{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:37:36Z","timestamp":1760056656390,"version":"build-2065373602"},"reference-count":72,"publisher":"Association for Computing Machinery (ACM)","issue":"6","funder":[{"name":"Institute of Information and Communications Technology Planning and Evaluation"},{"name":"Development of High-Assurance (\u2265EAL6) Secure Microkernel","award":["RS-2018-II180532"],"award-info":[{"award-number":["RS-2018-II180532"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2025,11,30]]},"abstract":"<jats:p>Sound event detection (SED) based on on-device machine learning (ML) presents considerable energy challenges for ultra-low-power sensor devices. In this article, we propose DASH, a duration-aware SED system designed for energy-constrained sensor devices in domestic environments. As repeated inferences for continuous sound events lead to unnecessary energy consumption, DASH aims to minimize unnecessary inferences by predicting the duration of sound events. However, the variability of sound event durations across different environments and scenarios poses a major challenge in developing a responsive yet energy-efficient duration-aware SED system. To address this, DASH introduces three key solutions: (1) N-probability distribution-based event duration prediction, which identifies checkpoints where new inferences are likely needed; (2) Affinity-guided event classification, which performs low-energy affinity matching at checkpoints to determine whether ML inference is necessary; and (3) Interrupt blocking-enabling cycle-based device state control, which periodically checks for event presence with minimal energy consumption at non-checkpoint times. We implemented DASH on MSP430-based sensor devices deployed in real home environments. Experimental results demonstrate that DASH reduced energy consumption by approximately 97\u201398% compared to evaluation baselines, with only a 4.7% error rate.<\/jats:p>","DOI":"10.1145\/3761806","type":"journal-article","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T11:28:08Z","timestamp":1755602888000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Duration-Aware Sound Event Detection on Ultra-Low-Power Sensor Devices"],"prefix":"10.1145","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7336-6295","authenticated-orcid":false,"given":"Seonghoon","family":"Park","sequence":"first","affiliation":[{"name":"Computer Science and Engineering, Yonsei University","place":["Seoul, Korea (the Republic of)"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8775-5614","authenticated-orcid":false,"given":"Junick","family":"Ahn","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Yonsei University","place":["Seoul, Korea (the Republic of)"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1453-4156","authenticated-orcid":false,"given":"Daeyong","family":"Kim","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Yonsei University","place":["Seoul, Korea (the Republic of)"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9060-5091","authenticated-orcid":false,"given":"Hojung","family":"Cha","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Yonsei University","place":["Seoul, Korea (the Republic of)"]}]}],"member":"320","published-online":{"date-parts":[[2025,10,9]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3294111"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3448090"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","unstructured":"Junick Ahn Daeyong Kim and Hojung Cha. 2024. Split learning-based sound event detection in energy-constrained sensor devices. In 2024 23rd ACM\/IEEE International Conference on Information Processing in Sensor Networks (IPSN). 176\u2013187. DOI:10.1109\/IPSN61024.2024.00019","DOI":"10.1109\/IPSN61024.2024.00019"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3560905.3568561"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3560905.3568512"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3478077"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPSN54338.2022.00044"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3444490"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3666025.3699364"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690575"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3608475"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3406588"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2999388"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMD57530.2022.10058217"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173210"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3666025.3699335"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3088949"},{"key":"e_1_3_1_20_2","first-page":"32","volume-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2017 Workshop (DCASE\u201917)","author":"Dekkers Gert","year":"2017","unstructured":"Gert Dekkers, Steven Lauwereins, Bart Thoen, Mulu Weldegebreal Adhana, Henk Brouckxon, Toon van Waterschoot, Bart Vanrumste, Marian Verhelst, and Peter Karsmakers. 2017. The {SINS} database for detection of daily activities in a home environment using an acoustic sensor network. In Proceedings of the Detection and Classification of Acoustic Scenes and Events 2017 Workshop (DCASE\u201917). 32\u201336."},{"key":"e_1_3_1_21_2","unstructured":"Dennis Don Kurian and Gaurkar Yash and Gopinath Sridhar and Goyal Sachin and Gupta Chirag and Jain Moksh and Jaiswal Shikhar and Kumar Ashish and Kusupati Aditya and Lovett Chris and Patil Shishir G and Saha Oindrila and Simhadri and Harsha Vardh. 2021. EdgeML: Machine Learning for resource-constrained edge devices. https:\/\/github.com\/Microsoft\/EdgeML. Access date: May 1st 2025."},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510850"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2021.100461"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2405.10426"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404191"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3384419.3430734"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304011"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3131672.3131699"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411808"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE54114.2022.9774756"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581791.3596845"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3307334.3326080"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3506732"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS52030.2021.00020"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/PERCOM56429.2023.10099205"},{"key":"e_1_3_1_39_2","first-page":"1","volume-title":"Proceedings of the ICML Deep Learning Workshop","author":"Koch Gregory","year":"2015","unstructured":"Gregory Koch, Richard Zemel, and Ruslan Salakhutdinov. 2015. Siamese neural networks for one-shot image recognition. In Proceedings of the ICML Deep Learning Workshop. 1\u20138."},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3356250.3360030"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3478384.3478408"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/DCOSS52077.2021.00018"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2962526"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3385412.3385998"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPSN48710.2020.00-36"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.suscom.2019.100368"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2389618"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3090678"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890685"},{"key":"e_1_3_1_51_2","first-page":"100","volume-title":"Proceedings of the 5th Workshop on Detection and Classification of Acoustic Scenes and Events 2020 (DCASE \u201920)","author":"Miyazaki Koichi","year":"2020","unstructured":"Koichi Miyazaki, Tatsuya Komatsu, Tomoki Hayashi, Shinji Watanabe, Tomoki Toda, and Kazuya Takeda. 2020. Conformer-based sound event detection with semi-supervised learning and data augmentation. In Proceedings of the 5th Workshop on Detection and Classification of Acoustic Scenes and Events 2020 (DCASE \u201920). 100\u2013104."},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3140807"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581791.3596859"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3384419.3430782"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10127"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/2742647.2742674"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746093"},{"key":"e_1_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2005.9"},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-123"},{"key":"e_1_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2015.7324337"},{"key":"e_1_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3064066"},{"key":"e_1_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"e_1_3_1_64_2","unstructured":"Texas Instruments. [n. d.]. MSP430FR599x MSP430FR596x Mixed-Signal Microcontrollers. Retrieved from https:\/\/www.ti.com\/lit\/ds\/symlink\/msp430fr5994.pdf"},{"key":"e_1_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2997047"},{"key":"e_1_3_1_66_2","volume-title":"Proceedings of the Workshop on Detection and Classification of Acoustic Scenes and Events","author":"Turpault Nicolas","year":"2019","unstructured":"Nicolas Turpault, Romain Serizel, Ankit Parag Shah, and Justin Salamon. 2019. Sound event detection in domestic environments with weakly labeled data and soundscape synthesis. In Proceedings of the Workshop on Detection and Classification of Acoustic Scenes and Events. New York City, United States. Retrieved from https:\/\/hal.inria.fr\/hal-02160855"},{"key":"e_1_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472176"},{"key":"e_1_3_1_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/3715014.3722059"},{"key":"e_1_3_1_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3384419.3430898"},{"key":"e_1_3_1_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/3274783.3274837"},{"key":"e_1_3_1_72_2","first-page":"339","volume-title":"Proceedings of the 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Yildiz Eren","year":"2022","unstructured":"Eren Yildiz, Lijun Chen, and Kasim Sinan Yildirim. 2022. Immortal threads: Multithreaded event-driven intermittent computing on {Ultra-low-power} microcontrollers. In Proceedings of the 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). USENIX Association, Carlsbad, CA, 339\u2013355. Retrieved from https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/yildiz"},{"key":"e_1_3_1_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178031"}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3761806","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T12:41:11Z","timestamp":1760013671000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3761806"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,9]]},"references-count":72,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11,30]]}},"alternative-id":["10.1145\/3761806"],"URL":"https:\/\/doi.org\/10.1145\/3761806","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"type":"print","value":"1539-9087"},{"type":"electronic","value":"1558-3465"}],"subject":[],"published":{"date-parts":[[2025,10,9]]},"assertion":[{"value":"2025-05-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-11","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}