The growing scale and sophistication of modern cyberattacks demand anomaly detection models capable of capturing non-Euclidean and highly relational patterns embedded within network traffic. This study introduces a unified and interpretable graph-based framework for network anomaly detection that systematically evaluates four representative graph neural network (GNN) architectures—GCN, GAT, GIN, and GraphSAGE—under identical experimental settings. Using the UNSW-NB15 benchmark dataset, IP addresses are modeled as graph nodes and communication flows are modeled as directed edges with flow-level attributes, enabling the extraction of structural attack behaviors. To provide complementary external robustness evidence, the framework is additionally evaluated on CIC-DDoS2019 under a DDoS-focused scenario and on a CSE-CIC-IDS2018-based diverse intrusion dataset under a broader multi-attack benchmark setting. A consistent preprocessing pipeline, standardized model configuration, 5-fold stratified cross-validation, statistical validation, and sensitivity analysis are employed to evaluate robustness and stability. Experimental results show that GIN and GraphSAGE achieve the strongest performance, with F1-scores of 0.9693 ± 0.0007 and 0.9721 ± 0.0006, respectively, and ROC-AUC values above 0.99 across folds. In addition, computational profiling is conducted to analyze inference latency, throughput, the number of trainable parameters, and GPU memory usage, highlighting the scalability advantages of aggregation-based models. Beyond quantitative evaluation, a dynamic D3.js-based attack topology visualization is presented to reveal attacker–target interactions, dominant attack categories, and high-frequency communication paths. Overall, this study provides a reproducible benchmarking and visualization framework for interpretable and structurally aware graph-based cybersecurity analytics.

Handover management in mobile networks is challenged by high latency and reduced reliability in dense deployments and under user mobility. Here, existing schemes improve handover initiation by optimising the candidate handover at the decision time. However, these are applied after a non-negligible delay due to the control-plane signalling. Then, when applied, it may become invalid or degrade performance. To address this, we propose a Digital Twin (DT)-assisted handover scheme that performs predictive execution-time validation prior to the preparation of the Next Generation (NG)-based handover. To this end, the DT-What-If Generator (DT-WIG) is used to emulate short-horizon future network states under uncertainty. Here, the DT-WIG is a spatiotemporal graph generative model that uses variational latent sampling to generate counterfactual post-handover trajectories for the candidate handover decision. Then, the AMF estimates the failure and QoS risks associated with the candidate handover and approves/rejects it via standard-compliant signalling. With this, we form a policy-agnostic mechanism that runs on the underlying handover policy. Consequently, we evaluate performance using ns-3/5G-LENA trace generation and replay-based policy analysis, with OpenAirInterface-based signalling evaluation. The results show that the proposed method reduces the handover failure rate and handover interruption time while improving latency, jitter, throughput, and packet loss.

G communication plays a crucial role in enabling high-speed, low-latency data transfer for underwater operations. Underwater communications need optimization support to overcome various problems such as packet loss and latency. This study presents a simulation model for underwater 6 G networks, focusing on the optimized placement of sensors, AUVs, and hubs. The network architecture consists of fixed hub stations, mobile autonomous underwater vehicles (AUVs), and numerous sensor nodes. Environmental parameters such as temperature, salinity, and conductivity are considered in the transmission of electromagnetic signals; signal attenuation and transmission delays are calculated based on physical models. The optimization process begins with K-Means clustering, followed by sequential application of Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) to refine the cluster configurations. The simulation includes key network dynamics such as multi-hop data transmission, cluster leader selection, queue management, and traffic load balancing. To compare performance, two distinct scenarios-one with cluster leaders and one without-are modeled and visualized through a PyQt5-based real-time graphical interface. The results demonstrate that 6 G network architectures in underwater environments can be effectively modeled and optimized by incorporating environmental conditions.

The rollout of 6G networks introduces unprecedented demands for autonomy, reliability, and scalability. However, the transmission of sensitive telemetry data to central servers raises concerns about privacy and bandwidth. To address this, we propose a federated edge learning framework for predictive maintenance in 6G small cell networks. The system adopts a Knowledge Defined Networking (KDN) architecture in Data, Knowledge, and Control Planes to support decentralized intelligence, telemetry-driven training, and coordinated policy enforcement. In the proposed model, each base station independently trains a failure prediction model using local telemetry metrics, including SINR, jitter, delay, and transport block size, without sharing raw data. A threshold-based multi-label encoding scheme enables the detection of concurrent fault conditions. We then conduct a comparative analysis of centralized and federated training strategies to evaluate their performance in this context. A realistic simulation environment is implemented using the ns-3 mmWave module, incorporating hybrid user placement and base station fault injection across various deployment scenarios. The learning pipeline is orchestrated via the Flower framework, and model aggregation is performed using the Federated Averaging (FedAvg) algorithm. Experimental results demonstrate that the federated model achieves performance comparable to centralized training in terms of accuracy and per-label precision, while preserving privacy and reducing communication overhead.

This paper presents the development of an institutional metaverse environment that enables interaction within a virtual space specifically tailored for learning or skill acquisition. It explores the advantages of employing immersive virtual reality technologies across different corporate contexts, highlighting improvements in employee engagement and teamwork, increased productivity and training efficiency, and contributions towards environmental sustainability. Furthermore, the paper details a collaborative project with Türk Telekom, a leading Turkish telecommunications firm, outlining the creation of five distinct virtual spaces within the metaverse, the development platform, backend architecture, and the networking framework employed.

Gamification is one of the new trend in software development and it has already gained a well-deserved popularity in finance, healthcare, education and even manufacturing. Software testing is a continuous cycle layered with several stages and spanning across multiple types of testing. Teams need to design test suites and implement test execution methodologies in each stage of development. For this reason, software testing teams comprise many individuals skilled in different aspects of software testing. The inclusion of gamification in this course can lead to positive benefits based on the idea that it is used to influence behavior. This paper presents an preliminary study of Machine Learning (ML) approach for predicting performance gamification of software tester specialists under a gamified testing environment. ImonaGame is a software company that delivers gamification as a service for software testing team of 30 members with different static and dynamic data. User behavior collected in dynamic data sets was classified into categories by deconstructing complex activities into behavior chains using supervision of domain experts. The classification approach was centered on the system’s testing processes’ performance objectives and potential for encouragement or dissuasion. Motivators and obstacles for the target activity and its behaviors will be found when the model has been developed. After conducting preliminary research, it is possible to determine whether gameful design is an effective and efficient tactic for achieving the desired result by analyzing needs, motives, and obstacles. The source data was classified target data in four categories such as I: Static feature (personal information; 4), II: Daily feature (gamification elements; 14), III: Mission feature (points; 7 sources) and IV: Cumulative futures (Sum of daily and mission features; 13).