Differences

This shows you the differences between two versions of the page.

--- projects [2017/08/10 19:38] – jenkin
+++ projects [2018/05/07 14:39] (current) – peterlian
@@ Line 1: / Line 1: @@
 ~~NOTOC~~
 ====== Proposed Projects   ======
+====== Detecting and visulizing anomalies in dynamic networks ======
+**Supervisor:** Aijun An
+In this project, the goal is to detect and visualize anomalies in dynamic graphs. Graphs are powerful tools to model networks and relationships between their entities. Many of the real-world graphs are dynamic in which nodes and edges are being added and deleted over time. Some of the dynamic network examples include social networks and computer networks. Anomalies are any deviation from the normal. For example, in a computer network, communications are normal over time until a single machine is attacked by a large number of other machines at a specific time point. We work on finding time points that an anomaly occurs and nodes, edges or subgraphs that are responsible for this anomalous behavior. This project focuses on finding and visualizing anomalies in a stream of graphs. The student will first use a visualization tool to visualize the network over time. This helps in better understanding the changes in the structure of the network. There are various visualization tools available to use for this purpose. In the second phase, the student will implement a graph anomaly detection method and combine it with the visualzation program so that the graph stream can be monitored through visualization and anomalies can be detected and illustrated in an online fashion. This project is a part of a collaborative project with  IBM and the student will work closedly with a PhD student in the project.
+**Required skills:** Good programming skills in Python and Java.
+**Recommended skills:** Experience with visualization tools is very helpful, Interest in algorithms for graphs.
+====== Graphical User Interface for Power System Simulator ======
+**Supervisor:** Afshin Rezaei
+The project is to develop a user-friendly Graphical User Interface (GUI) for a power system simulator program. Similar to all circuit simulation programs, the GUI should provide a library of the system components. These elements include not only the basic circuit elements such as resistor, capacitor, and inductor but also more complex equipment models such as transformers, generators, etc. The library elements can be dragged and dropped on the design page. The user would be also able to add new elements to the library. Each element has its own dialog box for entering the parameters which is displayed by double-clicking on that element. The elements will be connected by the user. The GUI should provide the common tasks for drawing, removing, grouping, and construction of a circuit. The GUI can write an output data file of the system element parameters and connections and call an available executable program to run. After, the GUI will display the simulation results.
+**Required background:** General CSE408x prerequisites, good programming skill, good knowledge of GUI design tools
+====== Development of a Standalone Power System Optimization Toolbox ======
+**Supervisor:** Afshin Rezaei
+Finding the optimum system condition and maximum/minimum of analytical or numerical functions are of fundamental needs and widely used in various fields of Engineering. This project is to develop a standalone optimization toolbox based on Intel Visual FORTRAN for power system applications. FORTRAN language with its highly developed math library is a powerful tool to solve complicated mathematical problems. A group of such mathematical problems are those dealing with the optimization algorithms particularly the curve fitting and global optimization methods such as genetic algorithm.
+In this project, the developer is expected to explore Intel FORTRAN Math Kernel Library (MKL) and Intel Mathematics and Statistics Library (IMSL) and develop a program code in FORTRAN to call built-in functions and perform the requested optimizations specified by the user. Due to compatibility of the MS Visual Studio with both FORTRAN and C++, some parts of the code can also be developed in C++.
+**Required background:** General CSE408x prerequisites, good programming skill, good math skill, good knowledge of Intel FORTRAN and C++
+====== Palpation Task Trainer ======
+**Supervisors:** Petros Faloutsos (EECS) and Iris Epstein (School of Nursing)
+Palpation of head and neck region is an integral part of a complete physical health assessment performed by both physicians (e.g., physician assistant; family doctor; Ear Nose and throat specialist and surgeon) and Nurses (Nurse practitioners, registered nurses). During palpation practitioners use their sense of touch with knowledge of anatomy of the head and neck to feel, differentiate and characterize the masses within their anatomical landmark (e.g.,lymph nodes; fat; size; texture; movements). With increase prevalence of cancer in head and neck early detection and appropriate referral and treatments are paramount. In 2016, George Brown College Capstone Engineering program together with the help of the nursing lab simulation specialist constructed a head and neck normal task trainer (prototype 1) with 32 touch sensors (see image bellow). During a multidiscipline conference in May 2017 we tested the task trainer with over 47 experts’ practitioners (Doctors and Nurses). Two important themes emerged from the survey. First, the need to render the task trainer more realistic (e.g., the touch of the skin and bonny structure). The second, focus on making the task trainer more interactive. The purpose of this project is to create a second prototype with an interactive gaming capabilities during a head to neck palpation.  Perhaps creating an algorithm gaming from simple to complex palpation assessment skills (e.g., to create a game around not only palpating to locate the mass but also to characterizing it.). Possible directions:
+. Head to neck anatomical structure - Making the task trainer more "real" with anatomical / bone/ cartilage/ glands structures.
+. Head and neck skin - Because we are focusing on palpation touching the skin and making the skin respond to touch is important.
+. Head to neck engaging and interactive - Several health care providers perform palpation. In fact there is a hierarchy among them (nurse vs doctor; family doctor vs Ear Nose and throat). Creating some kind of interactive game to find and characterize the gland with multidiscipline.
+**Required Background:** Standard prerequisites,some knowledge of C++.
+**Other experience:** Knowledge of computer graphics (e.g. EECS3431)  and  familiarity with programming computer games would be useful for the gaming aspect, while familiarity with making and 3D printing  might be useful for developing the prototype system.
+**Resources and readings:** Here are two links to articles we published. The reference list has more resources
+http://www.ijocs.org/clinical-journal/head-to-neck-task-trainer-to-teach-palpation-skills-back-to-basic-12036.html
+http://www.sciedu.ca/journal/index.php/jnep/article/view/11461
+====== Custom Camera App using the Andriod Camera 2 API ======
+**Supervisor:** Michael S. Brown
+Cameras have a number of processing steps that convert the incoming sensor image to the final sRGB-JPEG image.  These steps are collectively referred to as the "camera processing pipeline".  The camera processing pipeline has traditionally been fixed in a camera's onboard hardware. This made changing it difficult to develop a custom camera application. The new Camera 2 API for Android, however, allows developers significant more control over the entire imaging pipeline.
+The primary goal of this project is to develop custom camera applications that manipulate individual components of the imaging pipeline (e.g., custom white-balance, custom colour mapping, custom tone-manipulation, etc.).   These applications will all be built on top of the Camera 2 API for Android phones.
+**Required Background:** General EECS 408x prerequisites, knowledgeable with photography, experience with Java programming for Android platforms.
 ====== Ultrasound simulation/trainer ======
@@ Line 298: / Line 353: @@
 **Required Background:** Good programming skills; Good math skills; Knowledge of C and MATLAB programming languages.
-====== Continuation of a Path Diagram to Syntax Application ======
-**Supervisor:** Jeff Edmonds
-Structural equation modeling (SEM) is a statistical technique that is becoming increasingly popular in the educational and behavioral sciences. SEM allows researchers to test the validity of hypothesized models involving complex relationships among multiple variables. Collected data is used to estimate the parameters of the equations and assessing the fit of the model.
-The software required is an application that allows researchers to define their hypothesized models visually and will output the correct syntax for the analytical software of their choosing.
-To date a promising functional application has been developed in JAVA by a Computer Science student as a 4080 project. The existing software allows the user to draw a path diagram and outputs code for the R package sem. There are a number of improvements to be made (refinements and additions to graphical user interface) and then the application needs to be extended to output syntax appropriate for additional software applications (openMX, MPlus and EQS). Though this project may not begin at “the first stages” of the software lifecycle, this scenario is likely common in the software development market. In addition, the student will be working with a primary “client” who is far less technically advanced, which is also reflective of real-world situations.
-**Required Background**: General EECS 408x prerequisites
-**Recommended Background:** Java software development
@@ Line 341: / Line 380: @@
 Description: Tracked pointers are the most common tools used in surgical navigation systems. A typical pointer has a tracked target on one end and a sharp or ball tip on the other end. Finding the location of the tip relative to the target is a calibration problem. One solution to the calibration problem involves pivoting the pointer about the tip while tracking the target; if the tip is kept stationary, then the target moves on the surface of a sphere. Fitting the tracking data to the surface of a sphere yields the location of the tip as the sphere center. Unfortunately, the calibrated tip position obtained using such a spherical calibration has high variance. This project will investigate how much variance there is in the calibrated tip position, and methods for reducing the variance of the calibrated tip position.
-====== A privacy safeguard framework for sharing photos on Facebook ======
-**Supervisor:** Uyen Trang Nguyen
-One of the major privacy concerns in Online Social Networks is photo sharing. A user may post his/her friends’ photos without their consent. The friends have no control over the user’s Facebook activities, namely photo sharing. In this project, we design and implement a third-party Facebook application that allows people to protect their identities in photos uploaded by another user without their consent.
-**Required prerequisite background:** Proficiency in programming, especially in Java and Web application programming.
-**Desired prerequisite:** Knowledge of image processing, Facebook API, JavaScript Object Notation (JSON)
 ====== Simulation for Forest Fire Detection ======
@@ Line 438: / Line 469: @@
 **Recommended background:** Java (including 2D graphics); Some knowledge of PC hardware architecture; Some knowledge of (any) assembler language is an asset.