Vietnam Journal of Computer Science

The new generation of industry, i.e. Industry 4.0, pertains to the processing of immense amounts of data, resulting, among other things, from the large-scale use of microcontrollers to control machines, an increase in the scale of automation, the use of the Internet of Things technology — e.g. in sensors installed at different stages of the production process, the implementation of the digital twin concept, and many other technologies designed to collect data (e.g. GPS or RFID). These data are collected in the enterprise’s variety of resources and databases. These data can be a valuable source of information and knowledge if the right approach to advanced data analysis is adopted, which depends, among other things, on the enterprise’s existing IT infrastructure. This paper sets out to present conclusions formulated on the basis of research consisting in the analysis of multinational manufacturing companies’ existing IT infrastructures. Three basic model solutions of IT architecture occurring in multi-site enterprises were identified, which made it possible to identify the main problems stemming from the IT architecture in place and concerning the analysis of data for the needs of company management. Additionally, this paper discusses the challenges faced by multi-site manufacturing companies. One such activity is the modification and expansion of the company’s IT infrastructure, including the implementation of Big Data and Master Data Management (MDM) solutions. The contribution provided by this paper consists in the analysis of the IT infrastructure in large, multi-site enterprises, which enabled the identification of problems and challenges related to advanced data analysis in this type of companies.

The COVID-19 is a global disease that occurred at the end of 2019 and it has shown its effects all over the world in a very short time. World Health Organization has mobilized all the countries of the world to survive with minimal damage from this outbreak. The situation in some countries was under control as their health infrastructure is robust enough. On the other hand, many countries suffered significant damage from the outbreak. The countries that have already taken their precautions have suffered less, Turkey is one of the leading countries. Besides taking precautions in advance, countries are guiding each other throughout the outbreak. Therefore, the countries leading the fight against the outbreak should be analyzed and each country should update its precautions to fight the outbreak. In this study, COVID-19 deaths are taken into account and similar countries to Turkey are identified by K-means clustering. Later, by comparing the various characteristics of Turkey with these similar countries, Turkey’s status in fighting the outbreak is revealed. The precautions Turkey took before the outbreak showed that Turkey can fight the COVID-19 outbreak successfully.

Along with the rapidly growing scale of relational database (RDB), how to construct domain-related ontologies from various databases effectively and efficiently has been a bottleneck of the ontology-based integration. The traditional methods for constructing ontology from RDB are mainly based on the manual mapping and transformation, which not only requires a lot of human experience but also easily leads to the semantic loss during the transformation. Ontology learning from RDB is a new paradigm to (semi-)automatically construct ontologies from RDB by borrowing the techniques of machine learning, it provides potential opportunities for integrating heterogeneous data from various data sources efficiently. This paper surveys the recent methods and tools of the ontology learning from RDB, and highlights the potential opportunities and challenges of using ontology learning in semantic information integration. Initially, the previous surveys on the topic of the ontology-based integration and ontology learning were summarized, and then the limitations of previous surveys were identified and analyzed. Furthermore, the methods and techniques of ontology learning from RDB were investigated by classifying into three categories: reverse engineering, mapping, and machine learning. Accordingly, the opportunities and possibility of using ontology learning from RDB in semantic information integration were discussed based on the mapping results between the bottlenecks of ontology-based integration and the features of ontology learning.

In this investigation, state vector estimation of the Permanent Magnet Synchronous machine (PMSM) using the nonlinear Kalman estimator (Extended Kalman Filter) is considered. The considered states are the speed of the rotor, its angular position, the torque of the load and the resistance of the stator. Since the extended Kalman filter contains some free parameters, it will be necessary to optimize them in order to obtain a better efficiency. The free parameters of EKF are the covariance matrices of state noise and measurement noise. These later will be auto adjusted by a new metaheuristic optimization technique called Biogeographical-based optimization (BBO). As far as we know, BBO–EKF optimization for PMSM state was not treated in the literature. The suggested estimation tuning approach is demonstrated using a computer simulation of a PMSM. Simulated experimentations show the robustness and effectiveness of the proposed scheme. In addition, a detailed comparative study with conventional methods like Particle Swarm Optimization and Genetic Algorithms will be given.

For many years now, the mining industry has seen a boost in exploring and developing the systems for monitoring operational parameters of mining machines, in particular load-haul-dump machines. Therefore, further researches on algorithmics have also advanced dynamically regarding effective performance management as well as predictive maintenance. Nonetheless, the issue of road conditions is still being neglected. That issue has a substantial impact on both the overall operator’s convenience, their performance, and machinery reliability, especially its construction node and tire damages. Moreover, such negligence pertains also to the maintenance of mine infrastructure, including the network of passages. The paper explains the use of the portable inertial measurement unit (IMU) in evaluating road conditions in the deep underground mine. The detailed descriptions of the road quality classification procedure and bump detection have been included. The paper outlines the basic method of tracking the motion trajectory of vehicles and suggests the method of visualization of the results of the road conditions evaluation. This paper covers the sample results collected by the measurements unit in the deep underground mine during six experiments. This paper is an extended version of a paper presented at the ACIIDs 2020 conference [P. Stefaniak, D. Gawelski, S. Anufriiev and P. Śliwiński, Road-quality classification and motion tracking with inertial sensors in the deep underground mine, Asian Conference on Intelligent Information and Database Systems, March 2020, Springer, Singapore, pp. 168–178].

Virtual restoration of digital copies of the human documental heritage is crucial for facilitating both the traditional work of philologists and paleographers and the automatic analysis of the contents. Here we propose a practical and fast procedure for the correction of the typically complex background of recto–verso historical manuscripts. The procedure has two main, distinctive features: it does not need for a preliminary registration of the two page sides, and it is non-invasive, as it does not alter the original appearance of the manuscript. This makes it suitable for the routinary use in the archives, and permits an easier fruition of the manuscripts, without any information being lost. In the first stage, the detection of both the primary text and the spurious strokes is performed via soft segmentation, based on the statistical decorrelation of the two recto and verso images. In the second stage, the noisy pattern is substituted with pixels that simulate the texture of the clean surrounding background, through an efficient technique of image inpainting. As shown in the experimental results, evaluated both qualitatively and quantitatively, the proposed procedure is able to perform a fine and selective removal of the degradation, while preserving other informative marks of the manuscript history.