Programa del congreso

This study investigates how adaptability mechanisms enhance supply chain performance in nanostores, focusing on the mediating role of digital transformation and the moderating role of operational flexibility in micro-retail networks. It addresses the limited understanding of adaptability in resource-constrained micro-retail contexts, a significant gap given nanostores’ economic importance and challenges like resource constraints. Using Structural Equation Modeling (SEM), data from 204 Honduran nanostore owners and employees, collected via stratified random sampling, were analyzed to test a theoretical framework linking adaptability, digital transformation, operational flexibility, and supply chain performance. Results show that adaptability enhances performance (β = 0.548, p < 0.001), with digital transformation partially mediating (indirect effect = 0.255, p < 0.001) and operational flexibility moderating (interaction effect = 0.264, p < 0.01) this relationship, explaining 68.4% of performance variance. Limitations include the cross-sectional design and self-reported measures, though urban (65%) and rural (35%) representation supports generalizability. Findings highlight digital integration and flexible operations as key to nanostore resilience. Managers can develop targeted interventions, and policymakers should prioritize digital infrastructure. This first SEM-based analysis of nanostore adaptability in emerging markets offers a novel framework for micro-retail resilience.

In the Peruvian fashion retail sector, companies operating with manual processes face significant logistical challenges that affect their OTIF compliance. This study was conducted in a mid-sized company dedicated to the marketing of well-known brand apparel, which has an OTIF level of 81.61%, below the desired standard. Through a detailed diagnosis, three critical causes were identified: errors in manual label placement, incorrect SKU selection, and packaging inspection failures, with impacts of 41.5%, 31.1%, and 15.1%, respectively, on OTIF noncompliance.
As a solution, an innovative business model was implemented, based on tool innovation structured in three components: technological innovation and Standardized Work (SW) in the labeling process, RFID, and IoT; Standardized Work (SW) in the picking process; and visual control in the final inspection through Poka-Yoke. The model was validated through a pilot test, achieving an increase in OTIF from 81.61% to 89.44%, reducing operational errors in labeling from 20.72% to 17.16%, order picking from 15.60% to 13.32%, and errors in the inspection of finished packages from 16.90% to 13.56%. In addition, average labeling time and standard picking time were reduced by approximately 58.60 to 47.20 minutes and from 78.72 to 58.21 minutes, respectively.
The proposal proved to be technically and economically viable, with favorable financial indicators (NPV, IRR, and WACC). This study demonstrates how business model innovation, combined with accessible technologies, enables mid-sized companies with manual processes to advance toward digital transformation in a profitable and sustainable manner.

A systematic review was conducted under the PRISMA methodology to identify the implications of the use of time series techniques in the health sector. Studies published between 2021 - 2025, in English and with direct application of time series in health contexts were included. After using exclusion and inclusion criteria, 54 articles were analyzed, with a predominance of quantitative studies using the ITS technique. The results refer to relevant implications in the response, such as hospital efficiency, mortality reduction, resource optimization and clinical decision making. It is concluded that these techniques are valuable for evaluating health interventions, although there are still methodological limitations and sustainability challenges to be addressed.

This study evaluates the impact of a predictive model based on artificial intelligence (AI), specifically Machine Learning, for accident prevention in surface mining, applied to the case of Cerro Dorado company in Cajamarca. The objective was to determine whether the implementation of an AI-based model can improve occupational risk management. A non-experimental, descriptive-correlational research design with a quantitative approach was used. The sample consisted of 100 workers from various operational areas. A validated structured survey was applied, and the data were statistically analyzed using frequencies, percentages, and correlation analysis.

The results show that 82% of respondents expressed a favorable perception regarding the integration of AI in prevention of accidents. This acceptance was higher among younger workers with technical education. A statistically significant association was found between technological familiarity and level of acceptance (p < 0.05). The main conclusion is that artificial intelligence has strong potential as a preventive tool, especially when adapted to local conditions and accompanied by appropriate training strategies for users.

The banana crop faces critical phytosanitary challenges, notably Black Sigatoka, which significantly reduces productivity. Traditional visual inspection methods are slow and subjective, prompting the use of artificial intelligence (AI) to enhance detection efficiency. This study presents a systematic literature review focused on evaluating the performance of AI models in detecting diseases and assessing banana ripeness, based on experimental studies published between 2020 and 2025. The review applied the PRISMA protocol and included 55 articles indexed in Scopus and Web of Science, selected using strict inclusion criteria involving real image datasets and performance metrics. The results indicate that deep learning models, particularly convolutional neural networks (CNN), outperform traditional machine learning approaches. Among them, SqueezeNet emerged as the most effective model for detecting Black Sigatoka, with precision values exceeding 97% in studies specifically focused on this disease. Other high-performing models include ShuffleNetv2 and MobileNetv3Small. While ResNet50 exhibited excellent metrics in broader disease classification contexts, the data reveal that lightweight architecture such as SqueezeNet offers the highest consistency and performance in field conditions. The study concludes that SqueezeNet is the most suitable architecture for detecting Black Sigatoka, due to its high precision, lightweight structure, and consistent performance across evaluations. These findings support the adoption of efficient deep learning architecture in precision agriculture scenarios.

This paper presents the design of a computer vision system based on convolutional neural networks (CNNs) for the detection of Tetranychus urticae in Hass avocado leaves. This pest represents a significant phytosanitary challenge affecting the export quality of Peruvian avocados. The proposed approach uses the ResNet-50 architecture with transfer learning to classify images into two categories: healthy and infested leaves. The model was trained with a proprietary dataset of 900 images, collected under controlled lighting conditions, and split into 70% for training, 15% for validation, and 15% for testing. The images were preprocessed using normalization, resizing to 224×224 pixels, and data augmentation techniques to improve model robustness. The resulting system achieved a classification accuracy of 96% on the test dataset, confirming its effectiveness under controlled conditions. Although the system demonstrated high accuracy in a simulated environment, further validation with field data is necessary to assess its generalization and deployment feasibility in real agricultural scenarios. The development process adhered to the VDI 2206 methodology for mechatronic systems design and was implemented using Python, TensorFlow, Keras, and Jupyter Notebook. This study constitutes a validated proof of concept for intelligent pest classification in precision agriculture, with future work focusing on system validation in field conditions, integration with mobile platforms, and expansion to detect multiple pest types.