Search

In the last period, especially during the COVID-19 pandemics, individuals as well as institutions globally and in North Macedonia particularly, have failed to correctly respond to the new challenges related to cyber security, online attacks, and fake news. Being that in a state of isolation and quarantine most governmental institutions have heavily relied on online tools to communicate among each other and with the public, it is quite evident that they have not been well prepared to adopt new technologies. This paper aims to bridge together the needs for technology during the COVID-19 pandemics versus the security challenges that many forget to mention. The primary focus of this paper is to elaborate on the security challenges associated with technology with several examples from incidents around the world and from North Macedonia. As such, it represents a perspective paper with focus on current and emerging advances on IT security for running the “new normal” world.

The interest collected by the main borrowers is collected to pay back the principal borrowed from the depositary bank. In financial risk management, credit risk assessment is becoming a significant sector. For the credit risk assessment of client data sets, many credit risk analysis methods are used. The assessment of the credit risk datasets leads to the choice to cancel the customer's loan or to dismiss the customer's request is a challenging task involving a profound assessment of the information set or client information. In this paper, we survey diverse automatic credit risk analysis methods used for credit risk assessment. Data mining approach, as the most often used approach for credit risk analysis was described with the focus to various algorithms, such as neural networks. This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Peer Assessment is a potentially promising pedagogical approach for enhancing the e-learning and supporting student self-regulated learning. The purpose of this paper is by reviewing the research on current trends on the use of ICT in Education, in particular on peer assessment in e-learning, to propose a new peer assessment methodology using the social media platforms in the digital environment. We conclude that a blended approach is more suitable as it is not possible to have a fully automatic peer assessment methodology. The proposed online model needs to be subject of particular careful monitoring and evaluation from teachers.

In recent decades, machine learning has become a crucial factor in terms of automating business operations and assisting in the decision-making process within an organization. With the huge volume of data generated at an unprecedented rate has motivated researchers and industry analysts to constantly develop effective and efficient analytical models machine learning techniques. This study adds to the data mining community by evaluating some of the most significant text mining techniques and presenting a predictive model that will supposedly ease the process of literature review for researchers. In addition, it compares the execution of the model in terms of cost, energy consumption, accuracy and scalability in three different environments, namely, google cloud instance, google cloud functions and distributed raspberry PIs. Results yielded in our study showed that distributed Raspberry PIs can have a highly positive impact in terms of lowering costs and being energy efficient. On one hand, we found out that machine learning algorithms can be adapted and run on distributed raspberry PIs with low cost and low energy consumption compared to cloud alternatives. On the other hand, this solution does not offer great scalability and it requires more time on management, deployment and configuration. The distributed Raspberry PIs also showed bad performance on execution time compared to the other alternatives when comes to high processing power.

Next Generation Incident Response System (NICS) is a platform developed by MIT Lincoln Lab that is currently being used in Macedonia by the Centre for Crisis Management (CCM). It allows coordination during natural disasters between first responders of various departments and allows them to use state of the art tools to communicate and share information. This research focuses on advancing the platform by introducing intelligent agents to the platform, based on machine learning techniques and natural language processing. Our goal is to leverage data generated in social media and feed NICS with automatically processed information from these media categorized in twelve different needs (categories). This paper presents the current state of our research, preliminary results and final goals. This work is licensed under aCreative Commons Attribution-NonCommercial 4.0 International License.

The paper aim is to define a method for performing video learning data history of learner’s video watching logs, video segments or time series data in consistency with learning processes. To achieve this aim, a theoretical method is introduced. Sequential pattern mining with learning histories are used to extract the most difficult learning subjects. Based on this method, it is designed a model for understanding and learning the most difficult topics of students. The performed video learning history data of learner’s video watching logs makeup of stop/replay/backward data activities functions. They correspond as output of sequence of the learning histories, extraction of significant patterns by a set of sequences, and findings of learner’s most difficult/important topic from the extracted patterns. The paper mostly aim to devise the model for understanding and learning the most difficult topics through method of mining sequential pattern. This work is licensed under aCreative Commons Attribution-NonCommercial 4.0 International License.

The need for independent media and powerful media is a must for any country aspiring to build upon values of a democratic society. Unfortunately, even though Macedonia has often been shaken by huge corruption scandals the general public is often ill informed or misguided by the media. This paper presents our efforts to create tools that will aid investigative journalists to better collect, analyze and present data to their audience. For this purpose a system that collects and organizes public procurement data in Macedonia has been generated. Furthermore, the developed system applies data mining algorithms against the datasets with the purpose of discovering trends, hidden information, relations between entities and anomalies.

Common security problems when creating a new system range from basic browser authentication to physical access to servers. The security perspective in e-learning systems is often ignored, and this why this paper tends to emphasize common security issues when developing new Information Systems. We introduce a three layered security measure, such as: the physical control layer, the software control layer and the social engineering training. These three layers tend in various methods to secure users credentials and other data in the newly created Learning Content Management System (LMS).