A Novel Discriminative Dictionary Pair Learning Constrained by Ordinal Locality for Mixed Frequency Data Classification


One of the challenges that classification must overcome is the fact that the data are not gathered at the same frequency in all applications. We investigate the mixed frequency data in a new way and recognize them as a special style of multi-view data. In this particular form of multi-view data, the data for each view is collected at a different sampling frequency than the other views' data. This article presents a discriminative dictionary pair learning method for mixed frequency data classification that is constrained by ordinal locality (shorted by DPLOL-MF). This method combines the synthesis dictionary and the analysis dictionary into a single dictionary pair. This not only reduces the amount of computational work required due to the l0 or l1 -norm constraint, but it also allows for the sampling frequency inconsistency to be taken into account. The DPLOL-MF makes use of a synthesis dictionary to learn information about class-specific reconstruction, and it makes use of an analysis dictionary to generate coding coefficients by analyzing samples. Both dictionaries are utilized in the learning process. Specifically, the ordinal locality preserving term is used to constrain the atoms of dictionary pairs in order to further facilitate the learned dictionary pair's ability to be more discriminative. This is done in order to improve the accuracy of the learned dictionary pair. In addition to that, we devise a particular classification scheme in order to account for the varying sample sizes of the mixed frequency data. The purpose of this paper is to present a novel approach to the problem of classifying data with a mixed frequency distribution, and the experimental results demonstrate that the proposed method is effective.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE : Identity-Based Attack Detection and Classification Utilizing Reciprocal RSS Variations in Mobile Wireless Networks ABSTRACT: One of the most dangerous dangers that wireless networks face is that of identity-based
PROJECT TITLE : Efficient Shapelet Discovery for Time Series Classification ABSTRACT: Recently, it was discovered that time-series shapelets, which are discriminative subsequences, are effective for the classification of time
PROJECT TITLE : MM-UrbanFAC Urban Functional Area Classification Model Based on Multimodal Machine Learning ABSTRACT: The majority of the classification methods that are currently used for urban functional areas are only based
PROJECT TITLE : Interaction-Aware Spatio-Temporal Pyramid Attention Networks for Action Classification ABSTRACT: When it comes to CNN-based visual action recognition, the accuracy of the process could be improved by concentrating
PROJECT TITLE : End-to-End Automatic Morphological Classification of Intracranial Pressure Pulse Waveforms Using Deep Learning ABSTRACT: Objective. The mean intracranial pressure, also known as ICP, is a measurement that is frequently

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry