Template:SYSU-Software/statics/html/Projects/Techniques.html

Projects

Techniques & Search Algorithm

Techniques

   In consideration of the stable, robust and friendly performance of Django with Python 3, we
   chose it as the back-end for CO-RAD, a web application; Sqlite3 with Django models binding gives us a lighter but
   still powerful database support; For front-end, we build the view with customized Semantic UI, and control the
   logic behind beautiful widgets using jQuery. Some other open-source JavaScript libraries are also used, such as
   Chart.js and echart.js for displaying chart, jsPlumb for showing the relationships in circuit in the design page,
   etc... jQuery and CSS3 was used to build the interesting game 'Little tomato with big dreams', hope you will enjoy
   it!

   <img src="">
   <img src="">
   <img src="">

Search Algorithm

   As is known to us, the users of our software are all innovative researchers who are interested in utilizing
   Synthetic Biology to tackle many different real-world problems. The purpose of our system is to recommend the most
   related projects to the users based on their research interests detected by our system.

   When it comes to the advanced algorithms behind our project, we mainly use Python3 to implete the Ball Tree,
   Word2Vec, Encoder-Decoder model and so forth in Machine Learning. As for the powerful Search & Recommendation
   system, we mainly use TensorFlow, an open source software library for high performance numerical computation, to
   train 2 Deep Neural Networks for a great many of times. Moreover, the collaborative filtering framework enables
   users to get accurate recommendation after offering their interest to our system, which is based on a database
   powered by Deep Neural Network.

 <img src="">