Portfolio

Here is an overview of what I've done so far, different projects in different areas! By clicking on each project, you'll see a brief description of each.

Humans' psychological patterns in texts

X

Computational Social Science Laboratory, University of Southern California, under supervision of Prof. Dehghani, May 2104 - present

Using Natural Language Processing techniques, the pyschological patterns beyond texts can be extracted. Different patterns during different time/events and among different groups can lead to predictive psychological actions and interesting discussions.

Transparent consistency technique for RDBMS augmented with a KVS

X

Database Laboratory, University of Southern California, under supervision of Prof. Ghandeharizadeh, August 2103 - May 2014

For those applications whose read ration is larger than write, it seems reasonable to store results of queries in cache so that the application will see faster performance. The issue which rise up here is how to keep RDBMS consisten with cache.

Empirical Study and Analysis of Programmers' Behaviour While Doing the Monkey See, Monkey Do Operation

X

‎ ‎Sharif ‎University ‎of ‎Technology, under ‎supervision ‎of ‎Prof. ‎Heydarnoori, Tehran, Iran, Winter 2013 - Summer 2013

In this research project, I intended to create a recommender system under the supervision of Dr. Heydarnoori that would help programmers to reuse parts of a verified and tested code in their own projects by reducing the time they spend finding a proper sample code and even highlighting the most relevant codes for them.

This copy-pasting and reuse of sample codes is termed as the Monkey See, Monkey do rule. We initially ran an empirical study on several programmers performing this rule and afterwards analyzed the actions they performed while doing so. The results of the empirical study was published in a paper that was submitted to SAC2014 and is currently being used in the implementation of the aforementioned recommender system.

Predicting CAD and normal patients ‎without‎ ‎Angiography

X

‎ Performance Evaluation ‎Soft‎ware ‎Engineering ‎Laboratory, ‎Sharif ‎University ‎of ‎Technology, under ‎supervision ‎of ‎Prof. ‎J.‎ ‎Habibi. Tehran, Iran, 2012 - 2013

Coronary Artery Disease (CAD) is the most common fatal heart disease. Present methods for CAD diagnosis are costly, time-consuming, and hazardous. Therefore, study of non-invasive methods has proved to be effective. We have worked on various techniques relying on advanced data mining methods of hundreds of patients’ medical information.

We sought effective features in CAD diagnosis other than those previously studied. Not only did we consider these new features, but we also proposed an ensemble algorithm, therefore higher accuracy was achieved. For improved diagnosis, we decided to examine the stenosis of each vessel separately by means of data mining algorithms and measure their accuracy with tenfold cross validation. We further advanced our algorithms by considering diagnosis of diseased patients vital, since misclassification of them has more side effects. For considering this fact, we proposed a new algorithm by use of various cost-sensitive algorithms.

Design an interactive website for managing documents (MagicDoc)

X

‎ ‎Sharif ‎University ‎of ‎Technology, 2012

Managing documents in companies is a time-consuming task for both customers and employees since most of the companies are paper-based. We have designed an interactive and useful environment for workers to manage documents more beneficially.

Using different kinds of techniques we gathered data regarding the behavior of different users, including interviews, observation, questionnaires. Analyzing our data, we studied 360 degree feedback and sort these behaviors from multiple perspectives. We used three different models to capture Customer Needs, Competitive Positions, and Client Opportunities to set our patterns on a perceptual map, this allowed us to find the strategies to create a potential scenario. Giving two scenarios led us to create two different prototypes. Having in mind users feedback about these prototypes, we started working on MagicDoc and the final version was designed.

Tetris-like game, Worms-like game

X

Tetris-like game is written in Modelsim, and Worms-like game is written in Java

Feel free to contact me if you want to see the source code.

About Me

My name is Reihane Boghrati. I'm currently a second year Ph.D student at the Department of Computer Science, University of Southern California. I'm working as a research assistant in the Computational Social Science Laboratory under supervision of Professor Morteza Dehghani.

I completed my undergraduate studies in Computer Engineering (Software Engineering) at Sharif University of Technology in Tehran, Iran.

Currently my research interests include Social Media Analysis, Social Science Computing, and Natural Language Processing. I am currently working on extracting psychological patterns from different texts and groups.

Besides I am also interested in psychology and human behaviour. Taking in mind this interest and Computer Science, I worked on what programmers pursue when facing new concepts, called Monkey see, Monkey do rule as my B.S thesis.

And finally, here is my CV .

Contact

Feel free to contact me if you're interested in my research or have any question.
You can directly email to mylastname@usc.edu by clicking the envelope icon at the bottom-left corner.