Optical sensors offer a painless method of monitoring blood glucose levels using various light technologies to analyze blood characteristics without penetrating the skin. The literature review part reflects the progress in optical sensor technology evaluates its potential in blood glucose monitoring by overcoming the limitations of conventional methods and recognizes the challenges and future prospects in this rapidly developing area of research. The results of empirical studies are then presented. The methodology is presented as a non-invasive method of blood glucose monitoring based on near-infrared spectroscopy. To precisely evaluate blood glucose concentrations, spectroscopy techniques involving absorption and reflection are employed at wavelengths 450, 900, 1350, and 1800 nm. After absorption and reflection of glucose molecules, light is generated. An experimental study of different samples revealed a linear relationship between the final output voltage and sugar concentration. The results demonstrate a correlation between blood glucose level and signal intensity after transmission.

The object of this study is the process of detecting threats and vulnerabilities in hacker forums, which are a well-known source of potential dangers for Internet users. However, the problem of analyzing and classifying data from these forums is its complexity due to such features of the participants' language as specific slang, jargon, etc., which requires the use of modern tools of their processing. This paper explores the application of machine learning to devise an effective method for analyzing sentiment and trends in hacker forums to identify potential threats and vulnerabilities in cyberspace. All necessary stages of the process of detecting threats and vulnerabilities have been developed, ranging from data collection and preprocessing to the training of a model that is capable of processing “raw” unstructured data from hacker forums. The implementation of six popular machine learning algorithms, namely k Nearest Neighbors (kNN), Random Forest, Naive Bayes, Logistic Regression, Support Vector Machines (SVM), and Decision Tree algorithms have been studied with a view to determining their efficiency of threat and vulnerability detection and classification. The experiments have been conducted on real data (150,000 messengers). It has been determined that the Random Forest algorithm coped with the task the best (accuracy=0.89, recall=0.84, precision=0.91, F1-score=0.87 and ROC-AUC=0.89). The proposed tool based on machine learning not only collects data that poses a potential threat but also processes and classifies it according to the specified keywords. This allows detecting threats and vulnerabilities at a high speed. The results of the study make it possible to identify potential trends in threats and vulnerabilities. This will contribute to the improvement of cybersecurity systems and ensure more reliable protection of information resources

Non-invasive blood glucose monitoring remains a major challenge in biomedical sensing due to strong light scattering in biological tissues, physiological variability, and limited signal stability of existing optical methods. Near-infrared (NIR) spectroscopy has attracted significant...

This study proposes a four-layer AI agent architecture for automating routine web security operations, integrating Large Language Model (LLM) reasoning with a hybrid Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) detection engine and implementing a Reasoning-Acting (ReAct) loop for autonomous testing with human-in-the-loop validation. The proposed architecture was empirically evaluated across 50 web applications sourced from OWASP WebGoat, DVWA, and custom-developed test environments over a six-month period. The experimental results demonstrate that the AI agent achieved an overall detection accuracy of 89.2% (95% CI: 86.4-92.0%), significantly outperforming traditional automated methods (67.4% accuracy, p < 0.001). Mean Time to Remediation (MTTR) decreased from 74.3 days to 28.5 days (61.6% reduction), while false positive rates decreased from 24.3% to 4.8%. According to these findings, AI agent-driven automation can substantially enhance the efficiency and reliability of web security testing. However, human expertise remains important for assessing complex vulnerabilities and detecting zero-day threats.

The current trend of converging various network types, coupled with the rising traffic volumes and the increasing use of real-time and multimedia applications, has necessitated the transportation of diverse types of traffic, particularly those sensitive to latency. Traditional TCP/IP networks fall short in providing the required Quality of Service (QoS) for these applications, prompting the development of supplementary mechanisms to meet the necessary service levels. Additionally, the advent of new multimedia and cloud services, the expansion of the Internet of Things (IoT), and the integration of optical and wireless communications within the 5G optical network framework demand modifications to network infrastructure. These changes are essential to accommodate scalable traffic growth while simultaneously maintaining high levels of dynamic connectivity, complete flexibility, and enhanced energy efficiency. Within this context, QoS is crucial across all layers of the OSI model, ensuring effective and reliable data transmission within network systems.

This research presents a comprehensive investigation into the application of machine learning techniques for addressing the pervasive security challenges within Internet of Things (IoT) networks. With the exponential growth of interconnected devices, ensuring the integrity and confidentiality of data transmissions has become increasingly critical. In this study, we deploy and evaluate seven distinct machine learning methods tailored to the IoT network intrusion detection problem. Leveraging the rich and diverse UNSW-NB15 dataset, encompassing real-world network traffic scenarios, our analysis encompasses a thorough examination of both traditional and state-of-the-art algorithms. Through rigorous experimentation and performance evaluation, we assess the efficacy of these methods in accurately detecting and classifying various forms of network intrusions. Our findings provide valuable insights into the strengths and limitations of different machine learning approaches for enhancing the security posture of IoT environments, thereby facilitating informed decision-making for network administrators and cybersecurity practitioners.