Senior Design Projects - 2004

This page contains the project synopsis of Senior Design Projects completed in 2004.

Handwritten Character Recognition - Hailah Albalaa

The project is a Handwritten Character Recognition system. It uses a pen and a pressure-sensitive pad to get input (the handwritten character) from the user and transform it into printed characters using a Neural Network. The input from the input device is stored, processed and resized before it is sent to the Neural Network. The Neural Network processes the input, recognizes what character has been written and gives an output representing this character. The Neural Network's output is a set of bits. Different sequences of bits represent different characters. The output is processed and the printed character is produced.

For the Neural Network to recognize characters, it must be trained using different sets of input/output pairs. The more it is trained the better results it gives. Input to the Neural Network must have a specific size and pattern. A back propagation feedback for Neural Network is used . It has three layers; Input layer, Hidden Layer, Output Layer. The number of neurons in the input layer is 315. The number of output neurons in the output layer is 36. The number of neurons on the hidden layer was selected after experimenting with a different number of neurons and is 32 neurons.

E-Orchestra - Allison Greene

E-Orchestra is a system that uses Tablet PCs, to facilitate a band or orchestra by making changes to musical piece. A library of sheet music is stored on a server and is accessible to each Tablet PC. The music can be retrieved from the database, viewed, and edited. The program is comprised of a client side and a server side that interact by passing messages.

The main window of EOrchestra is shown below. The menu bar (Letter A) is used to open files, exit out of E-Orchestra, change view preferences, and interact with the database. The file tree (Letter B) will display all the sheet music files that can be opened by double clicking on a file. The editor options (Letter C) displays the current color and figure (curve, straight line, oval, and rectangle) for editing the sheet music. The display window (Letter D) displays the contents of the sheet music file and provides buttons for the user to flip through the pages of music.

The Phylogenetic Tree-Maker is a program that will produce a phylogenetic tree of DNA sequences using an algorithm of the user's choice. The program will accept the sequences from the user as a text file. The user must then choose an algorithm from the program's menu to use in calculating the tree, which the user can supplement with additional algorithms.
The user can also either add scoring and distance matrices for the program to use in its calculations or let the program create its own. The scoring matrix holds accuracy scores between all possible DNA nucleotide-nucleotide pairs. The smaller a score between two nucleotides is, the more similar they are, with the score between two identical nucleotides being zero (the lowest possible value). Whether it is the default or provided by the user, the scoring matrix is used to determine the distance matrix, which holds the distance values between all possible sequence-sequence pairs. The smaller the distance between two sequences is, the more similar they are, with the distance between two identical sequences being zero (the lowest possible value).
Once the tree is calculated, it will be displayed to the user in a separate window. The program creates two different versions of the tree, the Simple Tree and the Data Tree. The Simple Tree shows only the tree and the sequences associated with it. The Data Tree, however, shows how the quantitative data determined by the algorithm affects the tree's structure, displaying the branches of the tree in their calculated lengths. These versions are displayed in the separate window, where the user can toggle between the two.
The program is comprised of three main modules. They are the Graphical User Interface (GUI), Relation, and Display modules. The GUI allows the user to submit input data while the Display shows the user the resulting tree. The Relation Module is composed of four sub-modules, the Parser (which extracts data from the user's files), Alignment (which creates the distance matrix), and the two default Algorithm sub-modules, Unweighted Pair Group Method with Arithmetic Mean (UPGMA) and Neighbor-Joining (NJ). The program will run on a Windows 98/2000/NT/XP operating system. It will also require at least 4MB of RAM and 400KB of hard disk space.