Artificial Intelligence and Multi-Sensor Fusion Based Universal Fire Detection System for Smart Buildings Using IoT Techniques

Gaur, Anshul; Singh, Abhishek; Verma, Amitabh; Kumar, Anuj

doi:10.1080/03772063.2022.2088626

Cited by 5 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(10) A smart building fire detection system leveraging artificial intelligence and multisensor fusion has also been designed. (11) However, it was observed that the prevailing techniques predominantly issue warnings after fire inception, indicating a deficiency in preventive measures. Among the catalysts for electrical fires, residual current is identified as a principal factor contributing to these incidents.…”

Section: Introductionmentioning

confidence: 99%

Prediction Model of Residual Current Based on Grey Association and Neural Network

Sun

2024

Sensors and Materials

View full text Add to dashboard Cite

To enhance early electrical fire warning in power IoT systems, we propose a residual current modeling method combining grey correlation and neural networks. By analyzing 27985 sets of data from an intelligent fire monitoring system, effective data collection and processing with advanced sensor technology in an IoT context were demonstrated. The model, derived from correlation analysis and grey prediction algorithms, uses a trained neural network for predicting residual current. This method not only augments the efficiency and accuracy of data processing in IoT but also underscores the significance of sensor technology in electrical monitoring and fire prevention. The comparative analysis of predicted and actual residual currents, showing an error range of 0.18 to 3.21%, validates the accuracy of the model and the utility of sensor-driven methods in IoT applications.

show abstract

Section: Introductionmentioning

confidence: 99%

Prediction Model of Residual Current Based on Grey Association and Neural Network

Sun

2024

Sensors and Materials

View full text Add to dashboard Cite

show abstract

“…The use of TL is then extended to IoT-based applications in the mobile edge networks for resource optimization, aiming to comply with the inherent challenge of IoT in terms of limited computing resource. For example, the work in [30] proposes a TL-based IoT framework for fire detection. Specifically, a pre-trained CNN model using MobileNet is executed for fine-tuning to improve the fire detection accuracy with fewer false positives.…”

Section: Introductionmentioning

confidence: 99%

Image classification-based transfer learning framework for image detection of IoT devices

Saputra,

Chandra Utomo,

Alfian

2024

IJEECS

View full text Add to dashboard Cite

For artificial intelligence (AI) applications, centralized learning on a cloud server and local learning on an internet-of-things device may suffer from data privacy leakage due to data sharing and inaccurate prediction due to limited computing resources. Transfer learning has been proposed as one potential solution to the world's big data problems. Transfer learning eliminates the need for each internet-of-things device to share local data with the cloud server during the training process. Instead, it can go through the training process on its own, using a cloud server's pre-trained model with high accuracy. As a result, despite its limited computing resources, the internet of things device can still predict with high accuracy. This paper proposes a transfer learning model for improving image detection accuracy on IoT devices with restricted computation. To obtain accurate image classification, a deep learning approach based on convolutional neural networks is used. The proposed method with freeze and unfreeze approaches achieves a higher validation accuracy (up to 43.6%) and a lower validation loss (up to 6.5 times) than the non-transfer learning method, according to simulation results using three relevant internet-of-things datasets.

show abstract

The role of IoT sensor in smart building context for indoor fire hazard scenario: A systematic review of interdisciplinary articles

et al. 2023

View full text Add to dashboard Cite

Artificial Intelligence and Multi-Sensor Fusion Based Universal Fire Detection System for Smart Buildings Using IoT Techniques

Cited by 5 publications

References 19 publications

Prediction Model of Residual Current Based on Grey Association and Neural Network

Prediction Model of Residual Current Based on Grey Association and Neural Network

Image classification-based transfer learning framework for image detection of IoT devices

The role of IoT sensor in smart building context for indoor fire hazard scenario: A systematic review of interdisciplinary articles

Contact Info

Product

Resources

About