CrowdVAS-Net: A Deep-CNN Based Framework to Detect Abnormal Crowd-Motion Behavior in Videos for Predicting Crowd Disaster

With the increased occurrences of crowd disasters like human stampedes, crowd management and their safety during mass gathering events like concerts, congregation or political rally, etc., are vital tasks for the security personnel. In this paper, we propose a framework named as CrowdVAS-Net for crowd-motion analysis that considers velocity, acceleration and saliency features in the video frames of a moving crowd. CrowdVAS-Net relies on a deep convolutional neural network (DCNN) for extracting motion and appearance feature representations from the video frames that help us in classifying the crowd-motion behavior as abnormal or normal from a short video clip. These feature representations a…

Big Data in Emergency Management: Exploitation Techniques for Social and Mobile Data

The Internet of Things, crowdsourcing, social media, public authorities, and other sources generate bigger and bigger data sets. Big and open data offers many benefits for emergency management, but also pose new challenges. This chapter will review the sources of big data and their characteristics. We then discuss potential benefits of big data for emergency management along with the technological and societal challenges it poses. We review central technologies for big-data storage and processing in general, before presenting the Spark big-data engine in more detail. Finally, we review ethical and societal threats that big data pose.

Visualization of Exchanged Information with Dynamic Networks: A Case Study of Fire Emergency Search and Rescue Operation

To perform emergency response activities, complex networks of emergency responders from different emergency organizations work together to rescue affected people and to mitigate the property losses. However, to work efficiently, the emergency responders have to rely completely on the data which gets generated from heterogeneous data sources during search and rescue operation (SAR). From this abundant data, rescue teams share needed information which is hidden in the abundant data with one another to make decisions, obtain situational awareness and also to assign tasks. Moreover, understanding and analyzing the shared information is a complex and very challenging task. Therefore, in this pap…

LifeRescue Software Prototype for Supporting Emergency Responders During Fire Emergency Response: A Usability and User Requirements Evaluation

For an efficient emergency response, emergency responders (ERs) should exchange information with one another to obtain an adequate understanding and common operational picture of the emergency situation. Despite the current developments on information systems, many ERs are unable to get access to the relevant information as the data is heterogeneous and distributed at different places and due to security and privacy barriers. As a result, ERs are unable to coordinate well and to make good decisions. Therefore, to overcome these difficulties, a web-based application called LifeRescue was developed for supporting easy information access during emergency search and rescue operation. The goal o…

The Impacts of ICT Support on Information Distribution, Task Assignment for Gaining Teams’ Situational Awareness in Search and Rescue Operations

Information and Communication Technology (ICT) has changed the way we communicate and work. To study the effects of ICT for Information Distribution (ID) and Task Assignment (TA) for gaining Teams’ Situational Awareness (TSA) across and within rescue teams, an indoor fire game was played with students. We used two settings (smartphone-enabled support vs. traditional walkietalkies) to analyze the impact of technology on ID and TA for gaining TSA in a simulated Search and Rescue operation. The results presented in this paper combine observations and quantitative data from a survey conducted after the game. The results indicate that the use of the ICT was good in second scenario than first sce…

Model-Driven Data Integration for Emergency Response : Doctoral Dissertation for the Degree Philosophiae Doctor (PhD) at the Faculty of Engineering and Science, Specialization in Information and Communication Technology

Pattern recognition based prediction of the outcome of radiotherapy in cervical cancer treatment

Masteroppgave i informasjons- og kommunikasjonsteknologi IKT590 2011 – Universitetet i Agder, Grimstad Cervical Cancer is one the most common cancers amongst women. Ev- ery year almost 300 Norwegian women are diagnosed with cervical cancer. It is the 5th most deadly cancer type amongst women in the world. Esti- mates show that there are approximately 473,000 cases of cervical cancer in 2008 and 253,500 deaths per year. As we can see from the statistics, cer- vical cancer is a very severe and common type of cancer which costs many human lives every year. Therefore any progression in prognostication of this disease is very essential to treatment of its patients. Our task in this project was t…

On the Usability of Smartphone Apps in Emergencies

It is very critical that the disaster management smartphone app users be able to interact efficiently and effectively with the app during an emergen-cy. An overview of the challenges face for designing mobile HCI in emergency management tools is presented in this paper. Then, two recently developed emergency management tools, titled GDACSmobile and SmartRescue, are studied from usability and HCI challenges point of view. These two tools use mobile app and smartphone sensors as the main functionality respectively. Both have a smartphone app and a web-based app with different UIs for their different user groups. Furthermore, the functionality of these apps in the format of a designed scenario…

A Multi-layer Feed Forward Neural Network Approach for Diagnosing Diabetes

Diabetes is one of the worlds major health problems according to the World Health Organization. Recent surveys indicate that there is an increase in the number of diabetic patients resulting in an increase in serious complications such as heart attacks and deaths. Early diagnosis of diabetes, particularly of type 2 diabetes, is critical since it is vital for patients to get insulin treatments. However, diagnoses could be difficult especially in areas with few medical doctors. It is, therefore, a need for practical methods for the public for early detection and prevention with minimal intervention from medical professionals. A promising method for automated diagnosis is the use of artificial…

LifeRescue: A web based application for emergency responders during fire emergency response

In order to respond to any kind of building fire emergencies, first-responders have to use lot of time to get access to the emergency data such as location of the victims who are still inside the building, location of the hazardous material, location of the resources and location of the exits in order to perform search and rescue. However, search is possibly one of the most dangerous activities on the fire ground. Sometimes the visibility is zero and the environment is really hot. Because of the limited operating time in the building, the key to successful search is how quickly emergency responders can get access to the emergency related information in order to save victims and the property…

Identifying First Responders Information Needs

At the onset of an indoor fire emergency, the availability of the information becomes critical due to the chaotic situation at the emergency site. Moreover, if information is lacking, not shared, or responders are too overloaded to acknowledge it, lives can be lost and property can be harmed. Therefore, the goal of this paper is to identify information items that are needed for first responders during search and rescue operations. The authors use an educational building fire emergency as a case and show how first responders can be supported by getting access to information that are stored in different information systems. The research methodology used was a combination of literature review,…

Deep Learning for Classifying Physical Activities from Accelerometer Data

Physical inactivity increases the risk of many adverse health conditions, including the world’s major non-communicable diseases, such as coronary heart disease, type 2 diabetes, and breast and colon cancers, shortening life expectancy. There are minimal medical care and personal trainers’ methods to monitor a patient’s actual physical activity types. To improve activity monitoring, we propose an artificial-intelligence-based approach to classify the physical movement activity patterns. In more detail, we employ two deep learning (DL) methods, namely a deep feed-forward neural network (DNN) and a deep recurrent neural network (RNN) for this purpose. We evaluate the proposed models on two phy…

Qualitative and Quantitative Study on Videotaped Data for Fire Emergency Response

During search and rescue (SAR) operations, information plays a significant role in empowering the emergency response personnel at various levels. But, understanding the information which is being shared between/among emergency personnel is necessary to improve current coordination systems. However, such systems can help the first responders to gain/increase their situational awareness and coordination. Moreover, there is still the lack of automatic and intelligent tools that can contribute to structure, categorize, and visualize the communicated content that occur during SAR operations. Therefore, in this paper, we present the concept of such analysis by using the qualitative methodology an…

Neuroevolution of Actively Controlled Virtual Characters - An Experiment for an Eight-Legged Character

Physics-based character animation offers an attractive alternative for traditional animations. However, it is often strenuous for a physics-based approach to incorporate active user control of different characters. In this paper, a neuroevolutionary approach is proposed using HyperNEAT to combine individually trained neural controllers to form a control strategy for a simulated eight-legged character, which is a previously untested character morphology for this algorithm. It is aimed to evaluate the robustness and responsiveness of the control strategy that changes the controllers based on simulated user inputs. The experiment result shows that HyperNEAT is able to evolve long walking contr…

Big Data Metadata Management in Smart Grids

Smart home, smart grids, smart museum, smart cities, etc. are making the vision for living in smart environments come true. These smart environments are built based upon the Internet of Things paradigm where many devices and applications are involved. In these environments, data are collected from various sources in diverse formats. The data are then processed by different intelligent systems with the purpose of providing efficient system planning, power delivery, and customer operations. Even though there are known technologies for most of these smart environments, putting them together to make intelligent and context-aware systems is not an easy task. The reason is that there are semantic…

The Use of Artificial Intelligence in Disaster Management - A Systematic Literature Review

Whenever a disaster occurs, users in social media, sensors, cameras, satellites, and the like generate vast amounts of data. Emergency responders and victims use this data for situational awareness, decision-making, and safe evacuations. However, making sense of the generated information under time-bound situations is a challenging task as the amount of data can be significant, and there is a need for intelligent systems to analyze, process, and visualize it. With recent advancements in Artificial Intelligence (AI), numerous researchers have begun exploring AI, machine learning (ML), and deep learning (DL) techniques for big data analytics in managing disasters efficiently. This paper adopt…

The Role of Artificial Intelligence in Social Media Big data Analytics for Disaster Management -Initial Results of a Systematic Literature Review

When any kind of disaster occurs, victims who are directly and indirectly affected by the disaster often post vast amount of data (e.g., images, text, speech, video) using numerous social media platforms. This is because social media has recently become a primary communication channel among people to report either to public or to emergency responders (ERs). ERs, who are from various emergency response organizations (EROs), usually consider to gain awareness of the situation in order to respond to occurred disaster. However, with the occurrence of the disaster, within minutes, the social media platforms are flooded with various kinds of data which become overwhelmed for ERs with big data. Fu…

Taking the Advantage of Smartphone Apps for Understanding Information Needs of Emergency Response Teams’ for Situational Awareness: Evidence from an Indoor Fire Game

In search and rescue (SAR) operation, a lot of information is being shared among different emergency response groups. However, one of the key challenges experienced by these rescue groups during SAR operation is obtaining the complete awareness of the situation from the shared information. Moreover, one of the key actions of rescue leaders is to get the needed information in order to coordinate effectively with other teams and perform well. So, in this study we conduct an indoor fire drill with the help of Smartphone application with two settings (without SmartRescue smartphone application and with SmartRescue smartphone application) to find out what type of information is mostly communicat…

A Study on the Usage of Smartphone Apps in Fire Scenarios - Comparison between GDACSmobile and SmartRescue Apps

In this paper, we present a thorough overview of the two recently developed applications in the field of emergency management. The applications titled GDACSmobile and SmartRescue are using mobile app and smartphone sensors as the main functionality respectively. Furthermore, we argue the differences and similarities of both applications and highlight their strengths and weaknesses. Finally, a critical scenario for fire emergency in a music festival is designed and the applicability of the features of each application in supporting the emergency management procedure is discussed. It is also argued how the aforementioned applications can support each other during emergencies and what the pote…

Deep Neural Networks for Prediction of Exacerbations of Patients with Chronic Obstructive Pulmonary Disease

Chronic Obstructive Pulmonary Disease (COPD) patients need help in daily life situations as they are burdened with frequent risks of acute exacerbation and loss of control. An automated monitoring system could lead to timely treatments and avoid unnecessary hospital (re-)admissions and home visits by doctors or nurses. Therefore we present a Deep Artificial Neural Networks for approach prediction of exacerbations, particularly Feed-Forward Neural Networks (FFNN) for classification of COPD patients category and Long Short-Term Memory (LSTM), for early prediction of COPD exacerbations and subsequent triage. The FFNN and LSTM models are trained on data collected from remote monitoring of 94 pa…

Data Sources Handling for Emergency Management: Supporting Information Availability and Accessibility for Emergency Responders

Information is an essential component for better emergency response. Although a lot of information being available at various places during any kind of emergency, many emergency responders (ERs) use only a limited amount of the available information. The reason for this is that the available information heterogeneously distributed, in different formats, and ERs are unable to get access to the relevant information. Moreover, without having access to the needed information, many emergency responders are not able to obtain a sufficient understanding of the emergency situation. Consequently, a lot of time is being used to search for the needed information and poor decisions may be made. Therefo…

Representing fire emergency response knowledge through a domain modelling approach

When any kind of emergency occurs, Emergency Responders (ERs) from different emergency organizations (such as police, fire, ambulance and municipality) have to act concurrently to solve the difficulties which are posed at the emergency site. Moreover, during the immediate response, getting the awareness of the situation is very crucial for ERs to lessen the emergency impacts such as loss of life and damage to the property. However, this can only be done when ERs get access to the information in timely manner and share the acquired information with one another during emergency response. Despite ERs share knowledge with one another they have to use same concepts to obtain the semantic underst…