A systematic literature review on state-of-the-art deep learning methods for process prediction

AbstractProcess mining enables the reconstruction and evaluation of business processes based on digital traces in IT systems. An increasingly important technique in this context is process prediction. Given a sequence of events of an ongoing trace, process prediction allows forecasting upcoming events or performance measurements. In recent years, multiple process prediction approaches have been proposed, applying different data processing schemes and prediction algorithms. This study focuses on deep learning algorithms since they seem to outperform their machine learning alternatives consistently. Whilst having a common learning algorithm, they use different data preprocessing techniques, implement a variety of network topologies and focus on various goals such as outcome prediction, time prediction or control-flow prediction. Additionally, the set of log-data, evaluation metrics and baselines used by the authors diverge, making the results hard to compare. This paper attempts to synthesise the advantages and disadvantages of the procedural decisions in these approaches by conducting a systematic literature review.

Download Full-text

A Systematic Literature Review of Multi-Criteria Decision-Making Methods for Sustainable Selection of Insulation Materials in Buildings

Sustainability ◽

10.3390/su13020737 ◽

2021 ◽

Vol 13 (2) ◽

pp. 737

Author(s):

Indre Siksnelyte-Butkiene ◽

Dalia Streimikiene ◽

Tomas Balezentis ◽

Virgilijus Skulskis

Keyword(s):

Decision Making ◽

Literature Review ◽

Systematic Literature Review ◽

Energy Demand ◽

Energy Performance ◽

Future Research ◽

Multi Criteria Decision Making ◽

Insulation Materials ◽

Advantages And Disadvantages ◽

Selection Of

The European Commission has recently adopted the Renovation Wave Strategy, aiming at the improvement of the energy performance of buildings. The strategy aims to at least double renovation rates in the next ten years and make sure that renovations lead to higher energy and resource efficiency. The choice of appropriate thermal insulation materials is one of the simplest and, at the same time, the most popular strategies that effectively reduce the energy demand of buildings. Today, the spectrum of insulation materials is quite wide, and each material has its own specific characteristics. It is recognized that the selection of materials is one of the most challenging and difficult steps of a building project. This paper aims to give an in-depth view of existing multi-criteria decision-making (MCDM) applications for the selection of insulation materials and to provide major insights in order to simplify the process of methods and criteria selection for future research. A systematic literature review is performed based on the Search, Appraisal, Synthesis and Analysis (SALSA) framework and the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement. In order to determine which MCDM method is the most appropriate for different questions, the main advantages and disadvantages of different methods are provided.

Download Full-text

Process Mining Perspectives in Software Engineering: A Systematic Literature Review

10.1109/enc53357.2021.9534824 ◽

2021 ◽

Author(s):

Silvia Jaqueline Urrea-Contreras ◽

Brenda L. Flores-Rios ◽

Maria Angelica Astorga-Vargas ◽

Jorge E. Ibarra-Esquer

Keyword(s):

Software Engineering ◽

Literature Review ◽

Systematic Literature Review ◽

Process Mining

Download Full-text

EEG signal analysis using deep learning: A systematic literature review

10.1109/icds53782.2021.9626707 ◽

2021 ◽

Author(s):

Ghita Amrani ◽

Amina Adadi ◽

Mohammed Berrada ◽

Zouhayr Souirti ◽

Said Boujraf

Keyword(s):

Deep Learning ◽

Literature Review ◽

Systematic Literature Review ◽

Signal Analysis ◽

Eeg Signal ◽

Eeg Signal Analysis

Download Full-text

A systematic literature review of deep learning neural network for time series air quality forecasting

Environmental Science and Pollution Research ◽

10.1007/s11356-021-17442-1 ◽

2021 ◽

Author(s):

Nur’atiah Zaini ◽

Lee Woen Ean ◽

Ali Najah Ahmed ◽

Marlinda Abdul Malek

Keyword(s):

Neural Network ◽

Time Series ◽

Deep Learning ◽

Air Quality ◽

Literature Review ◽

Systematic Literature Review ◽

Deep Learning Neural Network ◽

Air Quality Forecasting

Download Full-text

Deep Learning in Smart Video Surveillance for Crowd Management: A Systematic Literature Review

10.1145/3473141.3473240 ◽

2021 ◽

Author(s):

Andrea Camille Garcia ◽

Jealine Eleanor Gorre ◽

Joshua Angelo Karl Perez ◽

Mary Jane Samonte

Keyword(s):

Deep Learning ◽

Literature Review ◽

Video Surveillance ◽

Systematic Literature Review ◽

Crowd Management

Download Full-text

Research and Implementation of the Text Matching Algorithm in the Field of Housing Law and Policy Based on Deep Learning

Complexity ◽

10.1155/2021/3165600 ◽

2021 ◽

Vol 2021 ◽

pp. 1-9

Author(s):

Yin Xu ◽

Hong Ma

Keyword(s):

Deep Learning ◽

Affordable Housing ◽

Legal System ◽

Learning Algorithm ◽

Matching Algorithm ◽

Advantages And Disadvantages ◽

Housing Security ◽

Law And Policy ◽

Depth Learning ◽

Text Matching

Machine learning enables machines to learn rules from a large amount of data input from the outside world through algorithms, so as to identify and judge. It is the main task of the government to further emphasize the importance of improving the housing security mechanism, expand the proportion of affordable housing, increase financial investment, improve the construction quality of affordable housing, and ensure fair distribution. It can be seen that the legal system of housing security is essentially a system to solve the social problems brought by housing marketization, and it is an important part of the whole national housing system. More and more attention has been paid to solving the housing difficulties of low- and middle-income people and establishing a housing security legal system suitable for China’s national conditions and development stage. Aiming at the deep learning problem, a text matching algorithm suitable for the field of housing law and policy is proposed. Classifier based on matching algorithm is a promising classification technology. The research on the legal system of housing security is in the exploratory stage, involving various theoretical and practical research studies. Compare the improved depth learning algorithm with the general algorithm, so as to clearly understand the advantages and disadvantages of the improved depth learning algorithm and depth learning algorithm. This paper introduces the practical application of the deep learning model and fast learning algorithm in detail. Creatively put forward to transform it into an independent public law basis or into an independent savings system.

Download Full-text

How is process mining technology used by organizations? A systematic literature review of empirical studies

Business Process Management Journal ◽

10.1108/bpmj-06-2017-0148 ◽

2018 ◽

Vol 24 (4) ◽

pp. 900-922 ◽

Cited By ~ 8

Author(s):

Malte Thiede ◽

Daniel Fuerstenau ◽

Ana Paula Bezerra Barquet

Keyword(s):

Literature Review ◽

Systematic Literature Review ◽

Enterprise Resource Planning ◽

Process Mining ◽

Empirical Studies ◽

Resource Planning ◽

Classification Model ◽

Organizational Process ◽

Content Type ◽

Cross System

Purpose The purpose of this paper is to review empirical studies on process mining in order to understand its use by organizations. The paper further aims to outline future research opportunities. Design/methodology/approach The authors propose a classification model that combines core conceptual elements of process mining with prior models from technology classification from the enterprise resource planning and business intelligence field. The model incorporates an organizational usage, a system-orientation and service nature, adding a focus on physical services. The application is based on a systematic literature review of 144 research papers. Findings The results show that, thus far, the literature has been chiefly concerned with realization of single business process management systems in single organizations. The authors conclude that cross-system or cross-organizational process mining is underrepresented in the ISR, as is the analysis of physical services. Practical implications Process mining researchers have paid little attention to utilizing complex use cases and mining mixed physical-digital services. Practitioners should work closely with academics to overcome these knowledge gaps. Only then will process mining be on the cusp of becoming a technology that allows new insights into customer processes by supplying business operations with valuable and detailed information. Originality/value Despite the scientific interest in process mining, particularly scant attention has been given by researchers to investigating its use in relatively complex scenarios, e.g., cross-system and cross-organizational process mining. Furthermore, coverage on the use of process mining from a service perspective is limited, which fails to reflect the marketing and business context of most contemporary organizations, wherein the importance of such scenarios is widely acknowledged. The small number of studies encountered may be due to a lack of knowledge about the potential of such scenarios as well as successful examples, a situation the authors seek to remedy with this study.

Download Full-text