Convolutional Neural Network (CNN-SA) based Selective Amplification Model to Enhance Image Quality for Efficient Fire Detection

Sarkar, Sagnik; Menon, Aditya Sunil; Gopalakrishnan, T.; Kumar, Kakelli Anil

doi:10.5815/ijigsp.2021.05.05

Cited by 7 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then the convolution results will be processed using the activation function and used as input for the next layer. This process will continue to repeat until, finally, the model is sufficiently precise to the desired level [30], [45]. Once the CNN model has been trained, it may be applied to new microscopic photographs to generate predictions [46]- [48].…”

Section: Methodsmentioning

confidence: 99%

Enrichment of microscopic photographs by utilizing CNN regarding soil-transmitted helminths identification

Malik,

Frimadani,

Putra

2024

IJAAS

View full text Add to dashboard Cite

Soil-transmitted helminth (STH) infection remains a significant global health challenge, affecting millions of people, particularly in developing countries. A convolutional neural network (CNN) approach to optimize the detection of STH infections in microscopic images. The study aims to assess the effectiveness of the CNN model in identifying and classifying STH worm eggs accurately. The research employs MATLAB as the primary tool for conducting experiments and validation tests. By implementing image preprocessing techniques to enhance image quality and applying precise segmentation methods, the CNN model is trained on a dataset of microscopic images to learn and classify STH infections effectively. The validation test results demonstrate that the CNN model achieved a high accuracy rate of 92.31% in classifying STH infections. This accuracy surpasses traditional methods, which are time-consuming and susceptible to human errors. This study underscores the importance of integrating artificial intelligence, particularly CNN, into the healthcare domain to support detecting and diagnosing diseases requiring specialized expertise, such as STH infections. The findings of this research can serve as a valuable reference for researchers, medical practitioners, and data scientists in leveraging artificial intelligence to enhance the quality of healthcare services, leading to positive impacts on society worldwide.

show abstract

Section: Methodsmentioning

confidence: 99%

Enrichment of microscopic photographs by utilizing CNN regarding soil-transmitted helminths identification

Malik,

Frimadani,

Putra

2024

IJAAS

View full text Add to dashboard Cite

show abstract

“…Attention-based networks have also been used to enhance the accuracy of fire detection, with evaluations performed on custom datasets and compared with state-of-the-art CNN architecture [30]. Other deep-learning-based strategies for fire detection include the attention-and squeeze-customized CNN [31], U-shape network [31], Adam network [32], CNN-SA [33], and Adams predictor-corrector color weights network [34]. Moreover, Khan et al [35] proposed the ConvNeXtTiny model for fire detection in a real-world environment.…”

Section: Introductionmentioning

confidence: 99%

Efficient Fire Detection with E-EFNet: A Lightweight Deep Learning-Based Approach for Edge Devices

Farman,

Nasralla,

Khattak

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Fire detection employing vision sensors has drawn significant attention within the computer vision community, primarily due to its practicality and utility. Previous research predominantly relied on basic color features, a methodology that has since been surpassed by adopting deep learning models for enhanced accuracy. Nevertheless, the persistence of false alarms and increased computational demands remains challenging. Furthermore, contemporary feed-forward neural networks face difficulties stemming from their initialization and weight allocation processes, often resulting in vanishing-gradient issues that hinder convergence. This investigation recognizes the considerable challenges and introduces the cost-effective Encoded EfficientNet (E-EFNet) model. This model demonstrates exceptional proficiency in fire recognition while concurrently mitigating the incidence of false alarms. E-EFNet leverages the lightweight EfficientNetB0 as a foundational feature extractor, augmented by a series of stacked autoencoders for refined feature extraction before the final classification phase. In contrast to conventional linear connections, E-EFNet adopts dense connections, significantly enhancing its effectiveness in identifying fire-related scenes. We employ a randomized weight initialization strategy to mitigate the vexing problem of vanishing gradients and expedite convergence. Comprehensive evaluation against contemporary state-of-the-art benchmarks reaffirms E-EFNet’s superior recognition capabilities. The proposed model outperformed state-of-the-art approaches in accuracy over the Foggia and Yar datasets by achieving a higher accuracy of 0.31 and 0.40, respectively, and its adaptability for efficient inferencing on edge devices. Our study thoroughly assesses various deep models before ultimately selecting E-EFNet as the optimal solution for these pressing challenges in fire detection.

show abstract

“…Other examples include CNN-based fire detection methods using pre-processing algorithms known as selective amplification. This technique enhances images that are to be used in CNN, which are then trained on pre-processed images to detect fires with high accuracy [4]. Other studies have shown adaptive priority mechanisms and fire detection methods using AlexNet.…”

Section: Introductionmentioning

confidence: 99%

A Method of Detecting Candidate Regions and Flames Based on Deep Learning Using Color-Based Pre-Processing

Ryu

Kwak

2022

Fire

View full text Add to dashboard Cite

Recently, object detection methods using deep learning have made significant progress in terms of accuracy and speed. However, the requirements of a system to provide real-time detection are somewhat high, and current methods are still insufficient to accurately detect important factors directly related to life and safety, such as fires. Therefore, this study attempted to improve the detection rate by supplementing the existing research to reduce the false detection rate of flame detection in fire and to reduce the number of candidate regions extracted in advance. To this end, pre-processing based on the HSV and YCbCr color models was performed to filter the flame area simply and strongly, and a selective search was used to detect a valid candidate region for the filtered image. In addition, for the detected candidate region, a deep learning-based convolutional neural network (CNN) was used to infer whether the object was a flame. As a result, it was found that the flame-detection accuracy of the model proposed in this study was 7% higher than that of the other models presented for comparison, and the recall rate was increased by 6%.

show abstract

Convolutional Neural Network (CNN-SA) based Selective Amplification Model to Enhance Image Quality for Efficient Fire Detection

Cited by 7 publications

References 17 publications

Enrichment of microscopic photographs by utilizing CNN regarding soil-transmitted helminths identification

Enrichment of microscopic photographs by utilizing CNN regarding soil-transmitted helminths identification

Efficient Fire Detection with E-EFNet: A Lightweight Deep Learning-Based Approach for Edge Devices

A Method of Detecting Candidate Regions and Flames Based on Deep Learning Using Color-Based Pre-Processing

Contact Info

Product

Resources

About