Capstone Project: Blogs Report on Data Science Techniques

This capstone project report explores various data science techniques relevant to blog analysis and data processing. The report covers multi-linear subspace learning, a technique for dimensionality reduction and data transformation, which is crucial for processing high-dimensional data often encountered in blog-related projects. It also discusses the use of parallel algorithms to improve efficiency in handling large datasets and performing complex computations. Furthermore, the report details the importance of data integration, modeling, and visualization components, which are essential for collecting, processing, and presenting data effectively. The report emphasizes how these components contribute to the overall project's ability to generate meaningful insights from the collected data, and how they can be integrated to create an efficient system for data analysis. The bibliography includes references to relevant literature supporting the methodologies and techniques discussed in the report.

Running head: BLOGS
Capstone Project: Blogs
Name of the Student:
Name of the University:
Author Note

1
BLOGS
Table of Contents
Blog1:..............................................................................................................................................2
Multi linear subspace learning.....................................................................................................2
Blog 2:.............................................................................................................................................2
Parallel algorithm.........................................................................................................................2
Blog 3:.............................................................................................................................................2
Data integration, modeling, and visualization components.........................................................2
Bibliography....................................................................................................................................4

2
BLOGS
Blog1:
Multi linear subspace learning
The learning related to the reduction in dimensionality is known as Multi linear subspace
learning. The processes can be performed on the data that is already vectorized the resultant data
is organized into a data tensor. The procedure is performed after the mapping of the high
dimensional vector space is transformed into a lower dimensional vector spaces and this process
is known as multi linear projection. This process is used in the project for tracking the data. In
addition to this the data transformation is also done by using this method so that the data is ready
for the analysis.
Blog 2:
Parallel algorithm
The parallel algorithm is a very efficient technique that helps the systems to carry out parallel
procedures. The processes can be integrated into a parallel algorithm so that all the processes can
be executed concurrently. This algorithm is only possible when the results can be combined for
obtaining the final result into the system. For the project the algorithm would be helpful in
performing parallel processes of the data collection and data analysis. This is better than the
sequential algorithms in a sense that the processes in the system would be less time consuming as
that system has to deal with huge sets of data.
Blog 3:
Data integration, modeling, and visualization components
The data integration and visualization components are very important aspects of the system. The
system that is to be constructed in the project have to go through a number of procedures to

3
BLOGS
produce the required results. First is the data gathering technique where large sets of data are to
be collected. Then in the process modelling technique the data are subjected to different
processes. All the obtained results are then integrated to provide an efficient result by the
integration modeling technique. The report design provides an efficient system of displaying the
data. This process provides the processed data as the final result. The visualization components
helps in the co-ordination of all the other sectors.

4
BLOGS
Bibliography
Kan, M., Shan, S., Zhang, H., Lao, S., & Chen, X. (2016). Multi-view discriminant
analysis. IEEE transactions on pattern analysis and machine intelligence, 38(1), 188-
194.
Gelman, A., Carlin, J. B., Stern, H. S., Dunson, D. B., Vehtari, A., & Rubin, D. B.
(2014). Bayesian data analysis (Vol. 2). Boca Raton, FL: CRC press.
Solomonik, E., Ballard, G., Demmel, J., & Hoefler, T. (2017, July). A communication-avoiding
parallel algorithm for the symmetric eigenvalue problem. In Proceedings of the 29th
ACM Symposium on Parallelism in Algorithms and Architectures (pp. 111-121). ACM.