Fire detection is an important task in the field of safety and emergency prevention. In recent years, deep learning methods have shown high efficiency in solving various computer vision problems, including detecting objects in images. In this paper, monitoring wildfires was considered, which allows you to quickly respond to them and prevent their spread using deep learning methods. For the experiment, images from the satellite and images from the FireWatch sensor were taken as initial data. In this work, the deep learning algorithms you only look once (YOLO), convolutional neural network (CNN), and fast recurrent neural network (FastRNN) were considered, which makes it possible to determine the accuracy of a natural fire. As a result of the experiments, an automated fire recognition algorithm using YOLOv4 deep learning methods was created. It is expected that the results of the study will show that deep learning methods can be successfully applied to detect fire in images. This may lead to the development of automated monitoring systems capable of quickly and reliably detecting fire situations, which will help improve safety and reduce the risk of fires.
1 April 2024 in International Journal of Electrical and Computer Engineering (IJECE)
This article examines a current area of research in the field of ophthalmology the use of deep learning methods for automated analysis of retinal structures. This work explores the use of deep learning methods such as EfficientNet and DenseNet for the automated analysis of retinal structures in ophthalmology. EfficientNet, originally proposed to balance between accuracy and computational efficiency, and DenseNet, based on dense connections between layers, are considered as tools for identifying and classifying retina features. Automated analysis includes identifying pathologies, assessing the degree of their development and, possibly, diagnosing various eye diseases. Experiments are performed on a dataset containing a variety of images of retinal structures. Results are evaluated using metrics of accuracy, sensitivity, and specificity. It is expected that the proposed deep learning methods can significantly improve the automated analysis of retinal images, which is important for the diagnosis and monitoring of eye diseases. As a result, the article highlights the significance and promise of using deep learning methods in ophthalmology for automated analysis of retinal structures. These methods help improve the early diagnosis, treatment and monitoring of eye diseases, which can ultimately lead to improved healthcare quality and improved patient lives.
Ғылым мен технологияның қарқынды дамуы жағдайында ұйымдардың тиімділігі мен сапасын едәуір жақсарту ажырамас қажеттілікке айналады. Осы тұрғыда «Ұлттық сараптама орталығында» (ҰСО) өндірістік бақылау үшін ақпараттық жүйені зерттеу және әзірлеу өзекті міндет болып табылады. ҰСО Қазақстан Республикасында халықтың денсаулығын қамтамасыз ету үшін қажетті тамақ өнімдерінің, дәрілік заттардың және басқа да тауарлардың сапасын бақылауда шешуші рөл атқарады. Зерттеудің мақсаты ҰСО жұмысының тиімділігін арттыруға және оның қызметкерлерінің еңбек жағдайларын жақсартуға ықпал ететін ақпараттық жүйені әзірлеу және енгізу болып табылады.
An adaptation of the AlphaZero model for the game Togyzkumalak, a national Kazakh board game with high combinatorial complexity is presented. The aim of the research was to develop an artificial intelligence capable of independently learning optimal game strategies without using predefined templates. The paper uses an approach based on the modification of the architecture of the AlphaZero neural network, which includes deep learning and the Monte Carlo search method (MCTS). The model was implemented on the PyTorch platform and was trained in the process of self-play, which allowed us to gradually improve strategic skills. The key features of Togyzkumalak's game are taken into account, such as a large number of possible positions on the playing field, and specialized network architectures have been developed for their effective modeling. The results demonstrate the significant potential of combining deep learning and MCTS to solve non-standard game tasks and create effective strategies in Togyzkumalak.
Energy consumption prediction plays a critical role in optimizing resource allocation, reducing costs, and promoting sustainability in various industries. The goal of this study is to predict energy consumption using three machine learning models: Linear Regression, LightGBM, and a Neural Network. After conducting comprehensive exploratory data analysis (EDA) to understand the dataset's structure and key features, the models were built and evaluated using metrics such as Mean Squared Error (MSE), Mean Absolute Error (MAE), and R² score. The results demonstrate that LightGBM outperforms the other models, achieving the highest prediction accuracy. These findings emphasize the importance of advanced machine learning methods in energy forecasting for improving predictive performance and decision- making.