Modern data centers face increasing complexity with distributed microservice architectures, making anomaly detection and fault localization challenging yet critical. Traditional monitoring sensor tools struggle with heterogeneous metrics, temporal correlations, and precise root cause analysis in these environments. This paper proposes a dual-channel deep learning framework that integrates Temporal Convolutional Networks with Variational Autoencoders to address these challenges. Our approach employs contrastive learning to create unified representations of diverse service metrics and incorporates causal inference mechanisms to trace fault propagation paths. We evaluated our framework using a semi-supervised learning approach that leveraged both labeled anomalies and abundant normal data, achieving 95.4% detection accuracy, 93.8% F1-score, and 87.6% precision in fault component localization. The system reduced the average troubleshooting time by 43% and false localization rates by 31% compared to state-of-the-art methods, while maintaining a computational efficiency suitable for real-time monitoring. These results demonstrate the effectiveness of our approach in identifying and precisely localizing anomalies in complex microservice environments through intelligent sensing of system metrics, enabling proactive maintenance strategies that minimize service disruptions.

Traditional marketing uplift models suffer from a fundamental limitation: they typically operate under static assumptions that fail to capture the temporal dynamics of customer responses to marketing interventions. This paper introduces a novel framework that combines causal forest algorithms with deep reinforcement learning to dynamically model marketing uplift effects. Our approach enables the real-time identification of heterogeneous treatment effects across customer segments while simultaneously optimizing intervention strategies through an adaptive learning mechanism. The key innovations of our framework include the following: (1) a counterfactual simulation environment that emulates diverse customer response patterns; (2) an adaptive reward mechanism that captures both immediate and long-term intervention outcomes; and (3) a dynamic policy optimization process that continually refines targeting strategies based on evolving customer behaviors. Empirical evaluations on both simulated and real-world marketing campaign data demonstrate that our approach significantly outperforms traditional static uplift models, achieving up to a 27% improvement in targeting efficiency and an 18% increase in the return on marketing investment. The framework leverages inherent symmetries in customer-intervention interactions, where balanced and symmetric reward structures ensure fair optimization across diverse customer segments. The proposed framework addresses the limitations of existing methods by effectively modeling the dynamic and heterogeneous nature of customer responses to marketing interventions, providing marketers with a powerful tool for implementing personalized and adaptive campaign strategies.

Automated food safety inspection systems rely heavily on the visual detection of contamination, spoilage, and foreign objects in food products. Current approaches typically require extensive labeled training data for each specific hazard type, limiting generalizability to novel or rare safety issues. We propose a zero-shot detection framework for visual food safety hazards that enables the identification of previously unseen contamination types without requiring explicit training examples. Our approach adapts and extends the Knowledge-Enhanced Feature Synthesizer (KEFS) methodology to the food safety domain by constructing a specialized knowledge graph that encodes visual safety attributes and their correlations with food categories. We introduce a Food Safety Knowledge Graph (FSKG) that models the relationships between 26 food categories and 48 visual safety attributes (e.g., discoloration, mold patterns, foreign material characteristics) extracted from food safety databases and expert knowledge. Using this graph as the prior knowledge, our system synthesizes discriminative visual features for unseen hazard classes through a multi-source graph fusion module and region feature diffusion model. Experiments on our newly constructed Food Safety Visual Hazards (FSVH) dataset demonstrate that our approach achieves 63.7% mAP in zero-shot hazard detection, outperforming state-of-the-art general zero-shot detection methods by 6.9%. Furthermore, our framework demonstrates robust generalization to fine-grained novel hazard categories while maintaining high detection performance (59.8% harmonic mean) in generalized zero-shot scenarios where both seen and unseen hazards may occur simultaneously. This work represents a significant advancement toward automated, generalizable food safety inspection systems capable of adapting to emerging visual hazards without a costly retraining process.

Battery health monitoring and remaining useful life (RUL) estimation for electric vehicles face two significant challenges: battery data heterogeneity and sample imbalance. This study presents a novel approach based on Transformer architecture to specifically address these issues. We utilized the NASA lithium-ion battery cycling dataset, which contains charge-discharge and impedance measurement data under various temperature conditions. To tackle data heterogeneity, we developed a multimodal feature fusion strategy that effectively integrates battery sensor data from different sources and formats, including time-series charge-discharge sensor data and spectral impedance sensor measurements. To mitigate sample imbalance, we implemented an adaptive resampling technique and hierarchical attention mechanism, enhancing the model’s ability to recognize rare degradation patterns. Our Transformer-based model captures long-term dependencies in the battery degradation process through its self-attention mechanism. Experimental results demonstrate that the proposed solution significantly improves battery degradation prediction accuracy, achieving a 21.3% increase in accuracy when processing heterogeneous data and a 24.5% improvement in prediction capability for imbalanced samples compared to traditional methods. Additionally, through case studies, we validate the applicability of this method in actual electric vehicle battery management systems, providing reliable data support for battery preventive maintenance and replacement decisions. The findings have important implications for enhancing the reliability and economic efficiency of electric vehicle battery management systems.

The rapid proliferation of Internet of Things (IoT) devices and their associated application programming interfaces (APIs) has significantly increased the complexity of sensor network traffic management, necessitating more sophisticated and transparent control mechanisms. In this paper, we introduce XGate, a novel explainable reinforcement learning framework designed specifically for API traffic management in sensor networks. XGate addresses the critical challenge of balancing optimal routing decisions with the interpretability demands of network administrators operating large-scale IoT deployments. Our approach integrates transformer-based attention mechanisms with counterfactual reasoning to provide human-comprehensible explanations for each traffic management decision across distributed sensor data streams. Through extensive experimentation on three large-scale sensor API traffic datasets, we demonstrate that XGate achieves 23.7% lower latency and 18.5% higher throughput compared to state-of-the-art black-box reinforcement learning approaches. More importantly, our user studies with sensor network administrators (n=42) reveal that XGate’s explanation capabilities improve operator trust by 67% and reduce intervention time by 41% during anomalous sensor traffic events. The theoretical analysis further establishes probabilistic guarantees on explanation fidelity while maintaining computational efficiency suitable for real-time sensor data management. XGate represents a significant advancement toward trustworthy AI systems for critical IoT infrastructure, providing transparent decision making without sacrificing performance in dynamic sensor network environments.

Modern database systems require autonomous CPU scheduling frameworks that dynamically optimize resource allocation across heterogeneous workloads while maintaining strict performance guarantees. We present a novel hierarchical deep reinforcement learning framework augmented with graph neural networks to address CPU scheduling challenges in mixed database environments comprising Online Transaction Processing (OLTP), Online Analytical Processing (OLAP), vector processing, and background maintenance workloads. Our approach introduces three key innovations: first, a symmetric two-tier control architecture where a meta-controller allocates CPU budgets across workload categories using policy gradient methods while specialized sub-controllers optimize process-level resource allocation through continuous action spaces; second, graph neural network-based dependency modeling that captures complex inter-process relationships and communication patterns while preserving inherent symmetries in database architectures; and third, meta-learning integration with curiosity-driven exploration enabling rapid adaptation to previously unseen workload patterns without extensive retraining. The framework incorporates a multi-objective reward function balancing Service Level Objective (SLO) adherence, resource efficiency, symmetric fairness metrics, and system stability. Experimental evaluation through high-fidelity digital twin simulation and production deployment demonstrates substantial performance improvements: 43.5% reduction in p99 latency violations for OLTP workloads and 27.6% improvement in overall CPU utilization, with successful scaling to 10,000 concurrent processes maintaining sub-3% scheduling overhead. This work represents a significant advancement toward truly autonomous database resource management, establishing a foundation for next-generation self-optimizing database systems with implications extending to broader orchestration challenges in cloud-native architectures.