Earthquake disaster avoidance learning system using deep learning

Amin, Muhammad; Ahn, Huynsik

doi:10.1016/j.cogsys.2020.11.002

Cited by 20 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These were limited to the form and configuration of structures, soft stories, and short columns that could be physically identified using the campus-watching method. Furthermore, the safety of the furniture within the rooms was based on principles found in previous studies [28][29][30]. The hazardous objects were categorized into quickly rolling (B1), sliding (B2), easily breakable (B3), easily flammable (B4), and toxic substances (B5).…”

Section: Methodsmentioning

confidence: 99%

Configuration, furniture layout, and earthquake hazards in campus buildings

Khaerunnisa,

Anes

2024

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Indonesia is the most disaster-prone country in the world because it is geographically located in the ring of fire and tectonic plate confluence. Campus buildings have large occupancy of up to 10,000 students at a time, increasing their vulnerability to disasters. The 2006 Yogyakarta earthquake affected several campuses, such as soft stories and short columns. It is clarified that the movement and shifting of furniture during the earthquake caused 90% of casualties and injuries. This study aims to identify the physical characteristics of the campus in general as well as the potential for earthquake hazards, specifically in the aspects of building configuration and furniture layout. This research was conducted using the campus-watching method that allows the students to identify the risks in the campus building. This research found that the campus buildings in Indonesia generally had an elongated space configuration with O, I, T, L, and U shapes with a ratio of more than 1:2, causing a higher risk of earthquake hazards. The risk of the soft story was identified in the lobby. The short columns in the campus building were formed due to a consecutive halved window-wall application in the classrooms and were observed to be prone to weakening. Using movable furniture, glass partitions, and racks raises the risk during the earthquake. Tables inside the room can be utilized as a temporary safe place during the earthquake. So, it is essential to use sturdy tables and ensure sufficient tables to be used as a temporary shelter during an earthquake.

show abstract

Section: Methodsmentioning

confidence: 99%

Configuration, furniture layout, and earthquake hazards in campus buildings

Khaerunnisa,

Anes

2024

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…In Oishi et al (2021), vision algorithms were developed to reach the third generation of surveillance systems. In Sung and Park (2021), operational analytics were discussed by crowd counting and modelling and in Amin and Ahn (2021), the focus was on queue monitoring and anomaly detection. Commercial systems are fewer in number and operate only with specially placed cameras.…”

Section: Related Workmentioning

confidence: 99%

Intelligent video surveillance using enhanced deep belief based multilayered convolution neural network classification techniques

Kaliappan

Saravanan

Dakshinamoorthy

et al. 2022

The Photogrammetric Record

View full text Add to dashboard Cite

Video surveillance has undergone numerous changes in the past few years and several pieces of research have been carried out in this field. Object tracking is the significant task in such systems, and hence it is essential to review the standard approaches dealing with object detection, classification and tracking. This work proposes a novel classification technique for a detected object of a moving scene from a video dataset. Initially the dataset has been processed and prepared for data training based on neural networks. The data has been classified using the proposed enhanced deep belief based multilayered convolutional neural network (EBMCNN). The major focus is on deep learning applications involved in estimating the count, total persons involved and the activities in a crowd where all criteria are taken into consideration, thereby achieving security through video analysis. Identifying theft and the detection of violence are some security measures where video is converted to frames which are then processed to analyse the individuals along with their activities. The classification is performed through comparative analysis of a real‐time dataset. Experimental results show the accuracy 97%, precision 93.8%, recall 87.7% and F‐1 score 87.5%.

show abstract

“…To this end, visual content will deliver precise information on the severity and extent of the damage, a better understanding of shelter needs, a more precise assessment of current emergency operations, and easier identification of missing and wounded. Early studies explore the significance of analyzing social media visual content in diverse catastrophe/disaster situations, such as flooding [ 43 ], fires, and earthquakes [ 44 , 45 ], motivated by this phenomenon.…”

Section: Related Workmentioning

confidence: 99%

Human Sentiment and Activity Recognition in Disaster Situations Using Social Media Images Based on Deep Learning

Sadiq

Ahn

Choi

2020

Sensors

Self Cite

View full text Add to dashboard Cite

A rapidly increasing growth of social networks and the propensity of users to communicate their physical activities, thoughts, expressions, and viewpoints in text, visual, and audio material have opened up new possibilities and opportunities in sentiment and activity analysis. Although sentiment and activity analysis of text streams has been extensively studied in the literature, it is relatively recent yet challenging to evaluate sentiment and physical activities together from visuals such as photographs and videos. This paper emphasizes human sentiment in a socially crucial field, namely social media disaster/catastrophe analysis, with associated physical activity analysis. We suggest multi-tagging sentiment and associated activity analyzer fused with a a deep human count tracker, a pragmatic technique for multiple object tracking, and count in occluded circumstances with a reduced number of identity switches in disaster-related videos and images. A crowd-sourcing study has been conducted to analyze and annotate human activity and sentiments towards natural disasters and related images in social networks. The crowdsourcing study outcome into a large-scale benchmark dataset with three annotations sets each resolves distinct tasks. The presented analysis and dataset will anchor a baseline for future research in the domain. We believe that the proposed system will contribute to more viable communities by benefiting different stakeholders, such as news broadcasters, emergency relief organizations, and the public in general.

show abstract

Earthquake disaster avoidance learning system using deep learning

Cited by 20 publications

References 18 publications

Configuration, furniture layout, and earthquake hazards in campus buildings

Configuration, furniture layout, and earthquake hazards in campus buildings

Intelligent video surveillance using enhanced deep belief based multilayered convolution neural network classification techniques

Human Sentiment and Activity Recognition in Disaster Situations Using Social Media Images Based on Deep Learning

Contact Info

Product

Resources

About