Parameter Settings of CNN for Miner Emotion Recognition

A 5.5 KB Excel file containing parameter settings for a convolutional neural network (CNN) combined with a Bi-LSTM network. The model was developed to recognize five categories of unsafe emotions exhibited by miners using a bimodal framework integrating speech and facial expression features. The dataset was uploaded by Ying Lu on May 15, 2026.

Use Cases

• Training CNN-BiLSTM models for speech-based emotion recognition based on the described architecture.
• Benchmarking feature enhancement strategies for multimodal emotion classification.
• Reproducing the reported 85.56% mean recognition accuracy for miner safety applications.

Strengths

• The model described achieved a reported mean recognition accuracy of 85.56% on a five-category emotion dataset.
• The dataset is associated with a model that underwent preliminary field testing in a real mining environment.

Limitations

• The dataset is very small at 5.5 KB, suggesting limited scope.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

Ying Lu via figshare

Collection Method

Likely contains parameters from a CNN-BiLSTM model developed for miner emotion recognition.

Freshness

Last updated 2026-05-15 17:36:59; freshness should be verified.