What does this research mean for the field?

A hybrid CNN-LSTM deep learning model provides superior predictive performance for IoT-based smoke detection compared to other neural architectures, while simpler models like MLP, LSTM, and CNN offer the best computational efficiency. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

This research aims to develop a deep learning framework that enhances smoke detection performance and efficiency.

April 30, 2026Open Access

An optimized deep learning framework for IoT-based smoke detection with enhanced performance and computational efficiency

Key Points

This research aims to develop a deep learning framework that enhances smoke detection performance and efficiency.
Integrated various neural architectures, including MLP, CNN, LSTM, and hybrid models like CNN-LSTM.
Used StandardScaler and SMOTE for dataset standardization and balancing to tackle class imbalance.
Employed Optuna for Bayesian hyperparameter optimization to fine-tune learning parameters.
Hybrid CNN-LSTM model showed superior predictive performance across evaluation metrics.
MLP, LSTM, and CNN had the lowest memory usage and shortest training/testing durations.
All models demonstrated strong predictive performance, indicating deep learning's effectiveness for smoke detection.

Abstract

Early and reliable smoke detection is critical for preventing fire-related disasters, safeguarding human lives, and ensuring infrastructure safety. Conventional sensor-based systems, however, are often constrained by fixed threshold settings, delayed responses, and high false alarm rates, which limit their reliability in dynamic real-world Internet of Things (IoT) environments. To address these limitations, this study presents a comprehensive deep learning-based framework for intelligent smoke detection, integrating a diverse set of neural architectures ranging from conventional models such as Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM), to advanced architectures including Bidirectional LSTM (BiLSTM), Gated Recurrent Unit (GRU), Deep LSTM, Deep BiLSTM, Deep GRU, and hybrid models such as CNN-LSTM and Stacked CNN-LSTM. To ensure robust model learning, the dataset was standardized using the StandardScaler and balanced using the Synthetic Minority Over-sampling Technique (SMOTE) to address class imbalance between smoke and non-smoke samples. Each model was further optimized using the Optuna Bayesian hyperparameter optimization framework, enabling systematic and automated fine-tuning of learning parameters for optimal convergence. The experimental evaluation employed multiple binary classification metrics, including Accuracy, Precision, Recall, F 1 -Score, ROC-AUC, and PR-AUC, alongside computational efficiency indicators such as training time, testing time, and peak memory usage. The results demonstrate strong predictive performance across all models, with the Hybrid CNN-LSTM model consistently outperforming others across most predictive evaluation metrics, exhibiting superior generalization capability and convergence behavior. Furthermore, the MLP, LSTM, and CNN models achieved the lowest memory footprints and shortest training and testing durations. These findings highlight the effectiveness of deep learning for intelligent smoke detection systems capable of delivering early, accurate, and reliable fire warnings, offering a scalable solution for modern fire prevention and safety applications.

AI से पूछें

Bookmark

View Full Paper

Cite This Study

Nazish et al. (Tue,) studied this question.

synapsesocial.com/papers/69f2f1471e5f7920c6386f44 https://doi.org/https://doi.org/10.1186/s43067-026-00345-x

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

AI से पूछें

Bookmark

View Full Paper