In this study, yawning, which is considered one of the physiological deviations of humans, mouth opening state classification and several machine learning algorithms were used. The CNN model outperformed traditional machine learning methods such as SVM, MLP and KNN with an accuracy of 97.07%. In the study, a dataset was formed using mouth part images extracted from face images using CNN and the model was trained. In addition, the overall performance of the model is improved by dataset normalization and dropout methods. The results demonstrate the effectiveness of the CNN algorithm in detecting the mouth opening state (yawning) and open the possibility for further improvement of fatigue state detection systems in the future.
| Mualliflar | Назаров, Файзулло, Хамидов, Мунис |
|---|---|
| Jurnal | Рақамли технологияларнинг назарий ва амалий масалалари |
| Nashr sanasi | 2024-10-09 |
| Jild | 7 |
| Son | 3 |
| Betlar | 131-136 |
| Til | Rus |
| DOI | 10.62132/ijdt.v7i3.207 |
DOI: 10.62132/ijdt.v7i3.207 · Maqolaning asl sahifasi
обнаружение зевания, сверточные нейронные сети (CNN), машинное обучение, классификация изображений, извлечение признаков изображения, yawn detection, convolutional neural networks (CNN), machine learning, image classification, image feature extraction
Magnetoelastic materials are gaining significant importance in research aimed at utilizing new technologies, such as smart materials and nanotechnology, which may lead to the development of new devices and systems in…
This article is dedicated to studying the bending characteristics of thin plates under the influence of non-stationary stresses. The deformation process of plates under non-stationary loads is analyzed based on…
Mathematical modeling is the main method and means for understanding objects, processes, and phenomena occurring in nature. It is used in all areas of science, technology, and the national economy, including solving…
This article reviewed the methods and algorithms for processing and diagnosing X-ray images that are widely used in medicine today. In order to improve the implementation of deep learning in modern medicine and further…
Today, the volume of information is growing at a rapid pace and the process of giving opinions for each person using records from different databases is improving. By aggregating records from different databases into a…
This paper presents an analysis of the application of the Low-Rank Adaptation method (LoRA) for the task of monolingual text generation in Uzbek. We used the T5-base, T5-Large and uzT5 models to determine which one…
This article presents a mathematical model for analyzing and predicting the dispersion of toxic substances in the atmospheric boundary layer. The model takes into account the particle transport velocities in the air…
While non-linear S-tables are important in the security of symmetric cryptosystems, their hardware implementation also requires a large number of logic elements compared to the rest of the mappings. This makes it…
Data privacy issues are increasing significantly in computing systems implemented by the Internet of Things, cloud computing, e-government, artificial intelligence applications, and neural networks. Homomorphic…
In the article, a study was conducted to comprehensively study the important factors affecting the process of migration and diffusion of harmful substances and dust particles in the atmosphere. The physical and…
Рақамли технологияларнинг назарий ва амалий масалалари — barcha maqolalar