{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T19:17:23Z","timestamp":1784920643591,"version":"3.55.0"},"publisher-location":"Cham","reference-count":73,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031398469","type":"print"},{"value":"9783031398476","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-39847-6_1","type":"book-chapter","created":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T17:02:46Z","timestamp":1692291766000},"page":"3-18","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Data Integration Revitalized: From Data Warehouse Through Data Lake to\u00a0Data Mesh"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6037-5718","authenticated-orcid":false,"given":"Robert","family":"Wrembel","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,8,18]]},"reference":[{"key":"1_CR1","unstructured":"Ahle, U., Hemetsberger, L., \u0141akomski, M., Wrembel, R.: AI and data: how cities of the future will use data in their development (2023)"},{"key":"1_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.105899","volume":"120","author":"Y Akkem","year":"2023","unstructured":"Akkem, Y., Biswas, S.K., Varanasi, A.: Smart farming using artificial intelligence: a review. Eng. Appl. Artif. Intell. 120, 105899 (2023)","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"1","key":"1_CR3","doi-asserted-by":"publisher","first-page":"69","DOI":"10.2478\/amcs-2019-0005","volume":"29","author":"SMF Ali","year":"2019","unstructured":"Ali, S.M.F., Mey, J., Thiele, M.: Parallelizing user-defined functions in the ETL workflow using orchestration style sheets. Int. J. Appl. Math. Comput. Sci. 29(1), 69\u201379 (2019)","journal-title":"Int. J. Appl. Math. Comput. Sci."},{"issue":"6","key":"1_CR4","doi-asserted-by":"publisher","first-page":"777","DOI":"10.1007\/s00778-017-0477-2","volume":"26","author":"SMF Ali","year":"2017","unstructured":"Ali, S.M.F., Wrembel, R.: From conceptual design to performance optimization of ETL workflows: current state of research and open problems. VLDB J. 26(6), 777\u2013801 (2017). https:\/\/doi.org\/10.1007\/s00778-017-0477-2","journal-title":"VLDB J."},{"key":"1_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1007\/978-3-030-28730-6_27","volume-title":"Advances in Databases and Information Systems","author":"SMF Ali","year":"2019","unstructured":"Ali, S.M.F., Wrembel, R.: Towards a cost model to optimize user-defined functions in an ETL workflow based on user-defined performance metrics. In: Welzer, T., Eder, J., Podgorelec, V., Kami\u0161ali\u0107 Latifi\u0107, A. (eds.) ADBIS 2019. LNCS, vol. 11695, pp. 441\u2013456. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-28730-6_27"},{"key":"1_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/978-3-030-59065-9_11","volume-title":"Big Data Analytics and Knowledge Discovery","author":"SMF Ali","year":"2020","unstructured":"Ali, S.M.F., Wrembel, R.: Framework to optimize data processing pipelines using performance metrics. In: Song, M., Song, I.-Y., Kotsis, G., Tjoa, A.M., Khalil, I. (eds.) DaWaK 2020. LNCS, vol. 12393, pp. 131\u2013140. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59065-9_11"},{"key":"1_CR7","unstructured":"Andrzejewski, W., Bebel, B., Boi\u0144ski, P., Sienkiewicz, M., Wrembel, R.: Text similarity measures in a data deduplication pipeline for customers records. In: International Workshop on Design, Optimization, Languages and Analytical Processing of Big Data (DOLAP), volume 3369 of CEUR Workshop Proceedings, pp. 33\u201342. CEUR-WS.org (2023)"},{"key":"1_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.datak.2019.101727","volume":"123","author":"B Bilalli","year":"2019","unstructured":"Bilalli, B., Abell\u00f3, A., Aluja-Banet, T., Wrembel, R.: PRESISTANT: learning based assistant for data pre-processing. Data Knowl. Eng. 123, 101727 (2019)","journal-title":"Data Knowl. Eng."},{"key":"1_CR9","unstructured":"Bode, J., K\u00fchl, N., Kreuzberger, D., Hirschl, S., Holtmann, C.: Data mesh: best practices to avoid the data mess. CoRR, abs\/2302.01713 (2023)"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Bodziony, M., Krzyzanowski, H., Pieta, L., Wrembel, R.: On discovering semantics of user-defined functions in data processing workflows. In: International Workshop on Big Data in Emergent Distributed Environments (BiDEDE) @ SIGMOD\/PODS, pp. 7:1\u20137:6. ACM (2021)","DOI":"10.1145\/3460866.3461771"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Bodziony, M., Morawski, R., Wrembel, R.: Evaluating push-down on nosql data sources: experiments and analysis paper. In: International Workshop on Big Data in Emergent Distributed Environments (BiDEDE) @ SIGMOD\/PODS, pp. 4:1\u20134:6 (2022)","DOI":"10.1145\/3530050.3532916"},{"key":"1_CR12","unstructured":"Bodziony, M., Roszyk, S., Wrembel, R.: On evaluating performance of balanced optimization of ETL processes for streaming data sources. In: International Workshop on Design, Optimization, Languages and Analytical Processing of Big Data (DOLAP), volume 2572 of CEUR Workshop Proceedings, pp. 74\u201378 (2020)"},{"key":"1_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-86472-9_1","volume-title":"Database and Expert Systems Applications","author":"M Bodziony","year":"2021","unstructured":"Bodziony, M., Wrembel, R.: Reference architecture for running large scale data integration experiments. In: Strauss, C., Kotsis, G., Tjoa, A.M., Khalil, I. (eds.) DEXA 2021. LNCS, vol. 12923, pp. 3\u20139. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86472-9_1"},{"key":"1_CR14","unstructured":"Bodziony, M., Wrembel, R.: Data source connectors layer as a service - design patterns. In: International Workshop on Design, Optimization, Languages and Analytical Processing of Big Data (DOLAP), volume 3369 of CEUR Workshop Proceedings, pp. 76\u201380. CEUR-WS.org (2023)"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Boi\u0144ski, P., Andrzejewski, W., B\u0119bel, B., Wrembel, R.: On tuning the sorted neighborhood method for record comparisons in a data deduplication pipeline. In: International Conference on Database and Expert Systems Applications (DEXA). Springer, Cham (2023). Volume to appear of LNCS","DOI":"10.1007\/978-3-031-39847-6_11"},{"key":"1_CR16","unstructured":"Boinski, P., Sienkiewicz, M., Bebel, B., Wrembel, R., Galezowski, D., Graniszewski, W.: On customer data deduplication: lessons learned from a R&D project in the financial sector. In Workshops of the EDBT\/ICDT Joint Conference, volume 3135 of CEUR Workshop Proceedings (2022)"},{"key":"1_CR17","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5567-4","volume-title":"Interconnecting Heterogeneous Information Systems","author":"A Bouguettaya","year":"1998","unstructured":"Bouguettaya, A., Benatallah, B., Elmargamid, A.: Interconnecting Heterogeneous Information Systems. Kluwer Academic Publishers, Alphen aan den Rijn (1998). ISBN: 0792382161"},{"key":"1_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1007\/978-3-540-24669-5_103","volume-title":"Parallel Processing and Applied Mathematics","author":"P Brezany","year":"2004","unstructured":"Brezany, P., Tjoa, A.M., Wanek, H., W\u00f6hrer, A.: Mediators in the architecture of grid information systems. In: Wyrzykowski, R., Dongarra, J., Paprzycki, M., Wa\u015bniewski, J. (eds.) PPAM 2003. LNCS, vol. 3019, pp. 788\u2013795. Springer, Heidelberg (2004). https:\/\/doi.org\/10.1007\/978-3-540-24669-5_103"},{"issue":"9","key":"1_CR19","doi-asserted-by":"publisher","first-page":"2261","DOI":"10.14778\/3598581.3598597","volume":"16","author":"X Chen","year":"2023","unstructured":"Chen, X., et al.: Leon: a new framework for ml-aided query optimization. VLDB Endowment 16(9), 2261\u20132273 (2023)","journal-title":"VLDB Endowment"},{"issue":"6","key":"1_CR20","doi-asserted-by":"publisher","first-page":"127:1","DOI":"10.1145\/3418896","volume":"53","author":"V Christophides","year":"2021","unstructured":"Christophides, V., Efthymiou, V., Palpanas, T., Papadakis, G., Stefanidis, K.: An overview of end-to-end entity resolution for big data. ACM Comput. Surv. 53(6), 127:1-127:42 (2021)","journal-title":"ACM Comput. Surv."},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Chu, X., Ilyas, I.F., Krishnan, S., Wang, J.: Data cleaning: overview and emerging challenges. In: International Conference on Management of Data (SIGMOD), pp. 2201\u20132206. ACM (2016)","DOI":"10.1145\/2882903.2912574"},{"key":"1_CR22","volume-title":"Data Mesh: Delivering Data-Driven Value at Scale","author":"Z Dehghani","year":"2022","unstructured":"Dehghani, Z.: Data Mesh: Delivering Data-Driven Value at Scale. O\u2019Reilly, Newton (2022). ISBN: 1492092398"},{"key":"1_CR23","unstructured":"DICOM. Dicom - digital imaging and communications in medicine. https:\/\/www.dicomstandard.org\/"},{"key":"1_CR24","volume-title":"Management of Heterogeneous and Autonomous Database Systems","author":"A Elmagarmid","year":"1999","unstructured":"Elmagarmid, A., Rusinkiewicz, M., Sheth, A.: Management of Heterogeneous and Autonomous Database Systems. Morgan Kaufmann Publishers, Burlington (1999). ISBN: 1-55860-216-X"},{"key":"1_CR25","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.jpdc.2023.02.007","volume":"176","author":"SA Errami","year":"2023","unstructured":"Errami, S.A., Hajji, H., Kadi, K.A.E., Badir, H.: Spatial big data architecture: from data warehouses and data lakes to the Lakehouse. J. Parallel Distrib. Comput. 176, 70\u201379 (2023)","journal-title":"J. Parallel Distrib. Comput."},{"key":"1_CR26","unstructured":"Fivetrain. Connectors for every data source. Accessed June 2023"},{"issue":"2","key":"1_CR27","doi-asserted-by":"publisher","first-page":"1402","DOI":"10.14778\/1687553.1687567","volume":"2","author":"E Friedman","year":"2009","unstructured":"Friedman, E., Pawlowski, P., Cieslewicz, J.: SQL\/MapReduce: a practical approach to self-describing, polymorphic, and parallelizable user-defined functions. VLDB Endowment 2(2), 1402\u20131413 (2009)","journal-title":"VLDB Endowment"},{"key":"1_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1007\/978-3-030-79382-1_23","volume-title":"Advanced Information Systems Engineering","author":"A Gillet","year":"2021","unstructured":"Gillet, A., Leclercq, \u00c9., Cullot, N.: Lambda+, the renewal of the lambda architecture: category theory to the rescue. In: La Rosa, M., Sadiq, S., Teniente, E. (eds.) CAiSE 2021. LNCS, vol. 12751, pp. 381\u2013396. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-79382-1_23"},{"key":"1_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2021.101957","volume":"108","author":"J Giovanelli","year":"2022","unstructured":"Giovanelli, J., Bilalli, B., Abell\u00f3, A.: Data pre-processing pipeline generation for AutoETL. Inf. Syst. 108, 101957 (2022)","journal-title":"Inf. Syst."},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Gro\u00dfe, P., May, N., Lehner, W.: A study of partitioning and parallel UDF execution with the SAP HANA database. In; Conference on Scientific and Statistical Database Management (SSDBM), p. 36 (2014)","DOI":"10.1145\/2618243.2618274"},{"key":"1_CR31","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/4472.001.0001","volume-title":"Materialized Views: Techniques, Implementations, and Applications","author":"A Gupta","year":"1999","unstructured":"Gupta, A., Mumick, I.S.: Materialized Views: Techniques, Implementations, and Applications. The MIT Press, Cambridge (1999)"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Hai, R., Koutras, C., Quix, C., Jarke, M.: Data lakes: a survey of functions and systems (2023)","DOI":"10.1109\/TKDE.2023.3270101"},{"key":"1_CR33","unstructured":"Halasipuram, R., Deshpande, P.M., Padmanabhan, S.: Determining essential statistics for cost based optimization of an ETL workflow. In: International Conference on Extending Database Technology (EDBT), pp. 307\u2013318 (2014)"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Harby, A.A., Zulkernine, F.: From data warehouse to Lakehouse: a comparative review. In: IEEE International Conference on Big Data, pp. 389\u2013395 (2022)","DOI":"10.1109\/BigData55660.2022.10020719"},{"key":"1_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1007\/978-3-030-59051-2_4","volume-title":"Database and Expert Systems Applications","author":"G Heidsieck","year":"2020","unstructured":"Heidsieck, G., de Oliveira, D., Pacitti, E., Pradal, C., Tardieu, F., Valduriez, P.: Distributed caching of scientific workflows in multisite cloud. In: Hartmann, S., K\u00fcng, J., Kotsis, G., Tjoa, A.M., Khalil, I. (eds.) DEXA 2020. LNCS, vol. 12392, pp. 51\u201365. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59051-2_4"},{"key":"1_CR36","doi-asserted-by":"publisher","first-page":"1076","DOI":"10.1016\/j.future.2017.07.003","volume":"86","author":"\u00c1B Hern\u00e1ndez","year":"2018","unstructured":"Hern\u00e1ndez, \u00c1.B., P\u00e9rez, M.S., Gupta, S., Munt\u00e9s-Mulero, V.: Using machine learning to optimize parallelism in big data applications. Future Gener. Comput. Syst. 86, 1076\u20131092 (2018)","journal-title":"Future Gener. Comput. Syst."},{"key":"1_CR37","unstructured":"Herodotou, H., et al.: Starfish: a self-tuning system for big data analytics. In: Conference on Innovative Data Systems Research CIDR, pp. 261\u2013272 (2011)"},{"key":"1_CR38","doi-asserted-by":"crossref","unstructured":"Hueske, F., et al.: Peeking into the optimization of data flow programs with mapreduce-style UDFs. In: International Conference on Data Engineering (ICDE), pp. 1292\u20131295 (2013)","DOI":"10.1109\/ICDE.2013.6544927"},{"issue":"11","key":"1_CR39","doi-asserted-by":"publisher","first-page":"1256","DOI":"10.14778\/2350229.2350244","volume":"5","author":"F Hueske","year":"2012","unstructured":"Hueske, F., et al.: Opening the black boxes in data flow optimization. VLDB Endowment 5(11), 1256\u20131267 (2012)","journal-title":"VLDB Endowment"},{"key":"1_CR40","unstructured":"IBM. IBM Cloud Pak for Data: Supported data sources. Accessed June 2023"},{"key":"1_CR41","unstructured":"IBM: Introduction to InfoSphere DataStage balanced optimization. Documentation. Accessed June 2023"},{"key":"1_CR42","unstructured":"Informatica: Pushdown optimization overview. Documentation. Accessed June 2023"},{"key":"1_CR43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-05153-5","volume-title":"Fundamentals of Data Warehouses","author":"M Jarke","year":"2003","unstructured":"Jarke, M., Lenzerini, M., Vassiliou, Y., Vassiliadis, P.: Fundamentals of Data Warehouses. Springer, Cham (2003). https:\/\/doi.org\/10.1007\/978-3-662-05153-5"},{"issue":"5","key":"1_CR44","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1007\/s42979-022-01287-7","volume":"3","author":"R Jemmali","year":"2022","unstructured":"Jemmali, R., Abdelh\u00e9di, F., Zurfluh, G.: Dltodw: transferring relational and NoSQL databases from a data lake. SN Comput. Sci. 3(5), 381 (2022)","journal-title":"SN Comput. Sci."},{"issue":"5","key":"1_CR45","doi-asserted-by":"publisher","first-page":"1203","DOI":"10.1109\/TKDE.2016.2515609","volume":"28","author":"P Jovanovic","year":"2016","unstructured":"Jovanovic, P., Romero, O., Simitsis, A., Abell\u00f3, A.: Incremental consolidation of data-intensive multi-flows. IEEE Trans. Knowl. Data Eng. 28(5), 1203\u20131216 (2016)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"6","key":"1_CR46","doi-asserted-by":"publisher","first-page":"927","DOI":"10.1016\/j.is.2012.12.001","volume":"38","author":"A Karagiannis","year":"2013","unstructured":"Karagiannis, A., Vassiliadis, P., Simitsis, A.: Scheduling strategies for efficient ETL execution. Inf. Syst. 38(6), 927\u2013945 (2013)","journal-title":"Inf. Syst."},{"key":"1_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1007\/978-3-031-12670-3_7","volume-title":"International Conference Big Data Analytics and Knowledge Discovery","author":"M Kechar","year":"2022","unstructured":"Kechar, M., Bellatreche, L.: Safeness: suffix arrays driven materialized view selection framework for large-scale workloads. In: Wrembel, R., Gamper, J., Kotsis, G., Tjoa, A.M., Khalil, I. (eds.) DaWaK 2022. Lecture Notes in Computer Science, vol. 13428, pp. 74\u201386. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-12670-3_7"},{"key":"1_CR48","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2019.101480","volume":"92","author":"N Konstantinou","year":"2020","unstructured":"Konstantinou, N., Paton, N.W.: Feedback driven improvement of data preparation pipelines. Inf. Syst. 92, 101480 (2020)","journal-title":"Inf. Syst."},{"key":"1_CR49","series-title":"Lecture Notes in Business Information Processing","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1007\/978-3-642-22970-1_6","volume-title":"Enabling Real-Time Business Intelligence","author":"N Kumar","year":"2011","unstructured":"Kumar, N., Kumar, P.S.: An efficient heuristic for logical optimization of ETL workflows. In: Castellanos, M., Dayal, U., Markl, V. (eds.) BIRTE 2010. LNBIP, vol. 84, pp. 68\u201383. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-22970-1_6"},{"issue":"1","key":"1_CR50","first-page":"60","volume":"43","author":"A Lerner","year":"2020","unstructured":"Lerner, A., Hussein, R., Ryser, A., Lee, S., Cudr\u00e9-Mauroux, P.: Networking and storage: the next computing elements in exascale systems? IEEE Data Eng. Bull. 43(1), 60\u201371 (2020)","journal-title":"IEEE Data Eng. Bull."},{"key":"1_CR51","doi-asserted-by":"crossref","unstructured":"Liu, X., Iftikhar, N.: An ETL optimization framework using partitioning and parallelization. In: ACM Symposium on Applied Computing, pp. 1015\u20131022 (2015)","DOI":"10.1145\/2695664.2695846"},{"key":"1_CR52","doi-asserted-by":"publisher","first-page":"40463","DOI":"10.1109\/ACCESS.2018.2858256","volume":"6","author":"AA Munshi","year":"2018","unstructured":"Munshi, A.A., Mohamed, Y.A.I.: Data lake lambda architecture for smart grids big data analytics. IEEE Access 6, 40463\u201340471 (2018)","journal-title":"IEEE Access"},{"issue":"12","key":"1_CR53","doi-asserted-by":"publisher","first-page":"1986","DOI":"10.14778\/3352063.3352116","volume":"12","author":"F Nargesian","year":"2019","unstructured":"Nargesian, F., Zhu, E., Miller, R.J., Pu, K.Q., Arocena, P.C.: Data lake management: challenges and opportunities. VLDB Endowment 12(12), 1986\u20131989 (2019)","journal-title":"VLDB Endowment"},{"issue":"1","key":"1_CR54","doi-asserted-by":"publisher","first-page":"71","DOI":"10.14778\/3357377.3357383","volume":"13","author":"M Owaida","year":"2019","unstructured":"Owaida, M., Alonso, G., Fogliarini, L., Hock-Koon, A., Melet, P.: Lowering the latency of data processing pipelines through FPGA based hardware acceleration. VLDB Endowment 13(1), 71\u201385 (2019)","journal-title":"VLDB Endowment"},{"key":"1_CR55","doi-asserted-by":"crossref","unstructured":"Popescu, A.D., Ercegovac, V., Balmin, A., Branco, M., Ailamaki, A.: Same queries, different data: can we predict runtime performance? In: Workshops @ International Conference on Data Engineering (ICDE), pp. 275\u2013280. IEEE Computer Society (2012)","DOI":"10.1109\/ICDEW.2012.66"},{"key":"1_CR56","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.is.2019.03.005","volume":"85","author":"A Quemy","year":"2019","unstructured":"Quemy, A.: Binary classification in unstructured space with hypergraph case-based reasoning. Inf. Syst. 85, 92\u2013113 (2019)","journal-title":"Inf. Syst."},{"issue":"4","key":"1_CR57","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1145\/3186728.3164140","volume":"11","author":"K Ramachandra","year":"2017","unstructured":"Ramachandra, K., Park, K., Emani, K.V., Halverson, A., Galindo-Legaria, C.A., Cunningham, C.: Froid: optimization of imperative programs in a relational database. VLDB Endowment 11(4), 432\u2013444 (2017)","journal-title":"VLDB Endowment"},{"key":"1_CR58","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.is.2015.04.002","volume":"52","author":"A Rheinl\u00e4nder","year":"2015","unstructured":"Rheinl\u00e4nder, A., Heise, A., Hueske, F., Leser, U., Naumann, F.: SOFA: an extensible logical optimizer for UDF-heavy data flows. Inf. Syst. 52, 96\u2013125 (2015)","journal-title":"Inf. Syst."},{"key":"1_CR59","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/978-3-030-59065-9_13","volume-title":"Big Data Analytics and Knowledge Discovery","author":"O Romero","year":"2020","unstructured":"Romero, O., Wrembel, R.: Data engineering for data science: two sides of the same coin. In: Song, M., Song, I.-Y., Kotsis, G., Tjoa, A.M., Khalil, I. (eds.) DaWaK 2020. LNCS, vol. 12393, pp. 157\u2013166. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59065-9_13"},{"key":"1_CR60","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1007\/978-3-7091-7555-2_52","volume-title":"Database and Expert Systems Applications","author":"M Rusinkiewicz","year":"1991","unstructured":"Rusinkiewicz, M., Czejdo, B., Embley, D.W.: An implementation model for muldidatabase queries. In: Karagiannis, D. (ed.) Database and Expert Systems Applications, pp. 309\u2013314. Springer-Verlag, Vienna (1991). https:\/\/doi.org\/10.1007\/978-3-7091-7555-2_52"},{"issue":"5","key":"1_CR61","doi-asserted-by":"publisher","first-page":"1119","DOI":"10.14778\/3510397.3510408","volume":"15","author":"M Sichert","year":"2022","unstructured":"Sichert, M., Neumann, T.: User-defined operators: efficiently integrating custom algorithms into modern databases. VLDB Endowment 15(5), 1119\u20131131 (2022)","journal-title":"VLDB Endowment"},{"key":"1_CR62","unstructured":"Sienkiewicz, M., Wrembel, R.: Managing data in a big financial institution: conclusions from a R&D project. In: Workshops of the EDBT\/ICDT Joint Conference, vol. 2841 (2021)"},{"key":"1_CR63","unstructured":"Simitsis, A., Skiadopoulos, S., Vassiliadis, P.: The history, present, and future of ETL technology (invited). In: International Workshop on Design, Optimization, Languages and Analytical Processing of Big Data (DOLAP), volume 3369 of CEUR Workshop Proceedings, pp. 3\u201312. CEUR-WS.org (2023)"},{"key":"1_CR64","unstructured":"Simitsis, A., Vassiliadis, P., Sellis, T.K.: Optimizing ETL processes in data warehouses. In: International Conference on Data Engineering (ICDE), pp. 564\u2013575. IEEE Computer Society (2005)"},{"issue":"10","key":"1_CR65","doi-asserted-by":"publisher","first-page":"1404","DOI":"10.1109\/TKDE.2005.169","volume":"17","author":"A Simitsis","year":"2005","unstructured":"Simitsis, A., Vassiliadis, P., Sellis, T.K.: State-space optimization of ETL workflows. IEEE Trans. Knowl. Data Eng. 17(10), 1404\u20131419 (2005)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"1_CR66","volume-title":"Data Management at Scale: Modern Data Architecture with Data Mesh and Data Fabric","author":"P Strengholt","year":"2023","unstructured":"Strengholt, P.: Data Management at Scale: Modern Data Architecture with Data Mesh and Data Fabric. O\u2019Reilly, Newton (2023). ISBN: 1098138864"},{"key":"1_CR67","doi-asserted-by":"crossref","unstructured":"Tan, R., Chirkova, R., Gadepally, V., Mattson, T.G.: Enabling query processing across heterogeneous data models: a survey. In: IEEE International Conference on Big Data, pp. 3211\u20133220 (2017)","DOI":"10.1109\/BigData.2017.8258302"},{"key":"1_CR68","series-title":"In Encyclopedia of Big Data Technologies","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-77525-8","volume-title":"ETL","author":"C Thomsen","year":"2019","unstructured":"Thomsen, C.: ETL. In Encyclopedia of Big Data Technologies, Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-319-77525-8"},{"key":"1_CR69","doi-asserted-by":"crossref","unstructured":"Tsesmelis, D., Simitsis, A.: Database optimizers in the era of learning. In: International Conference on Data Engineering (ICDE), pp. 3213\u20133216 (2022)","DOI":"10.1109\/ICDE53745.2022.00301"},{"key":"1_CR70","series-title":"Data-Centric Systems and Applications","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-65167-4","volume-title":"Data Warehouse Systems - Design and Implementation","author":"AA Vaisman","year":"2022","unstructured":"Vaisman, A.A., Zim\u00e1nyi, E.: Data Warehouse Systems - Design and Implementation. Data-Centric Systems and Applications, 2nd edn. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-662-65167-4","edition":"2"},{"issue":"3","key":"1_CR71","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1109\/2.121508","volume":"25","author":"G Wiederhold","year":"1992","unstructured":"Wiederhold, G.: Mediators in the architecture of future information systems. Computer 25(3), 38\u201349 (1992)","journal-title":"Computer"},{"key":"1_CR72","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.is.2019.01.006","volume":"82","author":"C Witt","year":"2019","unstructured":"Witt, C., Bux, M., Gusew, W., Leser, U.: Predictive performance modeling for distributed batch processing using black box monitoring and machine learning. Inf. Syst. 82, 33\u201352 (2019)","journal-title":"Inf. Syst."},{"key":"1_CR73","unstructured":"Zaharia, M., Ghodsi, A., Xin, R., Armbrust, M.: Lakehouse: a new generation of open platforms that unify data warehousing and advanced analytics. In: Conference on Innovative Data Systems Research (CIDR) (2021)"}],"container-title":["Lecture Notes in Computer Science","Database and Expert Systems Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-39847-6_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T12:25:35Z","timestamp":1710332735000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-39847-6_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031398469","9783031398476"],"references-count":73,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-39847-6_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"18 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DEXA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Database and Expert Systems Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Penang","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malaysia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dexa2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.dexa.org\/dexa2023","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EquinOCS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"155","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"49","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"35","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"32% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"For the workshops 7 full and 3 short papers have been accepted from 20 submissions","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}