Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 4 of 4
Full-Text Articles in Computer Engineering
Improving Automatic Content Type Identification From A Data Set, Kathy T. Dai
Improving Automatic Content Type Identification From A Data Set, Kathy T. Dai
Computer Science and Computer Engineering Undergraduate Honors Theses
Data file layout inference refers to building the structure and determining the metadata of a text file. The text files dealt within this research are personal information records that have a consistent structure. Traditionally, if the layout structure of a text file is unknown, the human user must undergo manual labor of identifying the metadata. This is inefficient and prone to error. Content-based oracles are the current state-of-the-art automation technology that attempts to solve the layout inference problem by using databases of known metadata. This paper builds upon the information and documentation of the content-based oracles, and improves the databases …
Project Pradio, Trigg T. La Tour
Project Pradio, Trigg T. La Tour
Computer Science and Computer Engineering Undergraduate Honors Theses
This paper examines the design and manufacturing of a device that allows two or more users to share a wireless audio stream. Effectively, this allows a group of people to listen to the same audio in a synchronized manner. The product was unable to be completed in the allotted time. Regardless, significant progress was made and valuable insight into the circuit board design process was gained.
A Study Of Activation Functions For Neural Networks, Meenakshi Manavazhahan
A Study Of Activation Functions For Neural Networks, Meenakshi Manavazhahan
Computer Science and Computer Engineering Undergraduate Honors Theses
Artificial neural networks are function-approximating models that can improve themselves with experience. In order to work effectively, they rely on a nonlinearity, or activation function, to transform the values between each layer. One question that remains unanswered is, “Which non-linearity is optimal for learning with a particular dataset?” This thesis seeks to answer this question with the MNIST dataset, a popular dataset of handwritten digits, and vowel dataset, a dataset of vowel sounds. In order to answer this question effectively, it must simultaneously determine near-optimal values for several other meta-parameters, including the network topology, the optimization algorithm, and the number …
Music Feature Matching Using Computer Vision Algorithms, Mason Hollis
Music Feature Matching Using Computer Vision Algorithms, Mason Hollis
Computer Science and Computer Engineering Undergraduate Honors Theses
This paper seeks to establish the validity and potential benefits of using existing computer vision techniques on audio samples rather than traditional images in order to consistently and accurately identify a song of origin from a short audio clip of potentially noisy sound. To do this, the audio sample is first converted to a spectrogram image, which is used to generate SURF features. These features are compared against a database of features, which have been previously generated in a similar fashion, in order to find the best match. This algorithm has been implemented in a system that can run as …