Location-aware hazardous litter management for smart emergency governance in urban eco-cyber-physical systems

Abstract

Smart city management is facing a new challenge from littered face masks during COVID-19 pandemic. Addressing the issues of detection and collection of this hazardous waste that is littered in public spaces and outside the controlled environments, usually associated with biomedical waste, is urgent for the safety of the communities around the world. Manual management of this waste is beyond the capabilities of governments worldwide as the geospatial scale of littering is very high and also because this contaminated litter is a health and safety issue for the waste collectors. In this paper, an autonomous biomedical waste management framework that uses edge surveillance and location intelligence for detection of the littered face masks and predictive modelling for emergency response to this problem is proposed. In this research a novel dataset of littered face masks in various conditions and environments is collected. Then, a new deep neural network architecture for rapid detection of discarded face masks on the video surveillance edge nodes is proposed. Furthermore, a location intelligence model for prediction of the areas with higher probability of hazardous litter in the smart city is presented. Experimental results show that the accuracy of the proposed model for detection of littered face masks in various environments is 96%, while the speed of processing is ten times faster than comparable models. The proposed framework can help authorities to plan for timely emergency response to scattering of hazardous material in residential environments.

Face Mask Detection in Smart Cities Using Deep and Transfer Learning: Lessons Learned from the COVID-19 Pandemic

“…By splitting the FMD task into two or more cascade stages, such as the location of faces in images, the extraction of image features, and the classification of the detected faces as masked and non-masked (and/or improperly masked), it would be easier to federate the learning task [124] and take advantage of locally trained models. Similar architectures can be employed for social distancing screening [227], detecting littered face masks [228], etc. Besides, another way to implement FL for face mask detection is to have multiple parties contribute to the model training by providing their datasets of images.…”

Remote Big Data Management Tools, Sensing and Computing Technologies, and Visual Perception and Environment Mapping Algorithms in the Internet of Robotic Things

“…Image processing and visual modeling tools, edge surveillance and computing technologies, and deep neural networks [61][62][63][64] optimize robotic agent behaviors in uncontrolled environments. Collaborative and cognitive robotics develop on multi-sensor data fusion technology, object localization, recognition, and mapping tools, and autonomous navigation systems.…”

“…[ [61][62][63][64][65][66][67][68] Blockchain technologies and autonomous systems enhance IoRT device interconnection and networking by decentralized data sharing and decision processes, collaborative techniques, and machine learning algorithms. Cloud networked robotics and IoRT systems harness autonomous learning capabilities and deep learning techniques for object motion, detection, mapping, and tracking.…”

“…Smart devices, context aware systems, and artificial neural networks [53][54][55][56] further continuous sensing and contextual data monitoring [57][58][59][60] across the ambient environment and spatial surroundings. Robotic operating and autonomous control systems are pivotal in reconfigurable manufacturing processes [61][62][63][64] in Industry 4.0-based networked environments. Robot vision and navigation systems [65][66][67][68] harness sensor-actuator networks, semantic technologies, and cloud-based object tracking tools [69][70][71][72] in relation to predictive performance of navigation and mapping tasks.…”

Digital twin modelling for smart fruit-growing: eco-cyber-physical system 4+1 architecture

“…Eco-cyber-physical systems (ECPS) concept is a relatively new concept applied for describing complex systems. ECPS is defined as a "combination of the living and non-living components of the ecosystem in conjunction with the cyber-physical sensors and intelligent agents in the environment, interacting as a system" [1].…”