Alex Ferworn

Followers

Following

Public Views

Interests

Uploads

Papers by Alex Ferworn

Disaster scene reconstruction: modeling and simulating urban building collapse rubble within a game engine

Summer Computer Simulation Conference, Jul 7, 2013

Various natural and human-made events can occur in urban settings resulting in buildings collapsi... more Various natural and human-made events can occur in urban settings resulting in buildings collapsing and trapping victims. The task of a structural engineer is to survey the resulting rubble to assess its safety and arrange for structural stabilization, where necessary. Urban Search and Rescue (USAR) operations can then begin to locate and rescue people. Our previous work reported the use of an Unmanned Aerial Vehicle (UAV) equipped with a RGB-Depth sensor to build 3D point cloud models of disaster scenes. In this paper we extend this work by converting the point clouds into 3D models and importing them into a state-of-the-art game engine. We present a method to use these models to allow first responders to interact with the simulated rubble environment in real-time, without risk to human life. Experiments are conducted measuring traversal time both in the real world environment and using the simulation. We argue that this work will improve the safety of workers and allow a better understanding of extremely dangerous environments without unnecessary exposure during disaster response planning. * In this work we use the term "patient" in the USAR context-meaning any person trapped in rubble, in need of rescue.

Download

Mobile medical application model for heterogeneous networks

Communications and Networking Symposium, Apr 3, 2011

ABSTRACT This paper presents a model for mobile medical applications for a near --real-time binar... more ABSTRACT This paper presents a model for mobile medical applications for a near --real-time binary data exchange over heterogeneous networks. The model was tested with a software simulation and a real fully mobile system which monitors oxygenated hemoglobin (HBO) and deoxygenated hemoglobin (HB) concentration changes in the brain and tissues. The system used global system for mobile communications (GSM) Bluetooth networks and the internet. The application used the proposed model. The model consists of four processing nodes: the first node collect data from the brain and send it to the second node over a short range network; the second node act as a intermediate mobile server that holds capture data and transmit it over a long range networks; the third node act a remote server that store data for long term, the fourth ac as a monitoring station that monitor test subjects in near-real-time.

Using cloud computing for medical applications

Annual Simulation Symposium, Mar 26, 2012

ABSTRACT This paper presents the necessary element to enable brain spectroscopy and medical appli... more ABSTRACT This paper presents the necessary element to enable brain spectroscopy and medical applications over the Cloud. The paper presents a model for mobile medical applications for a near real-time binary data exchange over the Cloud. The model was tested with a software simulation and a real fully mobile system that monitors oxygenated hemoglobin (HBO) and deoxygenated hemoglobin (HB) concentration changes in the brain and tissues. The system used global system for mobile communications (GSM) Bluetooth networks and the Cloud. The paper shows it is possible to use the Cloud to enable medical applications.

Classifying Holes, Voids, Negative Objects and Nothing

Advanced Information Networking and Applications, 2021

In the field of Urban Search and Rescue (USAR), searching for people trapped in the rubble of a c... more In the field of Urban Search and Rescue (USAR), searching for people trapped in the rubble of a collapsed building largely assumes the presence of many objects that are not the trapped victims, but may provide clues as to the location of them. However, the lack of objects can be just as informative. Unlike positive objects (POs), negative objects extend into the surface of interest [1], and may contain people. These negative objects (NOs) are commonly known as “holes” or “voids”. In this paper we discuss the necessity for creating a lexicon and classifier for negative objects or holes. We review current efforts to detect and classify them, and finally begin building a vocabulary to effectively discuss negative objects. This paper aims to spark a discussion about negative object research and suggest a starting point for a novel research area.

Police learning: examining the use of simulations in police training and the associated learning theories

In addition to the cost savings, technology such as e-learning, hybrid learning and simulations a... more In addition to the cost savings, technology such as e-learning, hybrid learning and simulations are tools that are used to equip police force with the competencies and skills needed to protect the public and respond to the changing demographics. That is, the future of police training will be geared towards developing competencies to support existing training for police and the recruitment process that relies on technology and integrated crisis management systems. Simulations, robotics and reallife situations are vital in preparing the first responders and decision makers with the skills and competencies needed to respond effectively to a crisis. The successful design of the training strategies will provide police force with tactics that will enable them to offer the training in a suitable delivery medium. In this paper, we explore the use of simulations and virtual environments in police training, investigate examples of integrated simulation architectures and list how the various l...

Download

Physical and digital architecture for collection and analysis of imparted accelerations on Zip Line attractions

The accelerations experienced by riders of Zip Line attractions is an underexplored area of publi... more The accelerations experienced by riders of Zip Line attractions is an underexplored area of public safety assurance. These amusement devices require complex processes to collect and analyze acceleration data. Highly versatile and effective rider-worn and ride-carried devices are necessary to collect acceleration and velocity data without affecting the integrity of the ride. This paper introduces the use of a sensor device for collecting Zip Line acceleration data in the form of a Trailing Trolley. This architecture extends the work of Sicat et. al.’s which proposed the use of a Sensor Vest and Headwear to collect linear and rotational accelerations of a Zip Line rider. We investigate the logistics of combining the two sensor platforms and formulate a procedure to post-process and analyze the data. Techniques to extract, filter, and process the accelerations recorded is discussed and the potential for the synthesis of positioning linear and rotational data is described. Additional te...

Download

Comparing Quantative and Comment-Based Ratings for Recommending Open Educational Resources

The recent application of recommender systems for educational resources and e-learning has facili... more The recent application of recommender systems for educational resources and e-learning has facilitated online and accessible education on social networks. However, there are currently few studies about the methods for evaluation and performance measurement of these recommender systems in the complicated environment of educational and social networking platforms. The purpose of this research paper is to investigate the effectiveness of using sentiment analysis methods for educational resources based on user comments and compare it with the quantitative approach based on user rating to recommend best open learning resources (OER) available through online OER repositories. The quality of the OER will be justified by comparing the user rating and the users' reviews. The quality of users' reviews is based on calculating the term frequency for selected positive and negative terms, then determining the similarity among the comments. Comments with positive or negative words confirm ...

Download

Using Unmanned Aerial Vehicles (UAVs) in locating wandering patients with dementia

2018 IEEE/ION Position, Location and Navigation Symposium (PLANS), 2018

This paper presents findings from three experiments involving the use of Unmanned Aerial Vehicles... more This paper presents findings from three experiments involving the use of Unmanned Aerial Vehicles (UAVs) for the purpose of locating a wandering person whose behavior resembles the behavior of a wandering patient with dementia. Additionally, it presents research review on the use of UVs in locating wandering eprsons with dementia. The characteristics of this critical form of wandering-or eloping-are discussed. By using test subjects simulating individual lost patients with dementia, along with current Search and Rescue (SAR) operational methods, experiments were performed employing drones to find the wandering persons. The algorithm used to determine the drone paths is based on the analysis of incidents analyzed in the literature from the International Search and Rescue Incident Database (ISRID) which contains thousands of international and national police records on lost persons. The experiments revealed that UAVs, if used with the predetermined path, could expedite the search process thus improving the survivability of the lost person. The paper considers the time needed to detect the person, duration of the complete mission, the differential longitude and latitude analysis from an Initial Planning Point (IPP), the time taken to find the test subject and the battery life of the drone. Challenges and recommendations are presented to inform future experiments.

Download

Serious Gaming for Improvised Explosive Device Neutralization Training

MATEC Web of Conferences, 2016

An improvised explosive device (IED) is a "homemade" bomb intended to cause great harm when it ex... more An improvised explosive device (IED) is a "homemade" bomb intended to cause great harm when it explodes. The public safety task of identifying and neutralizing IEDs falls to military and police services often called explosive disposal units (EDU) who act to neutralize the threat associated with the IED either rendering it inoperable or destroying it safely. EDUs train in various aspects of explosive handling and investigation but are limited in the tools available for safely analyzing real world bombs. This paper describes a game based approach to IED training that employs an interactive 3D simulation to spatially identify key IED components of interest. We give an example of how this approach might be used and provide a preliminary evaluation of its potential effectiveness. We employ images formed from a Digital Imaging and Communications in Medicine (DICOM) system captured using Magnetic Resonance Imaging (MRI) technology to a virtual IED in a game. Empirical evaluation and EDU testimony suggest accurate representation of the IED and the potential efficacy of the proposed approach for successfully identifying components in the bomb for the purposes of EDU training.

Download

CAT 360 — Canine augmented technology 360-degree video system

2015 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), 2015

We present the latest advances of our Canine Augmentation Technology (CAT) system. Our new approa... more We present the latest advances of our Canine Augmentation Technology (CAT) system. Our new approach to Urban Search and Rescue canine search sensing involves the use of stabilized and stitched multi-camera views and produces panoramic video that can be further processed for better human understanding. We discuss our initial results, some of the outstanding challenges and the existing and possible capabilities of the system. The results of our field testing are also presented.

Remote parcel deployment system

Constrained image understanding for an Internet robot supporting telepresence

Canadian Conference on Electrical and Computer Engineering 2001. Conference Proceedings (Cat. No.01TH8555), 2001

The Network-Centric Applied Research Team (N-CART) introduces a distributed model for constrained... more The Network-Centric Applied Research Team (N-CART) introduces a distributed model for constrained image recognition for a web-enabled video robot supporting aspects of telepresence. The recognition engine resides on a network node apart from the actual robot streaming the video. We have found that by employing such a model, the cost and complexity of the robot can be reduced while allowing the recognition services to be reused by other devices. At the end of the paper, we discuss how we are using the notion of distributed services to deploy video preprocessing for limited capability wireless devices.

Download

Adaptive Engineering of an Embedded System, Engineered for use by Search and Rescue Canines

In Urban Search and Rescue (US&R) operations, canine teams are deployed to find live patients, an... more In Urban Search and Rescue (US&R) operations, canine teams are deployed to find live patients, and save lives. US&R may benefit from increased levels of situational awareness, through information made available through the use of embedded systems attached to the dogs. One of these is the Canine Pose Estimation (CPE) system. There are many challenges faced with such embedded systems including the engineering of such devices for use in disaster environments. Durability and wireless connectivity in areas with materials that inhibit wireless communications, the safety of the dog wearing the devices, and form factor must be accommodated. All of these factors must be weighed without compromising the accuracy of the application and the timely delivery of its data. This paper discusses the adaptive engineering process and how each of the unique challenges of emergency response embedded systems can be defined and overcome through effective design methods.

Download

Challenges for Mobile Internet Appliances

We in the Network-Centric Applied Research Team (N- CART) are conducting an on-going study design... more We in the Network-Centric Applied Research Team (N- CART) are conducting an on-going study designed to resolve issues associated with the reality of movement and interaction of a Web-enabled mobile teleoperated device in a dynamic, unstructured indoor environment. Our goal is to document anomalies in the form of extensive recreation and annotated video. We have undertaken this task in order to develop strategies, tools and techniques for dealing with mobility issues likely to be encountered by actual teleoperated devices in their role as Internet Appliances (IAs). In this paper we outline our experimental design and describe some of the difficulties we have encountered.

Download

Implementation of architectural model for grid resources discovery

In this paper, a brief introduction of grid computing and services has been discussed. Next, grid... more In this paper, a brief introduction of grid computing and services has been discussed. Next, grid simulation software GridSim is explained. The J2EE enterprise application architecture is compared to implement the proposed architecture within NetBeans IDE 6.1. Then the implementation of proposed architecture as J2EE enterprise application is elaborated. The architecture is implemented as enterprise application because it addresses the scalability issues of grid computing. Finally, the simulation results of initial implementation of architecture model for grid resources discovery are given. This model for resource discovery is found more scalable due to use of semantic information such as metadata. The initial results of simulation of grid resource discovery model are compared with GridSim that represents no architecture in our simulation and it is found efficient.

Panoramic Spherical Video — The Space Ball

Lecture Notes in Computer Science, 2003

Techniques for synthesizing panoramic scenes are widespread. Such a scene can be automatically cr... more Techniques for synthesizing panoramic scenes are widespread. Such a scene can be automatically created from multiple displaced images by aligning and overlapping them using an image registration technique. The ability to generate panoramic scenes has many applications including the generation of virtual reality backgrounds, model-based video compression, and object recognition. These techniques-and consequently their associated applications share the restriction that all scenes are limited to a 360 degree view of the horizontal plane at the particular moment in time the images were taken. Until recently, there has been little motivation to develop techniques for the presentation of complete spherical views in real time-scenes that present the entire potential visible fields of view, through time. With the advent of space exploration and associated micro-gravity environments, "up" and "down" are relative terms and locally fixed points of reference are difficult to come by. It may be useful to rethink how video is captured and presented to a user working in such an environment employing extended notions of what a panorama is. The Panoramic Spherical Video (PSV) system described in this paper allows a user to view and pan through arbitrary angles of view including elevation and declination as well as providing the view in real time from an array of 16 synchronized CCD video cameras whose video output are selectively "stitched" together to provide a smooth transition between camera fields of view. In this way, the user can smoothly pan through all the fields of view that are generated by the system. All video processing is done in software-there are no moving parts.

Download

Scalable Grid Resource Discovery Through Distributed Search

International Journal of Distributed and Parallel systems, 2011

This paper proposes a simple and scalable web-based model for grid resource discovery for the Int... more This paper proposes a simple and scalable web-based model for grid resource discovery for the Internet. The resource discovery model contains the metadata and resource finder web services. The information of resource finder web services is kept in the repositories that are distributed in the application layer of Internet. The resource finder web services will be discovered by sending queries to the repositories in a similar way as the DNS protocol. The underlying technology for implementation of the two architectures of this model is introduced. These architectures are: Direct and Centralized Web-Based Grid Resource Discovery. The resource discovery time is computed after simulating each of these models in GridSim. By performing scalability tests, we found that when increasing the load on the grid with more users and resources, the cost of our model in comparison to the grid resource discovery time is marginal.

Download

An assessment of a Wireless Mesh Network performance for Urban Search and Rescue task

2009 IEEE Toronto International Conference Science and Technology for Humanity (TIC-STH), 2009

In this paper we present a reliable system for predicting the body position, or pose, of Urban Se... more In this paper we present a reliable system for predicting the body position, or pose, of Urban Search and Rescue (US&R) dogs. We demonstrate that the Canine Pose Estimation (CPE) system can provide a reliable estimate for some poses and when coupled with effective wireless transmission over a mesh network, pose information can be made available to remote a handler who cannot see her dog due to visual and physical obstructions. Pose estimates are time sensitive as the dog changes its body position often, thus it is important that pose data arrives at its destination quickly. Propagation delay and packet delivery ratio measuring algorithms were developed and used to appraise Wireless Mesh Network (WMN) performance as a means of carriage for this time-critical data. The experiments were conducted in the rooms of a building where the radio characteristics closely resembled those of a partially collapsed building-a typical US&R environment. This paper presents the results of experiments conducted in this environment-not through simulation. The results demonstrate that it is possible to receive the canine pose estimation data in real-time although accuracy of the results depend on the network size and the deployment environment.

Download

Wireless estimation of canine pose for search and rescue

2008 IEEE International Conference on System of Systems Engineering, 2008

In this paper we discuss the use of accelerometers and Bluetooth to monitor canine pose in the co... more In this paper we discuss the use of accelerometers and Bluetooth to monitor canine pose in the context of common poses observed in Urban Search and Rescue dogs. We discuss the use of the Canine Pose System in a disaster environment, and propose techniques for determining canine pose. In addition we discuss the challenges with this approach in such environments. The paper presents the experimental results obtained from the Heavy Urban Search and Rescue disaster simulation, where experiments were conducted using multiple canines, which show that angles can be derived from acceleration readings. Our experiments show that similar angles were measured for each of the poses, even when measured on multiple USAR canines of varying size. We also found measurable and consistent differences between each of the poses, making them clearly distinguishable from one another, again even when comparing with different USAR canines.

Download

Solenodon: Unstable Hexapod Walking

The Solenodon research robot is a six legged mechanical walking platform designed at Ryerson Poly... more The Solenodon research robot is a six legged mechanical walking platform designed at Ryerson Polytechnic University's School of Computer Science. It was our goal to develop a platform that would facilitate the examination of issues involving stability in walking robots. The vehicle is available in several configurations ranging from fully teleoperated to low level autonomous operation.

Download

Alex Ferworn

Uploads

Papers by Alex Ferworn

Log In