This paper proposes a deep reinforcement learning-based coordination model for adaptive scheduling in cloud systems. The framework leverages collaborative agent feedback, enhances task prioritization accuracy, and supports scalable deployment for complex workflows with dynamic resource availability.

Amit Sharma, Jean Dupont, Sneha Joshi, Taro Suzuki, Maria Garcia

This work presents a transformer-based architecture for real-time data fusion from heterogeneous sources. It employs layered attention, enabling robust representation learning and predictive modeling in environments with high-dimensional, noisy, and temporally inconsistent input streams.

Wei Zhang, Xu Ping, Zhang Wei, Yang Lin, Huang Lei

We develop a deep probabilistic model using hierarchical Bayesian networks to enhance predictive maintenance. The model identifies failure patterns and generates early alerts with quantifiable uncertainty, improving decision-making and equipment reliability in complex industrial systems.

Neha Reddy, Ivan Petrov, Elena Rossi, Kunal Desai, Ali Hassan

This study benchmarks quantum kernel methods against traditional SVMs in non-Euclidean domains. The results indicate that quantum-enhanced classifiers exhibit improved generalization, reduced overfitting, and computational scalability on high-dimensional, topologically complex datasets.

Michael Foster, Benjamin Cole, Laura Evans, Anna Jensen, Robert King

A quantum-inspired pipeline is introduced to enhance sparse signal reconstruction in IoT ecosystems. The method integrates non-linear optimization and adaptive filtering, achieving high fidelity in signal recovery while reducing computational overhead in large-scale, bandwidth-constrained environments.

James Wilson, Sarah Thompson, Emily Carter, Ryan Summers, Laura Evans