This article proposes an innovative machine learning (ML)-based approach to distinguish between users and bots in web applications. Due to the declining effectiveness and user inconvenience of traditional methods (e.g., CAPTCHA), the authors suggest detecting bots by analyzing interactive user behavior, such as mouse movements, keyboard inputs, scrolling patterns, and other parameters. The study employs a lightweight neural network model in ONNX format, demonstrating high accuracy (93.5%) and low error rates in real-time bot detection. Key advantages of the model include minimal impact on user experience, fast processing (<50ms), and adaptability to various devices
| Mualliflar | Zaynalov , Nodir, Maxmadiyorov, Faxriddin |
|---|---|
| Jurnal | Techscience.uz - техника фанлари долзарб масалалри |
| Nashr sanasi | 2025-08-11 |
| Jild | 3 |
| Son | 5 |
| Betlar | 11-16 |
| Til | O‘zbek |
| DOI | 10.47390/ts-v3i5y2025n2 |
DOI: 10.47390/ts-v3i5y2025n2 · Maqolaning asl sahifasi
bot detection, machine learning, user behavior analysis, ONNX model, real-time analysis, CAPTCHA alternatives., bot aniqlash, mashinaviy o‘rganish, foydalanuvchi xatti-harakatlari, ONNX modeli, real vaqtda tahlil, CAPTCHA alternativlari
This article explores modern approaches in the field of digital image processing, focusing on methods for noise detection and removal. It outlines the causes of noise in images and describes the main noise models…
Modern medicine — and oncology in particular — is on the verge of integrating artificial intelligence (AI) into routine clinical practice. This article highlights some of the most successful initiatives showcasing how…
The article examines modern methods of determining coordinates using unmanned aerial vehicles. RTK, PPK, GNSS and SLAM technologies are analyzed, formulas for calculating coordinates and errors are given. The prospects…
This article gives an idea of dust as one of the natural phenomena, its structural structure, analyzes the degree of impact of dust on the environment and a living organism associated with production, describes the…
This paper is about the ARIMA (Auto-Regressive Integrated Moving Average) model to forecast Uzbekistan’s GDP for the period 2025–2030, with country’s economic trajectory . GDP is a critical measure of economic activity…
This article analyzes environmentally friendly hydrogen production technologies based on renewable energy sources. Special attention is paid to the advantages of solar-powered portable alkaline electrolysis systems and…
This article analyzes the physical properties of surface waves and their significance in seismology. Surface waves are generated as a result of the impact of mechanical objects on the surface and consist of a…
This paper describes the experience of implementing the proposed neural network (NN) based routing protocol algorithm. This approach aims to improve the clustering efficiency. Energy consumption is an important factor…
Typically, a review includes not only an overall rating but also ratings for several aspects and accompanying text. The rating is considered a numerical representation of the author's overall satisfaction. Although the…
This article discusses the use of unmanned aerial vehicles (UAVs) to create georeferenced maps and 3D models. Particular attention is paid to RTK technology, GNSS solutions, and data post-processing methods. Formulas…
Techscience.uz - техника фанлари долзарб масалалри — barcha maqolalar