Home
 List
 Plan
 Policies
 Resources
 Announcements

2010-2011 Project List


The following is a list of suggested ideas catergoried based on the type of the project:

Type A: System Design and Implementation
1
Project Title Automated Visual Surveillance System for Outdoor Security
Description Effective monitoring of persistent and transient objects and events is a key to the effective protection of any Volume Of Interest (VOI). Surveillance is defined as systematic observation of aerospace, surface or subsurface areas, places, persons, or things, by visual, aural, electronic, photographic, or other means. This systematic observation includes the timely detection, localization, recognition and identification of objects and events, their relationships, activities, and plans, in a given VOI in order to determine whether they are behaving normally or if there is any deviation from their expected behavior. Growing demand for high-level security and safety in commercial, law enforcement, and military applications has led to active research to build intelligent automated surveillance system. The objective of this project is to design and implement a visual surveillance system for outdoor security. A demonstrative scenario will be implemented in which a person suspiciously abandons a package in front of a building and then runs away from the scene. As a result, the system detects that an object has been dropped into the scene and raises a red alert so that proper action can be taken by a human operator.
Prerequisites The project would require skills and knowledge in Computer Vision, Real-time interfacing, Matlab/LabView/Java Programming.
2
Project Title Automated Visual Surveillance System for Indoor Security
Description This project aims to design and implement a visual surveillance system for indoor security. A demonstrative scenario will be implemented that exhibits a classical indoor security application often referred as the burglar scenario. In this scenario, a static scene is being monitored to detect changes and, in particular, the removal of background objects. A first change in the scene occurs when a person enters the field of view of the camera. However, no alert is being raised yet. When the person steals the laptop from the desk, a persistent change in the background is identified and, consequently, a red alert is raised..
Prerequisites The project would require skills and knowledge in Computer Vision, Real-time interfacing, Matlab/LabView/Java Programming.
3
Project Title Automated Visual Surveillance System for Perimeter Security along a Fence
Description The objective of this project is to design and implement a visual surveillance system for perimeter security along a fence. A demonstrative scenario will be implemented to detect the intrusion of a moving foreground entity within a protected perimeter. In this scenario, the protected perimeter is a user-defined polygon located on the other side of a fence. When a person crosses the fence, an intrusion within the protected perimeter is detected and, as a consequence, a red alert is raised. The alert must be properly raised, without any false positives, even if environmental conditions are non-ideal (windy and cloudy) and even if the input video data is slightly out-of-focus and degraded due to compression artifacts.
Prerequisites The project would require skills and knowledge in Computer Vision, Real-time interfacing, Matlab/LabView/Java Programming.
4
Project Title Automated Visual Surveillance System for Perimeter Security along a Building
Description The objective of this project is to design and implement a visual surveillance system for perimeter security along a building. A demonstrative scenario will be implemented that demonstrates perimeter security along a building where two alerts are raised. An amber alert is raised when a car enters and then remains immobile in the scene. A red alert is later raised when a package is dropped and left out in the scene. This implemented scenario will show how the automated surveillance system can distinguish between two similar events (stopped versus abandoned objects).
Prerequisites The project would require skills and knowledge in Computer Vision, Real-time interfacing, Matlab/LabView/Java Programming.
5
Project Title Automated Visual Surveillance System for Road Security
Description The objective of this project is to design and implement a visual surveillance system for road security. A demonstrative scenario will be implemented that shows how the system can be used for road security monitoring. In this scenario, a user-defined polygon of interest counts the number of vehicles that utilizes a street. In addition, this scnario exhibits two amber alerts which are raised when a car remains immobile for too long.
Prerequisites The project would require skills and knowledge in Computer Vision, Real-time interfacing, Matlab/LabView/Java Programming.
6
Project Title Automated Visual Surveillance System for Border Security
Description The objective of this project is to design and implement a visual surveillance system for boarder security. The system will exhibit the capabilities of the license plate recognition module which can be applied to the field of border security. As a car approaches the camera, the position of its license plate is detected and tracked over time. Once the plate's position is known, the license plate characters are extracted. Recognized license plates are then compared to a database of allowed vehicles. A red alert is raised if the plate number is not matched in the database.
Prerequisites The project would require skills and knowledge in Computer Vision, Real-time interfacing, Matlab/LabView/Java Programming.
7
Project Title Sensor Web for GUC PV Station
Description The objective of this project is to design and implement a sensor web for GUC PV station. This system will allow researcher to access archive or live data from sensors (cameras, temperature sensors, wind speed, humidity sensors, etc.) from anywhere and at anytime. It can also provide services to perform various levels of data processing and models which describe how to create desired research products/algorithms from available sensor data. The system will contain a catalog server on which research products/algorithms such as data classification/clustering are registered and are easily discoverable, accessible, modifiable and extensible via web service chains.
Prerequisites The project requires skills and knowledge in Sensors, HTML, XML, SensorWebEnablement (SWE) Standards and Java programming.
8
Project Title Sensor and Actor Network (SANET)
Description SANET is a distributed system that incorporates a set of heterogeneous sensing agents, acting agents, situation awareness agents, management agents and decision support/making agents. These spatially distributed agents, when properly managed, can sense collaboratively and continuously a volume of interest and physically manipulate and interact with it. This project aims at designing and implementing a sensor and actor network for traffic control at a level-crossing of a railway and a road.
Prerequisites The project would require skills and knowledge in Java, PIC programming and Real-time interfacing
9
Project Title Wearable Energy Harvester
Description The project aims at developing a wearable energy harvesting device. An energy harvester (or an energy scavenger) is a small power generator that uses energy available in the ambient, such as electromagnetic energy, wind, water flow, or a temperature gradient. Everyday activity of walking is one such place where large amounts of energy are expended, up to 76 watts per step for a 68 kg person. Harvesting a small amount of this energy via a suitably selected transducer such Piezo-electic devices or using a wearable dynamo would enough to power a variety of small electronic devices. Similar commercial product can be found here (nPower PEG).
Prerequisites The project requires require skills and knowledge in Electronics

Type B: Empirical Evaluation
1
Project Title Metaheuristics-based Path Planning for Autonomous Mobile Robots
Description Path planning is the problem of finding a collision-free path for a robot from a start position to a given goal position, amidst a collection of obstacles. One major problem with local search algorithms such as potential field is that the robot is usually trapped at local minima and this prevents it from reaching the goal. The objective of this project is to study the applicability of metaheuristic optimization algorithms such as simulated annealing to get out of these local minima and continue moving towards the goal.
Prerequisites The project would require skills and knowledge in Mobile Robotics and Matlab/Java programming.
2
Project Title Ant Colony Optimization System for Manufacturing Cells Formation
Description Cellular manufacturing is a key production strategy, in the framework of group technology. The general idea is to decentralize processing and create manufacturing cells, which are effectively flow shop "islets" in a job shop environment. This is achieved by grouping the machines into clusters and the various parts into part families, and then allocating the processing of each part family to a single machine cluster. There are many benefits from such a production scheme such as the reduction of transport, queuing and processing times, the elimination of the need for frequent set-ups and tool changes in the machines, the reduction of inventories and the simplification of the production plan. These benefits lead to better delivery times, quality improvements, more efficient management and customer satisfaction. This project addresses solving the manufacturing cells design problem using an ant colony optimization system.
Prerequisites The project would require skills and knowledge in Matlab/Java programming.
3
Project Title Job Shop Scheduling using Metaheuristic Optimization
Description The Job Shop Scheduling Problem (JSSP) can be stated as follows: given a set M machines and a set J jobs, where the jobs each have an ordered sequence of operations to be executed on the machines, the scheduling objective is to minimize the production makespan over all jobs, subject to the constraints: (1) the order of the operations is fixed, (2) a machine can process only one job at a time, (3) all jobs are simultaneously available at time zero, and (4) operations can not be interrupted. In this project, we will study the applicability of metaheuristic optimization approach to solve this problem..
Prerequisites The project would require skills and knowledge in Matlab/Java programming.
4
Project Title Near-optimal Solution for Vehicle Routing Problem
Description The Vehicle Routing Problem (VPR) is defined by having m vehicles at the depot that need to serve c customers. The VPR consists of determining the routes to be taken by a set of m vehicles satisfying the following conditions: Starting and ending at the depot; having minimum travel cost; and each customer is visited exactly once by exactly one vehicle. The objective of this project is to solve the vehicle routing problem using a population-based optimization algorithm.
Prerequisites The project would require skills and knowledge in Matlab/Java programming.
5
Project Title Genetic Algorithm for Railway Scheduling Problems
Description The Train Timetabling Problem (TTP) is a difficult and time-consuming task in the case of real networks. The huge search space to explore when solving real-world instances of TTP makes population-based optimization tenchniques such as genetic algorithms, ant colony optimization or particle swarm optimization a suitable approach to efficiently solve it. The objective of this project is to study the applicability of these metaheuristic optimization algorithms in solving this problem.
Prerequisites The project would require skills and knowledge in Matlab/Java programming.
6
Project Title Assembly Line Balancing
Description Line and work cell balancing is an effective tool to improve the throughput of assembly lines and work cells while reducing manpower requirements and costs. Assembly Line Balancing, or simply Line Balancing (LB), is the problem of assigning operations to workstations along an assembly line, in such a way that the assignment be optimal in some sense. Ever since Henry Ford's introduction of assembly lines, LB has been an optimization problem of significant industrial importance: the efficiency difference between an optimal and a sub-optimal assignment can yield economies (or waste) reaching millions of dollars per year. This project studies the applicability of a procedure based on ant colonies to solve the assembly line balancing problem. Two criteria will be simultaneously considered for optimization: to maximize the production rate of the line (equivalently to minimize the cycle time), and to maximize the workload smoothing (i.e. to distribute the workload evenly as possible to the workstations of the assembly line).
Prerequisites The project would require skills and knowledge in Matlab/Java programming.

Type C: Algorithm Design
1
Project Title Multisensor Cooperation in Surveillance Systems
Description In multisensor systems, sensors cooperation is directed toward improving situation awareness through joint gathering and sharing of information. The objective of this project is to implement cooperative behaviors such as cueing and hand-off between multiple sensors for enabling continuous tracking of objects. Cueing and Hand-off will be implemented using a set of static and mobile sensors. The cueing or slaving is the process of using the detections (i.e., contact-level cueing) or tracks (i.e., track-level cueing) from a sensor A (master) to point another sensor B (slave) towards the same target or event. The handoff occurs when sensor A has cued sensor B for transferring the surveillance or the fire-control responsibility from A to B.
Prerequisites The project would require skills and knowledge in Mobile Robotics, Kalman Filter, Linux and Java/Matlab programming.
2
Project Title Emergent Control of Multirobot Formation (Flocking Behavior)
Description Bird flocking and fish schooling behaviors are examples of emergent behaviors, where complex global behavior can arise from the interaction of simple local rules. The objective of this project is to implement flocking behavior as a way of self-organization between multiple robots. A set of simulated mobile robots will be used to demonstrate this behavior.
Prerequisites The project requires skills and knowledge in Linux and Java programming.
3
Project Title Mobile Robot Motion Planning using Metaheuristic Optimization
Description Path planning is still considered as one of the core problems of autonomous mobile robots. Different approaches have been proposed with different levels of complexity, accuracy and applicability. The objective of this project is to apply one of the metaheuristic techniques such as genertic algorithm, ant colony optimization or particle swarm optimization in order to find global optimal collision-free paths for a mobile robot.
Prerequisites The project would require knowledge in Mobile Robotics, Matlab/Java programming
4
Project Title Communication Relay for Unmanned Aerial Vehicles in Autonomous Search and Rescue Mission
Description The objective of this project is to simulate search and rescue scenarios where autonomous unmanned aerial vehicles are deployed to locate multiple rescue targets. When a target is found, the swarm of micro-aerial vehicles (MAVs) self-organizes to utilize their range-limited communication capabilities for setting up a communication relay network between the target and the base. This solution is appropriate for real-world situations where rescue targets are trapped on intraversable terrain with a limited radius of communication.
Prerequisites The project requires skills and knowledge in Java/NetLogo programming.
5
Project Title Multiple Targets Clustering using Genetic Algorithm
Description Clustering in a d-dimensional Euclidean space is the process of partitioning a given set of n points into a number, say k, of groups (or clusters) based on some similarity metric between objects. Suppose that it is required to track n targets using k mobile trackers. If the number of available trackers is less than the number of targets to be tracked, the targets can be grouped into a number of clusters equal to the number of trackers. Then the tracker can track the centroid of the cluster instead of the target itself. The clustering process is based on the positions of targets. The objective of this project is to design a genetic algorithm to solve this clustering problem.
Prerequisites The project requires skills and knowledge in NetLogo programming.
6
Project Title A Bio-Inspired Coordination Mechanism for a Swarm of Miniature Robots
Description Coordination addresses the interdependency management among the cooperative or competitive entities of the system in order to achieve their goals. The objective of this project is to design a bio-inspired coordination algorithm that can be used to manage a group of tiny robots in a search and rescue mission. The algorithm will be based on understanding the crowd dynamics during emergency evacuation. Simulating this behavior can be useful in predicting occupants' distribution and the whole evacuation process. This simulation model can be applied in fire protection design, emergency preparation and planning an evacuation strategy from public areas (such as buildings, stadiums, subways, train stations, shopping malls, airports, etc.). In this project, this model will be applied to design the coordination mechanism of swarm robot system. NetLogo will be used as a simulation environment for complex systems. NetLogo will be used as a simulation environment for complex systems.
Prerequisites The project will require knowledge in NetLogo
7
Project Title Energy Optimizer for Smart Buildings
Description This project aims at designing and implementing an energy optimizer that can be used as a facility manger to rapidly zoom in on critical energy usage in buildings, to foresee and avoid costly demand peaks, and to implement an effective and measurable energy reduction plan. By developing a detailed understanding of how, when, and where energy is being consumed, this facility manager can accurately manage energy consumption.
Prerequisites The project requires skills and knowledge in Matlab/ Java programming.