CNN-based intelligent safety surveillance in green IoT applications

Cao, Wengang; Zhang, Jianing; Cai, Changxin; Chen, Quan; Zhao, Yu; Lou, Yimo; Jiang, Wei; Gui, Guan

doi:10.23919/jcc.2021.01.010

Cited by 39 publications

(17 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A low‐complexity precaching heuristic algorithm is designed for decreasing the energy consumption in blockchain‐based IoT 29 . The intelligent safety surveillance (ISS) method is proposed using a convolutional neural network (CNN), which is an auto‐supervised method for detecting the workers whether wearing or not wearing helmets 30 . The proposed research work is used to summarize the green IoT goals and achieve the green IoT design goals.…”

Section: Literature Surveymentioning

confidence: 99%

A novel hybrid meta‐heuristic concept for green communication in IoT networks: An intelligent clustering model

Akhtar

Ahamad²,

Abdalrahman

et al. 2022

Int J Communication

View full text Add to dashboard Cite

Summary Nowadays, there is an emerging need for applications based on the Internet of Things (IoT). The sensor nodes present in the IoT network produce data constantly, which directly influences the durability of the network. Therefore, two major challenges while designing IoT systems are network lifetime and energy consumption. Although the ability of IoT applications is huge, there are several limitations such as energy optimization, heterogeneity of devices storage, load balancing, privacy, and security that have to be addressed. These constraints have to be optimized for improving the efficiency of the networks. Hence, the main intention of this paper is to develop the intelligent‐based cluster head selection model for accomplishing green communication in IoT. The two famous algorithms like spotted hyena optimization (SHO) and sun flower optimization (SFO) are integrated to form sun flower‐spotted hyena optimization (SF‐SHO) by utilizing the hybrid meta‐heuristic concept for the optimal cluster head selection. The most significant parameters in IoT networks like delay, distance, energy, temperature, and load are considered for deriving a multi‐objective function to offer optimal clustering. The cluster head of the model is optimally tuned based on the hybrid SF‐SHO, to solve the multi‐objective problem, thus showing the enhanced green communication performance. The proposed model is analyzed and evaluated over different approaches in terms of energy‐specific factors, and the attained results confirm the efficiency of the developed method.

show abstract

Section: Literature Surveymentioning

confidence: 99%

A novel hybrid meta‐heuristic concept for green communication in IoT networks: An intelligent clustering model

Akhtar

Ahamad²,

Abdalrahman

et al. 2022

Int J Communication

View full text Add to dashboard Cite

show abstract

“…Due to the growth in a diverse range of intelligent applications, IoT systems have enriched our daily lives [4], involving aspects of healthcare [5], intelligent cities [6,7], agriculture [8], crowdsensing [9], and crowdsourcing [10], etc. IoT based on robust and suitable total solutions can also help manufacturers solve the problem from a conventional factory to a new smart factory to boost their productivity [11]. A real time optimization algorithm for a large framework based on IoT sensors and an ad-hoc connections system via TCP had been performed by Vaccari, et al [12].…”

Section: Introductionmentioning

confidence: 99%

The Vision-Based Data Reader in IoT System for Smart Factory

2022

View full text Add to dashboard Cite

The proposed research is based on a real plastic injection factory for cutting board production. Most existing approaches for smart manufacturing tried to build the total solution of IoT by moving forward to the standard of industry 4.0. Under the cost considerations, this will not be acceptable to most factories, so we proposed the vision based technology to solve their immediate problem. Real-time machine condition monitoring is important for making great products and measuring line productivity or factory productivity. The study focused on a vision-based data reader (VDR) in edge computing for smart factories. A simple camera embedded in Field Programmable Gate Array (FPGA) was attached to monitor the screen on the control panel of the machines. Each end device was preprogrammed to capture images and process data on its own. The preprocessing step was then performed to have the normalized illumination of the captured image. A saliency map was generated to detect the required region for recognition. Finally, digit recognition was performed and the recognized digits were sent to the IoT system. The most significant contribution of the proposed VDR system used the compact deep learning model for training and testing purposes to fit the requirement of cost consideration and real-time monitoring in edge computing. To build the compact model, different convolution filters were tested to fit the performance requirement. Experimentations on a real plastic cutting board factory showed the improvement in manufacturing products by the proposed system and achieved a high digit recognition accuracy of 97.56%. In addition, the prototype system had low power and low latency advantages.

show abstract

“…As the number of motor vehicles grows at a rate of about 10% per year, urban building congestion leads to slow development of road construction. The urbanization of China makes more and more rural population flock to the city, which leading to road congestion, traffic accidents, environmental pollution and other problems [3]. The rapid growth of vehicles not only makes urban traffic overload but also makes the frequent occurrence of criminal cases involving vehicles, bringing new challenges to public safety, and the current management and identification of vehicles basically rely on the existing road traffic management methods and manual judgment [4].…”

Section: Introductionmentioning

confidence: 99%

Intelligent Intersection Vehicle and Pedestrian Detection Based on Convolutional Neural Network

Yang

Chong²,

et al. 2022

Journal of Sensors

View full text Add to dashboard Cite

The preprocessed images are input to a pretrained neural network to obtain the corresponding feature mapping, and the corresponding region of interest is set for each point in the feature mapping to obtain multiple candidate feature regions; subsequently, these candidate feature regions are fed into a region proposal network and a deep residual network for binary classification and BB regression, and some of the candidate feature regions are filtered out, and the remaining feature regions are subjected to ROIAIign operation; finally, classification, BB regression, and mask generation are performed on these feature regions, and full convolutional nerve network operation is performed in each feature region and output. To further identify the specific model of the vehicle, this paper proposes a multifeature model recognition method that fuses the improved model with the optimized Mask R-CNN algorithm. A vehicle local feature dataset including vehicle badges, lights, air intake grille, and whole vehicle outline is established to simplify the network structure of model. Meanwhile, its detection frame generation process and the adjustment rules of overlapping frame confidence in nonmaximum suppression are improved for coarse vehicle localization. Then, the generated vehicle detection frames after localization are output to the Mask R-CNN algorithm after further optimizing the RPN structure. The localized vehicle detection frames are then output to the Mask R-CNN algorithm after further optimization of the RPN structure for local feature recognition, and good recognition results are achieved. Finally, this paper establishes a distributed server-based vehicle recognition system, which mainly includes database module, file module, feature extraction and matching module, message queue module, WEB module, and vehicle detection module. Due to the limitations of traditional region generation methods, this paper provides a brief analysis of the region generation network in the Faster R-CNN algorithm and details the loss calculation principle of the output layer.

show abstract

CNN-based intelligent safety surveillance in green IoT applications

Cited by 39 publications

References 36 publications

A novel hybrid meta‐heuristic concept for green communication in IoT networks: An intelligent clustering model

A novel hybrid meta‐heuristic concept for green communication in IoT networks: An intelligent clustering model

The Vision-Based Data Reader in IoT System for Smart Factory

Intelligent Intersection Vehicle and Pedestrian Detection Based on Convolutional Neural Network

Contact Info

Product

Resources

About