Ship Fire Detection Based on an Improved YOLO Algorithm with a Lightweight Convolutional Neural Network Model

Wu, Huafeng; Hu, Yiming; Mei, Xiaojun; Xian, Jiangfeng

doi:10.3390/s22197420

Cited by 27 publications

(12 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Park et al [ 31 ] further tested the performance of Tiny-YOLOv2 for fire detection in the environment of the ship engine room. Wu et al [ 32 ] proposed an improved YOLOv4-tiny algorithm for accurate and efficient ship fire detection. They improved the detection accuracy of small target objects by adding a detection layer and Squeeze-and-Excitation attention (SE) module to the network.…”

Section: Related Workmentioning

confidence: 99%

Fire Detection in Ship Engine Rooms Based on Deep Learning

Zhu

Zhang

Wang

et al. 2023

Sensors

View full text Add to dashboard Cite

Ship fires are one of the main factors that endanger the safety of ships; because the ship is far away from land, the fire can be difficult to extinguish and could often cause huge losses. The engine room has many pieces of equipment and is the principal place of fire; however, due to its complex internal environment, it can bring many difficulties to the task of fire detection. The traditional detection methods have their own limitations, but fire detection using deep learning technology has the characteristics of high detection speed and accuracy. In this paper, we improve the YOLOv7-tiny model to enhance its detection performance. Firstly, partial convolution (PConv) and coordinate attention (CA) mechanisms are introduced into the model to improve its detection speed and feature extraction ability. Then, SIoU is used as a loss function to accelerate the model’s convergence and improve accuracy. Finally, the experimental results on the dataset of the ship engine room fire made by us shows that the mAP@0.5 of the improved model is increased by 2.6%, and the speed is increased by 10 fps, which can meet the needs of engine room fire detection.

show abstract

Section: Related Workmentioning

confidence: 99%

Fire Detection in Ship Engine Rooms Based on Deep Learning

Zhu

Zhang

Wang

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Gas sensors detect fires by detecting changes in the concentration of specific gases in the air, such as carbon dioxide and carbon monoxide. Under the framework of IoT, various sensors can be networked and share data in real-time [21,22]. For example, by working together, multiple sensor nodes can form a network to monitor fire risk.…”

Section: A Overview Of Fire Detection Techniques and Grounded Theorymentioning

confidence: 99%

The Analysis of Tourist Satisfaction Integrating the Artistic Intelligence Convolutional Neural Network and Internet of Things Technology

Yan

2023

IEEE Access

View full text Add to dashboard Cite

Aiming at the limitations of existing fire detection technology and the multi-dimensional challenge of tourist satisfaction analysis, this study proposes a series of innovative methods and models. Regarding fire detection, Depth Separable Convolution (DSC) and multi-scale detection structure are introduced to improve the You Only Look Once version 3 (YOLOv3) model. Moreover, the DSC-Anchor-Isoft-Non Maximum Suppression-YOLO (DAI-YOLO) model is implemented for the fire detection of scenic spots. The experimental results show that the precision, recall, and average precision of the DAI-YOLO model are 92.1%, 84.2%, and 84.6%, respectively, compared with other models, a minimum increase of 4.1%, 8.8%, and 6.0%, with higher detection accuracy and performance. Based on the analysis of tourist satisfaction, a comprehensive index system is constructed using the grounded theory of text mining, and emotion analysis is integrated into the satisfaction evaluation to reveal tourists' evaluation of scenic spots more comprehensively. According to the analysis, the environmental factor receives the highest satisfaction rating, reaching a positive rate of 98.78%. However, the satisfaction evaluation of scenic spot management is relatively low, accounting for 6.06% of the negative evaluation. The importance-satisfaction analysis reveals that the key factors affecting tourist satisfaction are traffic level, scenic spot tickets, and service. The results of this study provide valuable reference for the managers and researchers of scenic spots and are expected to contribute to the construction of a safer and more satisfying tourism experience.

show abstract

“…From the image processing of failed components, it is possible to identify patterns and thus improve their identification in the field [ 28 ]. Several researchers are using object detection and image classification based on convolutional neural network (CNN) models [ 29 , 30 , 31 ].…”

Section: Related Workmentioning

confidence: 99%

Wavelet LSTM for Fault Forecasting in Electrical Power Grids

Branco

Cavalca

Stefenon

et al. 2022

Sensors

View full text Add to dashboard Cite

An electric power distribution utility is responsible for providing energy to consumers in a continuous and stable way. Failures in the electrical power system reduce the reliability indexes of the grid, directly harming its performance. For this reason, there is a need for failure prediction to reestablish power in the shortest possible time. Considering an evaluation of the number of failures over time, this paper proposes performing failure prediction during the first year of the pandemic in Brazil (2020) to verify the feasibility of using time series forecasting models for fault prediction. The long short-term memory (LSTM) model will be evaluated to obtain a forecast result that an electric power utility can use to organize maintenance teams. The wavelet transform has shown itself to be promising in improving the predictive ability of LSTM, making the wavelet LSTM model suitable for the study at hand. The assessments show that the proposed approach has better results regarding the error in prediction and has robustness when statistical analysis is performed.

show abstract

Ship Fire Detection Based on an Improved YOLO Algorithm with a Lightweight Convolutional Neural Network Model

Cited by 27 publications

References 41 publications

Fire Detection in Ship Engine Rooms Based on Deep Learning

Fire Detection in Ship Engine Rooms Based on Deep Learning

The Analysis of Tourist Satisfaction Integrating the Artistic Intelligence Convolutional Neural Network and Internet of Things Technology

Wavelet LSTM for Fault Forecasting in Electrical Power Grids

Contact Info

Product

Resources

About