VQC-ZTI: Variational Quantum Control for Zero Trust Protection of the Tactile Internet
本文提出VQC-ZTI框架，利用变分量子分类器保护触觉互联网服务安全，通过分离异常评分与执行路径来提高安全性并保持控制行为可预测性。
0 citationsRead paper
Selected work
Representative Papers
Robust Constraint-Aware Bayesian Tuning of BBRv2 for QUIC under Tactile Internet Constraints
This study addresses the challenge of balancing low latency and high throughput in QUIC-based Tactile Internet transmission by proposing a robust constraint-aware tuning framework. The approach formulates BBRv2 parameter configuration as a constrained black-box optimization problem, employing Tree-structured Parzen Estimator (TPE) Bayesian optimization combined with multi-scenario simulations for efficient search. Experimental results demonstrate that this framework strictly guarantees tail latency and packet loss rate constraints under diverse network impairments while significantly reducing jitter. Furthermore, it maintains competitive throughput levels, effectively achieving a robust trade-off among multiple performance metrics to satisfy the stringent Quality of Service requirements inherent to the Tactile Internet.
0 citationsRead paper
Identifying potentiating events in evolutionary search using replay experiments
This study addresses the identification of key historical events—termed potential-enhancing events—that increase the likelihood of specific evolutionary outcomes in evolutionary search. To this end, it systematically introduces replay experiments from evolutionary biology into evolutionary computation for the first time, proposing an analytical replay methodology. This approach quantifies changes in a population’s potential to produce a target outcome by restarting evolution from different points along its trajectory. Combining genetic programming with multi-round backward replays, the experiments demonstrate that a population’s problem-solving potential does not always coincide with improvements in fitness, revealing an asynchrony between the evolution of success potential and fitness. These findings offer a novel perspective on evolutionary dynamics.
0 citationsRead paper
MazzikaAI: A knowledge-based performance-to-prompt compiler for real-time Arabic maqam accompaniment with a streaming text-to-music model
This work addresses the limitations of existing generative music models, which predominantly rely on Western twelve-tone equal temperament and thus struggle to support the microtonal intervals, ornamental nuances, and real-time interactive accompaniment required by Arabic maqam music. The authors propose a knowledge-driven real-time accompaniment framework that dynamically compiles performer inputs—such as MIDI, gestures, and harmonic context—into natural language prompts via an expert rule base, directly guiding an unmodified, streaming text-to-music foundation model (Google Lyria RealTime) to generate culturally appropriate accompaniments. By integrating deterministic musicological rules with a general-purpose generative model without fine-tuning, this approach achieves sub-second end-to-end latency, significantly increases the usage of quarter tones, and enhances maqam fidelity, thereby demonstrating the feasibility of culturally inclusive audio generation.
0 citationsRead paper
Collaborative System Failure Prognostics via Federated Longitudinal-Survival Modeling
This study addresses the challenge of system failure prediction in distributed settings, where data privacy and proprietary constraints hinder the integration of multi-source sensor measurements and time-to-failure information. To overcome this limitation, the authors propose a federated vertical-survival modeling framework that, for the first time, incorporates a separable discrete-time hazard function into federated learning. By combining local temporal representation learning on client devices with global collaborative optimization, the method enables cross-institutional reliability modeling and remaining useful life (RUL) estimation without sharing raw data. This approach circumvents the intractability of directly optimizing traditional Cox models under federated settings. Experiments on the four C-MAPSS turbofan engine datasets demonstrate that the proposed method significantly outperforms locally trained models and achieves performance approaching that of centralized training, even under heterogeneous operating conditions and diverse failure modes.
0 citationsRead paper
Recent publications
Latest Papers
VQC-ZTI: Variational Quantum Control for Zero Trust Protection of the Tactile Internet
本文提出VQC-ZTI框架，利用变分量子分类器保护触觉互联网服务安全，通过分离异常评分与执行路径来提高安全性并保持控制行为可预测性。
0 citationsRead paper
Robust Constraint-Aware Bayesian Tuning of BBRv2 for QUIC under Tactile Internet Constraints
This study addresses the challenge of balancing low latency and high throughput in QUIC-based Tactile Internet transmission by proposing a robust constraint-aware tuning framework. The approach formulates BBRv2 parameter configuration as a constrained black-box optimization problem, employing Tree-structured Parzen Estimator (TPE) Bayesian optimization combined with multi-scenario simulations for efficient search. Experimental results demonstrate that this framework strictly guarantees tail latency and packet loss rate constraints under diverse network impairments while significantly reducing jitter. Furthermore, it maintains competitive throughput levels, effectively achieving a robust trade-off among multiple performance metrics to satisfy the stringent Quality of Service requirements inherent to the Tactile Internet.
0 citationsRead paper
Identifying potentiating events in evolutionary search using replay experiments
This study addresses the identification of key historical events—termed potential-enhancing events—that increase the likelihood of specific evolutionary outcomes in evolutionary search. To this end, it systematically introduces replay experiments from evolutionary biology into evolutionary computation for the first time, proposing an analytical replay methodology. This approach quantifies changes in a population’s potential to produce a target outcome by restarting evolution from different points along its trajectory. Combining genetic programming with multi-round backward replays, the experiments demonstrate that a population’s problem-solving potential does not always coincide with improvements in fitness, revealing an asynchrony between the evolution of success potential and fitness. These findings offer a novel perspective on evolutionary dynamics.
0 citationsRead paper
MazzikaAI: A knowledge-based performance-to-prompt compiler for real-time Arabic maqam accompaniment with a streaming text-to-music model
This work addresses the limitations of existing generative music models, which predominantly rely on Western twelve-tone equal temperament and thus struggle to support the microtonal intervals, ornamental nuances, and real-time interactive accompaniment required by Arabic maqam music. The authors propose a knowledge-driven real-time accompaniment framework that dynamically compiles performer inputs—such as MIDI, gestures, and harmonic context—into natural language prompts via an expert rule base, directly guiding an unmodified, streaming text-to-music foundation model (Google Lyria RealTime) to generate culturally appropriate accompaniments. By integrating deterministic musicological rules with a general-purpose generative model without fine-tuning, this approach achieves sub-second end-to-end latency, significantly increases the usage of quarter tones, and enhances maqam fidelity, thereby demonstrating the feasibility of culturally inclusive audio generation.
0 citationsRead paper
Collaborative System Failure Prognostics via Federated Longitudinal-Survival Modeling
This study addresses the challenge of system failure prediction in distributed settings, where data privacy and proprietary constraints hinder the integration of multi-source sensor measurements and time-to-failure information. To overcome this limitation, the authors propose a federated vertical-survival modeling framework that, for the first time, incorporates a separable discrete-time hazard function into federated learning. By combining local temporal representation learning on client devices with global collaborative optimization, the method enables cross-institutional reliability modeling and remaining useful life (RUL) estimation without sharing raw data. This approach circumvents the intractability of directly optimizing traditional Cox models under federated settings. Experiments on the four C-MAPSS turbofan engine datasets demonstrate that the proposed method significantly outperforms locally trained models and achieves performance approaching that of centralized training, even under heterogeneous operating conditions and diverse failure modes.
0 citationsRead paper