This study explores the development of methods and algorithms for detecting hazardous objects in robotic systems powered by artificial intelligence. A specialized dataset named DENGROUS was created using the Roboflow platform, consisting of 10 classes, 15,668 images, and 21,944 annotations. Their performance was then comparatively evaluated on a validation dataset. Experimental results showed that YOLO26s achieved the highest accuracy with mAP@0.5 = 0.876 and mAP@0.5:0.95 = 0.701. The YOLO11s model ranked second with a Precision score of 0.897, while YOLOv8n demonstrated the fastest inference speed at 4.5 ms per image.
| Mualliflar | Khakimov, Allamurod, Nazarov, Fayzullo, Musurmonova , Ibodat |
|---|---|
| Jurnal | Al-Farg'oniy avlodlari |
| Nashr sanasi | 2026-05-11 |
| Son | 2 |
| Betlar | 158-164 |
| Til | Rus |
YOLO, hazardous object detection, child safety, robotic systems, convolutional neural networks, ResNet
Abstract: This article examines the digital literacy gap between parents and children in the modern digital environment and its impact on the effectiveness of parental supervision. A survey of 150 families from the…
This article discusses the issue of statistical analysis of electrocardiogram (ECG) signals. The main goal of the study is to determine the main characteristics of the signals by constructing a covariance matrix based…
This article presents the results of a study on applying the particle swarm optimization algorithm to extract informative features from a training dataset. An informative feature extraction model was developed based on…
This paper proposes a simple and visually intuitive method for constructing Islamic ornamental patterns based on the “contacting polygons” technique introduced by Hankin. The proposed approach enables the formation of…
Effective control of hydraulic processes in water management facilities, including irrigation canals, pumping stations, and reservoirs, is increasingly important under water scarcity and climate change. Traditional…
This article discusses the fundamental role of the Euler function and Euler's theorem in public-key cryptosystems, in particular the RSA algorithm. The article analyzes the mathematical foundations of the Euler…
This paper investigates the effectiveness of transformer-based models (mBERT, BERTbek, XLM-R, ALBERT, ELECTRA) in analyzing Telegram social media text data. The study represents text data as contextual embeddings and…
This article considers the issues of analyzing ECG signals based on statistical methods. In the study, the main parameters obtained from electrocardiogram signals were evaluated using mathematical and statistical…
Predicting hydrological dynamics in semi-arid regions is challenging due to climate instability. This study proposes a hybrid modeling framework integrating Seasonal-Trend decomposition (STL), SARIMA, and Long…
This article proposes a conceptual model of enterprise energy monitoring based on IoT and edge computing. The model is designed for real-time monitoring, analysis, and management of energy consumption in industrial…