Major Project Suggestion

Question

Hi,

I'm in the final year of computer science and engineering. I'm looking for ideas about a year long project,which is of great importance in my curriculum. So, I'm looking for a topic,that is not very simple but which can be implemented within a year.

My interests are

1. Data Mining
2. Distributed Computing
3. Data Structures and Algorithms
4. Neural Networks

Also, I'm open to suggestions regarding the same for any other field that could be of value to me, as I'm interested in higher studies post my bachelor's degree.

I want to improve my coding skills , so I'm interested in doing the implementation in C++/Java.

Please help me with some advice.

Answer 1

Make a social network.

:-D

Answer 2

sounds like a KDD project for me :) since the NetFlix winner's algorithms are not out, you might want to implement the blended algorithms outlined in the Progress Prizes:

http://www.netflixprize.com/assets/ProgressPrize2008_BellKor.pdf

and

http://www.netflixprize.com/assets/ProgressPrize2008_BigChaos.pdf

more here:

http://netflixkddworkshop2008.info/accepted.html

Answer 3

Something a firm had to do that I worked at once was to calculate the distance/drive time from every postcode sector to every other one forming a matrix that then allowed lookups of the data later on.

This used Djikstra's algorithm, required a custom datastructure to hold road information during the processing and required a sensible output file to allow the lookups later on. Because the task was so large though they had to run this over a small hive of computers, which is where the distributed networking stuff comes in. Maybe you could so something similar?

Answer 4

Create an application that can predict tomorrow's stock market level with 100% accuracy.

Stock market is full of data, and determining the relationship between prices are plain hard. Which is why you need to use neural network to train on the large sets of data, maybe over a dozens of computers.

It should be a challenging project.

Answer 5

given those, I'd take the Lucene project (or CLucene) as a start point and build a product on top of it. Search is pretty passe nowadays, but doing more interesting things with the results could be very interesting to your tutor.

Don't try to reinvent anything though, take something and build upon it.

Answer 6

I would suggest, Machine learning (which is very close to Neural networks). It is one of the emerging areas where things are happening, ...

As an example, a simple Bayesian can be used as a spam filter. SVM (Support Vector Machine), many believe is the best machine around.

All the above are just algorithms, for a particular type of problem, like say, - Stock market prediction - Medical diagnosis - AGV (Automatic Guided vehicles) etc etc ..

So,

Step-1: Decide on some interesting topic, Step-2: Decide on some (relatively) challenging algorithms Step-3: Implement and enjoy ...