https://www.scholarchain.eu/ser/issue/feed Software Engineering Review 2021-04-09T22:43:41+00:00 David Fisher david.fisher@webofopenscience.com Open Journal Systems <div id="i4c-draggable-container" style="position: fixed; z-index: 1499; width: 0px; height: 0px;"> <div class="resolved" style="all: initial;" data-reactroot="">&nbsp;</div> </div> <p>Software Engineering Review is interested in well-defined theoretical results and empirical studies that have potential impact on the construction, analysis, or management of software. The scope of this Transactions ranges from the mechanisms through the development of principles to the application of those principles to specific environments.</p> <div id="i4c-dialogs-container">&nbsp;</div> <div id="i4c-dialogs-container">&nbsp;</div> <div id="i4c-dialogs-container">&nbsp;</div> <div id="i4c-dialogs-container">&nbsp;</div> <div id="i4c-dialogs-container">&nbsp;</div> <div id="i4c-dialogs-container">&nbsp;</div> <div id="i4c-dialogs-container">&nbsp;</div> <div id="i4c-dialogs-container">&nbsp;</div> <div id="i4c-dialogs-container">&nbsp;</div> <div id="tap-translate">&nbsp;</div> <div id="i4c-dialogs-container">&nbsp;</div> https://www.scholarchain.eu/ser/article/view/60 System architecture for maintenance of complex distributed systems 2021-04-09T22:43:41+00:00 Nikolay Raychev nikolay.raychev@vumk.eu <p>This document addresses the key elements for implementing the PdM strategy. As a result, an architecture for predictable maintenance of complex multi-object systems in the Industry 4.0 concept has been proposed. The proposed system includes three modules: a module for offline analysis of accumulated data, a module for online analysis of flow data and a module for solution support. The main functions of the first two modules are early detection and prediction of equipment failure based on machine learning methods. Based on the information obtained from the online analysis module, the solution support module generates optimal solutions when choosing a strategy for influencing the equipment, if necessary. Properly designed equipment maintenance strategy plays a critical role in today's economic conditions, characterized by crisis phenomena and a high level of competition. Recently, as part of the implementation of Industry 4.0's concept in the maintenance of complex multi-object systems, the most promising approaches are based on the use of advanced big data analysis methods based on innovative artificial intelligence technologies. It is mainly about the concept of predictable maintenance (PdM), namely the creation of predictive models to prevent equipment damage. This maintenance strategy allows us to move from time-based maintenance to condition-based maintenance, taking into account the forecast for changes in system conditions, in order to achieve their maximum characteristics at minimum cost. the most promising approaches are based on the use of advanced big data analysis methods based on innovative artificial intelligence technologies. It is mainly about the concept of predictable maintenance (PdM), namely the creation of predictive models to prevent equipment damage</p> <div id="tap-translate">&nbsp;</div> 2020-07-16T13:01:44+00:00 Copyright (c) 2020 Nikolay Raychev https://www.scholarchain.eu/ser/article/view/77 A Graph-based Evolutionary Algorithm for Automated Machine Learning 2021-04-09T22:43:17+00:00 Fei Qi fei@gmail.com Zhaohui Xia fei@gmail.com Gaoyang Tang fei@gmail.com Hang Yang fei@gmail.com Yu Song fei@gmail.com Guangrui Qian fei@gmail.com Xiong An fei@gmail.com Chunhuan Lin fei@gmail.com Guangming Shi fei@gmail.com <p>As an emerging field, Automated Machine Learning (AutoML) aims to reduce or eliminate manual operations that require expertise in machine learning. In this paper, a graph-based architecture is employed to represent flexible combinations of ML models, which provides a large searching space compared to tree-based and stacking-based architectures. Based on this, an evolutionary algorithm is proposed to search for the best architecture, where the mutation and heredity operators are the key for architecture evolution. With Bayesian hyper-parameter optimization, the proposed approach can automate the workflow of machine learning. On the PMLB dataset, the proposed approach shows the state-of-the-art performance compared with TPOT, Autostacker, and auto-sklearn. Some of the optimized models are with complex structures which are difficult to obtain in manual design</p> <div id="tap-translate">&nbsp;</div> 2020-12-10T09:30:15+00:00 Copyright (c) 2020 Fei Qi, Zhaohui Xia, Gaoyang Tang, Hang Yang, Yu Song, Guangrui Qian, Xiong An, Chunhuan Lin, Guangming Shi