Revista Ingenieria Solidaria

Introduction: The present review article is the product of the research “Teaching digital modulation techniques in engineering: experiential learning theory “ developed at the Franciso de Paula Santander University and Pontificia Universidad Javeriana in 2022. Problem: The learning outcomes correspond to the statements related to what the future engineer is expected to be able to do, learn, understand and demonstrate. Objective: Analyze learning outcomes in engineering programs globally. Methodology: A methodology based on analysis stages is used for information selection through search filters and inclusion and exclusion criteria, design for the classification of information by geographic location and area of knowledge, with qualitative results by location and trends by area of knowledge. Results: Divergence was observed towards the way in which learning outcomes are evaluated, and convergence towards the need to involve agents external to the academy in the feedback for the learning outcomes evaluation processes. Conclusion: This allows for the identification of individual and collective strengths and weaknesses, which helps to make informed decisions to improve the quality of education. Originality: Originality is based on the way in which the information is analyzed, considering information by areas of knowledge as well as by continents. Limitations: None given the nature of the literature review.

Introduction: The productive and sustainable development in the department of Cauca depends to a large extent on the effective use of information and communication technologies (ICT). However, the institutional framework lacks mechanisms or methods to select investment projects with ICT resources. This situation has become an obstacle to economic growth and the improvement of social conditions in the region. Methods: In this article, the construction of a methodological design, one that allows for the selection and evaluation of projects with ICT resources that contribute to the solidarity economy of Cauca communities, is consolidated. The investigative process used a mixed approach, carrying out a systematic review of academic and political-organizational information, after which proposals and selection criteria used in Cauca in the last 5 years were analyzed. Results: With the information collected and analyzed, a route for the selection and evaluation of projects was compiled. Likewise, user stories were used to create a simulator that materializes the process of selecting and evaluating projects in a more efficient and effective way. Conclusions: In conclusion, the creation of the methodological design, materialized in the simulator, represents a valuable tool for the department of Cauca, since it allows for a rigorous and coherent evaluation of investment projects with ICT resources. Originality: Promoting productive growth, the solidarity economy also contributes to sustainable development for the communities of Cauca. Limitations: The sample was limited due to the geographical location of the municipalities.

Introduction: This paper is the outcome of a review survey, “Role of IoT, AI and blockchain in agriculture and crop disease detection using a text mining approach,” done at Lovely Professional University in Punjab, India, in 2023. Problem: Agriculture is a crucial industry that contributes significantly to the economies of many nations. Crop diseases are one of the issues that create a barrier to agricultural development. Objective: Using machine learning, deep learning, image processing methods, the Internet of Things, and blockchain technology, this study provides a current summary of research done over the past years on disease identification of various crops. Methodology: The text mining technique is applied to extract the related information from published papers and predict the following futuristic technologies to detect crop diseases early. Results: This paper also covers the various issues, challenges, and potential solutions. It also emphasizes the wide range of tools available for identifying crop diseases. Conclusion: This paper helps to extract valuable keywords through a text-mining approach and create a roadmap for another researcher. Originality: Applied text mining visualization techniques, such as word cloud and word frequency, to extract the keywords. Limitation: The literature survey only covers literature published prior to February 2023; it can be extended withmore studies published soon.

Introduction: This article is the result of the research project “User-Centered Web Accessibility: Recommendations for Ensuring Access to Governmental Information for Older Adults”, developed at the University of Cauca-Colombia in 2023. Problem: Despite the importance of web accessibility, web pages are not adapting to the evolution of web accessibility proposed by the international consortium, which can limit access for users with physical and/or cognitive limitations. Objective: This article presents a set of recommendations for the design and development of government websites specifically for older adults, to ensure access to government information and take into account their health, physical, and mental condition. Methodology: A relationship is established between the limitations of older adults and the recommendations of the Web Content Accessibility Guidelines (WCAG) 2.2, with the aim of proposing specific design and development guidelines for government websites to counteract a specific limitation. Results: The implementation of these recommendations will allow government portals to have greater acceptance among older adult users. In addition, a case study was conducted in which these recommendations were validated and adjusted, which allowed for access to government information as a means of protecting fundamental rights. Conclusion: This article highlights the importance of web accessibility and proposes specific recommendations for the design and development of accessible government websites for older adults. Originality: This article presents a specific approach to web accessibility for older adults and proposes recommendations that differ from WCAG guidelines. Limitations: The proposed recommendations focus on web accessibility for older adults and do not address the limitations of other groups with physical and/or cognitive limitations. In addition, they were validated and adjusted in a specific case study and may require additional adjustments in other contexts.

Introduction: This paper highlights the outcome of the comparative study of “Various Machine learning algorithms namely K-NN, Naive Bayes, and Logistic Regression for Credit Card Fraud Detection” carried out based on a dataset taken from UCI.com in 2022-23 at Manav Rachna International Institute of Research and Studies. Problem: Credit card fraud is still rife today and the modes are increasingly varied. Quite often we hear of fraud cases that cause irreplaceable injury to banks and financial institutions which cannot be compensated in terms of costs. To avoid scams with various modes of credit cards, we must be able to identify and find out the modes often used by fraudsters. This scheme liberates such financial institutions and banks with complete and appropriate information using Machine Learning Techniques, not only about the modes that scammers or fraudsters often use but also ways to protect against such frauds. Objective: The present paper discusses the various machine learning models based on classification and regression, namely K-Nearest Neighbors, Naïve Bayes, and Logistic Regression, which are successfully able to achieve the classification accuracy of 80% using Logistic Regression with a Precision of 78%, Recall of 100%, and F1-Score of 88% for fraudulent credit card transactions. Methodology: The comparative analysis demonstrates that for Precision, Recall, and Accuracy parameters, the K-Nearest Neighbor is a better approach for detecting fraudulent transactions than the Logistic Regression and Naïve Bayes. Results: The accuracy is marginal high in Logistic Regression but the False Positive parameters are not able to identify the imbalanced data; therefore, they disguise the results and accuracy of Logistic Regression and K-Nearest Neighbor deems fit for such cases. Conclusion: This scheme depicts the automated fraud classification systems using machine learning techniques, namely K-Nearest Neighbor, Logistic Regression, and Naive Bayes, to produce a model that can distinguish valid and invalid credit card transactions. Originality: Through this research, the most relevant features are used to go through the visualization of accuracy with the confusion matrix, and accuracy calculations are obtained from the dataset used.Limitations: Deep learning techniques could have been used to fetch even better results.