Abstract This study presents a fractal inspired ultra wideband (UWB) multiple input multiple output (MIMO) antenna design framework integrated with multi objective optimization for next generation 5G, IoT, and wireless communication systems. Addressing critical challenges of mutual coupling,... This study presents a fractal inspired ultra wideband (UWB) multiple input multiple output (MIMO) antenna design framework integrated with multi objective optimization for next generation 5G, IoT, and wireless communication systems. Addressing critical challenges of mutual coupling, limited isolation, and excessive hardware complexity in dense array deployments, we employ Pareto front analysis to systematically characterize fundamental trade offs in sparse array synthesis. Using the MOPET optimized dataset comprising 3,350 non-dominated solutions derived from aperture sizes spanning 196-2,025 elements, we reconstruct performance envelopes mapping hardware cost against electromagnetic metrics including sidelobe level (- 27.95 to 3.38 dB), directivity (18.36-34.01 dB), and sparsity ratios (26.7%-62.0%). Our analysis reveals four key insights: (i) sidelobe suppression exhibits diminishing returns beyond a critical "knee point" in element count; (ii) beamwidth degradation stems primarily from effective aperture contraction rather than sparsity alone; (iii) high directivity is preserved in sparse layouts through intelligent peripheral element placement; and (iv) Pareto optimal configurations achieve performance within a few decibels of dense arrays while reducing element count by 30-70% [Lorincz, J., 2019, 2022]. These findings validate multiobjective optimization as a physics grounded methodology for sustainable antenna design, directly addressing escalating energy consumption in 5G/6G infrastructure [Uluslu, A., 2025; Haxhiraj, E., 2023]. The reconstructed Pareto fronts serve as quantitative design maps enabling informed selection of array configurations that optimally balance spectral efficiency, interference suppression, angular resolution, and implementation cost for resource constrained wireless deployments. Read More Read Less

Abstract This research document comprehensively examines terahertz (THz) communications leveraging orbital angular momentum (OAM) for next generation 6G wireless systems. It establishes that OAM provides an additional spatial multiplexing dimension, thereby enhancing spectral efficiency beyond conventional techniques. However, the... This research document comprehensively examines terahertz (THz) communications leveraging orbital angular momentum (OAM) for next generation 6G wireless systems. It establishes that OAM provides an additional spatial multiplexing dimension, thereby enhancing spectral efficiency beyond conventional techniques. However, the analysis reveals fundamental physical constraints limiting practical deployment. Key findings demonstrate that THz propagation is governed by a dual loss mechanism: free space path loss and severe frequency selective molecular absorption particularly from water vapor resonances at 183, 325, and 380 GHz. These absorption peaks create distinct atmospheric transmission windows while rendering other bands unusable beyond short distances. Environmental factors critically impact performance: humidity variations introduce 6+ dB of path loss uncertainty at 500 m, and beam divergence combined with stringent alignment requirements further constrain reliability. The study presents a physics based simulation dataset comprising 270,000 samples across four deployment scenarios (laboratory, indoor, urban, and high mobility environments), characterized by 33 parameters spanning atmospheric conditions, channel physics, hardware impairments, and performance metrics. Results confirm THz OAM systems are inherently range limited (<100-500 m), environment sensitive, and require operation within specific atmospheric windows. Successful implementation demands adaptive strategies: dynamic frequency selection, high gain directional antennas ( 25 dBi), and AI-assisted beam steering. The technology is best suited for specialized short range applications indoor 6G networks, wireless backhaul, and device to device communications where environmental conditions can be controlled or dynamically adapted. Read More Read Less

Abstract This study investigates machine learning approaches for customer churn prediction and segmentation in the telecommunications sector, addressing the critical business challenge of subscriber retention amid rising acquisition costs. Leveraging the Telco Customer Churn dataset, comprising 7,043 customer... This study investigates machine learning approaches for customer churn prediction and segmentation in the telecommunications sector, addressing the critical business challenge of subscriber retention amid rising acquisition costs. Leveraging the Telco Customer Churn dataset, comprising 7,043 customer records with 21 demographic, service usage, and billing attributes, we implement a dual method framework that combines supervised classification and unsupervised clustering. A Support Vector Machine (SVM) with a radial basis function kernel models nonlinear relationships between customer attributes and churn behavior, achieving 79.18% accuracy and a ROC-AUC of 0.797. As an interpretable benchmark, Logistic Regression delivers superior ranking performance (ROC-AUC: 0.84) with 80.77% accuracy and a churn recall of 0.578, enabling actionable insights through coefficient analysis. Complementing prediction, K-means clustering identifies three distinct customer segments High Value Loyalists, Budget Newcomers, and Mid Tier Growth based on tenure, charges, and service adoption patterns. Cluster validity is confirmed through silhouette analysis (optimal K=3, score 0.52) and PCA visualization. The segmentation reveals strategic opportunities: loyalty programs for high value customers, onboarding support for at-risk newcomers, and cross selling for growthoriented mid tier users. Results demonstrate that effective churn management requires integrating predictive accuracy with nuanced customer understanding. While nonlinear models capture complex behavioral patterns, interpretable linear models offer practical advantages for operational deployment. This research provides a robust analytical foundation for data driven retention strategies, enabling telecom providers to transition from reactive interventions to proactive, personalized customer relationship management that enhances long term profitability in competitive markets. Read More Read Less