Building robust industrial machine learning (ML) models requires incorporating domain knowledge in feature selection. This ensures building meaningful ML models that fit the context of the industrial process that consists of complex networks of thousands of elements interconnected by flows of material, energy, and information. Despite the various automatic feature selection methods, they are still outperformed by the manual feature selection that embeds the industrial domain knowledge. This paper proposes an industrial feature selection method that (1) automatically captures domain knowledge from topology models holding information on the industrial plant and (2) identifies the relevant process signals (i.e., features) to a specified process element (i.e., to which an ML model is being built). We performed an empirical case study on an industrial use case to evaluate the effectiveness and efficiency of the proposed method in comparison to existing ones from literature.
{"title":"TopSelect","authors":"Hadil Abukwaik, L. Šula, Pablo Rodríguez","doi":"10.1145/3522664.3528618","DOIUrl":"https://doi.org/10.1145/3522664.3528618","url":null,"abstract":"Building robust industrial machine learning (ML) models requires incorporating domain knowledge in feature selection. This ensures building meaningful ML models that fit the context of the industrial process that consists of complex networks of thousands of elements interconnected by flows of material, energy, and information. Despite the various automatic feature selection methods, they are still outperformed by the manual feature selection that embeds the industrial domain knowledge. This paper proposes an industrial feature selection method that (1) automatically captures domain knowledge from topology models holding information on the industrial plant and (2) identifies the relevant process signals (i.e., features) to a specified process element (i.e., to which an ML model is being built). We performed an empirical case study on an industrial use case to evaluate the effectiveness and efficiency of the proposed method in comparison to existing ones from literature.","PeriodicalId":378109,"journal":{"name":"Proceedings of the 1st International Conference on AI Engineering: Software Engineering for AI","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121639702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
DevOps practices have increasingly been applied to software development and engineering, as well as the machine learning lifecycle – in a process also known as MLOps. Today, many companies and professionals have been working and writing on this topic. However, in the academic and scientific literature, few results can be found on MLOps and how to implement it efficiently. This paper presents five essential steps to guide the understanding and practice of MLOps, which, based on the authors’ research and experience, can assist in its effective implementation. The study aims to serve as a reference guide for all those who wish to learn more about the topic and intend to implement MLOps practices in the development of their systems. CCS CONCEPTS • Software and its engineering → Software creation and management; • Computing methodologies → Machine learning.
{"title":"MLOps","authors":"B. M. A. Matsui, D. Goya","doi":"10.1145/3522664.3528611","DOIUrl":"https://doi.org/10.1145/3522664.3528611","url":null,"abstract":"DevOps practices have increasingly been applied to software development and engineering, as well as the machine learning lifecycle – in a process also known as MLOps. Today, many companies and professionals have been working and writing on this topic. However, in the academic and scientific literature, few results can be found on MLOps and how to implement it efficiently. This paper presents five essential steps to guide the understanding and practice of MLOps, which, based on the authors’ research and experience, can assist in its effective implementation. The study aims to serve as a reference guide for all those who wish to learn more about the topic and intend to implement MLOps practices in the development of their systems. CCS CONCEPTS • Software and its engineering → Software creation and management; • Computing methodologies → Machine learning.","PeriodicalId":378109,"journal":{"name":"Proceedings of the 1st International Conference on AI Engineering: Software Engineering for AI","volume":"193 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114359032","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
E. J. Husom, Simeon Tverdal, Arda Goknil, Sagar Sen
Manufacturing has enabled the mechanized mass production of the same (or similar) products by replacing craftsmen with assembly lines of machines. The quality of each product in an assembly line greatly hinges on continual observation and error compensation during machining using sensors that measure quantities such as position and torque of a cutting tool and vibrations due to possible imperfections in the cutting tool and raw material. Patterns observed in sensor data from a (near-)optimal production cycle should ideally recur in subsequent production cycles with minimal deviation. Manually labeling and comparing such patterns is an insurmountable task due to the massive amount of streaming data that can be generated from a production process. We present UDAVA, an unsupervised machine learning pipeline that automatically discovers process behavior patterns in sensor data for a reference production cycle. UDAVA performs clustering of reduced dimensionality summary statistics of raw sensor data to enable high-speed clustering of dense time-series data. It deploys the model as a service to verify batch data from subsequent production cycles to detect recurring behavior patterns and quantify deviation from the reference behavior. We have evaluated UDAVA from an AI Engineering perspective using two industrial case studies.
{"title":"UDAVA","authors":"E. J. Husom, Simeon Tverdal, Arda Goknil, Sagar Sen","doi":"10.1145/3522664.3528603","DOIUrl":"https://doi.org/10.1145/3522664.3528603","url":null,"abstract":"Manufacturing has enabled the mechanized mass production of the same (or similar) products by replacing craftsmen with assembly lines of machines. The quality of each product in an assembly line greatly hinges on continual observation and error compensation during machining using sensors that measure quantities such as position and torque of a cutting tool and vibrations due to possible imperfections in the cutting tool and raw material. Patterns observed in sensor data from a (near-)optimal production cycle should ideally recur in subsequent production cycles with minimal deviation. Manually labeling and comparing such patterns is an insurmountable task due to the massive amount of streaming data that can be generated from a production process. We present UDAVA, an unsupervised machine learning pipeline that automatically discovers process behavior patterns in sensor data for a reference production cycle. UDAVA performs clustering of reduced dimensionality summary statistics of raw sensor data to enable high-speed clustering of dense time-series data. It deploys the model as a service to verify batch data from subsequent production cycles to detect recurring behavior patterns and quantify deviation from the reference behavior. We have evaluated UDAVA from an AI Engineering perspective using two industrial case studies.","PeriodicalId":378109,"journal":{"name":"Proceedings of the 1st International Conference on AI Engineering: Software Engineering for AI","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114625712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Proceedings of the 1st International Conference on AI Engineering: Software Engineering for AI","authors":"","doi":"10.1145/3522664","DOIUrl":"https://doi.org/10.1145/3522664","url":null,"abstract":"","PeriodicalId":378109,"journal":{"name":"Proceedings of the 1st International Conference on AI Engineering: Software Engineering for AI","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123042785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：