My advice? Come up with something you actually want and write that. Don't choose projects based on technology for something like this—choose the technology based on the project.
Deciding on which technology to use based on the project has some important advantages:
You're more likely to choose the right technology for the right purpose. If you set out to write a Java EE program, you might try to shoehorn Java EE on the wrong problem. On the other hand, if you start building something and realize Java EE would help you finish the project, you've probably chosen the correct tool for the job.
You're much more likely to not only finish the project, but ensure its quality. I know from experience that if I do a project just to learn a technology, I either leave it half-finished or barely working. When I do projects for fun, I actually finish them and add a bit of polish.
You will, quite simply, have more fun and enjoy the outcome more as well.
In short: think of a program you want to have—it can even be something relatively simple. Write that, choosing what tools to use based on what you're doing. Even using tools not directly related to your planned career is good—employers are probably going to look more favorably on a well-executed project not directly related to the job than on a half-hearted effort using the tools in question.