Conference Agenda

The rapid adoption of Generative Artificial Intelligence, especially Large Language Models (LLMs), is reshaping backend development by automating essential tasks such as code generation, automated testing, documentation, and API design. Despite their widespread use, the combined implications of LLMs on productivity, code quality, and security remain insufficiently consolidated in the current body of research. This study presents a Systematic Literature Review (SLR) aimed at analyzing how LLMs influence backend development processes, focusing on opportunities for efficiency as well as emerging security risks. Using the PICO methodology and PRISMA guidelines, 36 peer-reviewed studies from the Scopus database were evaluated.

Findings reveal that LLMs are predominantly integrated into hybrid development workflows, where they support developers by generating initial code for endpoints, validation layers, and database operations. These tools consistently improve productivity, particularly in high-complexity and high-risk domains such as finance and healthcare. However, the evidence also shows that AI-assisted code tends to contain a significantly higher density of vulnerabilities—including injection flaws, improper authentication logic, weak input validation, and misconfigured authorization checks—when compared to traditional development practices. The review also highlights a tendency among developers to overtrust AI-suggested code, which exacerbates security risks.

The study concludes that while LLMs are powerful enablers for accelerating backend development, their responsible adoption requires rigorous manual review, security-focused prompt engineering, and standardized metrics for quality evaluation. These insights provide a consolidated foundation for practitioners and researchers seeking to integrate LLM-based tools safely and effectively.

Given the increasing environmental crisis and the logistical challenges inherent in municipal solid waste management in modern cities, due to population growth and limitations in final disposal, it has become essential to evaluate advanced technological solutions. Therefore, this Systematic Literature Review (SLR) aimed to analyze and compare the performance of Artificial Intelligence (AI) algorithms applied to waste generation prediction, waste classification, and collection route optimization, against conventional methods. The methodology involved an SLR without meta-analysis, structured using the PICOC strategy and adhering to PRISMA guidelines, resulting in the selection of 56 studies from the Scopus and Scilit databases for synthesis. The findings revealed the consistent superiority of AI approaches. In the prediction domain, Deep Learning and Boosting models (XGBoost, DNN) achieved R² coefficients near 1.00 and predictive error reductions exceeding 40% compared to traditional linear regression. For classification, computer vision architectures like Swin Transformer V2 and hybrid CNN + Morph-HSV models achieved accuracies above 97% (up to 99.58%). In the logistics domain, metaheuristics such as I-ACO and PSO, integrated with IoT, demonstrated high operational efficiency, achieving average reductions of 25% to 42% in distance traveled, fuel consumption, and CO₂ emissions. It is concluded that AI is an essential tool for sustainability, demonstrating high adaptability in diverse urban contexts. However, critical challenges have been identified, such as methodological and metric heterogeneity in studies, which complicate generalization, and the persistent difficulty in discriminating waste based on visual similarity.

This research analyses the evolution and impact of artificial intelligence (AI) in the automation of administrative processes from 2015 to 2025. A systematic literature review was conducted using the PRISMA method, selecting 25 articles from specialized academic databases. The goal was to identify the main applications of AI in administrative contexts, as well as the benefits, limitations, and trends associated with its implementation in public and private organizations. The results show that AI-driven automation significantly improves operational efficiency by reducing time, costs, and human errors, while strengthening decision-making processes. Additionally, it was highlighted that the effective use of these technologies depends on data quality, transparent algorithm design, and human oversight to mitigate biases and ethical risks. Despite its benefits, the adoption of AI faces challenges such as technical limitations, infrastructure deficiencies, training gaps, resistance to organizational change, and concerns about privacy and equity. In conclusion, AI is established as a key tool for optimizing administrative processes, provided its implementation is planned comprehensively and accompanied by appropriate governance frameworks.

The metaverse is consolidating as an emerging digital infrastructure that integrates immersive environments, distributed architectures, artificial intelligence systems, and blockchain technologies, configuring itself as a high-impact sociotechnical ecosystem across multiple productive and social sectors. This study presents a systematic literature review aimed at analyzing its scientific evolution from an engineering perspective, identifying emerging technological, regulatory, and social dimensions. A total of 95 articles indexed in Scopus and published between 2012 and 2025 were examined, applying explicit inclusion, exclusion, and thematic categorization criteria under a structured protocol. The results reveal ten principal dimensions: immersive education, digital health, digital law, business transformation, virtual communication, gender and inclusion, digital art and heritage, cybersecurity, digital property, and technological governance. A significant acceleration in scientific production since 2021 is observed, associated with advances in immersive technologies, artificial intelligence, and decentralized digital economies. Gaps are identified in standardization, interoperability, regulation, and technological accessibility. It is concluded that the consolidation of the metaverse will depend on the design of interoperable architectures, digital governance frameworks, and responsible engineering approaches oriented toward sustainable development

This research work was carried out with the objective of determining the influence of the information system with quick response technology on the process of patrimonial control of one government entity in 2019. The type of study was pre-experimental, with a sample made up of 7 Patrimonial Management experts of one Government Entity. In addition, a data recording questionnaire and a level of reliability questionnaire that were used for data collection and the Microsoft Excel statistical tool XLSTAT was used for data analysis, as well as the T- student test. The dimensions included in the patrimonial control process are affect, inventory taking and supervision, while the dimensions included in the information system with quick response technology were usability, efficiency, integrity and interoperability. The results obtained showed that it is possible to reduce times and, in this way, increase the efficacy in the process of patrimonial control. Based on the above, we can conclude that the information system with quick response technology has a positive influence on the process of patrimonial control of one government entity.

Voice-based emotion recognition presents a fundamental challenge in the field of automotive driving, as the driver's emotional state directly influences their cognitive abilities and decision-making processes. Traffic conditions, such as congestion, rush hour, road infrastructure failures, or accidents, often elicit a range of emotional responses. This study employs semi-synthetic data to analyze continuous audio streams, evaluating the competitiveness of the Adaptive Random Forest (ARF) algorithm for emotion detection in driving scenarios. The proposed methodology integrates a hybrid strategy of real and synthetic data to model dynamically evolving emotional patterns. The experimental results demonstrate that using a mixed data stream significantly improves model reliability and learning capacity, validating the effectiveness of ARF in emotion recognition tasks. These findings not only confirm the potential of the ARF algorithm in real-time emotion recognition systems but also provide valuable insights for the future development of intelligent transportation systems and non-intrusive driver monitoring systems