Application of Image Analytics for Disaster Response in Smart Cities

Chaudhuri, Neha; Bose, Indranil

doi:10.24251/hicss.2019.367

Cited by 23 publications

(8 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we demonstrate extensive simulation results based on TensorFlow [11] to show the performance of the proposed learning-based approach, and validate its superiority by comparing it with other baseline schemes.…”

Section: Methodsmentioning

confidence: 98%

“…Under this network architecture, various kinds of User Equipments (UE) can exchange their messages or report their monitored information. For instance, victims can use their wireless devices to request help from responders or obtain instructions from the government agency; and rescue drones or robots with wireless transceivers can upload images or videos to facilitate the analytic tasks [11] in the MDRU for the detection of survivors or assessment of damage status. Without the loss of generality, it is reasonable to assume that UEs may move continuously and generate data either periodically or on-demand which depends on the applications, and they have the energy harvesting capability to prolong the operating time [12] due to no reliable power supply in disaster area.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Wireless Access Control in Edge-Aided Disaster Response: A Deep Reinforcement Learning-Based Approach

et al. 2021

View full text Add to dashboard Cite

The communication infrastructure is most likely to be damaged after a major disaster occurred, which would lead to further chaos in the disaster stricken area. Modern rescue activities heavily rely on the wireless communications, such as safety status report, disrupted area monitoring, evacuation instruction, rescue coordination, etc. Large amount of data generated from victims, sensors and responders must be delivered and processed in a fast and reliable way, even when the normal communication infrastructure is degraded or destroyed. To this end, reconstructing the post-disaster network by deploying MDRU (Movable and Deployable Resource Unit) and relay unit at edge is a very promising solution. However, the optimal wireless access control in this heterogeneous hastily formed network is extremely challenging, due to the frequent varying environment and the lack of statistics information in advance in post-disaster scenarios. In this paper, we propose a learning based wireless access control approach for edgeaided disaster response network. More specifically, we model the wireless access control procedure as a discrete-time single agent Markov decision process, and solve the problem by exploiting deep reinforcement learning technique. By extensive simulation results, we show that the proposed mechanism significantly outperforms the baseline schemes in terms of delay and packet drop rate.

show abstract

Section: Methodsmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

Wireless Access Control in Edge-Aided Disaster Response: A Deep Reinforcement Learning-Based Approach

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Visual records of disaster areas can have significant effects on the selection of an effective disaster response. In that light, Chaudhuri and Bose [186] examined the effectiveness of the machine learning technique to manage disasters in smart cities. The proposed technique was used to classify images, containing photographs of disaster areas, with high accuracy.…”

Section: Collaboration Of Drone and Iot For Disaster Managementmentioning

confidence: 99%

Survey on Collaborative Smart Drones and Internet of Things for Improving Smartness of Smart Cities

et al. 2019

View full text Add to dashboard Cite

Smart cities contain intelligent things which can intelligently automatically and collaboratively enhance life quality, save people's lives, and act a sustainable resource ecosystem. To achieve these advanced collaborative technologies such as drones, robotics, artificial intelligence, and Internet of Things (IoT) are required to increase the smartness of smart cities by improving the connectivity, energy efficiency, and quality of services (QoS). Therefore, collaborative drones and IoT play a vital role in supporting a lot of smartcity applications such as those involved in communication, transportation, agriculture,safety and security, disaster mitigation, environmental protection, service delivery, energy saving, e-waste reduction, weather monitoring, healthcare, etc. This paper presents a survey of the potential techniques and applications of collaborative drones and IoT which have recently been proposed in order to increase the smartness of smart cities. It provides a comprehensive overview highlighting the recent and ongoing research on collaborative drone and IoT in improving the real-time application of smart cities. This survey is different from previous ones in term of breadth, scope, and focus. In particular, we focus on the new concept of collaborative drones and IoT for improving smart-city applications. This survey attempts to show how collaborative drones and IoT improve the smartness of smart cities based on data collection, privacy and security, public safety, disaster management, energy consumption and quality of life in smart cities. It mainly focuses on the measurement of the smartness of smart cities, i.e., environmental aspects, life quality, public safety, and disaster management.

show abstract

“…Most works on identifying disasters from social media images have applied CNN-based classifier. For example, Chaudhuri and Bose [28] used CNN-based model to locate the human body parts from the wreckage images. Nguyen et al [29] developed a deep CNN architecture to label the social media images into multiple disaster categories (i.e., severe, mild, and no-damage).…”

Section: ) Image-based Disaster Identificationmentioning

confidence: 99%

A Deep Attentive Multimodal Learning Approach for Disaster Identification From Social Media Posts

Hossain

Hoque

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Microblogging platforms such as Twitter have become indispensable for disseminating valuable information, especially at times of natural and man-made disasters. Often people post multimedia contents with images and/or videos to report important information such as casualties, damages of infrastructure, and urgent needs of affected people. Such information can be very helpful for humanitarian organizations for planning adequate response in a time-critical manner. However, identifying disaster information from a vast amount of posts is an arduous task, which calls for an automatic system that can filter out the actionable and non-actionable disaster-related information from social media. While many studies have shown the effectiveness of combining text and image contents for disaster identification, most previous work focused on analyzing only the textual modality and/or applied traditional recurrent neural network (RNN) or convolutional neural network (CNN) which might lead to performance degradation in case of long input sequences. This paper presents a multimodal disaster identification system that utilizes both visual and textual data in a synergistic way by conjoining the influential word features with the visual features to classify tweets. Specifically, we utilize a pretrained convolutional neural network (e.g., ResNet50) to extract visual features and a bidirectional long-term memory (BiLSTM) network with attention mechanism to extract textual features. We then aggregate both visual and textual features by leveraging a feature fusion approach followed by applying the softmax classifier. The evaluations demonstrate that the proposed multimodal system enhances the performance over the existing baselines including both unimodal and multimodal models by attaining approximately 1% and 7% of performance improvement, respectively.

show abstract

Application of Image Analytics for Disaster Response in Smart Cities

Cited by 23 publications

References 40 publications

Wireless Access Control in Edge-Aided Disaster Response: A Deep Reinforcement Learning-Based Approach

Wireless Access Control in Edge-Aided Disaster Response: A Deep Reinforcement Learning-Based Approach

Survey on Collaborative Smart Drones and Internet of Things for Improving Smartness of Smart Cities

A Deep Attentive Multimodal Learning Approach for Disaster Identification From Social Media Posts

Contact Info

Product

Resources

About