Experimental Software and Hardware Configuration for ADSS Cable Vibration Recognition

LSTM-CNN-CatBoost-GSSSA, a hybrid model, achieved 97.6% accuracy in recognizing external disturbances on urban buried optical cables. The dataset likely contains the experimental configuration and results used to develop and test this model, as described by author Xiaojuan Chen. It was last updated on May 4, 2026, and is shared under a CC-BY-4.0 license.

Use Cases

• Training hybrid ML models for vibration signal classification based on temporal and frequency characteristics mentioned in the description
• Benchmarking CatBoost hyperparameter optimization techniques based on the improved golden sine–enhanced Sparrow Search Algorithm (GSSSA)
• Studying feature fusion methods for time-series and spatial-frequency domain data as described in the model architecture
• Developing real-time monitoring systems for urban power grid security based on the described application to ADSS optical cables

Strengths

• Model performance is quantitatively reported, achieving 97.6% accuracy and surpassing six other models by margins up to 15%
• The dataset is openly shared under a permissive CC-BY-4.0 license
• A specific hybrid model architecture (LSTM-CNN-CatBoost-GSSSA) is detailed, providing context for the data's purpose

Limitations

• Row count is unknown, which may limit suitability assessment
• Column-level documentation is absent; field semantics must be inferred after download
• The dataset is very small at 5.5 KB, suggesting limited scope, likely containing configuration parameters or summary results rather than raw signal data

Provenance

Source

figshare, authored by Xiaojuan Chen

Collection Method

Likely generated from experiments with the described LSTM-CNN-CatBoost-GSSSA recognition model

Time Range

null

Freshness

Last updated 2026-05 04 17:27:05; freshness should be verified

Geography

null