This paper investigates the use of deep learning ensemble strategies in outcome-based education (OBE) and examines how ideology and politics influence vocational training outcomes. The study evaluates three ensemble strategies, namely bagging, boosting, and stacking, for predicting vocational outcomes and explores how political and institutional contexts relate to training effectiveness. The dataset comprises vocational training results together with political-context information linked to vocational programs. Political ideology was quantified using policy and governance indicators and encoded as contextual features aligned with vocational training records. A deep learning ensemble framework was developed to predict outcomes such as skill acquisition, employment rates, and overall learner success. The results show that ensemble learning improves predictive performance, with the best-performing model achieving an accuracy of 98.45% in predicting student performance from training-related parameters. Model robustness was assessed using 10-fold cross-validation, and performance is reported as the cross-validated mean with confidence intervals. The findings further indicate that political and ideological factors are associated with variations in vocational outcomes, highlighting the importance of policy context in program design and alignment with labor market demands. Overall, the integration of ensemble learning with vocational education systems offers a promising approach for improving outcome prediction and supporting more effective and inclusive vocational training initiatives.

With the evolution of smart networked vehicles towards smart driving, smart cabin, and ecology, the modern Internet of Vehicles (IoV) has become a typical

The rapid growth of heterogeneous Internet of Things (IoT) networks introduces significant challenges in communication efficiency, energy consumption, and reliable distributed intelligence due to diverse device capabilities, dynamic channel conditions, and limited computational resources. Existing bit-level communication and conventional federated learning approaches often suffer from excessive communication overhead, inefficient resource utilization, and unstable model convergence under non-IID data and unreliable device participation. To address these limitations, this paper proposes FEI-SemCom, an adaptive federated edge intelligence framework that integrates semantic communication, federated learning, and joint resource optimization for heterogeneous IoT systems. The proposed framework introduces a heterogeneity-aware semantic encoder, adaptive semantic compression mechanism, semantic contribution-based client selection strategy, and trust-aware aggregation scheme to improve communication efficiency and learning robustness. Unlike existing approaches that optimize communication, learning, and resource allocation independently, FEI-SemCom jointly adapts semantic representation, client participation, transmission parameters, and aggregation weights according to device capability, channel quality, and energy availability. Furthermore, the proposed framework improves resilience under intermittent connectivity conditions by enabling adaptive client participation, reliability-aware aggregation, and resource-aware communication decisions, allowing federated edge intelligence to operate effectively despite temporary link failures and unstable device availability. Extensive simulation results demonstrate that the proposed framework achieves 91.2% accuracy at 5 dB signal-to-noise ratio (SNR), converges within approximately 120 training rounds, and reduces communication overhead, energy consumption, and latency to 45 MB, 48 J, and 110 ms, respectively. Compared with conventional approaches, FEI-SemCom reduces communication overhead by up to 38% while maintaining stable convergence and robust learning performance. These results demonstrate the potential of adaptive semantic communication combined with federated edge intelligence for scalable and resource-efficient IoT applications.