Portal de Periódicos da CAPES

Editorial of the special issue from WorldCIST' 20

2022; Wiley; Volume: 40; Issue: 1 Linguagem: Inglês

10.1111/exsy.13164

1468-0394

Álvaro Rocha, Simona Riurean,

Big Data and Business Intelligence

The world, as we know it, is changing every day thanks to intensive research in fields such as expert systems, and the unexpected discoveries that influence our daily life and habits. Researchers develop more and more innovative concepts and novel paradigms, outstanding technologies that become mature and are launched on the market ‘in a blink of an eye’ with applications in a large number of fields of activities. Smart devices with these novel technologies embedded have become inseparable partners with humans. The knowledge incorporated in advanced programs assist humans in solving difficult problems and taking fast and smart decisions with applications in many areas, starting from industry, healthcare, agriculture, education and many more. In this special issue, we present a range of papers covering some of the subareas of expert systems such as intelligent and decision support systems, ethics, computers, linear regression and big data analytics. This special issue comprises six research papers. All manuscripts are extended versions of selected papers from WorldCIST'20—8th World Conference on Information Systems and Technologies, held in Budva, Montenegro between 7 and 10 April 2020. The WorldCIST conference is already a well-known global forum for researchers and practitioners to present and discuss the most recent innovations, trends, results, experiences and concerns in several areas of Information Systems and Technologies, as well as computer science in general. The six selected papers in this special section include a study that identifies the main factors that can explain the number of patent filing requests made by residents in Brazil, the United States and Europe, detect if an information visualization can be potentially confusing and misunderstood based on the analytic task, a method to predict a model's performance metrics before it is trained, in order to decide whether it is worth to train it or not, a novel orca cultural algorithm, introduces the paradigm of machine culture as an extension to machine intelligence, and a decision model to take care of the water requirement of sensitive crops of agriculture industry. Sousa et al. (2020) present a study that identifies the main factors that can explain the number of patent filing requests made by residents in Brazil, the United States, Europe and triadic patent families. The methods used in the research are quantitative, using big data from private and public investments in Science and Technology, and about patent deposit numbers in Brazil from 2000 to 2017. A model of linear regression was performed and explains how these investments in Science and Technology influence patent deposit numbers. The results of this research study point towards the importance of universities, up and beyond the traditional training and education. The importance of public and private innovation investments is also shown to be important. This study shows that the patent registrations in the different regions under analysis are affected by different factors. There is thus no single formula towards the creation of innovation output and governments would do well to continue to invest in higher education while also investing in public research and development activities. Additionally, and not least important, private entities should be continually encouraged to make innovation investments and favourable government policies need to thus exist for this to happen. Finally, the low numbers regarding patent filings in Brazil may be linked to institutional deficiencies in the country. Patent breaches may be difficult to punish, and the judicial system may be slow and untrustworthy, compared with the United States and Europe—leading to diminished patent registrations in Brazil. Vázquez-Ingelmo et al. (2020), using the machine learning technique, search to find the possibility to detect if an information visualization can be potentially confusing and misunderstood based on the analytic task it tries to support. This approach is supported by fine-grained features identified through domain engineering and meta modelling on the information visualization and dashboards domain. Data visualizations encode data through different visual features, which have been captured and structured through a meta-modelling approach. The identified features were employed to automatically generate a set of parameterized visualizations that were subsequently discussed through a tagging process to obtain a training dataset of ‘helpful/not helpful’ information visualizations. Finally, the resulting dataset was employed to train ML algorithms that classify information visualizations as helpful or not helpful given their features and supported analytic task. The experiment shows promising results as the viability of the approach has been tested through a proof-of-concept in the domain of visualizations that display tri-variate datasets with the goal of identifying correlation among their variables. Although some limitations were identified, this experiment can set the foundations for subsequent research on this domain. Carneiro et al. (2020) present in this paper a method to predict a model's performance metrics before it is trained, in order to decide whether it is worth to train it or not. To see if the model proposed holds significantly better results than the current one, the authors propose the use of meta-learning. Therefore, two different meta-models are evaluated: one built for a specific machine learning problem, and another one built based on many different problems, meant to be a generic meta-model, applicable to virtually any problem. The focus is on the prediction of the root mean square error (RMSE). Results show that it is possible to accurately predict the RMSE of future models, event in streaming scenarios. Moreover, results also show that it is possible to reduce the need for re-training models between 60% and 98%, depending on the problem and on the threshold used. Drias et al. (2020) introduce in this article the paradigm of machine culture as an extension to machine intelligence. This new concept is modelled based on animal intelligence and culture. The example of orca intelligence and culture is considered as orcas possess in addition to skills allowing them to reach preys, the ability to transmit their culture from generation to generation. The orca intelligence is studied and then simulated to design an algorithm called Orca Algorithm (OA). OA consists in modelling the orca lifestyle and in particular the orca's social organization, echolocation behaviour and hunting techniques. In order to integrate the cultural dimension, OA was hybridized with the Cultural Algorithm (CA) to get an algorithm called Orca Cultural Algorithm (OCA). OCA was tested on 22 benchmark problems of the literature to evaluate its performance. Extensive experiments were first performed to set the algorithm parameters before measuring its effectiveness and efficiency. In the second stage, OCA was adapted to discrete problems and applied to the maze game with four levels of complexity. Additional experiments were held to compare the designed algorithm with recent state-of-the-art evolutionary algorithms. The overall obtained results are very promising. Nepomuceno et al. (2020) present in this work a time-series adaptation for the DEA directional model as an alternative for coping with this problem. The methodological approach has three stages for this benchmarking to occur: data, information and knowledge extraction. In the first stage, they compare the same unit in different moments to identify efficient periods instead of efficient competitors. As a result, successful performance strategies are investigated using the bibliometric coupling of employees' relevant statements in the second and third stages. The application in a branch of the Brazilian Federal Savings Bank allowed an internal benchmarking of efficient periods when specific performance incentives, innovative processes, competitive strategies, and human resource changes were adopted for improving the unit's performance. Thakur et al. (2020) introduce a decision model to take care of the water requirement of sensitive crops of agriculture industry. The proposed work presents a novel and proficient hybrid model for sensitive crop irrigation system (SCIS). For implementation of the model, brassica crop is taken. The duration and amount of water to be supplied are based upon the weather prediction and soil condition information. The decision model is developed using adaptive neuro-fuzzy inference system (ANFIS) and artificial neural network (ANN) for brassica crops. In this model, if the input data values are available in range, then ANFIS model would be preferred and if the data sets are available for training, testing and validation then ANN model would be the best choice. The soil moisture, soil status in terms of temperature and leaf wetness are the input and flow control of sprinklers is the output for SCIS. The predicted outputs are analysed to assert the suitability of the proposed approach in the brassica crops. The proposed SCIS achieved an accuracy of 91% and 99% for ANFIS and ANN models, respectively. Simona Mirela Riurean is associate professor at the University of Petroşani, Faculty of Mechanical and Electrical Engineering, Department of Computers and Electrical Engineering, Romania. In 1991, she graduated from Technical University of Petroşani, Faculty of Mining Machines and Equipment, Petroșani Romania as Engineer in Specialization Mining Machines and Equipment. In 2000, she achieved Ph.D. degree at University of Petroşani, Faculty of Electromechanical Machines and Installations, awarded by Ministry of Education, Romania. In 2012 graduated the University ‘1 Decembrie 1918’ Alba Iulia, Romania earning diploma and Bachelor degree in Informatics. In 2016, she graduated the Master Program at University ‘1 Decembrie 1918’ Alba Iulia, Romania in Advanced Programming and Database and in 2019 achieved Ph.D degree in the field of Systems Control Engineering at University of Petroşani, Doctoral School, Romania. In 2018, she received Professor Bologna Grade with Diploma of Appreciation from National Alliance of the Students Organizations in Romania. In 2019, she received Diploma of Excellence for ‘Contributions regarding VLC applicable in Industry’ at EuroInvent 11th Edition, European exhibition of Creativity and Innovation in Iasi, Romania and Gold Medal at International Event of Inventions ‘Traian Vuia’, Timisoara, Romania for ‘Underground Personnel Monitoring System Based on VLC Technology’. Her main research areas are Computer Networks, Optical Wireless Communication (VLC, LiFi, OCC), ICT in Higher Education, e-Learning, e-Commerce and Network Security. As guest editors, the authors wish to appreciate the outstanding contributions of researchers/scholars to this special issue and be thankful to reviewers for their valuable and professional input. The authors would also take this opportunity to thank Jon Hall, Editor-in-Chief of the Wiley journal Expert Systems. The authors also wish to express their gratitude specifically to the WorldCIST'20 program committee members for their hard work and dedication, which is highly admirable.