Conference Agenda

The aim of this investigation is to develop a smart garage access control system to improve the vehicle license plate recognition process, optimizing accuracy and response times in the identification and registration processes. Many current systems rely on manual intervention, causing delays and inconveniences. This system is based on the automated identification and verification of vehicle license plates, ensuring precise and efficient recognition. To achieve accurate recognition, YOLO neural networks, Python image processing techniques, and Optical Character Recognition (OCR) were used to extract data from the captured plates. The IP camera captured the vehicle plates, and access was validated by comparing the data with a database of authorized residents. These technologies enabled license plate detection in real-time, even under various environmental conditions, ensuring high accuracy. The system records and monitors activities in real-time, providing valuable data on the performance of license plate recognition. The user interface displayed images and analysis results, allowing for automatic garage door opening or manual intervention in case of error. This ensured more agile and efficient processes compared to traditional manual methods.

This research article aimed to determine the impact of a residential video surveillance system employing computer vision for the detection of suspicious behaviors in the province of Trujillo. The study was applied or technological in nature, with an experimental design, and the sample consisted of 12 residences in the city of Trujillo. Observation sheets were used as the primary instruments for data collection. The results showed that the implementation of the system reduced the detection time for suspicious behaviors by 20.83%, in addition to improving accuracy by 10.39% and both precision and sensitivity by 7.5%. It is concluded that the implementation of a video surveillance system integrating computer vision significantly enhances the efficiency of detecting suspicious behaviors, establishing itself as a reliable tool for residential security.

This study analyses the development of an educational chatbot as a tool to improve the learning experience of students in secondary schools. The implementation of innovative technologies in the educational field is crucial to meet the needs of students and enhance their academic performance. Currently, artificial intelligence, through applications such as chatbots, offers opportunities to personalize learning, facilitate access to information, and provide constant academic support. The main objective of this research is to develop an educational chatbot and evaluate its impact on the learning experience of secondary school students. The methodology used is of an applied type with a mixed approach, which includes the development of the chatbot and its validation by measuring student satisfaction, frequency of use, and compliance with functionalities. To do so, a bibliographic review of previous studies was carried out and data was collected through surveys applied to students. The expected results indicate that the educational chatbot will not only facilitate the resolution of frequently asked questions and the recommendation of relevant content but will also contribute positively to the students' perception of their learning process. Finally, this study highlights the importance of integrating AI-based tools into educational settings, recognizing their potential to transform the learning experience and improve academic outcomes in secondary schools.

The main objective of this study is to develop an expert system based on fuzzy logic to recommend personalized extracurricular activities to high school students. For this purpose, Mamdani's fuzzy inference method was used, implemented in Python with the Skfuzzy and Tkinter libraries, and validated by means of questionnaires applied to a sample of 30 students. The results revealed that the system provides recommendations aligned with the interests and skills of the users, with high levels of satisfaction and perception of academic relevance. In addition, fuzzy logic was found to provide flexibility and accuracy compared to traditional approaches, providing multiple options suitable for each student. In conclusion, the fuzzy logic-based expert system proved to be an effective tool to support the choice of extracurricular activities, contributing significantly to students' personal and academic development.

Many organizations find data reduction and analysis complex and costly. The Teacher Performance Assessment (VDD) process evaluates student satisfaction through open-ended questionnaires, using an algorithm with regular expressions for searching. However, this method may be outdated due to recent advancements in natural language processing (NLP) and artificial intelligence. These technologies can improve the analysis of unstructured text in the VDD by applying computational hermeneutics and NLP techniques. Tests indicate that NLP enhances the contextual search of relevant terms, yielding more accurate teacher evaluations while minimizing false positives and negatives. However, NLP implementation is more costly and time-consuming, making it suitable only for larger datasets and complex grammatical structures. Traditional algorithms remain effective for smaller datasets and simpler structures with limited computational resources.

The present study analyzes the unmet demand for bioplastics in Peru for the 2023–2027 period, considering the impact of policies such as Law No. 30884, which regulates the use of single-use plastics, and the growing interest in sustainability. Due to the lack of specific historical data for the bioplastics market, primary polypropylene (PP) destined for the packaging sector was used as a reference, given its relevance in the plastics industry and its potential to be replaced by biopolymers such as polyhydroxybutyrate (PHB).

Information was gathered from official sources such as SUNAT and BCRP to estimate historical demand and supply. The analysis was conducted in three stages: demand estimation, supply estimation, and calculation of unmet demand. Tools such as Minitab and RStudio were employed to carry out linear regression, multiple stepwise regression, and advanced time series models (ARIMA and nonlinear regressions).

The results reveal a significant unmet demand for bioplastics, representing an opportunity for investments in this emerging market. Additionally, a hypothetical investment scenario was developed to address part of this demand, projecting prices and market share. This study highlights the utility of data science in generating precise projections, optimizing strategic decisions, and fostering the transition toward a sustainable economy.