Consumer Document Analytical Accelerator Hardware
Document scanning devices are used for visual character recognition, followed by text analytics in the software. Often such character extraction is insecure, and any third party can manipulate the information. On the other hand, near-edge processing devices are restrained by limited resources and co...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10018187/ |
| _version_ | 1828011343002730496 |
|---|---|
| author | Aswani Radhakrishnan Dibyasha Mahapatra Alex James |
| author_facet | Aswani Radhakrishnan Dibyasha Mahapatra Alex James |
| author_sort | Aswani Radhakrishnan |
| collection | DOAJ |
| description | Document scanning devices are used for visual character recognition, followed by text analytics in the software. Often such character extraction is insecure, and any third party can manipulate the information. On the other hand, near-edge processing devices are restrained by limited resources and connectivity issues. The primary factors that lead to exploring independent hardware devices with natural language processing (NLP) capabilities are latency during cloud processing and computing costs. This paper introduces a hardware accelerator for information retrieval using memristive TF-IDF implementation. In this system, each sentence is represented using a memristive crossbar layer, with each column containing a single word. The number of matching scores for the TF and IDF values was implemented using operational amplifier-based comparator accumulator circuits. The circuit is designed with a 180nm CMOS process, Knowm Multi-Stable Switch memristor model, and WOx device parameters. We compared its performance with that of a standard benchmark dataset. Variability and device-to-device related issues were also taken into consideration in the analysis. This paper concludes with implementing TF-IDF score calculation for applications such as information retrieval and text summarization. |
| first_indexed | 2024-04-10T09:14:55Z |
| format | Article |
| id | doaj.art-fdc9bd67423a4727a0573ed98c7466a3 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-10T09:14:55Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-fdc9bd67423a4727a0573ed98c7466a32023-02-21T00:02:04ZengIEEEIEEE Access2169-35362023-01-01115161516710.1109/ACCESS.2023.323746310018187Consumer Document Analytical Accelerator HardwareAswani Radhakrishnan0https://orcid.org/0000-0002-1086-1870Dibyasha Mahapatra1Alex James2https://orcid.org/0000-0001-5655-1213School of Electronic Systems and Automation, Kerala University of Digital Sciences Innovation and Technology (Digital University Kerala), Thiruvananthapuram, Kerala, IndiaSchool of Electronic Systems and Automation, Kerala University of Digital Sciences Innovation and Technology (Digital University Kerala), Thiruvananthapuram, Kerala, IndiaSchool of Electronic Systems and Automation, Kerala University of Digital Sciences Innovation and Technology (Digital University Kerala), Thiruvananthapuram, Kerala, IndiaDocument scanning devices are used for visual character recognition, followed by text analytics in the software. Often such character extraction is insecure, and any third party can manipulate the information. On the other hand, near-edge processing devices are restrained by limited resources and connectivity issues. The primary factors that lead to exploring independent hardware devices with natural language processing (NLP) capabilities are latency during cloud processing and computing costs. This paper introduces a hardware accelerator for information retrieval using memristive TF-IDF implementation. In this system, each sentence is represented using a memristive crossbar layer, with each column containing a single word. The number of matching scores for the TF and IDF values was implemented using operational amplifier-based comparator accumulator circuits. The circuit is designed with a 180nm CMOS process, Knowm Multi-Stable Switch memristor model, and WOx device parameters. We compared its performance with that of a standard benchmark dataset. Variability and device-to-device related issues were also taken into consideration in the analysis. This paper concludes with implementing TF-IDF score calculation for applications such as information retrieval and text summarization.https://ieeexplore.ieee.org/document/10018187/Natural language processingTF-IDFhardware acceleratormemristive systemsmemristoranalog computation |
| spellingShingle | Aswani Radhakrishnan Dibyasha Mahapatra Alex James Consumer Document Analytical Accelerator Hardware IEEE Access Natural language processing TF-IDF hardware accelerator memristive systems memristor analog computation |
| title | Consumer Document Analytical Accelerator Hardware |
| title_full | Consumer Document Analytical Accelerator Hardware |
| title_fullStr | Consumer Document Analytical Accelerator Hardware |
| title_full_unstemmed | Consumer Document Analytical Accelerator Hardware |
| title_short | Consumer Document Analytical Accelerator Hardware |
| title_sort | consumer document analytical accelerator hardware |
| topic | Natural language processing TF-IDF hardware accelerator memristive systems memristor analog computation |
| url | https://ieeexplore.ieee.org/document/10018187/ |
| work_keys_str_mv | AT aswaniradhakrishnan consumerdocumentanalyticalacceleratorhardware AT dibyashamahapatra consumerdocumentanalyticalacceleratorhardware AT alexjames consumerdocumentanalyticalacceleratorhardware |