Projects: NSERC Undergraduate Student Research Awards 2015

Assistive technologies are used by people with disabilities help them accomplish tasks that they cannot accomplish otherwise or could not do easily. Our research specializes on technology for persons with vision impairment, with hearing impairment and with learning disabilities and mild cognitive impairment.

For visually impaired students we are developing “MathReader”, software that enables such students to independently study and practice mathematics; MathReader can automatically read aloud the equations and formulae with mathematical symbols inserting correct prosody where needed to disambiguate math expressions. We are also developing “MathMaster” to help students with learning disabilities to gradually develop skills required to solve math word problems.

SYSTEMX, our prototype natural language interface (English to SQL translator) to relational databases resulted in several state-of-the-art advances. These advances include design and implementation of an HPSG parser for multiple domains, inheritance reasoning for HPSG, learning of semantic & syntactic information through dialog, computing & utilizing correct navigation (join path) information during interface usage, and portability. We stimulate “technology transfer” with Rogers Cablesystems Ltd. (customer service), Environment Canada (information holdings), SaskTel (marketing) and NSERC (grants information database). We applied SYSTEMX technology in cooperation with Sask Health; this collaboration resulted in the HERMES database interface to a simulated Sask health database.

The Athenians Project is a multi-year, ongoing study of the persons of ancient Athens.

1. We determine the appropriate mechanism to illuminate and digitize a large number of "squeezes", which are formed through beating, by means of a specially designed brush, soft, wet, moldable paper, often filter paper obtained from a chemistry laboratory, into inscriptions where letters have been carved in shallow cuttings below the flat surface of the stone; when dried the squeeze thereby becomes a 3-dimensional mirror-image of the original document and the letters now appear raised in relief.

We catalogue what we have found. There are several thousand squeezes available to us, and in recent years they have increased in value. Because there is physical contact between the paper plus brush and the surface of the inscription, in the making of a squeeze, slight damage, virtually imperceptible with a single impression, is caused to the surface of the stone. The result has been that the taking of squeezes is now generally banned, except under very special circumstances, by the governments and ministries in charge of antiquities. By appropriately illuminating and scanning these squeezes we will be able to catalogue and put them on a website for all humanities researchers to share. Currently these scholars must travel to specialized collections in museums and libraries in order to study the squeezes.

2. We construct an interactive map, or series of maps, of ancient Athens and Attica for humanities researchers to query in their study of ancient Greek culture

Clustering is a basic analysis technique for data sets and many clustering algorithms have been developed over the years. However no single algorithm works well for all data sets. Biological data sets require modification of clustering algorithms to yield results that make sense to Biologists. More importantly, the large sizes of many Biological data sets make it infeasible to use many existing algorithms. In this project the student will learn about different clustering algorithms and implement some of them on real data sets and measure their performance.

The student will work closely with the supervisor and graduate students and learn about the challenges posed by large data sets as well as Biological context. This is an open ended project that may lead to publications if the student is creative.

Required background: Good programming skills, good algorithms knowledge, particularly the ability to read and understand existing algorithms.

One of the challenges in remote learning is to allow students to communicate effectively with the lecturer. For example, when a student asks a question, communication will be more effective if the instructor has a zoomed view of the student's face, so that s/he can interpret expressions etc.

The goal of this project is to apply attentive sensing technology (www.elderlab.yorku.ca) to this problem. This technology is able to monitor a large environment such as a classroom and direct a high-resolution 'attentive' sensor to events of interest.

In particular, working with a senior graduate student or postdoctoral fellow, the successful applicant will:

1. Study the problem of detecting hand-raises in the preattentive sensor stream
2. Implement algorithms for detecting hand-raises based upon this investigation
3. Evaluate these algorithms in a real-classroom setting, using proprietary attentive sensing technology

Required skills:
1. Good programming skills
2. Good math skills
3. Knowledge of C and MATLAB programming languages

Facilities planning at both city (e.g., Toronto) and institutional (e.g., York University) scales requires accurate data on the flow of people and vehicles throughout the environment. Acquiring these data can require the costly deployment of specialized equipment and people, and this effort must be renewed at regular intervals for the data to be relevant.

The density of permanent urban video surveillance camera installations has increased dramatically over the last several years. These systems provide a potential source of low-cost data from which flows can be estimated for planning purposes.

This project will explore the use of computer vision algorithms for the automatic estimation of pedestrian and vehicle flows from video surveillance data. The ultimate goal is to provide planners with accurate, continuous, up-to-date information on facility usage to help guide planning.

The student will work closely with graduate students and postdoctoral fellows at York University, as well as researchers at other institutions involved in the project. The student will develop skills in using MATLAB, a very useful mathematical programming environment, and develop an understanding of basic topics in image processing and vision.

For more information on the laboratory: www.elderlab.yorku.ca

Requirements: Good facility with applied mathematics.

To provide visual surveillance over a large environment, many surveillance cameras are typically deployed at widely dispersed locations. Making sense of activities within the monitored space requires security personnel to map multiple events observed on two-dimensional security monitors to the three-dimensional scene under surveillance. The cognitive load entailed rises quickly as the number of cameras, complexity of the scene and amount of traffic increases.

This problem can be addressed by automatically pre-mapping two-dimensional surveillance video data into three-dimensional coordinates. Rendering the data directly in three dimensions can potentially lighten the cognitive load of security personnel and make human activities more immediately interpretable.

Mapping surveillance video to three-dimensional coordinates requires construction of a virtual model of the three-dimensional scene. Such a model could be obtained by survey (e.g., using LIDAR), but the cost and time required for each site would severely limit deployment. Wide-baseline uncalibrated stereo methods are developing and have potential utility, but require careful sensor placement, and the difficulty of the correspondence problem limits reliability.

This project will investigate a monocular method for inferring three-dimensional context for video surveillance. The method will make use of the fact that most urban scenes obey the so-called .Manhattan-world. assumption, viz., a large proportion of the major surfaces in the scene are rectangles aligned with a three-dimensional Cartesian grid (Coughlan & Yuille, 2003). This regularity provides strong linear perspective cues that can potentially be used to automatically infer three-dimensional models of the major surfaces in the scene (up to a scale factor). These models can then be used to construct a virtual environment in which to render models of human activities in the scene.

Although the Manhattan world assumption provides powerful constraints, there are many technical challenges that must be overcome before a working prototype can be demonstrated. The prototype requires six stages of processing: 1) The major lines in each video frame are detected. 2) These lines are grouped into quadrilaterals projecting from the major surface rectangles of the scene. 3) The geometry of linear perspective and the Manhattan world constraint are exploited to estimate the three-dimensional attitude of the rectangles from which these quadrilaterals project. 4) Trihedral junctions are used to infer three-dimensional surface contact and ordinal depth relationships between these surfaces. 5) The estimated surfaces are rendered in three-dimensions. 6) Human activities are tracked and rendered within this virtual three-dimensional world.

The student will work closely with graduate students and postdoctoral fellows at York University, as well as researchers at other institutions involved in the project. The student will develop skills in using MATLAB, a very useful mathematical programming environment, and develop an understanding of basic topics in image processing and vision.

For more information on the laboratory: www.elderlab.yorku.ca

Requirement: Good facility with applied mathematics.

Crowd simulation for urban simulation and architectural design applications is increasingly important. For example, optimizing floor plans or exit size and placement to maximize crowd flow during emergency evacuations is crucial.

This project involves taking high fidelity descriptions of certain York buildings in Revvit format and importing them into our own research software, Steersuite, and the commercial game engine Unity3D in a way that is suitable for running architectural optimizations. The import process will have to support the creating of navigation meshes using an existing or a student developed approach.

The successful applicant will work with M.Sc. and Ph.D. candidates and our collaborators. He or she will gain experience with large scale crowd simulation and visualization research software, and with large scale mixed integer optimization.

Required prerequisite background:
1. Good programming skills (C, C++)
2. Ability to work with large research software
3. Ability to work as part of a team.

One of the most recognized components of smart grid is smart meters. A smart meter is usually an electronic device that records the consumption of electric energy in intervals. It also communicates that information to the utility for both monitoring and billing. Unlike conventional electricity meters, smart meters provide two-ways communication between the consumer and the supplier. The information that is collected to create a more efficient power grid may be used for other purposes. Hence the issue of privacy might be raised, especially of the residential consumers whose smart meter data is being collected.<\p>

This project aims to develop a new framework for smart meters privacy. The framework will provide a means for measuring the tradeoff between sharing specific information with the utility and hiding other information to protect the consumer privacy. The student(s) will evaluate the advantages and disadvantages of the available privacy techniques and he/she will implement the proposed framework in MATLAB environment to validate its effectiveness and robustness compared with the available privacy techniques.

Required prerequisite background: Good programming skills, MATLAB, strong at math, preferred to be specialized in communication networks

A cantilever sensor is used to measure the breathing air-flow. This sensor is connected to a computer through an interface circuit. The main role of the student is

(1) to recode the breathing signals from a number of people using the mentioned cantilever sensor, and

(2) calculate the lung capacity using Matlab (or other software).

Required prerequisite background: EECS3215 4.00;
Good analytical and communication skills.

Deep neural networks (DNNs) have achieved huge successes in many pattern classification tasks, including speech recognition and computer vision. In this project, the student will study DNN-based models for an interesting natural language processing (NLP) task, selecting from word embedding, language modelling, paraphrase or others. More specifically, the student will implement text pre-processing, neural model training and performance evaluation for the selected NLP task based on some standard corpora.

Required prerequisite background: strong at math; matlab programming.

Many large scale software systems ranging from e-commerce websites (e.g., eBay) to telecommunication infrastructures (e.g., AT&T) are required to be available and ready to service by millions of users all the time. It is essential to monitor the behavior of these systems in the field and troubleshoot problems whenever they arise.

Binary instrumentation is a program analysis technique, which can add additional monitoring points without modifying or restarting the system. This project aims to explore the feasibility of leveraging binary instrumentation to automatically monitor and debug the behavior of these field systems. The student(s) will first evaluate the pros and cons on various binary instrumentation libraries. Then he/she will implement a monitoring/debugging framework using the selected instrumentation library.

Required prerequisite background: Good programming skills (especially in Java);
Good analytical and communication skills.

Conduct experimental research on an Android device to test various input modalities for gaming on a mobile device. An example would be using the tilt of the device to control movements within a game.

Required prerequisite background: CSE4441, CSE4443, or equivalent

Conduct experimental research on an Android device to test a gesture-based text input method. The method supports eyes-free input by auto-correcting the gestures using a simple language model.

Required prerequisite background: CSE4441, CSE4443, or equivalent

NASA's Java PathFinder (JPF for short) is a tool to find intricate bugs in Java code. Although JPF is used by many and one can find a lot of information about JPF on the web, no comprehensive user manual exists. Such a user manual of course needs many illustrative examples. This is where you come in. You will develop those examples, implement them, and apply JPF to them. You will do this under the guidance of Franck van Breugel. You can also rely on the expertise of NASA developers and graduate students in the DisCoVeri group.

If you are interested and want to know more about thisproject, please do not hesitate to contact Franck.