Tensor Decomposition of Biometric Data using Singular Value Decomposition
| Autor: | Sudeep Tanwar, Sudhanshu Tyagi, Pradeep Kr Singh, Nirav Mistry |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
021103 operations research
Basis (linear algebra) business.industry Computer science Big data 0211 other engineering and technologies 020206 networking & telecommunications Pattern recognition 02 engineering and technology Column (database) Principal component analysis Singular value decomposition 0202 electrical engineering electronic engineering information engineering Tensor decomposition Artificial intelligence Biometric data business Wireless sensor network |
| Zdroj: | 2018 Fifth International Conference on Parallel, Distributed and Grid Computing (PDGC). |
| DOI: | 10.1109/pdgc.2018.8745719 |
| Popis: | In Body Area Sensor Network (BAN) a huge amount of data is generated rapidly due to monitoring of chronic diseases suffered patients on a regular basis because they require immediate medical services. The communication between IoT-enabled devices generates heterogeneous data which is dimensionally large in nature. To reduce its multidimensional, existing state-of-the-art approaches are inadequate to handle it. It has been noticed from the literature that two mechanisms, Singular value decomposition (SVD) and Principal component analysis (PCA) are used in tensor decomposition. To address the aforementioned issues, in this paper, we have applied the Tensor Decomposition technique (TD), i.e., an SVD to reduce dimensionally of data. Moreover, we compare the performance of SVD on using a different dataset of varying size data. Form the comparative analysis, it has been observed that the data sets with more parameters in columns prone to less error compared to fewer parameters in the column with original datasets. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|