CONTENTS
|
The Classification Module Intended to Be Used in the Didactic Assessment Natalia BURLACU, Alexandru COZLOVSCHI 5 The paper's purpose is to describe a modular component of a complex system capable of generating didactic assessment test items with a pronounced adaptive character. The respective component has a potential for integration into various Learning Management Systems (LMS) platforms, such as Moodle, and could be exploited by a wide range of users: from teachers and students enrolled in various forms and/or levels of education to LMS platform administrators and LMS systems’ developers, accessible in open-source and/or commercial formats. From a technical perspective, the component represents a classifier that turns out to be a fragment of a program product that interacts with the database, but especially with the LMS system question bank, created by the course developer, in order to satisfy the functionalities of the software product in question. The developed classification module was designed to operate based on labels created through artificial intelligence (AI) and machine learning (ML). Thanks to the aspects specified at the implementation level, AI and ML, these bring the respective classifier into the category of supervised learning program products. Aligning with national and international trends regarding the educational system's digitalization, this paper falls into fields such as applied computer science, software engineering, and artificial intelligence. Keywords: Modular classifier component, Labels classifier, Supervised learning, Educational program product, AI for e-learning Human Factors in Social Engineering: Psychological Components and Profiling of Targets Andreea BURADA 14 This paper examines the psychological underpinnings of human susceptibility to social engineering, with a focus on identifying and analysing the cognitive, emotional, and behavioural components that contribute to target vulnerability. Integrating insights from cybersecurity studies and psychological theory, this research seeks to construct a nuanced understanding of how threat actors manipulate human factors to bypass security protocols. Through critical analysis of empirical studies, documented attack scenarios, and profiling literature, the study aims to determine the strongest factors that influence one's susceptibility to becoming a victim, as well as understand the process behind a threat actor. The paper defines multiple categories of users that are deeply correlated to social engineering attacks and aims to establish an early methodology of determining one’s typology. Keywords: Cybersecurity, Social engineering, Psychology, User typologies Securing Business Applications in the Age of Digitalization: Challenges and Strategies for Data Confidentiality Claudia PARASCHIV 26 This paper examines rapid and generated integration into business applications and highlights the transformational potential in areas such as content, acquisition assistance, and process automation is securing sensitive inputs/outputs, preventing model abuse, and ensuring transparency. The proposal is for a more multi-tiered approach involving data minimization, zero-travel architecture, and continuous model auditing. The rapid expansion of digital transformation and interconnected systems has intensified cyber risks, making cybersecurity audits essential for safeguarding organizational assets. This study reviews current literature, regulatory developments such as GDPR updates, and leading IT audit frameworks - including COBIT, ISO/IEC 27001, NIST CSF, and SOC reports - to highlight the growing need for integrated security strategies that combine technical controls with strong organizational processes. A conceptual solution is proposed through an iOS-based cybersecurity audit application designed to replace traditional manual methods. The application streamlines workflows, automates data handling, and provides real-time insights, improving audit efficiency, accuracy, and compliance. Findings emphasize that modern, technology-enabled audit tools are crucial for addressing evolving threats, increasing regulatory demands, and the security challenges introduced by AI, IoT, and cloud systems. Effective cybersecurity audits remain vital for organizational resilience, business continuity, and the protection of digital assets in the advancing digital landscape. Keywords: Generative AI, Data Confidentiality, Cybersecurity, Business Applications, AI Security, Risk Management, Audit Ethical AI for Inclusive Economic Growth Muhammed MIAH 35 With artificial intelligence (AI) increasingly infiltrating multiple industries, the economic benefits are countered by concerns about fairness and inclusion. This paper covers the implications of the integration of AI in economic development and stresses the importance of leveling the field if Smart City and Blockchain digital disruptions are to work for all people in the Digital Age. We examine the ethical structure underpinning AI deployments and discuss use-cases of successful and failed implementations. To this end, we adopt qualitative methodologies to enu-merate the central issues and suggest ways in which an inclusive AI ecosystem can be nurtured. The results highlight the need for stakeholder involvement, regulatory pathways, and ethical principles to address systemic imbalances and establish more equitable systems in the AI era. Keywords: Artificial intelligence, Inclusion, Economic growth UrbanScore: A Real-Time Personalized Liveability Analytics Platform Alin-Vladut VRINCEANU 47 This paper introduces UrbanScore — a real-time web platform that computes a personalized liveability score for any urban address. The system fuses five data streams: (i) address geocoding via Nominatim, (ii) facility extraction from OpenStreetMap through Overpass QL, (iii) segment-level traffic metrics from TomTom Flow v10, (iv) hourly air-quality readings from OpenWeatherMap, and (v) user-declared preference profiles, all persisted in an Oracle 19c relational store. Six sub-scores (air, traffic, lifestyle, education, metro access, surface transport) are derived, adaptively weighted and combined; an OpenAI large-language model then converts the numeric results into concise, user-friendly explanations. A pilot deployment covering the 226 km2 metropolitan area of Bucharest evaluated 3 450 unique addresses over four weeks. Median end-to-end latency was 2.1 s (p95 = 2.9 s), meeting the !3 s non-functional requirement. Aggregate scores ranged from 34 to 92 (mean 68, SD 11), with high-scoring clusters along metro corridors that pair abundant green space with PM2.5 levels below 35 μg m−3. A detailed case study of the Tineretului district produced an overall score of 91/100 and demonstrated how the narrative layer guides users toward comparable neighborhoods. Limitations include dependence on third-party API uptime, spatial bias toward well mapped OSM regions and the absence of noise and crime layers, cited by 18 % of survey participants as a desired enhancement. Overall, the results show that open geodata, commercial mobility feeds and conversational AI can be integrated into a performant, explainable decision-support tool that places "liveability analytics" in the hands of every house-hunter, commuter and city planner. Keywords: Smart city, Liveability, Geodata, Urban area scoring A Mobile-Centric Conceptual Framework for Food Security Assessment Paul POCATILU, Eduard BUDACU 60 Food security is a critical research area with significant implications for population well-being and sustainable development. Existing standards, procedures, and methodologies for food security assessment mainly rely on indicators defined at the national level and derived from macro-level data. In this paper, we propose a mobile-based solution that enables real-time assessment of food security through indicators computed at multiple levels, including individual, household, regional, and national scales. The proposed solution models the interaction between food producers, retailers, and consumers, allowing data aggregation and analysis at the national level. Data are collected from heterogeneous sources - such as sensors, Internet of Things (IoT) devices, human input, and open data sources - using diverse formats. These data are normalized and aggregated through a dedicated processing component. Based on these elements, the paper introduces a conceptual architecture that integrates data acquisition, processing, and indicator computation components within a unified mobile-centric framework. The main objective of the proposed architecture is to increase transparency and enhance individual awareness, thereby supporting informed decision-making related to food security. Keywords: Food security, Metrics, Indicators, Big data, Mobile applications Publishing Guide for Authors 71 INFOREC Association 73 |
