To date, the main problem associated with the prevention of fires in open areas is their early detection. It is very difficult to put out a fire that has already begun, even with large modern firefighting equipment and human resources. However, using modern artificial intelligence technologies, it is possible to offer more effective ways to solve the problem - this is the detection of smoke and fire at the initial stages of ignition. The most promising method for early detection of a fire is its detection based on video surveillance. Monitoring of large areas and the rapid decline in the cost of video cameras will allow this latest technology to become truly widespread in the fire safety system. This article proposes object recognition by hybrid methods based on contour analysis and neural network technologies. Tests of the results of smoke and fire recognition by the methods of contour analysis and artificial neural network were carried out by the full-scale method in accordance with the test method defined by GOST R 53325-2012.
| Mualliflar | Хамдамов, Р.Х., Сакиев, Т.Р., Рахманов, Х.Э. |
|---|---|
| Jurnal | Рақамли технологияларнинг назарий ва амалий масалалари |
| Nashr sanasi | 2023-06-27 |
| Jild | 4 |
| Son | 2 |
| Betlar | 19-26 |
| Til | Rus |
artificial intelligence, contour analysis, convolutional neural network, YOLOv5 algorithm, type 1 error FRR, type 2 error FAR, искусственный интеллект, контурный анализ, свёрточная нейронная сеть, алгоритм YOLOv5, ошибка первого рода FRR, ошибка второго рода FAR
The study is devoted for statistical methods of threshold values selection for decision making in the case of iris identification, and the problem of determining threshold values according to Hamming distance based on…
The article considers the basic principles of constructing a system of error-correcting coding and decoding of high-precision iterative codes. For the practical implementation of methods and algorithms of high-precision…
The paper sets and solves the problem of assessing the conceptual features of the formation and formalization of an information-logical model of structural connections of gas supply systems tasks. In this regard, gas…
When a conducting body moves in a magnetic field or when the magnetic field changes with time, induced currents and the ponderomotive Lorentz forces caused by them arise in the body, which, in turn, is accompanied by…
Maqolada yuqori chekli oʻlchamli belgilar fazosida oʻquv tanlanma sinflari bir-biridan xatoli ajralganda timsollarni belgilangan xatolik va ishonchlilik bilan tanib olish masalasini yechish qaralgan. Oʻquv tanlanma har…
This paper has been discussed the CTC-based approach of the E2E model is used in speech recognition. The article discusses the steps of speech recognition based on the CTC approach. It also reviews the types of problems…
Ushbu maqolada OSI modelining transport sathida ishlovchi TCP/IP protokoliga maxfiy xabarlarni yashirish usullari haqida ma’lumotlar berilgan. Shuningdek, tarmoq steganografiyasi usullari imkoniyatlari boʻyicha tahlil…
This article is about a practical and effective cybersecurity insurance system. In ensuring cybersecurity, the insurance system was considered the main obstacle to the certification of information objects. Insurance is…
Makur maqola tibbiyot sohasida toʻplangan statistik ma’lumotlarni tahlil qilishda klasterli tahlil usullarini keng va muvaffaqiyatli qoʻllashga qaratilgan. Ushbu yondashuv yordamida samarali hal qilinishi mumkin boʻlgan…
The article deals with the problem of the importance of mathematical modeling in the digital economy as the main tool. The topic of the work is very relevant, since in the age of digitalization, the economy, like any…
Рақамли технологияларнинг назарий ва амалий масалалари — barcha maqolalar