In the field of predicting the remaining useful lifetime (RUL) of equipment based on health indicators (HIs), the effective extraction of equipment status poses a persistent challenge. Numerous studies have focused on the extraction of HI of an equipment, frequently proposing training methods that utilize one-dimensional latent space autoencoders for computing the loss function with HI. This was imperative due to the compositional nature of HIs are real numbers. However, in cases where equipment status exhibits nonlinear and intricate structuring, the latent vector necessitates representation within a sufficiently expansive space. This paper introduces a methodology for mapping real numbers to higher dimensions to achieve a more efficient representation of HI. Upon applying our proposed methodology to various HI extraction models, we observed that in most instances, the performance of HI extraction was enhanced. Ultimately, this contributed to an improvement in the prediction accuracy to RUL. The efficacy of our learning mechanism was validated across four subsets (FD001 to FD004) of the C-MAPSS dataset provided by NASA. Notably, the methodology presented in this study holds significance as a learning mechanism adaptable to various approaches.

Time-series forecasting (TSF) is a traditional problem in the field of artificial intelligence, and models such as recurrent neural network, long short-term memory, and gate recurrent units have contributed to improving its predictive accuracy. Furthermore, model structures have been proposed to combine time-series decomposition methods such as seasonal-trend decomposition using LOESS. However, this approach is learned in an independent model for each component, and therefore, it cannot learn the relationships between the time-series components. In this study, we propose a new neural architecture called a correlation recurrent unit (CRU) that can perform time-series decomposition within a neural cell and learn correlations (autocorrelation and correlation) between each decomposition component. The proposed neural architecture was evaluated through comparative experiments with previous studies using four univariate and four multivariate time-series datasets. The results showed that long- and short-term predictive performance was improved by more than 10%. The experimental results indicate that the proposed CRU is an excellent method for TSF problems compared to other neural architectures.

Metric learning as a service (MLaaS) represents one of the main learning streams to handle complex datasets in service computing research communities and industries. A common approach for dealing with high-dimensional and complex datasets is employing a feature embedding algorithm to compress data through dimension reduction while optimizing intra-class distance. To create generalizable MLaaS for high-performance artificial intelligence applications with high-dimensional Big Data, a robust and meaningful embedding space representation by efficiently optimizing both intra-class and inter-class relationships is required. We developed a novel MLaaS methodology that incorporates covariance to signify the direction of the linear relationship between data points in an embedding space. Our covariance-based feature embedding architecture introduces three different yet complementary mapping functions: inner-class mapping, intra-class with semi-inter-class mapping, and intra- and inter-class mapping. Unlike conventional metric learning, our covariance-embedding-enhanced approach is more expressive and explainable for computing similar or dissimilar measures and can capture positive, negative, or neutral relationships. Our MLaaS framework ensures efficient, composable, and extensible metric learning by supporting the selection of dimension reduction and data compression methods. Experiments conducted using various benchmark datasets demonstrate that the proposed model can obtain higher-quality, more separable, and more expressive embedding representations than existing models.

In most computing services, imperfect event logs with missing events are generated for a variety of reasons. Because missing events in imperfect event logs adversely affect the results of process mining analysis, it is essential to handle them effectively. Most existing process mining studies focus on methodologies for generation of good process models, very few methodologies, in fact, have been developed to deal with missing events. To the best of our knowledge, there is a lack of high-performance methods for restoration of missing events in actual event log data. In this paper, we propose a new categorical event imputation method that can restore missing categorical events by learning the structural features between observed events in the event log. We evaluated the proposed method by way of comparative experiments with previous studies using six real datasets, and the results demonstrate that the restoration performance was greatly improved and that thereby, our proposed method can significantly improve both the quality of event logs (specifically by restoring missing events in imperfect event logs) and the overall quality of process mining analysis.

This paper proposes a new hybrid framework called the Time-series Decomposition and Two-stage Attention (TDTA) for the long-term forecasting of container volume. Forecasting the container volume is essential for supporting portfolio decisions about port facility investment plans and port operation plans. This framework includes time-series decomposition to deconstruct time-series into several components (trend, seasonality, and residual), a two-stage attention mechanism that assigns priority to important variables to increase long-term prediction accuracy, and a long short-term memory network that predicts each component and then aggregates all components to derive the final output. In an experiment, the container volume was predicted after six months using the proposed method and compared to the method used in previous studies. The TDTA achieved a better predictive performance than the existing time-series models used in previous studies. Hence, our proposed method can help in decision-making through accurate long-term predictions of container volume, and can also help with the long-term prediction of other time-series data.

The event log recorded through an information system may be missing for various reasons, which fact may result in an imperfect event log. Performing analyses using such an imperfect event log can seriously affect the quality of the obtained results. Therefore, analyses should be performed only after processing of the missing part in the imperfect event log. In the fields of data mining and statistical analysis, various methodologies have been developed to handle data with missing values, but there are not many studies dealing with incomplete event logs that have missing data in the field of process mining. In this paper, we propose a likelihood-based Multiple Imputation by Event Chain (MIEC) method for dealing with imperfect event logs with missing data. An experiment was performed using sample event logs, and a case study was conducted using a real steel manufacturing event log to verify our method. We expect the proposed method to repair the imperfect event log to a high level and to obtain analysis result with high quality even if there are many missing data.

In Big data and IoT environments, process execution generates huge-sized data some of which is subsequently obtained by sensors. The main issue in such areas has been the necessity of analyzing data in order to suggest enhancements to processes. In this regard, evaluation of process model conformance to the execution log is of great importance. For this purpose, previous reports on process mining approaches have advocated conformance checking by fitness measure, which is a process that uses token replay and node-arc relations based on Petri net. However, fitness measure so far has not considered statistical significance, but just offers a numeric ratio. We herein propose a statistical verification method based on the Kolmogorov–Smirnov (K–S) test to judge whether two different log datasets follow the same process model. Our method can be easily extended to determinations that process execution actually follows a process model, by playing out the model and generating event log data from it. Additionally, in order to solve the problem of the trade-off between model abstraction and process conformance, we also propose the new concepts of Confidence Interval of Abstraction Value (CIAV) and Maximum Confidence Abstraction Value (MCAV). We showed that our method can be applied to any process mining algorithm (e.g. heuristic mining, fuzzy mining) that has parameters related to model abstraction. We expect that our method will come to be widely utilized in many applications dealing with business process enhancement involving process-model and execution-log analyses.

Key resources are important, influential and powerful performers in a social network structure. Identifying them in the social network of a business process activity is beneficial and rewarding. One of the most effective centrality measures for identification of the key nodes in a social network is to rank resources based on a selection of criteria. PageRank is a representative example of such algorithms, which was first utilized in the Google search engine in 1998. However, the PageRank approach merely assumes a single link as a vote, which allows one originator to link or transfer his work to others more than once in a handover work scenario. We argue that this problem can lead to inaccurate influence based ranking in the context of business processes for resources in a social network. In this paper, we propose f-PageRank, a new approach specifically designed to identify the key resources in a social network generated from a business process activity. We evaluate our proposed method by comparing it with the existing approaches in process mining tools, such as degree centrality, betweenness centrality, BaryRanker, and HITS. The experimental results show that our approach can obtain a satisfying outcome.

Changes in recent business environments have created the necessity for a more efficient and effective business process management. The workflow management system is software that assists in defining business processes as well as automatically controlling the execution of the processes. We propose a new approach to the automatic execution of business processes using event-condition-action (ECA) rules that can be automatically triggered by an active database. First of all, we propose the concept of blocks that can classify process flows into several patterns. A block is a minimal unit that can specify the behaviors represented in a process model. An algorithm is developed to detect blocks from a process definition network and transform it into a hierarchical tree model. The behaviors in each block type are modeled using ACTA formalism. This provides a theoretical basis from which ECA rules are identified. The proposed ECA rule-based approach shows that it is possible to execute the workflow using the active capability of database without users' intervention. The operation of the proposed methods is illustrated through an example process.