Database Systems Journal

ISSN 2069 - 3230

The journal is published under the sponsorship of
The Bucharest University of Economic Studies
and it is produced by the university's own publishing division,
The Bucharest University of Economic Studies Publishing House

Database Systems Journal, Vol. XIII, 2022

Open PDF Journal


1. Analysis of Romanian Air Quality using Machine Learning Techniques (p. 1-10)
Andreea-Mihaela NICULAE, The Bucharest University of Economic Studies, Romania
Air quality monitoring has become an increasingly important subject and is one of the most important concerns of governments worldwide. Monitoring is especially important in industrial and urban areas. Due to the many forms of pollution generated mainly by fuel consumption, means of transport, coal-fired electricity generation, etc., air quality is negatively affected. As the current trend is an increase in air pollution, it is necessary to install equipment to measure air quality both in areas with a high risk of pollution and in areas where pollution is low. These types of equipment must communicate in real-time their measured values, which then can be accessed to be able to make analyzes and predictions regarding air quality in a certain geographical area, areas with a high industrialization level, or in areas with a growing population. This paper aims to investigate the application of big data and machine learning techniques to make predictions on air quality using, as a source of data, data recorded in the period 2018-2021 from measurement probes throughout Romania for PM10, NO2, O3, and SO2. The results of this paper's analysis show that time-series models outperform traditional models. Moreover, ANN models are successful only in classifying pollutants' AQI levels and not their actual values.
Keywords: Big Data, Machine Learning, Romania, Air quality, MLR, SARIMA, C5.0, Random Forest, ANN
2. Facial Emotion Recognition and Detection Application (p. 11-18)
Ioana NAGIT, The Bucharest University of Economic Studies, Romania
Andreea-Ramona OLTEANU, The Bucharest University of Economic Studies, Romania
Ion LUNGU, The Bucharest University of Economic Studies, Romania
The purpose of the present paper is to study the process of face detection and recognition, followed by the ability to detect the drowsiness state of an individual. This experiment has been part of the bachelor thesis and aims to highlight some of the true power of Artificial Intelligence [1]. For a full perspective on the topic, an experiment was held in order to emphasize the flexibility and power of facial detection. It aims to analyze the real-time possible drowsiness of a driver by using a key point facial landmark detection and warn the individual when necessary.
Keywords: Artificial Intelligence, Face Recognition, Facial Landmarks, Eye Blink Detection
3. A Correlation Based Way to Predict the Type of Breast Cancer for Diagnosis (p. 19-26)
Shahidul Islam KHAN, International Islamic University Chittagong, Bangladesh
Nowadays, breast cancer is considered one of the most common causes of death among adult women. At the same time, the bright side is that among all the types of cancer, breast cancer is more curable, if diagnosed in the early stages. In this paper, the diagnosis of breast cancer has been proposed using the least possible number of features based on correlation. In the proposed method, we have used correlation to find the strength between the input and the target features. Then we provided a way to create a new subset that consists of only the most relevant features. We have used the Wisconsin breast cancer data set (WBCD) for the experiments. The performance of the model is justified using classification accuracy and the f-score. The result shows that our proposed method obtained the highest classification accuracy (95.26%) with the Random Forest classification using only 4 features from 29 available features, which led to a reduction of 86% in data set size.
Keywords: Health Data; Feature Selection; Correlation; Breast Cancer; Classification
4. Improving the Treatment Process of Bengali Autistic Children using Specialized Mobile Application (p. 27-34)
Rashid Al SHAFEE, International Islamic University Chittagong, Bangladesh
Rakibul HUDA, International Islamic University Chittagong, Bangladesh
Mohammad Imran HOSSAIN, International Islamic University Chittagong, Bangladesh
Md.Mahmudul Hasan SHOHAG, International Islamic University Chittagong, Bangladesh
Shahidul Islam KHAN, International Islamic University Chittagong, Bangladesh
Many children in Bangladesh have ASD. The rate of Autism Spectrum Disorder (ASD) is increasing in Bangladesh and other countries, day by day. Autistic children find it difficult to talk and express themselves regarding what they want or not. Also, some autistic children are not comfortable dealing with the outside world. For example, they do not feel comfortable in social settings or in any program. There are some schools and organizations where many kind-hearted people are trying to help those autistic children in many ways. We all know that there is no cure for autism. But it can be reduced. After good treatment, an autistic child can recover. To help the treatment process, we have developed an interactive app that will help them to cope with social events and places, as well as help them with verbal tasks. We have developed a model to access the severity of an autistic child and help the child to improve communication. This paper presents our interactive app and also provides a concise comparison of it with existing apps to support children with ASD.
Keywords: Autism, ASD, Android Apps, Bengali, Machine Learning, ABLLS
5. Solutions for Relaunching Art Consumption After COVID-19 - From the Perspective of Consumers with Higher Education (p. 35-46)
Iuliana COMAN, The Bucharest University of Economic Studies, Romania
The Covid-19 pandemic brought major changes to most areas of activity. Art was no exception and faced significant changes in both consumer behavior and the behavior of art producers who had to adapt to the difficulties of this period. The paper aims to present the image of art consumer behavior, including the socioeconomic context generated by the coronavirus pandemic in Romania, and to analyze the possible relaunching measures that can be taken for the restoration of the art market after the coronavirus pandemic. Another goal of the paper is to open this subject for future analysis, underlining the influences that art manifests in society.
The analysis uses macroeconomic indicators provided by the National Institute of Statistics, Eurostat, estimates of companies playing in the Romanian market, and a survey conducted in the first week of May 2020, during the COVID-19 crisis, on a sample of 200 persons from the south of Romania. The survey goal was to capture the image of art consumer behavior, the influence that art has on the lives of respondents as well as the respondents' attitude towards the possible relaunching measures that can be taken for the restoration of art consumption after the coronavirus pandemic. Art continued to influence the lives of individuals and society during the COVID-19 period, with a wide range of roles played in the evolution of society. The online promotion of all art forms was the relaunch measure that was best received by most of the respondents. In the assessment of the possible relaunch measures, an important role is played by the presence of art in the respondents' lives and their convictions regarding the influences of art upon society.
Keywords: Art Consumption, COVID-19, Solutions for relaunching art consumption
6. Oracle Machine Learning for Python in APEX - Analyzing and Predicting CO2 Emission by private vehicles (p. 47-56)
Miruna TELEASA, The Bucharest University of Economic Studies, Romania
Alexandra Teodora BARDICI, The Bucharest University of Economic Studies, Romania
Nowadays, the global warming threat is a highly discussed matter. One of the factors that accelerates this process is the air pollution that can be caused by cars' emissions. This paper concerns how the size of the engine, the type of fuel, the fuel consumption and the transmission type influence the emission of CO2. In order to understand and predict that variable, we used several machine learning algorithms, such as Regression for Generalized Linear Model or K-Means for Hierarchical Cluster Model. The technology that empowered this analysis was Oracle's Machine Learning for Python (OML4Py) that allowed us to integrate both database and data management concepts and data analysis algorithms. By doing that, we managed to discover a pattern for the emission of CO2 based on the factors previously mentioned and, after that, predict future levels of CO2 emissions for various car models.
Keywords: Machine Learning Algorithms, Python, Oracle Autonomous Database, Environment, Regression, K-Means
7. Deep Learning-based Solution for Mental Health Issues (p. 57-70)
Andreea RIZEA, The Bucharest University of Economic Studies, Romania
The current paper proposes a solution for the nowadays mental health problems using artificial intelligence algorithms. Making use of natural language processing (NLP) techniques, the main idea is to construct a conversational agent which can act as a psychologist. This can be possible by implementing sentiment analysis on the patient's input text. In order to cope with the user's feelings, the chatbot is developed to perform cognitive behavioral therapy (CBT) exercises with him or her. These exercises are effective even in an online environment. The analysis performed by the sentiment model will detect a dominant emotion in the user's behavior and in this way the bot will adapt the conversation for obtaining better results.
Keywords: Deep Learning, Natural Language Processing, Chatbot, Artificial Intelligence, Cognitive Behavioral Therapy
8. Human Resources Allocation Solution (p. 71-84)
Mihai-Cristian BALTAC, The Bucharest University of Economic Studies, Romania
As technology advances, so do its applications and standards. We are at a crossroads in a civilization that has grown based on the automation of operations and the development of technology to better human lives. As additional programs that do the same thing arrive, both large and small businesses utilize them, promoting their development. The approach in this paper is to address the major issue, which is the most frequently utilized capabilities in a company, whether it is IT or event production. My work involves minimizing these applications and developing a standard that may subsequently be updated on needs and demand.
Keywords: HRIS, Tasks, Meetings, Resource Allocation, Management
9. Making use of digital innovations in Business Process Improvements (p. 85-98)
Radu SAMOILA, The Bucharest University of Economic Studies, Romania
Business Process Management (BPM) concept is more and more influenced by the emerging technologies changing the conventional way of improving or optimizing the business processes. Digital innovations and technology have been used to improve and manage people, products, programmes and projects across the globe. Connected devices, big data analytics, cloud computing, robotics process automation, 3D printing or other emerging technologies are commonly used to generate more efficient and effective business processes.
Therefore, nowadays, the businesses are continuously undergoing changes which can be rapid and significant. There are many methodologies/ approaches available to support the businesses improve their processes through change. A strong connection exists between business process improvements and digital innovation as, through a proper combination, has a great potential of generating significant long-term benefits for organizations. Hence, focusing the organization's strategies on digital technology can be a successful direction.
The purpose of this paper is to present potential ways of integrating process improvements methodologies with digital innovation and the main market trends. It focuses on market trends concerning business process improvements and digital innovations. The work encompasses a 'status quo' review in this field together with the main trends in terms of new technologies and their adoption by organizations. Companies started to utilize a wide range of communication channels, integrated technologies or social media platforms to connect with their peers, employees, and clients but also to boost collaborative partnerships. Technology is used to create more participatory businesses by improving collaboration. Furthermore, newest technologies can support effective monitoring of business processes across diverse products and services and counterparties (e.g., suppliers, clients).
This work's conclusions confirm the significant role of digital innovations in business process improvements and provide further insights on how to embed a wide range of new technologies within the organizations' efforts to improve their business processes and operations.
Keywords: process improvement, improvement methodology, digital innovation, emerging technologies, process mining, business process management