Nowadays, huge and accessible data is an ever increasing field of study. The change in technology is, in turn, increasing its degree of interactivity, configuring several scenarios of great complexity in which data is understood on the basis of our interaction with it at different levels. Data visualization involves presenting data in graphical or pictorial form which makes the information easy to take in. It helps to explain facts and determine courses of action. Criminology is an interesting application where data visualization plays an important role in terms of prediction and analysis. Crime analysis plays an important role in devising solutions to crime problems and formulating crime prevention strategies. The purpose of this paper is to evaluate the performance of machine learning algorithms, which can be used for analyzing data collected of the past crimes. We identified the most appropriate machine learning algorithm to analyze the collected data from sources specialized in crime prevention. This study helps the institutions against crime to better predict and classify it.
In today's data-driven world, data storage and information extraction are key processes where the focus of researchers and industries is centralized. While relational databases are widely used, knowledge graphs have emerged as a cutting-edge idea and have begun to compete with them as a result of utilization from renowned companies. Nevertheless, creating knowledge graphs is a time-consuming process that needs domain experts' support. This motivated us to research automatic or semi-automatic creation of knowledge graphs from structured or unstructured data. To do that and comprehend the newest advancements in this field, we have analyzed papers published in the recent five years in well-known libraries such as ACM, IEEE, Springer Link, and ScienceDirect. The analysis takes into account the process of building knowledge graphs, which encompasses the steps involved in managing unstructured texts, defining nodes and relationships between them, and developing ontologies. Moreover, widely used machine learning algorithms including support vector machines, neural networks, random forests, and logistic regression, and other algorithms such as K-Means, TF-IDF, BERT, and skip-gram, the usage of graph database platform Neo4j and Python scripting language, were considered. Conclusive to the study, there exist some semi-automatic approaches but the fully automatic ones remain as ideas.
During the last decade, educational institutions have made many steps forward, not only in the teaching of technology, but also using it, mainly in the development of new information systems, which are increasingly required in all sectors of life, including natural sciences. Nowadays ICT is becoming key elements on teaching of the new generation. In the study are presented different platforms that can be used for teaching purposes in pre-university cycles. Platforms are discussed for their accessibility, how they work, how user-friendly are, the benefits of using them, and comparing them.
In the fintech industry, credit scoring plays a vital role in helping lenders assess the creditworthiness of potential borrowers. While traditional methods rely on regression analysis, machine learning techniques have become a popular alternative due to their increased accuracy and efficiency. However, effective credit scoring involves more than just selecting the right method; it requires a robust risk management framework that considers various data sources. In this study, we evaluate the effectiveness and efficiency of regression analysis and machine learning techniques in predicting creditworthiness, while also considering their role in an overall risk management strategy.
With the development of information and communication technologies (ICT) and the increasing of online teaching materials, ICT is becoming an essential aspect of teachers’ education and competencies. This paper aims to investigate how and why Albanian biology student-teachers use ICT during their master studies. The study method involved a survey (n = 56) of second-year biology student-teachers studying at the Faculty of Natural Sciences in two consecutive academic years, 2021-2022 and 2022-2023. The survey explored several topics, including general characteristics (age, gender, academic performance), access to digital equipment, digital competence, and the use of ICTs during studies. Our results show that students have low access to digital equipment. Students with high and average academic performance spent more time using ICT for study purposes than those with low academic performance (p<0.05). More than 90% of students emphasize that access to digital equipment and training is crucial to help them integrate ICT in their classes as teachers.
The COVID-19 pandemic has been characterized by many controversies regarding the illness itself as well as the vaccination process. Social media platforms play a major role in spreading both valuable and scarce information. This paper aims to conduct a social network analysis of Twitter posts mentioning one of the three major vaccine producers. Twitter was chosen because of its user base, open API access and the vast amount of information spread. Data were collected daily from Twitter API 1.1 over a period of nine months from November 2021 to July 2022. Graph metrics, groups and node metrics were calculated using SNAP. The analysis is focused on the most important nodes in the network ranked by betweenness centrality. For the highest ranked user, the content of his posts and the amount of engagements was analyzed. The results show that the highest ranked users are usually (not always) non-professionals who mainly post misinformation, fake-news or only negative true information about vaccines. Another interesting fact revealed is that some users are present in different datasets and their posts get engagements from users not speaking the same language. A more thorough analysis of this data using other techniques such as calculating the path of the information flow may reveal further valuable information.
Cloud technologies have covered the information technology landscape in the recent 15 years. They have been huge enablers of various IT startups and also empower large organizations through increased performance, scalability, and unprecedented resources optimization. Despite the potential for cloud technology to quickly bridge gaps in know-how, infrastructure, and budget that are common in developing countries, the pace of cloud adoption has varied across different regions and countries.. In this paper we report on an empirical study that aimed highlighting the influencing factors of cloud adoption in Albania. Various cloud adoption influencing factors that are reported in the literature have been investigated through a questionnaire filled by 71 members of the Albanian information technology community. Most of them work as software developers and the their respective organizations have an international market scope (offshore services). Through inferential statistics, results show that the most influencing factor of cloud adoption in Albania’s case is availability. Other confirmed influencing factors are cost, performance, and security.
This study contributes to the deep learning literature by investigating the applicability of different DL models to forecasting monthly LEK/EUR exchange rate. To demonstrate the effectiveness for exchange rate forecasting of this models we examine the performance of several deep learning techniques (DFNN, LSTM and 1D-CNN). For each architecture, we have used different configuration and diverse techniques to avoid overfitting of the models. The accuracy evaluation of each model was based on the out-of-sample prediction for different horizon (3, 6 and 12 months ahead), by analyzing the model estimation for preand postCovid pandemic. The comparison results show that the LSTM model with two hidden layers stands out as the best prediction model in the run-up to forecast three and six months ahead, followed by the three-layered 1DCNN model. However, they change places in the race for the 12 months horizon as the 1DCNN-3L becomes the first-best predicting model while leaving the LSTM-2L rank in second. These results demonstrate the potential of deep learning techniques, and also, they emphasize the importance of well configuring, implementing and selecting the different topologies.
This study provides an analysis of papers related to Home Energy Management (HEM) methodology and its potential for optimizing energy consumption in IoT-enabled smart homes. Innovative solutions such as machine learning algorithms, thermal imaging, and IoT sensors are discussed as strategies to improve energy efficiency, reduce waste, and improve security. The importance of sustainable energy systems and cloud-based infrastructures is emphasized, and the need for further development is discussed. The potential of these technologies to reduce carbon emissions and improve energy efficiency while maintaining user comfort levels is highlighted.
In recent years, the healthcare industry has been on the forefront of adopting cutting-edge technologies in order to deal with data integrity, security of the information, interoperability and information sharing between patients and healthcare providers. This paper proposes a model to improve the Radiology Information System (RIS) by integrating blockchain technology and the Internet of Things (IoT). The integration of these technologies has the potential to improve patient care by ensuring real-time monitoring of patients, a secure and tamper-proof system, as well as secure management and exchange of patient data. In addition, this paper discusses the advantages of using blockchain technology and IoT in healthcare, as well as the ways in which these technologies can address the challenges that currently exist within healthcare systems.
This paper aims to analyze climate change data using Hive and Hadoop, two big data processing frameworks. We collected data from various sources and used Hive to store and manage the data, and Hadoop to process it. By using these tools, we were able to perform complex queries and analysis on large datasets with ease. This paper also used Super Set, a data visualization tool, to create interactive dashboards that display the results of our analysis. The dashboards help users to explore the data and gain insights into climate change trends. Our findings show that the temperature in the city of Durrës has increased by 1.1°C since the pre-industrial era. This paper demonstrates the usefulness of big data processing tools for analyzing climate change data and provides valuable insights into the impact of global warming on our planet.
A city is "smart" if it uses different types of sensors and devices to collect data and provide information that is used to efficiently manage resources. The data can be processed and analyzed in order to monitor and manage traffic and transportation systems, waste recycling, water supply networks, air pollution, and other public services. The use of sensors would enable the collection of these data and their transfer in real time to the users. Based on the information provided online by a Swiss company called IQAir, it appears that Tirana has significant air pollution. Through a web application we could enable the possibility to receive and display data from the sensors and send them to a database so we can use them in different situations. In this paper we will show the use of the Internet of Things (IOT) to monitor pollution levels, especially levels in many positions in the Faculty of Natural Science where the number of students can be considered high. The aim of this paper has a correlation with people heath especially for this case study is students’ health. It serves for more detailed studies or evaluate whose are the element causing the greatest air pollution and a prediction of what measures should be taken to prevent it. Creating a suitable environment to make this information to be detailed in real-time of course will affect other fields and aspects of researchers in the future.
Nowadays with the development of technology and the fact that it has influenced every aspect of people’s lives, the information is the most essential factor to be considered, since it is the fundamental in which technology is being built. On the contrary, cybersecurity attacks are growing rapidly year after year since everyone around the world is seriously involved in this wild race of having access to the information owned by the others. Data breaches are also growing since hackers and non-authorized parties are attacking organizations, companies and other institutions of high importance. As a result, more and more companies are considering solutions that not only will protect the information, but will also keep un-authorized parties away from having access to it. Encryption is considered one of the most classic ways to ensure that sensitive information is converted into secret codes that will hide the information from un-authorized access. But what’s the point to encrypting the information, when the keys are not totally safe and are at risk of being exposed. Cryptographical keys should be stored, kept and managed carefully, since their exposure would disclose the sensitive data the same way it as not even encrypted. That is the reason why companies, organizations and institutions globally are using Hardware Security Modules as the solution to secure and protect their sensitive data and to provide functionality for their cyber security purposes, including authentication, authorization, data confidentiality and data integrity. This paper aims to give a brief analysis of what a HSM is, how it functions and how it helps the companies and organizations in the context of cybersecurity. Furthermore, it will provide information on types of HSMs, architecture, different options offered on the market and most common use cases inthe recent years.
Several techniques for the automatic detection of violent scenes in videos and security footage appeared in recent years, for example with the goal of unburdening authorities from the need of analyzing hours of Closed-Circuit TeleVision (CCTV) clips. In this regard, Deep Learning-based techniques such as Recurrent Neural Networks (RNNs) and Convolutional Neural Networks (CNNs) emerged as effective for violence detection. Nevertheless, most of such techniques require significant computational and memory resources to run the automatic detection of violence. Thus, we propose the combination of an established CNN, MobileNetV2, designed for the use in mobile and embedded devices with a recurrent layer to extract the spatio-temporal features in the security videos. A lightweight model can run in embedded devices, in a edge computing fashion, for example to allow processing the videos near the camera recording them, to preserve privacy. Specifically, we exploit transfer learning, as we use a pre-trained version of MobileNetV2, and we propose two different models combining it with a Bidirectional Long Short-Term Memory (Bi-LSTM) and a Convolutional LSTM (ConvLSTM). The paper presents accuracy tests of the two models on the AIRTLab dataset and a comparison with more complex models developed in our previous work, in order to evaluate the drop of accuracy necessary to use a model compatible with limited resources. The network composed of MobileNetV2 and the ConvLSTM scores a 94.1% accuracy, against the 96.1% of a model based on a more complex 3D CNN.
Data is very important for any business. Storage, management and use has helped them in their work. Making decisions based on data through the application of Data Warehouses or BI has been implemented for more than a decade and is increasing the interest more and more for managers. Technological developments and the addition of new trends in BI make it a technology that will be used for a long time. In this scientific paper we will analyze self-service BI qualified as a wish fulfilled for businesses. This study aims to explore study the benefits and challenges and how have they evaluated it different scientific researchers.
Machine learning (ML) can be used to analyze and predict student success outcome in order to avoid various problems and to plan future actions for helping students overcome difficulties during their study. This paper analyzes data from a digital system of 309 students who were enrolled in the Specialist Study in Trade Business at the Faculty of Tourism and Rural Development from 2010 to 2018. The paper explores the impact of four different data sets on the performance of ML algorithms. The first data set is with partially missing data on the length of study (around 7%), the second one uses arithmetic means in place of missing data, the third is based on median values, whereas the fourth uses the geometric mean instead. Four popular ML algorithms were considered: k-Nearest Neighbors (KNN), Naïve Bayes (NB), Random Forest (RF) and Probabilistic Neural Network (PNN). All of them are used for predicting student success based on achieved ECTS credit points. The aim of this paper is to compare and analyze the impact of missing values on the results of individual ML algorithms.
This paper focuses on the issue of image search engine results, which many authors claim are the result of biases, thereby multiplying those same biases. The Google search engine was analysed, where images of women from nine countries of the European Union were searched, but using three different languages to generate queries. In this way, we tried to compare the prejudices of other language groups reflected in the results obtained using the search engine. Two thousand seven hundred images of women were collected, and to quantify the results, an artificial intelligence algorithm was used to calculate the probability of nudity in the image. The hypothesis that there is no difference between the perception of women for a particular country by English, Chinese and Russian language users was generally rejected because there are statistically significant differences in 6 out of 9 countries.
Data mining and machine learning have become a vital part of different disease detection and prevention. One of them is diabetes. The purpose of this paper is to evaluate data mining methods and their performances that can be used for analyzing the collected data about the diabetes. We identified the most appropriate data mining methods to analyze the data by comparing them theoretically and practically. Some attributes of this dataset are: Age, Body Mass Index, Insulin, Glucose, etc. Methods are applied on these data to determine their effectiveness in analyzing and preventing diabetes. Evaluations on the data showed that the method with a higher performance is “Decision Tree”. This was achieved by some performance measures, such as the number of instances correctly classified, accuracy, precision, recall and F-measure, that has brought better results compared to other methods. We come to the conclusion that the data mining methods and machine learning contribute to the predictions on the possibility of occurrence of the diabetes.
Smart cities have emerged lately as a solution for the growing population and sizes of cities. This means that a better resources’ management is needed to be developed in the same time. A combination of cities and technology is today’s digital dream. We live in the age of technology and IoT (Internet of Things) plays a key role in developing smart cities. From this point of view, city planners should think seriously about this issue in order to forestall their future. The concept of smart city is related to sustainability, mentioning here many aspects such as reduction of environmental pollution, increase of energy efficiency, smart traffic management system, E-health services, etc. The main stakeholders are city’s residents, its government and also private enterprises. In this paper, we identify and analyze the main aspects of the city infrastructure as an integration of IoT technologies, highlighting the main approaches and challenges.
This paper examines the challenges of teaching technical courses through e-learning in Nigerian tertiary institutions during the COVID-19 pandemic lockdown. The COVID-19 pandemic has widespread aftereffect on education systems all over the world, with Nigeria, not an exception. The lack of the requirements needed for remote education during the worldwide lockdown caused by the COVID-19 pandemic has impeded teaching and learning. In the underdeveloped world, home education worked well for a few students who had adequate resources accessible to them and were adaptable to remote learning. This has not just affected teaching and learning but has posed a big problem in teaching technical courses. Problems associated with teaching technical courses in Nigeria during the pandemic lockdown especially the difficulties in handling practical and technical processes online are discussed. Students and educators at different programmes at the Federal Polytechnic Nekede Owerri, Nigeria will be interviewed to ascertain the most pressing problems. The paper will also proffer possible solutions through its recommendations at the different levels of the concerned stakeholders in the Nigerian education sector. © 2021 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
