Software
We developed the Encrypt & Decrypt software. Using DFS (Depth First Search) algorithm and optimization arithmetic, we discovered the correspondence between English letters and DNA codons for amino acids. The key part of our software is the Misleading Module. Through adding introns into DNA sequence containing the transmitted information, we can complicate the DNA sequence and increase the security levels of our Code Book. During the decryption process, we use regular expressions to match useless introns, eliminate them and convert codons of the rest RNA sequences into letters. In addition, we can integrate the information codons and letters into the image of a quick responsive (QR) code. This will allow the receptor to scan the QR code and quickly retrieve the information.
We developed English Word Segmentation software. Firstly, we implement word graph scanning based on prefix tree structure and construct DAG (Directed Acyclic Graph) to obtain all English word segmentation information. Secondly, we use an IF-IDF (Term Frequency-Inverse Document Frequency) model and maximum sharding method to obtain the optimal word segmentation information.
Build Coding Book.
By using DFS(Depth First Search) algorithm and optimization arithmetic, we find out the correspondence between letters and codons.
Enhance password security.
We added random sequences, introns, and enzymes to the codon sequences so that the intercepted codon information would not be easily decoded.
Segment English Sentences without Spaces.
Firstly, we implement word graph scanning based on prefix tree structure and construct DAG(Directed Acyclic Graph) to obtain all English word segmentation results. Secondly, we use IF-IDF(Term Frequency-Inverse Document Frequency) model and maximum sharding method to obtain the optimal word segmentation results.