Data and Metadata (Journal)
Not a member yet
727 research outputs found
Sort by
Financial predictors of sme failure: variable selection with lasso versus random forest
Full text linkIntroduction: The study aimed to identify the financial variables that best predicted the failure of small and medium-sized enterprises (SMEs). It addressed the need for reliable financial indicators capable of signaling early distress and supporting risk-management practices.Methods: A quantitative methodology was adopted within a hypothetico-deductive framework. Two complementary variable-selection techniques were applied. First, the LASSO regression method introduced a regularization constraint to eliminate variables with weak explanatory power. Second, the Random Forest algorithm assessed the relative importance of financial variables in overall model performance. The two approaches were compared to determine their effectiveness in identifying the most relevant predictors of SME failure.Results: The LASSO model produced a negative coefficient of determination (R² = –1.2179), demonstrating performance inferior to a simple mean-based prediction and indicating that LASSO was not suitable in this context. In contrast, the Random Forest model achieved a very high R² value (0.9571), reflecting strong predictive accuracy and robustness. Based on the Random Forest results, six key financial predictors of SME failure were identified: financial structure, return on assets, return on sales, return on equity, liquidity, and solvency.Conclusions: The study demonstrated that Random Forest outperformed LASSO in selecting meaningful financial predictors of SME failure. The six identified variables offered a reliable analytical framework for understanding and anticipating financial distress. These findings provided valuable insights for academic research and practical applications in risk assessment and early warning systems for SMEs.
Development of IT Project Management Learning Media Using YOLO and Reinforcement Learning
Full text linkThis study addresses the gap in traditional project management education by developing a web-based learning platform for the Information Technology Project Management course. The platform integrates YOLO technology for real-time visual detection and Reinforcement Learning (RL) for automated decision-making. The development process adopted a Research and Development (R&D) approach using the ADDIE model, which consisted of five phases: Analysis, Design, Development, Implementation, and Evaluation. This research is significant as it offers a solution to the challenge of bridging the gap between theoretical knowledge and practical application in project management. The primary objective is to enhance students’ understanding of project dynamics and improve their decision-making skills through real-time project monitoring and data-driven recommendations. The development process adopted a Research and Development (R&D) approach using the ADDIE model, consisting of five phases: Analysis, Design, Development, Implementation, and Evaluation. Evaluation results demonstrated that the developed learning media achieved an average validity score of 87.7%, a practicality score of 85.7%, and an effectiveness score of 86.4%, confirming that the platform is valid, practical, and effective in improving student engagement and conceptual understanding of project management. The integration of YOLO and RL technologies proved effective in helping students comprehend project dynamics and support data-driven decision-making
Transformer guided and GAN augmented deep learning for medical image diagnostics
Full text linkIntroduction: Medical imaging serves as a crucial tool for disease diagnosis but current image analysis techniques fail to handle noisy data and insufficient annotations and different imaging modalities. Deep learning techniques have transformed medical imaging but achieving high diagnostic accuracy alongside computational efficiency remains a key challenge in clinical deployment. Objective: The research proposes a single deep learning system which combines CNNs with RNNs and GANs to enhance automated disease detection from medical images through improved accuracy, better interpretability and faster processing times.Method: The proposed Transformer-guided hybrid model uses CNNs to extract spatial features and RNNs to detect temporal patterns while GANs perform data augmentation and anomaly detection. Use consistent passive or active voice. The model was trained, validated on multimodal datasets and subsequently evaluated against ten baseline models, including SVM, transfer learning, and attention-based architectures. The evaluation metrics consisted of accuracy and precision and sensitivity and ROC-AUC.Results: The integrated framework achieved superior diagnostic performance with 90% accuracy, 88% precision, 86% sensitivity and 0.95 ROC-AUC which outperformed all baseline models. The system delivered achieved faster processing without sacrificing diagnostic accuracy across imaging modalities without compromising its diagnostic accuracy for different imaging techniques. Conclusions: The research developed an AI diagnostic system which uses CNN, RNN and GAN technologies to achieve efficient and ethical medical image analysis. The system enhances precision and speed while ensuring patient data security and transparent clinical reporting, enabling scalable AI-driven diagnostics.
Can the Ocean Save Our Future? Marine Resources as Catalysts for Educational Sustainability
Full text linkMarine ecosystems face unprecedented threats from overexploitation, pollution, and climate change, necessitating urgent integration of sustainability principles into vocational education systems. However, the intersection of marine resources and educational sustainability remains inadequately explored. This systematic scoping review investigates how marine resources can serve as catalysts for sustainability education, mapping research trends and identifying critical knowledge gaps. Data were retrieved from Scopus (1999-2024) using the keywords "Marine Resources" OR "Marine Environment" OR "Marine Ecosystem" AND "Sustainability" AND "Education," yielding 124,492 initial records. Following PRISMA guidelines and exclusion of unrelated disciplines, 77 publications from 53 sources were analyzed using Biblioshiny. The analysis examined publication trends, citation patterns, authorship networks, and thematic clusters through co-occurrence network analysis. Results revealed four distinct research phases with 9.2% annual growth, involving 340 authors with 33.8% international collaboration. Four thematic clusters emerged: (1) sustainability and marine environment integration (highest centrality), (2) local participation and natural resource management, (3) resource management and stakeholder engagement, and (4) environmental protection and human dimensions. Ocean literacy, marine education, and sustainability emerged as pivotal conceptual nodes connecting ecological science with pedagogical practice. The findings demonstrate growing global attention to marine education sustainability, yet reveal insufficient integration into vocational curricula. Vocational education systems must adopt structured sustainability frameworks equipping students with competencies to address marine challenges. Future research should focus on developing localized, industry-oriented curricula that strengthen vocational education as a transformative driver of long-term marine resource sustainability and conservation
Automatic weed quantification in potato crops based on a modified convolutional neural network using drone images
Full text linkIdentifying and quantifying weeds is a crucial aspect of agriculture for efficiently controlling them. Weeds compete with the crop for nutrients, minerals, physical space, sunlight, and water, causing problems in crops ranging from low production to economic losses and environmental deterioration of the land. Weed quantification is generally a manual process requiring significant time and precision. Convolutional Neural Networks (CNN) are very common in weed quantification. Thus, the purpose of this research is the adaptation of the ResNeXt50 CNN architecture for semantic segmentation tasks, focused on the automatic quantification of weeds (Broadleaf dock, Dandelion, Kikuyo grass, and other unidentified classes) in potato fields using RGB images acquired by the DJI Mavic 2 Pro drone. The analytical model was trained following the Knowledge Discovery in Databases (KDD) methodology using Python and the TensorFlow-Keras frameworks. The results indicate that the modified ResNeXt50 model presented a mean IoU of 0.7350, a performance comparable to the values reported by other authors considering fewer weed classes. The Student´s t-test and Pearson correlation coefficient were applied to contrast the weed coverage from the model predictions and the ground truth, indicating no statistically significant differences between both measurements in most weed classes
Implementation of Industry 4.0 in metallurgical factories
Full text linkThis paper presents the preliminary results of a study on implementing Industry 4.0 in metallurgical factories. It showed that adopting Industry 4.0 technologies generates a productive environment characterized by real-time sensing, with high adaptability, flexibility, self-learning capacity, and fault tolerance. In the context of the Ecuadorian industry, particularly in micro, small, and medium-sized enterprises (MSMEs), there is limited integration of industrial technologies, both at the software and hardware levels. Additionally, many factories do not perceive the relevance of implementing solutions based on Industry 4.0 in key areas such as production, quality control, and maintenance. The study presents three case studies of metalworking factories that emerged as small locksmith workshops and analyzes the challenges related to incorporating new know-how in these industries. The findings concluded that Industry 4.0 has transformative potential for the value chain, facilitating the development of innovative products and services
Learning styles and academic performance in engineering students: A pre- and pos-pandemic bibliometric study
Full text linkIntroduction: The relationship between learning styles and academic performance has gained significant attention, particularly in engineering education, as it plays an important role in enhancing the quality of the learning process. This study aims to provide a comprehensive bibliometric analysis of research trends in this field, focusing on pre- and post-pandemic periods. Methods: A total of 1397 articles from the Scopus database were analyzed using VOSviewer software to map the scientific production until 2023. The analysis was divided into two periods: 2016-2019 and 2020-2023, identifying clústers of research focused on learning styles, academic performance, and the growing importance of e-learning post-pandemic.Results: Five main clústers were identified between 2016-2019, including learning styles, the development of evaluation instruments, psychological aspects, curricular development, and general learning. In the post-pandemic period, three dominant clústers emerged, focused on learning styles, academic performance, and e-learning. Co-authorship analysis revealed changes in collaboration patterns, with increased global cooperation, particularly in the United States, China, and Spain during the 2020-2023 period. Conclusions: The study highlights the increasing relevance of research on learning styles and the shift toward remote learning triggered by the pandemic. These findings underscore the need for further exploration of adaptive teaching strategies to diverse learning preferences in the evolving educational landscape
Integration of Artificial Intelligence and Robotics into the industrial sector
Full text linkThe 4th industrial revolution is driven by the implementation of automated robots and artificial intelligence (AI) to enhance efficiency, accuracy, and safety. This integration encompasses several vital domains like optimizing the supply chain, interaction between human and robots on the shop floor, predictive maintenance, automation of repetitive tasks, customisation, behaviour design, and safety management, data analysis, etc. AI-enabled robots perform repetitive tasks at very high precision, reducing the chances of human error and allowing workers to focus on more complex tasks. Automated upkeep utilizes AI to determine the time machinery will likely fail, which minimizes downtime and maintenance costs. Automated testing and AI-driven vision systems support quality control by ensuring a balanced quality of the product. AI improves supply chain processes, optimizing logistics and inventory management. Collaboration between humans and collaborative robot’s results in safer and more productive environments with people working alongside each other. Artificial Intelligence plays an important role in making smarter decisions, analysing data more effectively, and providing valuable information that can be used to improve operations. Manufacturing customization and flexibility are reliant on adaptive systems and the ability to manufacture personalized products by means of productivity. Safe and Risk Management is consolidated because robots work in dangerous scenarios and artificial intelligence models assess potential dangers. Despite challenges including labour displacement, cybersecurity, ethics, and data integration stemming from this technology, these are all potentially available on your terms. This article reviews the broader impacts that robots and artificial Intelligence have had on the industrial sector, placing emphasis on the revolution it could lead towards as well as the key elements to consider before implementing it
HR Aspects of Corporate Social Responsibility: A Comprehensive Review
Full text linkIntroduction: The paper emphasizes the growing significance of Corporate Social Responsibility (CSR) in the business world, particularly how it intersects with Human Resources (HR) practices. It highlights the necessity for organizations to align their CSR initiatives with HR functions to achieve better outcomes. Objective: The review explores how CSR initiatives influence various HR functions, including employee engagement, recruitment, training and development, and overall employee well-being. This indicates that CSR is not just a peripheral concern but is integral to HR strategies. The research synthesizes and analyzes relevant literature on the topic, providing insights into the relationship between CSR and HR. This comprehensive approach aims to clarify the role of HR in embedding CSR values within the organizational culture. Method: The methods used in this paper combine quantitative analysis of a comprehensive HR dataset with qualitative literature review and theoretical frameworks to explore the critical relationship between HR practices and CSR initiatives. Result: By applying these data-driven findings, the organization can better align its workforce planning and development strategies, ultimately enhancing organizational performance and employee satisfaction.Conclusion: This multifaceted approach allows for a deeper understanding of how organizations can effectively integrate CSR into their HR strategies for sustainable succes
Novel KNN with Differentiable Augmentation for Feature-Based Detection of Cassava Leaf Disease and Mitigation of Overfitting: An Innovative Memetic Algorithm
Full text linkMany tropical countries depend on cassava, which is susceptible to deadly illnesses. These abnormalities can be diagnosed accurately and quickly to ensure food security. This study compares healthy and sick cassava leaves for four diseases: bacterial blight, brown streak, green mottle, and mosaic. Leaf images were systematically feature extracted to reveal color patterns, morphology, and textural qualities. Model learning methods use this extracted feature dataset. A new KNN+DA method may improve disease identification. Differentiable Augmentation uses data unpredictability to create alternative training samples to increase KNN performance. KNN+DA was compared to SVM, KNN, LR, and a memetic-tuned KNN to comprehend it better. We reached calculation speed, accuracy, recall, precision, and F1-score. KNN+DA outperformed older approaches in accuracy and resilience. KNN with differentiable augmentation improved classification accuracy and reduced overfitting, improving model generalizability for real-world use. Memetic algorithm-tuned KNN is another potential hybrid technique for disease diagnosis. Integrating current machine learning algorithms with cassava leaf photos can provide reliable early disease detection. More environmentally friendly agriculture would resul