{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T14:08:53Z","timestamp":1781878133310,"version":"3.54.5"},"reference-count":72,"publisher":"Association for Computing Machinery (ACM)","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>\n            On-line decision augmentation (OLDA) has been considered as a promising paradigm for real-time decision making powered by Artificial Intelligence (AI). OLDA has been widely used in many applications such as real-time fraud detection, personalized recommendation, etc. On-line inference puts real-time features extracted from multiple time windows through a pre-trained model to evaluate new data to support decision making. Feature extraction is usually the most time-consuming operation in many OLDA data pipelines. In this work, we started by studying how existing in-memory databases can be leveraged to efficiently support such real-time feature extractions. However, we found that existing in-memory databases cost hundreds or even thousands of milliseconds. This is unacceptable for OLDA applications with strict real-time constraints. We therefore propose\n            <jats:bold>FEDB<\/jats:bold>\n            (\n            <jats:bold>&lt;u&gt;F&lt;\/u&gt;<\/jats:bold>\n            eature\n            <jats:bold>&lt;u&gt;E&lt;\/u&gt;<\/jats:bold>\n            ngineering\n            <jats:bold>&lt;u&gt;D&lt;\/u&gt;<\/jats:bold>\n            ata\n            <jats:bold>&lt;u&gt;b&lt;\/u&gt;<\/jats:bold>\n            ase), a distributed in-memory database system designed to efficiently support on-line\n            <jats:italic>feature extraction.<\/jats:italic>\n            Our experimental results show that FEDB can be one to two orders of magnitude faster than the state-of-the-art in-memory databases on real-time feature extraction. Furthermore, we explore the use of the Intel Optane DC Persistent Memory Module (PMEM) to make FEDB more cost-effective. When comparing the proposed PMEM-optimized persistent skiplist to the FEDB using DRAM+SSD, PMEM-based FEDB can shorten the tail latency up to 19.7%, reduce the recovery time up to 99.7%, and save up to 58.4% total cost of a real OLDA pipeline.\n          <\/jats:p>","DOI":"10.14778\/3446095.3446102","type":"journal-article","created":{"date-parts":[[2021,3,23]],"date-time":"2021-03-23T16:36:58Z","timestamp":1616517418000},"page":"799-812","source":"Crossref","is-referenced-by-count":19,"title":["Optimizing in-memory database engine for AI-powered on-line decision augmentation using persistent memory"],"prefix":"10.14778","volume":"14","author":[{"given":"Cheng","family":"Chen","sequence":"first","affiliation":[{"name":"4Paradigm Inc. and National University of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Yang","sequence":"additional","affiliation":[{"name":"4Paradigm Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mian","family":"Lu","sequence":"additional","affiliation":[{"name":"4Paradigm Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taize","family":"Wang","sequence":"additional","affiliation":[{"name":"4Paradigm Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhao","family":"Zheng","sequence":"additional","affiliation":[{"name":"4Paradigm Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuqiang","family":"Chen","sequence":"additional","affiliation":[{"name":"4Paradigm Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenyuan","family":"Dai","sequence":"additional","affiliation":[{"name":"4Paradigm Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingsheng","family":"He","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weng-Fai","family":"Wong","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoan","family":"Wu","sequence":"additional","affiliation":[{"name":"Intel Corporation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuping","family":"Zhao","sequence":"additional","affiliation":[{"name":"Intel Corporation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andy","family":"Rudoff","sequence":"additional","affiliation":[{"name":"Intel Corporation"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,3,23]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"Paul Alcorn. 2019. Intel Optane DIMM Pricing. https:\/\/www.tomshardware.com\/news\/intel-optane-dimm-pricing-performance 39007.html. Last accessed on 02-July-2020.  Paul Alcorn. 2019. Intel Optane DIMM Pricing. https:\/\/www.tomshardware.com\/news\/intel-optane-dimm-pricing-performance 39007.html. Last accessed on 02-July-2020."},{"key":"e_1_2_1_2_1","unstructured":"Alibabacloud. 2019. Key Concepts and Features of Time Series Databases. https:\/\/www.alibabacloud.com\/blog\/key-concepts-and-features-of-time-series-databases_594734 Last accessed on 02-July-2020.  Alibabacloud. 2019. Key Concepts and Features of Time Series Databases. https:\/\/www.alibabacloud.com\/blog\/key-concepts-and-features-of-time-series-databases_594734 Last accessed on 02-July-2020."},{"key":"e_1_2_1_3_1","volume-title":"Performance Analysis and Comparison of Distributed Machine Learning Systems. arXiv:1909.02061","author":"Alqahtani Salem","year":"2019","unstructured":"Salem Alqahtani and Murat Demirbas . 2019. Performance Analysis and Comparison of Distributed Machine Learning Systems. arXiv:1909.02061 ( 2019 ). Salem Alqahtani and Murat Demirbas. 2019. Performance Analysis and Comparison of Distributed Machine Learning Systems. arXiv:1909.02061 (2019)."},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.14778\/3137765.3137780"},{"key":"e_1_2_1_5_1","volume-title":"8th Biennial Conference on Innovative Data Systems Research.","author":"Appuswamy Raja","year":"2017","unstructured":"Raja Appuswamy , Manos Karpathiotakis , Danica Porobic , and Anastasia Ailamaki . 2017 . The case for heterogeneous HTAP . In 8th Biennial Conference on Innovative Data Systems Research. Raja Appuswamy, Manos Karpathiotakis, Danica Porobic, and Anastasia Ailamaki. 2017. The case for heterogeneous HTAP. In 8th Biennial Conference on Innovative Data Systems Research."},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2019.00083"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3328523"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3187009.3164147"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3054780"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3054780"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/3348513"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3399579.3399867"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2019.2948004"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2016.7897077"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.14778\/2752939.2752947"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378515"},{"key":"e_1_2_1_17_1","unstructured":"Salvatore Sanfilippo et. al. 2009. Redis. https:\/\/redis.io\/. Last accessed on 02-July-2020.  Salvatore Sanfilippo et. al. 2009. Redis. https:\/\/redis.io\/. Last accessed on 02-July-2020."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2094114.2094126"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751212"},{"key":"e_1_2_1_20_1","unstructured":"Google. 2019. In-Memory Database. https:\/\/cloud.google.com\/blog\/topics\/partners\/available-first-on-google-cloud-intel-optane-dc-persistent-memory Last accessed on 02-July-2020.  Google. 2019. In-Memory Database. https:\/\/cloud.google.com\/blog\/topics\/partners\/available-first-on-google-cloud-intel-optane-dc-persistent-memory Last accessed on 02-July-2020."},{"key":"e_1_2_1_21_1","unstructured":"The TANEJA Group. 2012. number of nines availability of systems. http:\/\/tanejagroup.com\/files\/Compellent_TG_Opinion_5_Nines_Sept_20121.pdf Last accessed on 02-July-2020.  The TANEJA Group. 2012. number of nines availability of systems. http:\/\/tanejagroup.com\/files\/Compellent_TG_Opinion_5_Nines_Sept_20121.pdf Last accessed on 02-July-2020."},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389741"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3314041"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/1855840.1855851"},{"key":"e_1_2_1_25_1","volume-title":"IDC marketscape: Manufacturer evaluation of China machine learning development platform","author":"IDC.","year":"2019","unstructured":"IDC. 2019. IDC marketscape: Manufacturer evaluation of China machine learning development platform 2019 . https:\/\/www.idc.com\/getdoc.jsp?containerId=CHC45389019 Last accessed on 02-July-2020. IDC. 2019. IDC marketscape: Manufacturer evaluation of China machine learning development platform 2019. https:\/\/www.idc.com\/getdoc.jsp?containerId=CHC45389019 Last accessed on 02-July-2020."},{"key":"e_1_2_1_26_1","unstructured":"Timescale Incorporated. 2019. TimescaleDB. https:\/\/github.com\/timescale\/timescaledb Last accessed on 02-July-2020.  Timescale Incorporated. 2019. TimescaleDB. https:\/\/github.com\/timescale\/timescaledb Last accessed on 02-July-2020."},{"key":"e_1_2_1_27_1","unstructured":"InfluxData. 2019. influxDB. https:\/\/www.influxdata.com\/. Last accessed on 02-July-2020.  InfluxData. 2019. influxDB. https:\/\/www.influxdata.com\/. Last accessed on 02-July-2020."},{"key":"e_1_2_1_28_1","unstructured":"Intel. 2015. Intel\u00ae OptaneTM DC persistent memory. \"https:\/\/www.intel.com\/content\/www\/us\/en\/architecture-and-technology\/optane-dc-persistent-memory.html. Last accessed on 02-July-2020.  Intel. 2015. Intel\u00ae Optane TM DC persistent memory. \"https:\/\/www.intel.com\/content\/www\/us\/en\/architecture-and-technology\/optane-dc-persistent-memory.html. Last accessed on 02-July-2020."},{"key":"e_1_2_1_29_1","unstructured":"Intel. 2015. Pmem.io. https:\/\/pmem.io\/libpmemobj-cpp\/ Last accessed on 26-January-2020.  Intel. 2015. Pmem.io. https:\/\/pmem.io\/libpmemobj-cpp\/ Last accessed on 26-January-2020."},{"key":"e_1_2_1_30_1","unstructured":"Intel. 2019. The Challenge of Keeping up with data. https:\/\/www.intel.com\/content\/dam\/www\/public\/us\/en\/documents\/product-briefs\/optane-dc-persistent-memory-brief.pdf) Last accessed on 02-July-2020.  Intel. 2019. The Challenge of Keeping up with data. https:\/\/www.intel.com\/content\/dam\/www\/public\/us\/en\/documents\/product-briefs\/optane-dc-persistent-memory-brief.pdf) Last accessed on 02-July-2020."},{"key":"e_1_2_1_31_1","unstructured":"Intel. 2019. Introduction to programming for persistent memory. https:\/\/github.com\/pmemhackathon\/2019-11-08\/blob\/master\/PMEM_INTRO.pdf Last accessed on 02-July-2020.  Intel. 2019. Introduction to programming for persistent memory. https:\/\/github.com\/pmemhackathon\/2019-11-08\/blob\/master\/PMEM_INTRO.pdf Last accessed on 02-July-2020."},{"key":"e_1_2_1_32_1","unstructured":"Intel. 2019. Ipmctl. https:\/\/github.com\/intel\/ipmctl. Last accessed on 02-July-2020.  Intel. 2019. Ipmctl. https:\/\/github.com\/intel\/ipmctl. Last accessed on 02-July-2020."},{"key":"e_1_2_1_33_1","unstructured":"Intel. 2019. libpmemobj. https:\/\/github.com\/pmem\/libpmemobj-cpp\/ Last accessed on 02-July-2020.  Intel. 2019. libpmemobj. https:\/\/github.com\/pmem\/libpmemobj-cpp\/ Last accessed on 02-July-2020."},{"key":"e_1_2_1_34_1","volume-title":"Zixuan Wang, Yi Xu, Subramanya R Dulloor, et al.","author":"Izraelevitz Joseph","year":"2019","unstructured":"Joseph Izraelevitz , Jian Yang , Lu Zhang , Juno Kim , Xiao Liu , Amirsaman Memaripour , Yun Joon Soh , Zixuan Wang, Yi Xu, Subramanya R Dulloor, et al. 2019 . Basic performance measurements of the intel optane DC persistent memory module. arXivpreprint arXiv:1903.05714 (2019). Joseph Izraelevitz, Jian Yang, Lu Zhang, Juno Kim, Xiao Liu, Amirsaman Memaripour, Yun Joon Soh, Zixuan Wang, Yi Xu, Subramanya R Dulloor, et al. 2019. Basic performance measurements of the intel optane DC persistent memory module. arXivpreprint arXiv:1903.05714 (2019)."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2015.7113373"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2018.00226"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/3129633.3129657"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.5555\/3291168.3291213"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.14778\/2794367.2794375"},{"key":"e_1_2_1_40_1","volume-title":"Dash: scalable hashing on persistent memory. arXiv preprint arXiv:2003.07302","author":"Lu Baotong","year":"2020","unstructured":"Baotong Lu , Xiangpeng Hao , Tianzheng Wang , and Eric Lo. 2020. Dash: scalable hashing on persistent memory. arXiv preprint arXiv:2003.07302 ( 2020 ). Baotong Lu, Xiangpeng Hao, Tianzheng Wang, and Eric Lo. 2020. Dash: scalable hashing on persistent memory. arXiv preprint arXiv:2003.07302 (2020)."},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3183751"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3035959"},{"key":"e_1_2_1_43_1","unstructured":"MemSQL. 2013. https:\/\/www.memsql.com\/ Last accessed on 02-July-2020.  MemSQL. 2013. https:\/\/www.memsql.com\/ Last accessed on 02-July-2020."},{"key":"e_1_2_1_44_1","unstructured":"Microsoft. Oct 30 2018. Windows Server 2019 with Intel\u00ae OptaneTM DC persistent memory. https:\/\/techcommunity.microsoft.com\/t5\/Storage-at-Microsoft\/The-new-HCI-industry-record-13-7-million-IOPS-with-Windows\/ba-p\/428314 Last accessed on 02-July-2020.  Microsoft. Oct 30 2018. Windows Server 2019 with Intel \u00ae Optane TM DC persistent memory. https:\/\/techcommunity.microsoft.com\/t5\/Storage-at-Microsoft\/The-new-HCI-industry-record-13-7-million-IOPS-with-Windows\/ba-p\/428314 Last accessed on 02-July-2020."},{"key":"e_1_2_1_45_1","unstructured":"MySQL. 1995. https:\/\/www.mysql.com\/ Last accessed on 02-July-2020.  MySQL. 1995. https:\/\/www.mysql.com\/ Last accessed on 02-July-2020."},{"key":"e_1_2_1_46_1","unstructured":"OpenJDK. 2013. https:\/\/openjdk.java.net\/projects\/code-tools\/jmh\/ Last accessed on 02-July-2020.  OpenJDK. 2013. https:\/\/openjdk.java.net\/projects\/code-tools\/jmh\/ Last accessed on 02-July-2020."},{"key":"e_1_2_1_47_1","unstructured":"Oracle. Sep 16 2019. Oracle Database with Intel Optane DC Persistent Memory. https:\/\/www.oracle.com\/corporate\/pressrelease\/oow19-oracle-intel-partner-optane-exadata-091619.html Last accessed on 02-July-2020.  Oracle. Sep 16 2019. Oracle Database with Intel Optane DC Persistent Memory. https:\/\/www.oracle.com\/corporate\/pressrelease\/oow19-oracle-intel-partner-optane-exadata-091619.html Last accessed on 02-July-2020."},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2915251"},{"key":"e_1_2_1_49_1","unstructured":"Top percentile. 2019. TP-X. https:\/\/support.huaweicloud.com\/intl\/en-us\/productdesc-apm\/apm_06_0002.html. Last accessed on 02-July-2020.  Top percentile. 2019. TP-X. https:\/\/support.huaweicloud.com\/intl\/en-us\/productdesc-apm\/apm_06_0002.html. Last accessed on 02-July-2020."},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299887.3299891"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3329785.3329917"},{"key":"e_1_2_1_52_1","unstructured":"Alexander Ratner Dan Alistarh Gustavo Alonso David G Andersen Peter Bailis Sarah Bird Nicholas Carlini Bryan Catanzaro Eric Chung Bill Dally etal 2019. SysML: The New Frontier of Machine Learning Systems. (2019).  Alexander Ratner Dan Alistarh Gustavo Alonso David G Andersen Peter Bailis Sarah Bird Nicholas Carlini Bryan Catanzaro Eric Chung Bill Dally et al. 2019. SysML: The New Frontier of Machine Learning Systems. (2019)."},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.14778\/3157794.3157797"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389783"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.14778\/3352063.3352149"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.14778\/3229863.3236260"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3324961"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.14778\/3137765.3137810"},{"key":"e_1_2_1_59_1","volume-title":"Competitive Landscape: AI Startups in China. Technical Report. Stamford, USA.","author":"Tsai Tracy","year":"2019","unstructured":"Tracy Tsai . 2019 . Competitive Landscape: AI Startups in China. Technical Report. Stamford, USA. Tracy Tsai. 2019. Competitive Landscape: AI Startups in China. Technical Report. Stamford, USA."},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196897"},{"key":"e_1_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196934"},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.5555\/1960475.1960480"},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3316482.3326358"},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3177915"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2018.00049"},{"key":"e_1_2_1_66_1","unstructured":"Wikipedia. 2019. Compare-and-swap. https:\/\/en.wikipedia.org\/wiki\/Compare-and-swap Last accessed on 02-July-2020.  Wikipedia. 2019. Compare-and-swap. https:\/\/en.wikipedia.org\/wiki\/Compare-and-swap Last accessed on 02-July-2020."},{"key":"e_1_2_1_67_1","unstructured":"Wikipedia. 2019. LLVM. https:\/\/en.wikipedia.org\/wiki\/Click-through_rate Last accessed on 02-July-2020.  Wikipedia. 2019. LLVM. https:\/\/en.wikipedia.org\/wiki\/Click-through_rate Last accessed on 02-July-2020."},{"key":"e_1_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.5555\/2930583.2930608"},{"key":"e_1_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.5555\/2750482.2750495"},{"key":"e_1_2_1_70_1","volume-title":"AutoCross: Automatic Feature Crossing for Tabular Data in Real-World Applications. arXiv preprint arXiv:1904.12857","author":"Yuanfei Luo","year":"2019","unstructured":"Luo Yuanfei , Wang Mengshuo , Zhou Hao , Yao Quanming , Tu WeiWei , Chen Yuqiang , Yang Qiang , and Dai Wenyuan . 2019. AutoCross: Automatic Feature Crossing for Tabular Data in Real-World Applications. arXiv preprint arXiv:1904.12857 ( 2019 ). Luo Yuanfei, Wang Mengshuo, Zhou Hao, Yao Quanming, Tu WeiWei, Chen Yuqiang, Yang Qiang, and Dai Wenyuan. 2019. AutoCross: Automatic Feature Crossing for Tabular Data in Real-World Applications. arXiv preprint arXiv:1904.12857 (2019)."},{"key":"e_1_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.14778\/3352063.3352124"},{"key":"e_1_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2867522"}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/3446095.3446102","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T11:22:29Z","timestamp":1672226549000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/3446095.3446102"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":72,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.14778\/3446095.3446102"],"URL":"https:\/\/doi.org\/10.14778\/3446095.3446102","relation":{},"ISSN":["2150-8097"],"issn-type":[{"value":"2150-8097","type":"print"}],"subject":[],"published":{"date-parts":[[2021,1]]}}}