Conference Agenda

This academic report provides a critical analysis of the influence of design patterns on the performance and maintainability of contemporary software architecture, with a particular focus on distributed environments such as microservices and blockchain. Through a systematic review of the scientific literature, based on articles published between 2020 and 2025 in databases such as Scopus and IEEE Xplore, this research identifies and classifies various patterns according to their structural, transactional, and security purposes. It finds that while the use of patterns like the "FAN" in microservices significantly increases performance and scalability, it also has technical drawbacks in terms of operational complexity and latency. The impact of artificial intelligence and machine learning on automatic pattern detection is also analyzed, highlighting the optimization that can be achieved in application architectural design despite current challenges related to bias and a lack of standardization. Therefore, the research defines guidelines for pattern selection in digital transformation projects and concludes by stating that their correct implementation requires a thorough analysis of quality objectives and the technological context, thus ensuring the system's sustainability.

Emerging technologies enable the provision of artificial intelligence-based solutions to improve the overall customer experience for various engineering companies. This study aimed to determine the influence of AI assistants on customer experience in Metropolitan Lima. A quantitative, explanatory, non-experimental, and cross-sectional methodology was used with a sample of 377 people to analyze the variables in question and apply statistical techniques to the proposed hypotheses. The results showed a significant influence of the conversational agent's quality dimensions on customer experience. This study concluded that the perceived experience within an environment is 96.1% explained by the behavior of AI assistants due to their technical, semantic, and interactive capabilities in addressing people's needs. Finally, this study contributed to the academic literature by being the first to use DeLone & McLean's Information Systems Success Model in its field.

This study presents an Internet of Things (IoT)-based solution to optimize waste collection management in a sector of the Comas district, Lima. The proposal integrates real-time geolocation of the collection truck, proximity-based mobile notifications, and a household alert activated by an ESP32 module, with the aim of synchronizing waste disposal with the effective passage of the truck. To evaluate its effectiveness, a quasi-experimental design was applied, combining field tests and structured surveys before and after the intervention.

The results demonstrated significant improvements in three dimensions. Operationally, the time that waste accumulated in public spaces was reduced by approximately 90% (from 12.5 min to 1.2 min). Informationally, knowledge of the truck's schedule increased from 30% to 95%, showing that timely delivered signals reduce uncertainty and improve neighborhood coordination. Experientially, usability, satisfaction, utility, and notification clarity scales showed consistent increases (d ≥ 0.8), with adequate levels of internal reliability (α ≥ 0.78).

The technical architecture—composed of a mobile application, Firebase, Google Maps, and a household IoT module—proved to be viable and replicable in similar urban contexts. Overall, the findings confirm that IoT can optimize waste collection by aligning citizen decisions with the actual service operation, reducing waste accumulation and improving user experience. The research provides evidence and a practical framework for future large-scale implementations.

This research evaluated the impact of the CAJAMARGA GO mobile application on the promotion of sustainable tourism in Cajamarca, Peru, in alignment with Sustainable Development Goals 8 and 12 of the 2030 Agenda. A pre-experimental design with pre-test/post-test measurement was employed, using a non-probabilistic sample of 50 participants (tourists and service providers). The data collection instrument, validated by five experts (content validity index = 0.92) and demonstrating acceptable reliability (Cronbach’s alpha = 0.87), measured three dimensions: knowledge of sustainability, intention toward responsible behavior, and satisfaction with the digital tool. The application was developed using the agile SCRUM methodology (three two-week sprints), integrating geolocation via the Mapbox API, route optimization using Dijkstra’s algorithm, 3D modeling with Three.js, and a conversational assistant based on retrieval-augmented generation (RAG) implemented in n8n with a local knowledge base. Results, analyzed using a paired t-test (SPSS v.28), showed statistically significant increases (p < 0.01) in knowledge of sustainable practices (+38.6%), intention toward responsible behavior (+32.4%), and perceived satisfaction (4.6/5.0). The conversational assistant resolved 92% of queries without human intervention. It is concluded that CAJAMARGA GO constitutes an empirically validated technological solution to strengthen sustainable tourism governance, with scalability potential in rural destinations of the Andean region. The main contribution lies in the integration of low-cost artificial intelligence with certifiable sustainable tourism standards.

At present, verbal communication between infants and their caregivers constitutes a clinical and everyday challenge, since many first-time parents and daycare staff often make ambiguous interpretations of the signals used by babies to express their needs. The objective of this research was to develop an intelligent system capable of detecting and classifying infants’ emotions in real time through the analysis of their gestures and facial expressions, as well as acoustic signals (crying), implemented and evaluated at the childcare center “El Nido.” The study was applied in nature and, according to its approach, quantitative, with a pre-experimental design. The population consisted of 100 infants; however, a non-probabilistic convenience sampling method was used, selecting a sample of 20 infants. Finally, the results showed that the Multimodal Intelligent System for the Early Detection of Infant Needs and Emotions through Real-Time Facial Expression Analysis achieved a 14% uncertainty rate and an 86% accuracy rate in detecting needs.

High Blood Pressure (HBP) is one of the leading causes of cardiovascular disease, premature mortality, and catastrophic health expenditure in Latin America, especially when it coexists with diabetes mellitus and progresses to chronic kidney disease (CKD). Despite the widespread availability of effective and low-cost antihypertensive treatments, traditional management models, reactive and focused on isolated clinical episodes, have shown a limited capacity to contain the lack of control and its clinical and financial consequences. That is why our objective is to develop a predictive model of risk of hypertensive decontrol and nephrological progression, and to propose a prescriptive analytics approach to optimize the allocation of financial resources in health. A retrospective study is carried out analyzing 24.2 million transactional records of medical care, pharmacy and diagnoses corresponding to 1.02 million patients treated between 2022 and 2024, using Big Data architecture based on Apache Spark. Different Machine Learning models were trained, and the Gradient Boosted Trees (GBT) model was chosen for the prediction of complications. As a result, we were able to identify a critical data quality gap. The predictive model reached a recall of 89.74%. Prescriptive analysis demonstrated that preventive intervention reduces cost compared to delayed renal treatment. We conclude that the sustainability of health systems requires a transition from reactive models to prescriptive nephroprotection strategies, supported by advanced analytics and systematic auditing of clinical data.