Current Issue : January-March Volume : 2025 Issue Number : 1 Articles : 5 Articles
In this paper, a deep-learning-based frame synchronization blind recognition algorithm is proposed to improve the detection performance in non-cooperative communication systems. Current methods face challenges in accurately detecting frames under high bit error rates (BER). Our approach begins with flat-top interpolation of binary data and converting it into a series of grayscale images, enabling the application of image processing techniques. By incorporating a scaling factor, we generate RGB images. Based on the matching radius, frame length, and frame synchronization code, RGB images with distinct stripe features are classified as positive samples for each category, while the remaining images are classified as negative samples. Finally, the neural network is trained on these sets to classify test data effectively. Simulation results demonstrate that the proposed algorithm achieves a 100% probability in frame recognition when BER is below 0.2. Even with a BER of 0.25, the recognition probability remains above 90%, which exhibits a performance improvement of over 60% compared with traditional algorithms. This work addresses the shortcomings of existing methods under high error conditions, and the idea of converting sequences into RGB images also provides a reliable solution for frame synchronization in challenging communication environments....
The publication addresses a current issue related to cyberbullying in the workplace, as much of today’s business activity is conducted online. The research is aimed at the typology and manifestation of cyberbullying in a practical environment, and a number of small- and medium-sized telecommunications enterprises have been studied. The research was conducted in the territory of three large cities in the Republic of Bulgaria, and a quantitative approach was used in the development of an online survey, through which empirical data were generated in the business of small- and mediumsized telecommunications enterprises. Based on the results, an analysis was made of the typology and manifestation of cyberbullying, in order to study how it affects the human factors and what its causes are. It has been established that cyberbullying causes negative effects, both in people’s professional activity and in their emotional state in the absence of adequate cybersecurity and prevention mechanisms on the part of the investigated enterprises. Based on the information obtained, methodological guidelines are proposed for improving cybersecurity and prevention against malicious cyberbullying attacks in the technological infrastructure of the telecommunications enterprise....
Nowadays,Wireless Mesh Networks (WMNs) are widely deployed in communication areas due to their ease of implementation, dynamic self-organization, and cost-effectiveness. The design of routing protocols is critical for ensuring the performance and reliability of WMNs. Although there have been numerous experimental works on WMNs in the past decade, only a few of them have been tested in real-world scenarios. This article presents a comparative analysis of three proactive routing protocols, OLSR, BATMAN, and Babel, using Raspberry Pi 4 devices. The evaluation, conducted at Al- Farabi Kazakh National University, covers both indoor and outdoor scenarios, focusing on key metrics such as bandwidth, Packet Delivery Ratio (PDR), and jitter. In outdoor scenarios, OLSR achieved the highest bandwidth at 2.9 Mbps, while BATMAN and Babel lagged. Indoor tests revealed that Babel initially outperformed with the highest bandwidth of 57.19 Mb/s but suffered from scalability issues, while BATMAN and OLSR exhibited significant declines in performance as network size increased. For PDR, BATMAN performed best with a decline from 100% to 42.8%, followed by OLSR with a moderate drop, and Babel with the greatest decrease. For jitter, OLSR showed the most stable performance, increasing from 0.281 ms to 2.58 ms at eleven nodes, BATMAN exhibited moderate increases, and Babel experienced the highest rise....
Customer retention is a key priority for mobile telecommunications companies, as acquiring new customers is significantly more costly than retaining existing ones. A major challenge in this field is predicting customer churn—users discontinuing services. Traditional predictive models such as rule-based systems often struggle with the complex, non-linear nature of customer behavior. To address this, we propose the use of deep learning techniques, specifically multi-layer perceptron (MLP) and radial basis function (RBF) networks, to improve the accuracy of churn predictions. However, while neural networks excel in predictive performance, they are often criticized for being “black-box” models, lacking interpretability. A real-world data set is considered, which originally contained information about 15,000 randomly selected clients. Various network structures and configurations are analyzed. The obtained results are compared with results generated using fuzzy rule-based and rough-set rule-based systems. The MLP model achieved an almost perfect accuracy of 0.999 with an F-measure of 0.989, outperforming traditional methods such as fuzzy rule-based and rough-set systems. Although the RBF model slightly lagged in accuracy, it demonstrated a superior recall of 0.993, indicating better identification of potential churners. These results demonstrate that neural network models significantly enhance predictive performance in churn modeling. The interpretability of the model is also discussed since it bears significance in real applications. Our contribution lies in showing that deep learning methods significantly enhance churn prediction accuracy, though the challenge of model interpretability remains a critical area for future work....
Telecom network fraud has arisen as a significant transnational crime impacting China and Laos, capitalizing on legal, jurisdictional, and technical discrepancies between the two nations. This paper analyzes the collaborative initiatives between China and Laos to address cross-border telecom network fraud, highlighting significant joint operations carried out from 2016 to 2024. The magnitude of telecom network fraud is shown by the extradition of over 2,500 criminals from Laos to China, which has averted millions of dollars in financial damages via collaborative law enforcement initiatives. The study analyzes significant hurdles, including jurisdictional limitations, technology inadequacies, and political factors that influence the effectiveness of joint operations. This paper proposes improved strategies for real-time digital evidence-sharing, the formation of joint task forces, enhanced financial intelligence monitoring, and expedited extradition processes through the analysis of case studies and ongoing collaborative efforts. By enhancing technological capabilities, offering training, and bolstering political support, China and Laos can establish a more robust framework for addressing telecom network fraud and ensuring regional security....
Loading....