Dynamic Detection Method of Network Digital Economy based on Multi-Region Full Distribution Algorithm

Existing intelligent perception and control technologies have problems of response lag, regional isolation, and insufficient global perception in dynamic detection of network digital economy, making it difficult to cope with the complex digital economy environment with high dynamics and multiple int...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2025 International Conference on Intelligent Computing and Knowledge Extraction (ICICKE) S. 1 - 6
Hauptverfasser: Fang, Chunjie, Ab Yajid, Mohd Shukri, Tham, Jacquline
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 06.06.2025
Schlagworte:
Accuracy
Adaptation models
anti-interference robustness
Delays
Digital economy
Distributed algorithms
dynamic detection
Heuristic algorithms
intelligent perception
Internet of Things
IoT integration
multi-regional fully distributed algorithm
Real-time systems
Robustness
Throughput
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Existing intelligent perception and control technologies have problems of response lag, regional isolation, and insufficient global perception in dynamic detection of network digital economy, making it difficult to cope with the complex digital economy environment with high dynamics and multiple interferences. To this end, this paper introduces the fusion mechanism of artificial intelligence and the Internet of Things, and constructs a dynamic detection method for the network digital economy based on a multi-region fully distributed algorithm. This method realizes cross-regional anomaly perception and dynamic behavior recognition through the distributed deployment of IoT nodes, combined with the regional collaborative scoring mechanism and the global aggregation model. Relying on the deep neural network and regional weighted fusion algorithm in artificial intelligence, this paper aggregates and optimizes the local anomaly scores of each region, thereby improving the system's robust perception of data disturbances, delay fluctuations and abnormal behaviors. Experimental results show that the proposed method is superior to traditional centralized and non-cooperative detection models in terms of accuracy, detection delay, TPS throughput performance, and anti-interference robustness. The accuracy is improved by 3.1%, the average delay is reduced by 40.7%, and the accuracy drop under high interference is controlled within 3.5%, which verifies the refined perception and global control capabilities of the proposed method for the dynamics of the digital economy in complex environments.
DOI:10.1109/ICICKE65317.2025.11136406