to detecting microorganisms such as Escherichia coli and Coliform bacteria, which serve as indicators of fecal contamination. The importance of this research lies in the need for effective methods of analysis and monitoring of drinking water quality to ensure compliance with sanitary and hygiene standards and to protect public health. The results highlight the necessity for strengthened water quality control in public areas and for implementing measures to prevent contamination and improve the overall state of water supply.

Measuring Social Interactions between Some Captive Animals Using Social Network Analysis in Duhok Zoo

2025-09-22T19:58:41+00:00

The present study was designed to measure social connection in three captive animals in Duhok zoo, including the American white pelican, wild dogs, and red deer, using Social Network Analysis (SNA). The present study was carried out at Duhok Zoo. The study was undertaken from October to December 2021. Three species of captive animals were used for this study, which were: the American white pelican, wild dogs, and red deer. Their numbers were 5, 7, and 6, respectively. Data were collected from the studied animals using direct observations of social interactions. According to the results found with the three species studied, all individuals have social interactions with each other. From the present study, according to the results found, it can be concluded that the social bonding was acceptable to some degree as strong relations were found between some individuals of all the three species studied. However, some individuals were not socially connected at all.