{"id":167055,"date":"2014-09-15T00:00:00","date_gmt":"2014-09-15T07:00:00","guid":{"rendered":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/msr-research-item\/energy-scaling-in-multi-tiered-sensing-systems-through-compressive-sensing\/"},"modified":"2018-10-26T14:45:01","modified_gmt":"2018-10-26T21:45:01","slug":"energy-scaling-in-multi-tiered-sensing-systems-through-compressive-sensing","status":"publish","type":"msr-research-item","link":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/publication\/energy-scaling-in-multi-tiered-sensing-systems-through-compressive-sensing\/","title":{"rendered":"Energy Scaling in Multi-tiered Sensing Systems Through Compressive Sensing"},"content":{"rendered":"<div class=\"asset-content\">\n<p>High functional complexity is leading us towards new architectures for sensing systems. Multi-tiered design is one among the many emerging alternatives. Such architectures bring new opportunities for effective system-level power management. For instance, varying one\/more tier-level parameters can provide substantial end-to-end energy scaling. In this paper, we review an existing approach that shows how one such parameter, namely data compression, can help us scale energy at the cost of algorithmic accuracy. The methodology is driven by a case study of inferring the onset of seizure events directly from compressively-sensed electroencephalograms. Results from an integrated circuit implementation have shown tier-level computational energy scaling in the range 1.2-214 \u03bcJ depending on the amount of compression (2-24\u00d7) and inference accuracy (sensitivity, latency, and specificity of 91-96%, 4.7-5.3 sec., and 0.17-0.30 false-alarms\/hr., respectively). The projections we make in this paper show that for similar systems, compressive sensing, through this approach, has the potential to prolong battery lives of all tiers by up to 5\u00d7.<\/p>\n<\/div>\n<p><!-- .asset-content --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>High functional complexity is leading us towards new architectures for sensing systems. Multi-tiered design is one among the many emerging alternatives. Such architectures bring new opportunities for effective system-level power management. For instance, varying one\/more tier-level parameters can provide substantial end-to-end energy scaling. In this paper, we review an existing approach that shows how one [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr-author-ordering":[{"type":"user_nicename","value":"Shuayb Zarar","user_id":"36563"},{"type":"user_nicename","value":"Jie Liu","user_id":"32707"},{"type":"user_nicename","value":"Matthai Philipose","user_id":"32834"}],"msr_publishername":"IEEE - Institute of Electrical and Electronics Engineers","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"","msr_editors":"","msr_how_published":"","msr_isbn":"","msr_issue":"","msr_journal":"","msr_number":"","msr_organization":"","msr_pages_string":"","msr_page_range_start":"1","msr_page_range_end":"8","msr_series":"","msr_volume":"","msr_copyright":"\u00a9 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting\/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.","msr_conference_name":"IEEE Custom Integrated Circuits Conference (CICC)","msr_doi":"","msr_arxiv_id":"","msr_s2_paper_id":"","msr_mag_id":"","msr_pubmed_id":"","msr_other_authors":"Matthai Phillipose","msr_other_contributors":"","msr_speaker":"","msr_award":"Best paper award nomination","msr_affiliation":"","msr_institution":"","msr_host":"","msr_version":"","msr_duration":"","msr_original_fields_of_study":"","msr_release_tracker_id":"","msr_s2_match_type":"","msr_citation_count_updated":"","msr_published_date":"2014-9-15","msr_highlight_text":"","msr_notes":"Best paper award nomination","msr_longbiography":"","msr_publicationurl":"http:\/\/ieeexplore.ieee.org\/xpls\/abs_all.jsp?arnumber=6946017","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"","msr_journal_url":"","msr_s2_pdf_url":"","msr_year":0,"msr_citation_count":0,"msr_influential_citations":0,"msr_reference_count":0,"msr_s2_match_confidence":0,"msr_microsoftintellectualproperty":true,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[],"msr_hide_image_in_river":0,"footnotes":""},"msr-research-highlight":[],"research-area":[13556,243062,13552,13553,13547],"msr-publication-type":[193716],"msr-publisher":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-167055","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-audio-acoustics","msr-research-area-hardware-devices","msr-research-area-medical-health-genomics","msr-research-area-systems-and-networking","msr-locale-en_us"],"msr_publishername":"IEEE - Institute of Electrical and Electronics Engineers","msr_edition":"","msr_affiliation":"","msr_published_date":"2014-9-15","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"Best paper award nomination","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"245453","msr_publicationurl":"http:\/\/ieeexplore.ieee.org\/xpls\/abs_all.jsp?arnumber=6946017","msr_doi":"","msr_publication_uploader":[{"type":"file","viewUrl":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-content\/uploads\/2014\/09\/Shoaib_CICC_2014.pdf","id":"245453","title":"Shoaib_CICC_2014","label_id":"243109","label":0},{"type":"url","viewUrl":"false","id":"false","title":"http:\/\/ieeexplore.ieee.org\/xpls\/abs_all.jsp?arnumber=6946017","label_id":"243109","label":0},{"type":"doi","viewUrl":"false","id":"false","title":"10.1109\/CICC.2014.6946017","label_id":"243109","label":0}],"msr_related_uploader":"","msr_citation_count":0,"msr_citation_count_updated":"","msr_s2_paper_id":"","msr_influential_citations":0,"msr_reference_count":0,"msr_arxiv_id":"","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[{"id":0,"url":"http:\/\/ieeexplore.ieee.org\/xpls\/abs_all.jsp?arnumber=6946017"}],"msr-author-ordering":[{"type":"user_nicename","value":"Shuayb Zarar","user_id":36563,"rest_url":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Shuayb Zarar"},{"type":"user_nicename","value":"Jie Liu","user_id":32707,"rest_url":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Jie Liu"},{"type":"user_nicename","value":"Matthai Philipose","user_id":32834,"rest_url":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Matthai Philipose"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[144899,144923],"msr_project":[430839],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":430839,"post_title":"On-device ML for Object and Activity Detection","post_name":"device-ml-ambient-aware-applications","post_type":"msr-project","post_date":"2017-10-05 11:03:40","post_modified":"2020-03-13 17:08:00","post_status":"publish","permalink":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/project\/device-ml-ambient-aware-applications\/","post_excerpt":"To process data locally, we have accelerated ML computations via ASICs that incorporate efficient pipelining and parallelism techniques. We have also compressed ML models by scaling their bit-precision values.","_links":{"self":[{"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/430839"}]}}]},"_links":{"self":[{"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/167055","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":2,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/167055\/revisions"}],"predecessor-version":[{"id":454440,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/167055\/revisions\/454440"}],"wp:attachment":[{"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/media?parent=167055"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=167055"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=167055"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=167055"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=167055"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=167055"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=167055"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=167055"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=167055"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=167055"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=167055"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=167055"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=167055"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}