Energy-Efficient Deep CNN for Smoke Detection in Foggy IoT Environment

Khan, Salman; Muhammad, Khan; Mumtaz, Shahid; Baik, Sung Wook; Albuquerque, Victor Hugo C. de

doi:10.1109/jiot.2019.2896120

Cited by 142 publications

(70 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Images taken from videos were used as the source for the analyses in [80], being non-hierarchical categorical data. The initial sample size was 72,012 images of 224 * 224 * 3 pixels.…”

Section: Application Of Sustainability-data Relationshipmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Technologies for Sustainability in Smart Cities in the Post-COVID Era

2020

View full text Add to dashboard Cite

The unprecedented urban growth of recent years requires improved urban planning and management to make urban spaces more inclusive, safe, resilient and sustainable. Additionally, humanity faces the COVID pandemic, which especially complicates the management of Smart Cities. A possible solution to address these two problems (environmental and health) in Smart Cities may be the use of Machine Learning techniques. One of the objectives of our work is to thoroughly analyze the link between the concepts of Smart Cities, Machine Learning techniques and their applicability. In this work, an exhaustive study of the relationship between Smart Cities and the applicability of Machine Learning (ML) techniques is carried out with the aim of optimizing sustainability. For this, the ML models, analyzed from the point of view of the models, techniques and applications, are studied. The areas and dimensions of sustainability addressed are analyzed, and the Sustainable Development Goals (SDGs) are discussed. The main objective is to propose a model (EARLY) that allows us to tackle these problems in the future. An inclusive perspective on applicability, sustainability scopes and dimensions, SDGs, tools, data types and Machine Learning techniques is provided. Finally, a case study applied to an Andalusian city is presented.

show abstract

“…Images taken from videos were used as the source for the analyses in [80], being non-hierarchical categorical data. The initial sample size was 72,012 images of 224 * 224 * 3 pixels.…”

Section: Application Of Sustainability-data Relationshipmentioning

confidence: 99%

“…Convolutional neural networks have been used to detect fire [80]. They were used for an image classification tool in 1000 categories.…”

Section: Relationship Between Sustainability Applications and Machinementioning

confidence: 99%

Machine Learning Technologies for Sustainability in Smart Cities in the Post-COVID Era

2020

View full text Add to dashboard Cite

show abstract

“…Before training the networks, the temporal evolution of smoke is also integrated with a motion-based transformation of images as a pre-processing step. Khan et al [ 26 ] proposed an energy-efficient system based on a deep CNN for early smoke detection in both normal and foggy environments. This method takes advantage of the VGG-16 architecture [ 27 ], considering its sensible stability between accuracy and time efficiency.…”

Section: Related Studiesmentioning

confidence: 99%

Light-Weight Student LSTM for Real-Time Wildfire Smoke Detection

Jeong

Park

Nam

et al. 2020

Sensors

View full text Add to dashboard Cite

As the need for wildfire detection increases, research on wildfire smoke detection combining low-cost cameras and deep learning technology is increasing. Camera-based wildfire smoke detection is inexpensive, allowing for a quick detection, and allows a smoke to be checked by the naked eye. However, because a surveillance system must rely only on visual characteristics, it often erroneously detects fog and clouds as smoke. In this study, a combination of a You-Only-Look-Once detector and a long short-term memory (LSTM) classifier is applied to improve the performance of wildfire smoke detection by reflecting on the spatial and temporal characteristics of wildfire smoke. However, because it is necessary to lighten the heavy LSTM model for real-time smoke detection, in this paper, we propose a new method for applying the teacher–student framework to deep LSTM. Through this method, a shallow student LSTM is designed to reduce the number of layers and cells constituting the LSTM model while maintaining the original deep LSTM performance. As the experimental results indicate, our proposed method achieves up to an 8.4-fold decrease in the number of parameters and a faster processing time than the teacher LSTM while maintaining a similar detection performance as deep LSTM using several state-of-the-art methods on a wildfire benchmark dataset.

show abstract

“…Different fire signatures such a flame, smoke, and heat were used for fire and smoke detection using CNN by different researchers [20][21][22][23][24][25][26]. Some authors extended their work to include the detection of forest fires and enable fast response time for firefighting and the performance of rescue operations.…”

Section: Literature Reviewmentioning

confidence: 99%

Hardware Module Design and Software Implementation of Multisensor Fire Detection and Notification System Using Fuzzy Logic and Convolutional Neural Networks (CNNs)

Sowah

Apeadu

Gatsi

et al. 2020

Journal of Engineering

View full text Add to dashboard Cite

This paper presents the design and development of a fuzzy logic-based multisensor fire detection and a web-based notification system with trained convolutional neural networks for both proximity and wide-area fire detection. Until recently, most consumer-grade fire detection systems relied solely on smoke detectors. These offer limited protection due to the type of fire present and the detection technology at use. To solve this problem, we present a multisensor data fusion with convolutional neural network (CNN) fire detection and notification technology. Convolutional Neural Networks are mainstream methods of deep learning due to their ability to perform feature extraction and classification in the same architecture. The system is designed to enable early detection of fire in residential, commercial, and industrial environments by using multiple fire signatures such as flames, smoke, and heat. The incorporation of the convolutional neural networks enables broader coverage of the area of interest, using visuals from surveillance cameras. With access granted to the web-based system, the fire and rescue crew gets notified in real-time with location information. The efficiency of the fire detection and notification system employed by standard fire detectors and the multisensor remote-based notification approach adopted in this paper showed significant improvements with timely fire detection, alerting, and response time for firefighting. The final experimental and performance evaluation results showed that the accuracy rate of CNN was 94% and that of the fuzzy logic unit is 90%.

show abstract

Energy-Efficient Deep CNN for Smoke Detection in Foggy IoT Environment

Cited by 142 publications

References 40 publications

Machine Learning Technologies for Sustainability in Smart Cities in the Post-COVID Era

Machine Learning Technologies for Sustainability in Smart Cities in the Post-COVID Era

Light-Weight Student LSTM for Real-Time Wildfire Smoke Detection

Hardware Module Design and Software Implementation of Multisensor Fire Detection and Notification System Using Fuzzy Logic and Convolutional Neural Networks (CNNs)

Contact Info

Product

Resources

About