The 20th International Conference on INFORMATICS in ECONOMY (IE 2021)
Education, Research & Business Technologies
Bucharest, Romania (via Online Meetings), May 14th, 2021
- Prof. Gang KOU, School of Business Administration, Southwestern University of Finance and Economics, PR China – Credit scoring for SMEs using transactional data: a profit- and risk -driven approach
- Prof. Janus KACPRZYK, Systems Research Institute, Polish Academy of Sciences, Poland – Towards trustworthy and human acceptable decision making and optimization models reflecting cognitive biases
IoT, Mobile-Embedded & Multimedia Solutions
Cloud & Distributed and Parallel Computing
Databases & Big Data
1. U-HEALTHCARE SOLUTIONS’ ACCEPTANCE FOR ADULTS – Sorin Câlea, Sergiu Jecan, Mihaela Luțaș, Lucia Rusu
Abstract. Most u-healthcare applications were developed based on five important dimensions: education, prevention, diagnosis, treatment, and monitoring of patients.
The starting point of our research was the need of finding out the way in which the current Covid-19 Pandemic influenced the dependency of chronic diseases’ persons over 50 to the M-health and E-health solutions in Romania. We focused on user’s experience and ability to use these systems, starting from the already known Smart-healthcare and U-healthcare ones, as developed in EU’s Horizon 2020 program and the way the new technologies like IoT, Smart Device and Wearable Technologies as part of U-Healthcare are accepted and used in Romania.
The focus group is made up of people aged 50 to 84, and the on-line questionnaire contained issues related to the acceptance of the IoT and the new technologies used in Telemedicine and U-healthcare systems for the prevention and monitoring of the chronic disease’s patients, starting from the influence UX factors.
Keywords: U-Health Monitoring (UHM), IoT, Smart Devices, UX
2. THE EFFECTIVENESS OF A MULTIMEDIA MOBILE APPLICATION, Dinu Mihail-Văduva
Abstract. The major preoccupation regarding the actual research is to visualize a theoretical model of the natural forces interaction between a multimedia mobile application deployed upon an educational activity over a group of students, and an automatic process of evaluation regarding the final academic results. We implemented a new metric indicator, named here with effectiveness of a multimedia mobile application, correlated with the educational resultant force emerged from a mobile environment learning experiment. The variables involved in our model are connected to the cross-disciplinary curricula, the educational time coverage disclosed by a multimedia mobile application, the multimedia concentration and the academic performance measured just in time at the interface between formal and informal evaluation. We are proposing another educational force couple, a resultant force, which is represented by the quality attributes allocated to the mobile devices and, furthermore, to the multimedia mobile applications. We are using the assumption that a multimedia mobile application generates an educational field in front of a learner taking into consideration not only the easiness of the process by which the learner’s attention is retaining toward a mobile device. The fact that between a mobile user and a multimedia mobile application could be established a quantitative relation of physical attraction or rejection, disclosed by surveys and questionnaires including qualities attributes, was an argument for our hypothesis that educational forces encountered could be explained by a cloaking educational field where a touch screen electric impulse is only the beginning of the educational magnetism encountered at the learners.
Keywords: mobile applications, mobile learning, Android, impact on academic performance.
3. AN ANALYSIS OF DIFFERENT BROWSER ATTACKS AND EXPLOITATION TECHNIQUES – Stefan Nicula, Răzvan-Daniel Zota
Abstract. Modern browsers are very complex pieces of software, having capabilities, and functionalities that have been compared to those of the operating systems. Although not quite the same, browsers do pack a lot of processing power and enough versatility to dictate a big part of our everyday internet-related activities by providing optimization and robust frameworks. A large range of functionalities and mechanisms are directly related to a bigger attack surface, complexity comes with hidden bugs and deeper analysis requirements. This paper aims to take a look and study some of the attack vectors and exploitation techniques applied for browser research security based on the Windows environment. Among the examples, we can note that some browser engines are so complex that they have their own classes of vulnerabilities while others are notorious for their flawed design. The paper dives into ways of evaluating a browser’s security level and conducting research based on multiple attack vectors by taking into consideration the latest protection mechanisms, exploitation techniques and vulnerabilities discovered.
Keywords: browser security, memory corruption, DOM exploit, fuzzing, vulnerabilities.
4. A GENERAL COST MODEL IN A CLOUD DATA CENTER – Constanta Zoie Radulescu, Delia Mihaela Radulescu, Gheorghe Lazaroiu, Alexandra Sipica, Dragos Barbu
Abstract. Cloud Computing is one of the technologies with a rapid development in recent years. This technology provides many services and resources to end users at low prices. Last decade witnessed a growing interest from industry and academia in the study of problems arising in cloud computing. A major condition for the commercial success of a business in cloud data centers is the formulation of a well-defined pricing strategy. Pricing models play a key role in the services purchase decision of the potential cloud customers. On the cloud market there are numerous Cloud Service Providers (CSPs) that offer users various pricing models for storage, databases, memory and applications. Cloud pricing models are de-pending on the cloud type: Infrastructure as a Service (IaaS), Platform as a Ser-vice (PaaS), and Software as a Service (SaaS). The present paper provides an overview on various price models present in the cloud market with price compar-isons for the three main CSPs: Amazon, Microsoft and Google. A general cost model is then proposed for computing the services costs in a Data Center. This model can be used by the manager to make comparisons between the cost of his own Data Center services and the cost of the same CSPs services computed ac-cording to the CSPs pricing models. For different types of hardware configura-tions different electricity consumption is taken into account.
Keywords: Cloud Data Center, Pricing models, Cloud Service Providers, Cost model, Electricity consumption.
5. OPPORTUNITIES AND DISADVANTAGES OF USING MOBILE TECHNOLOGIES BASED ON CLOUD IN LEARNING – Rares Constantin Ciobanu, Alexis Valentin Zaharia
6. CLOUD AUTHENTIFICATION USING FIDO COMPLIANT JAVA CARD TECHNOLOGY SECURE ELEMENTS – Cristian TOMA, Marius POPA, Mihai DOINEA
Abstract. The necessity of using secure elements for accessing different clouds or blockchain exchange websites in a secure manner has increased over years. Most of the websites and cloud platforms offer second factor authentication as mobile application, OTP token or even biometric key. The technology evolved and a market requirement appeared regarding the access with first and second factor as a combination between biometry and public key cryptography, therefore the non-usage of the passwords which often are not strong enough for the authentication. The first section is an introduction in the set of the standards for FIDO authentication and in the second section the authors present a proof of concept solution for Cloud authentication using Java Card Secure elements. The last section offers a view of a benchmark regarding the speed of performing cryptographic algorithms required by FIDO using different secure elements.
Keywords: Secure Elements, Java Card, FIDO, Second Factor Authentication
7. RESEARCH ON BIG DATA ANALYTICS USING A SCIENTOMETRIC APPROACH – Mihaela Muntean
Abstract. Big data analytics (BDA) have attracted attention from managers, academics, software vendors, and IT consultants. The primary goal of the BDA is to help organizations make informed business decisions. As the importance of BDA continue to increase, so does the number of studies for this concept. So, it is difficult for researchers to find topics they are interested in and track up to date. In this context, the primary goal of this paper is to provide a systematic investigation of a current state of Big data analytics and to identify the research gaps that provide the directions for future studies.
Keywords: Big Data Analytics, Keyword Analysis, Density Visualization
8. ALERTS AND FRAUD DETECTION IN ELECTRICITY CONSUMPTION RECORDED BY SMART METERING SYSTEMS – Simona Vasilica Oprea, Adela Bara, Vlad Diaconita, Niculae Oprea
Abstract. The fraud detection in electricity consumption represents a challenge as they produce significant financial losses for utility companies. The detection strategy could be also costly because the classification performance is not high when working with real, unbalanced data, sometimes containing missing intervals. This implies that the company budget for fraud detection should cover on-site investigations for both true and false positives. Hence, the best algorithm partly depends on the company strategy and budget for the identification of dishonest consumers. Various classification algorithms for time series data, such as distance-based (K-Nearest Neighbour), interval-based (TSF – Time Series Forest), Dictionary-based (Bag of SFA Symbols – BOSS, contractable BOSS – cBOSS), frequency-based (similar with TSF), shapelet-based (Shapelet Transform) are known to perform better than baseline classifiers. In this paper, using Machine Learning (ML) algorithms and stream ingestion, we analyze the electricity consumption data of some Chinese consumers for a data span of almost three years.
Keywords: fraud detection, smart metering systems, classification.
9. ANALYTICAL CAPABILITIES OF GRAPHS IN ORACLE MULTI-MODEL DATABASE – Iuliana Șimonca (Botha), Alexandra Corbea (Florea), Anda Belciu (Velicanu)
Abstract. Graphs exist in mathematics for more than 300 years, but their full expansion and usage in databases can be considered to be started about 10 years ago, when multi-model databases adopted graph models. This paper presents how the graph theory was used in computer science, focuses on graph databases, and on Oracle multi-model in particular, while the last part shows how graphs work in Oracle database. Graphs became more and more popular in databases because they use a flexible data model, with no predefined schema, which can adapt on the run. On the other hand, they offer an intuitive visualization and put in place new opportunities for analytical processing, which couldn’t be performed with the classical relational technology. Oracle Database offers property graph and RDF graph data models, specialized query languages (SPARQL, PGQL, SQL), visualizations tools and in-memory graph analytics that can help to identify clusters and patterns in sparse, semi-structured data.
Keywords: Graph Analytics, Multi-Model Database, Graph Database, Property Graph.
10. DISTRIBUTED LEDGER TECHNOLOGY ECONOMY – Felician Alecu, Paul Pocatilu, Silviu Ojog, Petru Simon Mot
Abstract. Distributed ledger technology (DLT) and blockchain are very popular these days, especially due the cryptocurrencies like Bitcoin, Ethereum, Dogecoin and others. To better understand these cryptocurrencies and the related transactions, it is important to know how these technologies work and how secure they are. This paper presents the concepts, technologies and security issues related to blockchain with respect to the economy.
Keywords: Blockchain, Distributed Ledger Technology, Security, Tokens.
11. DIGITAL HUMANISM: VIRTUAL EXHIBITIONS IN THE TIME OF PANDEMIC AND EVOLVING COLLABORATION OF RELEVANT ACTANTS – Cristian Ciurea, Florin Gheorghe Filip, Alin Zamfiroiu, Lorena Pocatilu
Abstract. Digital humanism (DH) aims to empower people to do something they never thought were feasible or to reimagine how they would achieve their goals. Virtual exhibitions (VE) represent one of the numerous possible deployments of IT (Information Technology) that is congruent with the main ideas of digital humanism (DH), which can be viewed as a concept about the contribution of IT to facilitate attaining human high aspirations. The paper aims at presenting the concepts, technologies of VE with particular emphasis on the evolutions caused by the current pandemic.
Keywords: Crowdsourcing, Information Technology, Future Internet.
Audit, Project Management and Quantitative Economics
1. RESEARCH ON DATA ANALYSIS (ENVIRONMENTAL, SOCIAL AND ECONOMIC) IN THE CONTEXT OF IMPLEMENTING THE CIRCULAR ECONOMY – Denis-Alexandru Dragomir
Abstract. As we know, a circular approach in economy means and promotes, in principle, the reusability of products and materials through different processes like recycling. refurbishment and remanufacturing. Thus, the latter is divided in categories based on their time through the cycles mentioned. To implement this system, compared to its long-lived predecessor, namely the linear perspective or model, a various number of actions and policies must be taken. The transition requires the setting of goals or targets meant for this operation. But will this result in a sustainable environment? In fact, the contribution and relationship between circular economy and a sustainable development and thus to a more sustainable society is under discussion. That being stated, this paper tries to analyze the concept of circular economy, describes its main principles and values, highlights the main differences in implementing these two antithetic systems – circular and linear – and gives information about the possibility of providing sustainability to the systemin cause, or the sustainable connotation, if you want.
Keywords: Circular, linear, principles, sustainability, reusability
2. APPLYING A SUSTAINABLE VECTOR MODEL TO GENERATE INNOVATION – Marian Pompiliu Cristescu, Mari Flori, Raluca Andreea Nerisanu
Abstract. Innovation is the main promoter of the technological progress, whether in neoclassical perspective or evolutionary models or theory of economic growth. In all classical, neoclassical or evolutionary models of economic growth, innovation is marked as a quantitative parameter, which, changing its volume, leads to a quantitative growth of the economy. Thus, it is questionable how could innovation be sustainable and how it could be emphasized. The present model proposes a qualitative approach to social processes, including economic ones, noting that these qualitative measurements are based on a measurement scale which, once established for each point in the model, changes depending on the direction and intensity of changes in its links. The model is constructed on a group of automorphisms, feedback loops and algebraic fractals, generating a sustainable and evolving structure that can be used in any type of system, especially within a universe of interrelated systems. Thus, the model stabilizes and supports itself, if the decisions made are rational, becoming a sustainable model of economic growth.
Keywords: innovation, vector model, algebraic fractals, automorphisms, sustainable economy.
3. OPTIMAL EMPLOYMENT CONTRACTS WITH SEVERAL TYPES OF AGENTS – Laura-Stefania Constantin, Dana Luiza Grigorescu
Abstract: Lack of information affects the relationship between a worker and the company he works for. In the Principal – Agent model, the Principal can be an individual (worker) or a group of workers that offers labor to a company, which in this case represents the Agent. We will assume that the Principal has all the bargaining power in relation to the company. The Agent obtains a profit quantified by the production function, an efficiency parameter and the transfer of the company to the worker. The efficiency parameter is specific for each Agent type: inefficient, medium and very efficient. The company’s goal is to maximize the profit. The utility function of the Agent depends on consumption and work, the disutility of work being evaluated in monetary terms. In the situation of informational symmetry (optimal of rank I) the optimal contract is also Pareto-optimal, regardless of the Agent type. If in the situation of informational asymmetry, the worker would offer this type of contracts (of rank I), the company is incited to claim that the very efficient state has been achieved and obtain more labor. To avoid this behavior, the Principal should propose a bundle of contracts, one for each type. With the help of incentive compatibility constraints, each type will choose exactly its dedicated contract. There is a loss of efficiency for the inefficient and medium Agents. Only the contract designated to the very efficient Agent remains Pareto-optimal.
Keywords: Pareto efficiency, profit, utility, optimum, incentive, contract.
4. LABOR MARKET TRENDS DURING THE COVID-19 PANDEMIC – Florin-Valeriu Pantelimon, Bogdan-Ștefan Posedaru, Tiberiu-Marian Georgescu, Răzvan Bologa
Abstract. The COVID-19 pandemic has caused several disruptions in almost all day-to-day matters around the world. In order to keep things under control, ever since the beginning authorities around the world imposed restrictions in relation to physical activities and therefore, organizations were forced to rethink the way they carry out professional activities. Thus, the majority of areas that were based on the physical interaction between people were severely impacted by these sets of measures. Unfortunately, a negative impact that the pandemic state has had over the fields that were based on physical work is that economic pressure has forced some of the entities to completely suspend their activity, leading to high rates of unemployment around the world, which also led to consistent financial efforts sustained by the government. Therefore, in order to come to relevant conclusions, we analyzed several datasets that offer insights over all aspects of the labor market around the world mainly before and during the pandemic period. We also computed a correlation matrix based on economic sectors to compare the effects in the labor market for various industries.
Keywords: COVID-19, Labor market, Unemployment, GDP
5. THE LABOR MARKET IN RELATION TO DIGITALIZATION – PERSPECTIVES ON THE EUROPEAN UNION – Ioana Andreea Bogoslov, Eduard Alexandru Stoica, Mircea Radu Georgescu
Abstract. Both digitalization and the labor market are intensely discussed subjects in the current context of global society and economy, characterized by intense competitiveness. In these circumstances, the efforts undertaken by EU Member States are focused on increasing the degree of digitalization and maintaining a low level of unemployment.
Providing an overview on the two dimensions mentioned, while considering the results registered for the EU Member States, the purpose of this paper consists in identifying the possible correlations between the DESI Index and three specific labor market indicators, namely: Employment/Population Ratio, Labor Force Participation Rate and Unemployment Rate.
The obtained results highlight a strong positive correlation between digitalization of the EU Member States and their Employment/Population Ratio, as well as on their Labor Force Participation Rate. Moreover, based on the linear regression model we expect increases of 3.4%, respectively 3.02% for the two indicators, in the context in which the DESI Index registers an increase of one unit.
Keywords: DESI Index, Digitalization, Employment/Population Ratio, Labor Force Participation Rate, Unemployment Rate
6. THE IMPACT OF BITCOIN IN THE FINANCIAL MARKET. A CYBERNETICS APPROACH – Nora Chiriță, Ionuț Nica, Mihaela Popescu
Abstract. The cryptocurrency market is now a decentralized system used more and more often, based on the concept of blockchain. A blockchain is essentially a growing list of records that are linked and secured using cryptography. This article presents the current situation and predicts possible situations that may arise in the future in the cryptocurrency market, blockchain and more. Both individuals and legal entities are starting to invest in cryptocurrencies, creating a quick and easy way to make a profit from them. In the near future, states and governments may also use cryptocurrencies for purposes such as storing fractional resources, thus replacing currently used resources such as gold. The main purpose of the paper is to explain this new emergence of cryptocurrencies from a cybernetic approach. Analyzing the cryptocurrency market from a cybernetic perspective means approaching this market as a complex adaptive system from the perspective of system dynamics. We believe that the results and analyzes of this article can contribute to the development of existing literature. The topicality of this research is the analysis performed from the cybernetic perspective, but also the construction of a complex adaptive system of the financial market to which we add the cryptocurrency market that interacts with the other markets that define the cybernetics system of the financial market.
Keywords: Cryptocurrencies, Complex Adaptive Systems, Altreva, Stella
7. CHALLENGES OF IT PROJECT MANAGEMENT – Cătălina Sitnikov, Ionela Staneci (Drinceanu), Mariana Paraschiva Olaru (Staicu), Aurel Dincă, Alina Mădălina Belu
Abstract. As the business environment has become increasingly complex worldwide, the use of interdisciplinary work teams has become a necessity, which has radically changed the work environment. These changes have acceler-ated the need for complex IT projects, thus creating the need for a more sophisticated, comprehensive project management. IT project management consists of applying knowledge, skills, tools and techniques specific to the activities of an IT project, which have defined objectives, goals and requirements, related to time, costs, quality and performance parameters. Time, cost, quality and performance are constraints for the IT project. In order to have as many competitive advantages as possible and to generate the appropriate competitive responses, an organization must know and use modern IT project management techniques. IT project management is a mana-gerial strategy applied especially in computerization and other investments. It involves the establishment of teams of specialists in the analysis, design and implementation of computer applications and the involvement of specialists from various functional departments, accounting, sales and human resources management. The pro-ject teams have as objective the launch and realization of the IT project with the observance of the technical specifications, of the execution terms and of the expenditure budget. The research study aims first of all to ana-lyze the main problems that may occur in IT projects, and secondly to identify the causes that generate these problems.
Keywords: management, IT projects, organization, planning, control.
8. THE IMPORTANCE OF CORRELATING THE ELEMENTS OF THE AUDIT MISSION FROM THE PERSPECTIVE OF IT PROJECTS – Anca Băndoi, Silvia Mioara Ilie (Troi), Costinel Cristian Militaru, Ionuț Riza
Abstract. The evolution of the information society towards the knowledge-based society, a process that involves the progressive transformation of the whole economy into a digital economy, involves major changes in the approach to external audit, with a double impact: both in terms of audit management and the role of auditor, as well as in terms of the associated architectural, methodological and procedural plan. These changes, which lead to a new treatment of the audit, highlight the need to create a new framework for the life cycle of the audit process, able to meet the new qualitative requirements of the areas and objectives of the audit: the audit will focus mainly on management and delivery of IT services, which involve the dominant presence of electronic document flows, as well as on specific associated processing procedures. For this reason, most traditional audit procedures will be replaced by procedures capable of ensuring auditing in the rapidly expanding digital context today. For the purpose appropriate to the new context, changes in the content of the audit lifecycle require the reengineering of audit architectures and the classical methodological and procedural framework leading to the creation of a new audit model. The classic audit will change its approach and content and will be based on information and communication technologies by adopting advanced concepts and methods: online audit, continuous audit, e-audit. In terms of the manner and modalities of work, the auditor will need to be prepared for collaborative work, as well as for the adoption of new styles of work: remote auditing, guidance on auditing electronic documents, use of computer-based or computer-assisted instrumental support. The main objective is to provide auditors with consistent information about the possibility of correlating the stages of the audit mission related to IT projects.
Keywords: IT projects, correlation, audit mission
Artificial Intelligence, Data-mining & Machine Learning
1. PRIVACY-PRESERVING FRAMEWORK FOR DEEP LEARNING CYBERSECURITY SOLUTIONS – Constantin Nilă, Marius Preda, Victor Patriciu
Abstract. Experimentation with artificial intelligence (AI) and machine learning (ML) has rapidly advanced in the last decade, mainly due to the progress made in data storage and processing technologies. As this technology is implemented in everyday devices, ranging from smart appliances to personal assistants, we observe an increase in interest in more rigid to change sectors, like governmental and military. Utilizing a machine learning service is a commodity for today’s society, introducing data privacy challenges for data owners and security concerns for model developers. As the EU plans to build a network of AI-enabled Security Operations Centers across Europe and NATO believes in including artificial intelligence in its decision-making process, we need to focus intensely on the security and privacy offered by machine learning-based applications. This paper contains our summarization of the current concerns regarding privacy-preserving machine learning and an analysis of the present frameworks highlighting possible attacks and methodology. Additionally, we present our approach as a potential solution for privacy-preserving models used in cybersecurity applications. Our research shows that even though all three methods guarantee privacy at a certain level, a holistic approach proves to be more efficient.
Keywords: Privacy-Preserving, Cybersecurity, Homomorphic Encryption, Differential privacy, Machine learning, Deep learning, Artificial intelligence.
2. CYBER SECURITY MATURITY MODEL FOR CRITICAL INFRASTRUCTURES – Aurelian Buzdugan, Gheorghe Capatana
Abstract. Critical infrastructures have one of the most important roles for our economy, society and government. The information systems that are often con-trolling and managing processes from this type of organizations, must fulfill stringent safety and security requirements. As a result, cyber security management becomes a challenging task due to the number, interdependencies and role that information systems have. In this paper we propose a model to evaluate the cyber security maturity in critical infrastructures built from the perspective of human dimension impact upon information systems, which also takes into ac-count technological aspects. This model can also support decision makers in identifying priorities and gaps when it comes to cyber security. The criteria and attributes were customized for the given context, however can be adapted and used by any type of organization.
Keywords: Critical Infrastructure, Cyber Security Maturity Model, Human Dimension, Decision Support Systems.
3. A GIS-BASED APPROACH IN SUPPORT OF MONITORING SUSTAINABLE URBAN CONSUMPTION VARIABLES – Julian Vasilev, Maria Kehayova-Stoycheva, Boryana Serbezova
Abstract. Urban consumption is critical to achieving the UN’s sustainable development goals. In recent years, the tendency of the earth’s population to concentrate in urban settlements has become increasingly clear. This brings to the fore the task of managing the consumption of cities. Sustainable urban consumption management processes require constant monitoring of key indicators and variables related to it. Maintaining good information of the solutions for sustainable consumption management of the cities requires maintaining adequate data and information. For various reasons, local administrations are not always able to provide the necessary data to derive up-to-date levels of monitoring variables and trends. Such problems put the whole system for monitoring variables for sustainable consumption to the test. The purpose of this article is to show the application of a GIS-based approach to vectorize cadastral data in support of monitoring sustainable urban consumption variables. The main approach is giving a methodology for using raster data, their vectorization in GIS and analysis of the vectorized data with Delphi. The use of free GIS software and a Delphi program allows fast calculations of the density of built area within several seconds. The practical implication of the research is for people who want to make fast and reliable analysis of raster data concerning the calculation of the density of built area. The research is funded by the Research Fund of Republic of Bulgaria in 2019 and is part of the scientific project “Sustainable Urban Consumption – Regional Diversity” № КП-06-Н35/7.
Keywords: Vectorization, Delphi, Cadaster, Density of built area, Sustainable consumption, Sustainable Cities, Monitoring variables.
4. INVESTIGATING THE IMPACT OF ORGANIZATIONAL ETHICS ON THE OPTIMIZATION OF ARTIFICIAL INTELLIGENCE MODELS – Bassel Diab
Abstract. This paper aims to examine the role of organizational culture, mainly ethics, in the field of artificial intelligence. More specifically, it tries to investigate the significance of ethics in designing and/or testing artificial models for organizations. The research methodology is based on developing an artificial model using a ready dataset from a developed country, Poland, which includes financial ratios of bankrupt and non-bankrupt companies, and then testing this model on a self-developed dataset of bankrupt companies in a developing country, Lebanon. It was concluded that the process of building new datasets in Lebanon is an exhaustive job, especially when it comes to accounting and finance which represents a threatening factor to the research work in such areas. The empirical findings reveal that the absence of ethical organizational conduct, high level of corruption and poor official governance are major examples of the barriers confronting the rewarding implementation of AI in Lebanon.
Keywords: Artificial intelligence, organizational culture, ethics, prediction.
5. DATA MINING IN SMART AGRICULTURE – Andreea-Elena Ogrezeanu
Abstract. This paper aims to present the ways in which data from agriculture can be analyzed in order to make predictions that could contribute in decision-making processes. With the industrialization of agriculture, the amount of data collected through this environment has increased considerably. In this paper, data mining methodologies were applied on a public data set that contains agriculture indicators from Romania in the year of 2016. For this purpose, two algorithms were trained: Multiple Linear Regression (MLR) and Generalized Linear Model (GLM), in order to identify the one that offers the best predictions.
Keywords: data mining, agriculture, prediction
6. MACHINE LEARNING AND DATA MINING TECHNIQUES FOR HUMAN RESOURCE OPTIMIZATION PROCESS – EMPLOYEE ATTRITION – Laura-Gabriela Tanasescu, Ana-Ramona Bologa
Abstract. This paper will present how machine learning and data mining techniques can be used in order to address one important challenge in human resources processes, more specifically employee attrition. For this purpose, the following sections include general techniques applied for classifications scenarios, ways in which a model can be build and analyzed and also the factors that need to be taken care into consideration when choosing an algorithm with which we should proceed to prediction. All the steps and implementations address a business need that exists in organizations worldwide and which could, once correctly targeted, reduce time, costs and improve company environment and performance.
Keywords: Human Resource Management, Data Mining, Machine Learning, Employee Attrition, Classification, Supervised Learning
7. MACHINE LEARNING TECHNIQUES FOR NETWORK INTRUSION DETECTION – A SYSTEMATIC ANALYSIS – George-Bogdan Mertoiu, Gabriela Meșniță
Abstract. As the world evolves toward a high dependency on computers and technology, systems and network security became one of the main challenges faced in the last decade. The number of threats that cause potential damage to the network system is rising exponentially due to the increasing complexity of networks and services of modern networks, while situational awareness of the critical assets thus becomes extremely important. The main objective of Cyber security is to protect the electronic data from attacks such as unauthorized network access, intrusion attack, or malware. This study aims to provide an overview of the trends of Machine Learning requirements in supporting the efforts to defend electronic data. The first part of this study is a quantitative analysis of the results obtained from consulting the Scopus and Web of Science databases. In this part, in addition to the most important authors and keywords used, we aimed to find if the countries that are the main targets of cyber-attacks are also involved in researching new ways to improve defending techniques. The second part reveals a brief analysis of Machine learning techniques, risks and innovations and how the next research activity should be conducted, considering the constant evolution of both sides: defenders and attackers.
Keywords: machine learning, cyber security, network intrusion detection.
8. WEB SCRAPING AND ETHICS IN AUTOMATED DATA COLLECTION – Marius Cristian Mazilu
Abstract. As a PhD student doing research in Big Data and Data Mining, the data collection is a big part of the process. Because I am also a programmer, the technique of Web Scraping became a fast and reliable method to collect the data that I needed. But once starting this process, a lot of legal and ethical questions appeared for me. Questions regarding the legality of the process itself or regarding of what type of data can be collected and how. This paper does not try to represent legal advice but tries to present a perspective of how we could do data collection, by presenting techniques and what are the laws, rules and guidelines that can apply to web scraping and what we can do, to keep the whole process not only legal but also ethical.
Keywords: data collection, web scraping, ethics in data collection.
9. CLASSICAL MACHINE LEARNING CLASSIFIERS TO PREDICT EMPLOYEE TURNOVER – Maria Carmen Lesan
Abstract. In the context of the increasing migration of employees from one company to another and given the career changes that many people desire in order to avoid monotony, the dynamics of the workforce puts great pressure on the stability of a company. HR departments can establish more effective mechanisms for preventing employee turnover and better recruitment strategies when given a reliable Machine Learning tool. Facing a classification problem (employees are either tagged as “left” or “not left”), this investigation attempts to conduct experiments with traditional methods such as Logistic Regression, Decision Tree, Random Forest, and Support Vector Machine to predict employee turnover. In our analysis Support Vector Machine showed promising results in predicting employee turnover. We conclude that we obtained sufficient results in order to trust a Machine Learning classifier to label correctly the employees that left the company and to advise practitioners to integrate such tools into the everyday activity of the HR department.
Keywords: Machine learning, Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, Specificity, Employee turnover
10. ASSESSING THE SHARE OF THE ARTIFICIAL AD-RELATED TRAFFIC: SOME GENERAL OBSERVATIONS – Marek Gajewski, Olgierd Hryniewicz, Agnieszka Jastrzebska, Mariusz Kozakiewicz, Karol Opara, Jan W. Owsinski, Sławomir Zadrozny, Tomasz Zwierzchowski
Abstract. Online advertising campaigns are adversely affected by bot traffic. In this paper, we develop and test a method for the estimation of its share, which is necessary for the evaluation of campaign efficiency. First, we present the nature of the problem as well as the underlying business rationale. Next, we describe the essential features of internet traffic, which ought to be accounted for, and the potential methodologies, which can be used to reach the objective of the project. Finally, some of the results are provided, along with the respective discussion, followed by both technical and also more general conclusions.
Keywords: Internet, Advertising, Artificial Traffic, Bots, Classification, Data Analysis, Online Marketing.
E-Society, Enterprise and Business Solutions
1. EXPERIMENTAL RESULTS REGARDING THE EFFICIENCY OF BUSINESS ACTIVITIES THROUGH THE USE OF CHATBOTS – Ionuț-Alexandru Cîmpeanu
Abstract. In this article we take into consideration the chatbots, describing some models used in different fields of activity comparing how to achieve them, the estimation effort given by the specialists who worked on their implementation, the benefits and efficiency at work. A chatbot is a computer program that has the role of connecting a verbal or written dialogue with a person. Over time, chatbots became necessary in all areas. They are used in healthcare, education, nutrition, transportation, finance, tourism, relaxation and rest. The trend of companies is to replace the customer service department with chatbots that are efficient, do not mean very high costs and work 24 hours a day helping employees with personalized explanations, sending messages or emails regardless of location, with possibility to upload some documents in the application. Chatbots are secure, and for a user to log into the chatbot, he/she must go through several steps. In this article we present the way of working, original solutions and experimental results analyzed in the development of three chatbots from different fields. Conversational skills are described, but the emphasis are on the four dimensions of the chatbot development in the chosen areas of activity: interaction, integration, testing and analysis. Moreover, we want to highlight the concern of business people for using the chatbot in any field of activity, streamlining economic activities and achieving the success of the chatbot.
Keywords: chatbots, development, business
2. ASSESSING STUDENTS’ KNOWLEDGE THROUGH E-LEARNING PLATFORMS – Svetlozar Stefanov
Abstract. In this report, an attempt is made to examine issues of discussion related to assessment of students’ knowledge and skills in the field of Accounting in general, and in „Financial Control“ course in particular. The issue of measuring students’ knowledge and skills is a very important issue that has always caused controversy and discussion among professionals working in the education system. It is so because one of the most important indicators of the quality of education is students’ performance expressed through the grades that teachers give to students. It is quite understandable that it is of the interest of all members of society and especially employers that students’ grades correspond to the maximum extent possible to the knowledge and skills acquired at the university. This issue has not been given enough attention recently, which is why when students get employed it is often found that their knowledge and skills gained at the university do not meet the requirements of the employers.
The object of study in this report is the possibilities for assessing students’ knowledge and skills through the use of web-based computer tests consisting of both practical tasks and different types of test questions, allowing a comprehensive assessment of knowledge and skills acquired at the university. The report outlines the advantages and disadvantages of the different types of test questions used to assess students’ knowledge and skills. Emphasis is placed on the search for opportunities through the use of computer tests to achieve an objective assessment of students’ knowledge and skills in the field of Accounting.
Keywords: assessment, knowledge, skills, Financial Control, web-based tests.
3. AGILE PERSPECTIVES IN HIGHER EDUCATION – Margarita Bogdanova, Evelina Parashkevova-Velikova
Abstract. The objective of the paper is to outline adaptable practices for the ap-plication of agile principles in higher education, further provoked by the Covid-19 pandemic. In the short term, agility can lead to more effective and creative ways to solve problems caused by environmental uncertainty, but in the medium and long term – it can be the basis for developing a modern vision for the suc-cessful transformation of the university business models. An empirical study in conditions of remote learning due to the imposed anti-epidemiological measures was conducted using an electronic questionnaire among 105 students from “Tsenov ”Academy of Economics – Svishtov. Various aspects of the application of the agile methodologies in education during the Covid-19 pandemic are ana-lyzed, related to the more frequent feedback between students and teachers, to the overall attitude towards enhancing digitalization, and the introduction of hy-brid forms of education. The study does not provide a definite answer to the ques-tion of students’ readiness to apply agile approaches in teaching and assessment. The probable reason is that some of the agile forms were introduced partially due to the need for a rapid pandemic response. Effective agile university governance entails a combination of a bottom-up approach, in which learners are more moti-vated and willing to put in more personal effort when they are given more self-organization rights, and a top-down approach, in which the system allows and encourages initiative. of teachers to develop interactive teaching and research.
Keywords: Agile, Higher Education, Covid-1
4. DIGITALIZATION OF BUSINESS AND PUBLIC ORGANIZATIONS – COMMUNICATION PROBLEMS WITH IT COMPANIES AND POSSIBLE SOLUTIONS – Desislava Serafimova, Andriyana Andreeva, Vanya Banabakova
Abstract. The paper outlines communication problems between IT companies and organizations from the sectors of logistics and that of court administration in Bulgaria connected with digitalization of activity. The research aims to identify the main problems and forms of communication between it services client organizations and IT companies, expectations of various participants in the process and suggest directions for more effective clarification of the assignor’s requirements towards the contractors of IT services A specific aim of the research is to check whether there are significant differences in the problems organizations from the public sector and those from the business one experience in communicating with servicing IT companies. Structurally, the report consists of three parts – the first one clarifies the conceptual framework for relationship management between assignor organizations and IT companies, emphasizing on well-established good practices of IT Service Management. The second part presents the results of an empirical research and the research methods are explained, including desk research, in-depth interviews, focus-group interviews, and questionnaire survey. The third part summarizes results, differences and shared difficulties in digitalization for logistic businesses and court administration. Paths are suggested for improving communication between assignors and IT service providers with an accent on the stakeholders to attract at the initial stage of the process, expanding IT managers competences and the roles they perform. Conclusions are made about the higher education sector in Bulgaria and IT managers training.
Keywords: IT Service management, Digitalization process, Business and public sector, IT companies.
5. AN ASSISTED INSTRUCTION SYSTEM DESIGNED FOR ONLINE TEACHING AND LEARNING – Gabriel ZAMFIR
Abstract. In 2020 education had to stop its engine and let the e-education for teaching and learning, without a certified standard educational system. This is an argument to promote the idea that e-education includes education. The keyword was “online” and the environment was the technological infrastructure available at the moment of the decision. So, e-education it is used like an extension of the education. This image reflects an aggregate approach, but a functional solution should integrate education in the e-education. Assisted design is the keyword in order to clarify the context. A standard E-Classroom should be the new classroom in education and then online teaching and learning should be an option. This paper describes an assisted instruction approach developed as a teaching and learning system in a standard E-Classroom, improved for a T-Class (teaching and learning in the same time, but in different places). The T-Class is the previous version of the E-Class, but the diversity of the user’s cognitive infrastructure tends to react as a priority, relating to the conceptual infrastructure or the technological one.
Keywords: Assisted Design, Assisted Instruction, E-Education Processes, E-Society Classes, E-Society Resources
6. BUILDING RESILIENCE THROUGH DIGITAL TRANSFORMATION – Iulia Daniela Postolea, Constanta-Nicoleta Bodea
Abstract. In a world where change is the only constant, building abilities like resilience, flexibility and agility becomes imperative to keep or increase competitiveness and staying connected with the actual trends. The paper reviews the literature on building resilience through digital transformation and proposes a framework for assuring this characteristic in organizations. Several technologies and solutions related to this framework are discussed and compared. The authors conclude that only by defining and implementing a digital transformation strategy in organization the proposed framework may be efficiently implemented and operated.
Keywords: Resilience, Artificial Intelligence, Analytics.
7. CRYPTOCURRENCY WALLET PASSWORDLESS AUTHENTICATION – Dominic Bucerzan, Bogdan George Gros, Crina Anina Bejan
Abstract. Cryptocurrency and Blockchain are two cutting-age topics that have a major influence in shaping our daily lives. Starting from 2009 cryptocurrency has become a presence in the ordinary economic landscape. The form of money needed a change due to technological progress, globalization and the need of faster financial transactions. This paper proposes a solution based on passwordless authentication for crypto-wallets. In the first section of the paper is presented current state of threats that target cryptocurrency wallets. In the second section of the paper, we propose a solution for authentication process based on image steganography and SmartSteg algorithm. The proposed solution aims to minimize the threats that target the security of user authentication process. It proposes another way in which users store their credentials (private keys/passwords) so they do not have to use a keyboard to retype credentials every time they login. Once the private key is generated it is stored inside a digital image in such a way that the human visual system cannot distinguish between the original image and the image with secret credential embedded. When the user logs in to the wallet it loads the image with the secret credentials from which the wallet system will extract the credentials. This method removes the need to type the any credentials or the need of showing them on the screen. This solution is in its early stages and more test are need to be done in order to detect new possible threats to crypto wallets that can emerge from the usage of the proposed solution. The main target of the work presented in this paper is to minimize as much as possible the keylogger attacks.
Keywords: Blockchain, Cryptocurrency, Crypto Wallets, Steganography.
8. VISUAL TOOL FOR STIMULATING EMPLOYEE INTELLIGENT ATTITUDE – Smaranda Derscanu, Vasile Paul Bresfelean, Liana Stanca, Monica Ciaca, Alexandru Vancea
Abstract. In the new economic landscape, companies wish to become agile and instantly react to occurring opportunities, and moreover wish to offer their clients excellent experiences, to take advantage of the new technologies, and cutting costs. Thus, they need employees that show intelligent attitudes towards work. This paper is designed based on a literature review regarding interdisciplinary theories gravitating around the concept of innovating task management processes – activity management in the digital era. In this context, the authors have developed a visual tool to manage tasks within a project/job, allowing the development of studies focused on the stimulation and identification of employees showing an intelligent attitude towards work, essential for the company’s development, for the increase of digital business and for maintaining market competitive advantage.
Keywords: Task Management, Visualization, Fast Syncing.
9. MANAGEMENT INFORMATION SYSTEMS IN KNOWLEDGE SOCIETY – Marian Stoica, Elena Mircea, Bogdan Ghilic-Micu, Marinela Mircea
Abstract. The technical and practical dimensions of the management field are deeply related to information and decision, two main components of any managerial process. The decision, as a managerial tool, is the very reason for the existence of information. Same as the real system, in which the managerial processes take place, both components are the result of the activity of two relatively distinct systems – the information system and the decisional system. Due to strong dependencies and mutual correlations, they constitute the information-decision dual as an image/reflection of the real economic system for the manager. In the current context of technology development, this dual is increasingly built through information technology and communication specific tools, in a knowledge-based social development. Although management as a science has emerged relatively independent of the concerns in the information-decision, there is an obvious functional interconnection between the two fields. The aim of this paper is to present a progressive analysis of developments related to information systems in the last sixty years. Thus, in the first part we will analyze from different perspectives the four generations of information systems development. In the last part, we will present a typological synthesis of information systems and the specific architectural concepts in the ecosystem of knowledge society. The most important aspects regarding security, control and audit of information systems, will also be examined. In the end of the paper, we will highlight the characteristics of the relationship between the knowledge society and the age of agile development for information systems.
Keywords: information system, information and communication technology, knowledge society, management.
10. BUSINESS ANALYTICS FOR VISUAL MANAGEMENT – Mihaela Muntean, Claudiu Brândaș, Otniel Didraga, Florin Daniel Militaru
Abstract. The purpose of the paper is to study the interconnection between Visual Management and Business Analytics and to suggest a practical framework to monitor E-commerce processes. Based on a theoretical approach regarding Visual Management, Business Analytics is proposed to optimize operations and decisions. The design of Visual Management boards is theoretically substantiated and implemented in an E-commerce case study.
Keywords: visual management · business analytics · MS Power BI.
11. CLASSIFICATION OF SOFTWARE METHODS EXTRACTED FROM BUSINESS USE CASE DESCRIPTIONS WITH NATURAL LANGUAGE PROCESSING – Sabina-Cristiana Necula, Florin Dumitriu
Abstract. Natural language processing and other artificial intelligence techniques create new opportunities in the area of automation of requirements analysis. There are various attempts in the literature to use such techniques to process software artifacts written in natural language for automated creation of conceptual or other models. In this research paper, we extracted software methods/ functions from narrative use case descriptions by using natural language processing techniques. We augmented the current state of research in this field by using natural language processing for improving software functions/methods’ automated extraction from use case descriptions and their classification as belonging to Application Layer or Domain Layer. Our research consisted of (i) understanding the challenges of business use cases, (ii) applying natural language processing to detect classes names and functions/ methods definition name, (iii) evaluating the model. Based on our results, we consider that our contribution could improve the state of the software engineering field.
Keywords: Python, spacy, Application Layer, Domain Layer, verb, natural language processing (NLP), relationship, methods, software function
12. ANALYZING BUSINESS PERFORMANCES WITH A MULTICRITERIA DECISION METHOD – Catalin Marcu, Luminita Duta, Marinela Daniela Manea
Abstract. Business performance is a reference concept in the economic theory, as well as a permanent and major concern in practice. There are old tools in evaluating the companies’ performances, but they are no longer sufficient in a modern management. The purpose of this work is to present how a multicriteria decision support system can help companies to assess their economic performances and therefore to take the best decisions in their future development directions.
Keywords: performance indicators, multi-criteria decision making, business intelligence
13. MEASURING REAL TIME OCCUPATIONAL STRESS IN ORGANIZATIONS VIA A DIGITALIZED RISK MANAGEMENT APP – Magali Dubosson, Emmanuel Fragnière, Arnaud Fournier, Samuele Meier, Sacha Varone
Abstract. Various studies (e.g., European Agency for Safety and Health at Work, 2007) have shown the highly detrimental effects of toxic environments on human health and organizational performance. For organizations, the implication about stress is that it leads to harmful behaviors that prevent managers and their teams from achieving goals. In the literature, many questionnaires based on a variety of metrics have been developed and tested to measure and assess the quality of work life (i.e., stress, organizational justice, etc.). The goal of our original research was to identify the most meaningful items and combine them into a unique score and an effective decision-making module. In this new paper, we report on the development of a new app that we developed and used for the first time to regularly take a kind of temperature of job stress in two companies. A long process of trial and error was necessary to be able to collect very confidential information from employees, both anonymously and longitudinally, to measure human risk in the workplace objectively and globally. As a next step, our goal is for the organization to be able to provide a preventive risk response in case of identification of a deterioration of occupational stress.
Keywords: Data Collection, Occupational Stress, Risk Management