LSTM-CNN-CatBoost: Model Evaluation Results for ADSS Cable Vibration Recognition

Experimental results for a hybrid LSTM-CNN-CatBoost-GSSSA model designed to recognize external disturbances on urban All-Dielectric Self-Supporting optical cables. The dataset, shared by Xiaojuan Chen on figshare, contains evaluation metrics showing the model achieved 97.6% accuracy. The file was last updated on 2026-05-04.

Use Cases

• Benchmarking hybrid deep learning models based on reported accuracy metrics.
• Analyzing vibration signal recognition performance for power grid security applications.
• Optimizing hyperparameters for CatBoost models using evolutionary algorithms as described.
• Comparing model computational efficiency for real-time monitoring systems.

Strengths

• Model accuracy of 97.6% is explicitly reported and compared against six other models.
• Dataset is openly shared under a CC-BY-4.0 license, permitting reuse with attribution.
• The description provides a detailed technical context for the model's application.

Limitations

• Row count and column-level documentation are absent; field semantics must be inferred after download.
• The dataset is very small at 5.5 KB, indicating limited scope, likely containing only summary results.
• Last updated 2026-05-04; freshness should be verified for current research.

Provenance

Source

figshare, author Xiaojuan Chen.

Collection Method

Likely contains experimental results from model training and testing as described in the accompanying paper.

Time Range

null

Freshness

Last updated 2026-05-04 17:27:09.

Geography

null