HyperSense: Hyperdimensional Intelligent Sensing for Energy-Efficient Sparse Data Processing

Introducing HyperSense, our co-designed hardware and software system efficiently controls Analog-to-Digital Converter (ADC) modules' data generation rate based on object presence predictions in sensor data. Addressing challenges posed by escalating sensor quantities and data rates, HyperSense r...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2024-10
Hauptverfasser: Sanggeon Yun, Hanning Chen, Masukawa, Ryozo, Hamza Errahmouni Barkam, Ding, Andrew, Huang, Wenjun, Rezvani, Arghavan, Angizi, Shaahin, Imani, Mohsen
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Sanggeon Yun
Hanning Chen
Masukawa, Ryozo
Hamza Errahmouni Barkam
Ding, Andrew
Huang, Wenjun
Rezvani, Arghavan
Angizi, Shaahin
Imani, Mohsen
description Introducing HyperSense, our co-designed hardware and software system efficiently controls Analog-to-Digital Converter (ADC) modules' data generation rate based on object presence predictions in sensor data. Addressing challenges posed by escalating sensor quantities and data rates, HyperSense reduces redundant digital data using energy-efficient low-precision ADC, diminishing machine learning system costs. Leveraging neurally-inspired HyperDimensional Computing (HDC), HyperSense analyzes real-time raw low-precision sensor data, offering advantages in handling noise, memory-centricity, and real-time learning. Our proposed HyperSense model combines high-performance software for object detection with real-time hardware prediction, introducing the novel concept of Intelligent Sensor Control. Comprehensive software and hardware evaluations demonstrate our solution's superior performance, evidenced by the highest Area Under the Curve (AUC) and sharpest Receiver Operating Characteristic (ROC) curve among lightweight models. Hardware-wise, our FPGA-based domain-specific accelerator tailored for HyperSense achieves a 5.6x speedup compared to YOLOv4 on NVIDIA Jetson Orin while showing up to 92.1% energy saving compared to the conventional system. These results underscore HyperSense's effectiveness and efficiency, positioning it as a promising solution for intelligent sensing and real-time data processing across diverse applications.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2917417851</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2917417851</sourcerecordid><originalsourceid>FETCH-proquest_journals_29174178513</originalsourceid><addsrcrecordid>eNqNjdEKgjAYhUcQJOU7DLoW3NS0bsuwu6AuAxn2TyZrs_3zwrdPowfo6pzD98FZkIAnCYuKlPMVCRG7OI75LudZlgTkUY09uBsYhAP99qd6TUtZIzS9GA9aqxaMp7OjTEuldbQ04NoxKqVUjfrCXjgEehJe0KuzDeDsbshSCo0Q_nJNtufyfqyi3tn3AOjrzg5uOsKa71mesrzIWPKf9QEJ0UPc</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2917417851</pqid></control><display><type>article</type><title>HyperSense: Hyperdimensional Intelligent Sensing for Energy-Efficient Sparse Data Processing</title><source>Freely Accessible Journals</source><creator>Sanggeon Yun ; Hanning Chen ; Masukawa, Ryozo ; Hamza Errahmouni Barkam ; Ding, Andrew ; Huang, Wenjun ; Rezvani, Arghavan ; Angizi, Shaahin ; Imani, Mohsen</creator><creatorcontrib>Sanggeon Yun ; Hanning Chen ; Masukawa, Ryozo ; Hamza Errahmouni Barkam ; Ding, Andrew ; Huang, Wenjun ; Rezvani, Arghavan ; Angizi, Shaahin ; Imani, Mohsen</creatorcontrib><description>Introducing HyperSense, our co-designed hardware and software system efficiently controls Analog-to-Digital Converter (ADC) modules' data generation rate based on object presence predictions in sensor data. Addressing challenges posed by escalating sensor quantities and data rates, HyperSense reduces redundant digital data using energy-efficient low-precision ADC, diminishing machine learning system costs. Leveraging neurally-inspired HyperDimensional Computing (HDC), HyperSense analyzes real-time raw low-precision sensor data, offering advantages in handling noise, memory-centricity, and real-time learning. Our proposed HyperSense model combines high-performance software for object detection with real-time hardware prediction, introducing the novel concept of Intelligent Sensor Control. Comprehensive software and hardware evaluations demonstrate our solution's superior performance, evidenced by the highest Area Under the Curve (AUC) and sharpest Receiver Operating Characteristic (ROC) curve among lightweight models. Hardware-wise, our FPGA-based domain-specific accelerator tailored for HyperSense achieves a 5.6x speedup compared to YOLOv4 on NVIDIA Jetson Orin while showing up to 92.1% energy saving compared to the conventional system. These results underscore HyperSense's effectiveness and efficiency, positioning it as a promising solution for intelligent sensing and real-time data processing across diverse applications.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Analog to digital converters ; Cost analysis ; Data processing ; Digital data ; Hardware ; Machine learning ; Object recognition ; Real time ; Sensors ; Software</subject><ispartof>arXiv.org, 2024-10</ispartof><rights>2024. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Sanggeon Yun</creatorcontrib><creatorcontrib>Hanning Chen</creatorcontrib><creatorcontrib>Masukawa, Ryozo</creatorcontrib><creatorcontrib>Hamza Errahmouni Barkam</creatorcontrib><creatorcontrib>Ding, Andrew</creatorcontrib><creatorcontrib>Huang, Wenjun</creatorcontrib><creatorcontrib>Rezvani, Arghavan</creatorcontrib><creatorcontrib>Angizi, Shaahin</creatorcontrib><creatorcontrib>Imani, Mohsen</creatorcontrib><title>HyperSense: Hyperdimensional Intelligent Sensing for Energy-Efficient Sparse Data Processing</title><title>arXiv.org</title><description>Introducing HyperSense, our co-designed hardware and software system efficiently controls Analog-to-Digital Converter (ADC) modules' data generation rate based on object presence predictions in sensor data. Addressing challenges posed by escalating sensor quantities and data rates, HyperSense reduces redundant digital data using energy-efficient low-precision ADC, diminishing machine learning system costs. Leveraging neurally-inspired HyperDimensional Computing (HDC), HyperSense analyzes real-time raw low-precision sensor data, offering advantages in handling noise, memory-centricity, and real-time learning. Our proposed HyperSense model combines high-performance software for object detection with real-time hardware prediction, introducing the novel concept of Intelligent Sensor Control. Comprehensive software and hardware evaluations demonstrate our solution's superior performance, evidenced by the highest Area Under the Curve (AUC) and sharpest Receiver Operating Characteristic (ROC) curve among lightweight models. Hardware-wise, our FPGA-based domain-specific accelerator tailored for HyperSense achieves a 5.6x speedup compared to YOLOv4 on NVIDIA Jetson Orin while showing up to 92.1% energy saving compared to the conventional system. These results underscore HyperSense's effectiveness and efficiency, positioning it as a promising solution for intelligent sensing and real-time data processing across diverse applications.</description><subject>Analog to digital converters</subject><subject>Cost analysis</subject><subject>Data processing</subject><subject>Digital data</subject><subject>Hardware</subject><subject>Machine learning</subject><subject>Object recognition</subject><subject>Real time</subject><subject>Sensors</subject><subject>Software</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNjdEKgjAYhUcQJOU7DLoW3NS0bsuwu6AuAxn2TyZrs_3zwrdPowfo6pzD98FZkIAnCYuKlPMVCRG7OI75LudZlgTkUY09uBsYhAP99qd6TUtZIzS9GA9aqxaMp7OjTEuldbQ04NoxKqVUjfrCXjgEehJe0KuzDeDsbshSCo0Q_nJNtufyfqyi3tn3AOjrzg5uOsKa71mesrzIWPKf9QEJ0UPc</recordid><startdate>20241029</startdate><enddate>20241029</enddate><creator>Sanggeon Yun</creator><creator>Hanning Chen</creator><creator>Masukawa, Ryozo</creator><creator>Hamza Errahmouni Barkam</creator><creator>Ding, Andrew</creator><creator>Huang, Wenjun</creator><creator>Rezvani, Arghavan</creator><creator>Angizi, Shaahin</creator><creator>Imani, Mohsen</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20241029</creationdate><title>HyperSense: Hyperdimensional Intelligent Sensing for Energy-Efficient Sparse Data Processing</title><author>Sanggeon Yun ; Hanning Chen ; Masukawa, Ryozo ; Hamza Errahmouni Barkam ; Ding, Andrew ; Huang, Wenjun ; Rezvani, Arghavan ; Angizi, Shaahin ; Imani, Mohsen</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_29174178513</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Analog to digital converters</topic><topic>Cost analysis</topic><topic>Data processing</topic><topic>Digital data</topic><topic>Hardware</topic><topic>Machine learning</topic><topic>Object recognition</topic><topic>Real time</topic><topic>Sensors</topic><topic>Software</topic><toplevel>online_resources</toplevel><creatorcontrib>Sanggeon Yun</creatorcontrib><creatorcontrib>Hanning Chen</creatorcontrib><creatorcontrib>Masukawa, Ryozo</creatorcontrib><creatorcontrib>Hamza Errahmouni Barkam</creatorcontrib><creatorcontrib>Ding, Andrew</creatorcontrib><creatorcontrib>Huang, Wenjun</creatorcontrib><creatorcontrib>Rezvani, Arghavan</creatorcontrib><creatorcontrib>Angizi, Shaahin</creatorcontrib><creatorcontrib>Imani, Mohsen</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Sanggeon Yun</au><au>Hanning Chen</au><au>Masukawa, Ryozo</au><au>Hamza Errahmouni Barkam</au><au>Ding, Andrew</au><au>Huang, Wenjun</au><au>Rezvani, Arghavan</au><au>Angizi, Shaahin</au><au>Imani, Mohsen</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>HyperSense: Hyperdimensional Intelligent Sensing for Energy-Efficient Sparse Data Processing</atitle><jtitle>arXiv.org</jtitle><date>2024-10-29</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>Introducing HyperSense, our co-designed hardware and software system efficiently controls Analog-to-Digital Converter (ADC) modules' data generation rate based on object presence predictions in sensor data. Addressing challenges posed by escalating sensor quantities and data rates, HyperSense reduces redundant digital data using energy-efficient low-precision ADC, diminishing machine learning system costs. Leveraging neurally-inspired HyperDimensional Computing (HDC), HyperSense analyzes real-time raw low-precision sensor data, offering advantages in handling noise, memory-centricity, and real-time learning. Our proposed HyperSense model combines high-performance software for object detection with real-time hardware prediction, introducing the novel concept of Intelligent Sensor Control. Comprehensive software and hardware evaluations demonstrate our solution's superior performance, evidenced by the highest Area Under the Curve (AUC) and sharpest Receiver Operating Characteristic (ROC) curve among lightweight models. Hardware-wise, our FPGA-based domain-specific accelerator tailored for HyperSense achieves a 5.6x speedup compared to YOLOv4 on NVIDIA Jetson Orin while showing up to 92.1% energy saving compared to the conventional system. These results underscore HyperSense's effectiveness and efficiency, positioning it as a promising solution for intelligent sensing and real-time data processing across diverse applications.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2024-10
issn 2331-8422
language eng
recordid cdi_proquest_journals_2917417851
source Freely Accessible Journals
subjects Analog to digital converters
Cost analysis
Data processing
Digital data
Hardware
Machine learning
Object recognition
Real time
Sensors
Software
title HyperSense: Hyperdimensional Intelligent Sensing for Energy-Efficient Sparse Data Processing
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-08T07%3A12%3A47IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=HyperSense:%20Hyperdimensional%20Intelligent%20Sensing%20for%20Energy-Efficient%20Sparse%20Data%20Processing&rft.jtitle=arXiv.org&rft.au=Sanggeon%20Yun&rft.date=2024-10-29&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2917417851%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2917417851&rft_id=info:pmid/&rfr_iscdi=true