Juan Carlos Guzmán

Agile methodologies have become established in software engineering education due to their emphasis on collaboration, iterative cycles, and early value delivery. However, their effective adoption in academic projects is not guaranteed simply by incorporating them into the curriculum; factors such as a lack of daily practice, low automation, and unstable coordination routines also play a role. This study describes the level of adoption/perception of agile practices among 108 students at a public university in Mexico (two parallel groups: A = 54; B = 54) at the beginning of the academic year. A standardized questionnaire of 24 questions was administered, organized into eight domains (Likert 1–5): iteration planning (IP), iterative development (ID), continuous integration (CI), daily stand-ups (DS), customer/user contact (CU), acceptance testing (AT), retrospectives (RT), and visual management/workflow with WIP limits (VF). In this study, means, standard deviations, ranges, frequencies (1–5), low percentages (1–2), and high percentages (4–5) were calculated. Internal reliability was estimated by subscale and overall using Cronbach's alpha. Exploratory comparisons were also performed using ANOVA for Group (A/B) and for the stated methodology. The study yielded a total index of 4.00 with a standard deviation (SD) of 0.66. Means per domain ranged from 3.82 (SD) to 4.19 (AT). Subscale reliability was α = .662–.832, and the overall α was .946. Comparisons between Groups A/B and by methodology showed little difference and were not statistically significant. The results suggest reinforcing daily meetings, implementing continuous integration and work-in-progress (WIP) limits, and maintaining strengths in acceptance testing and user contact.

The use of artificial intelligence techniques such as fuzzy logic, neural networks and evolutionary computation is currently very important in medicine to be able to provide an effective and timely diagnosis. The use of fuzzy logic allows to design fuzzy classifiers, which have fuzzy rules and membership functions, which are designed based on the experience of an expert. In this particular case a fuzzy classifier of Mamdani type was built, with 21 rules, with two inputs and one output and the objective of this classifier is to perform blood pressure level classification based on knowledge of an expert which is represented in the fuzzy rules. Subsequently different architectures were made in type-1 and type-2 fuzzy systems for classification, where the parameters of the membership functions used in the design of each architecture were adjusted, which can be triangular, trapezoidal and Gaussian, as well as how the fuzzy rules are optimized based on the ranges established by an expert. The main contribution of this work is the design of the optimized interval type-2 fuzzy system with triangular membership functions. The final type-2 system has a better classification rate of 99.408% than the type-1 classifier developed previously in “Design of an optimized fuzzy classifier for the diagnosis of blood pressure with a new computational method for expert rule optimization” with 98%. In addition, we also obtained a better classification rate than the other architectures proposed in this work.

In this paper, the optimal designs of type-1 and interval type-2 fuzzy systems for the classification of the heart rate level are presented. The contribution of this work is a proposed approach for achieving the optimal design of interval type-2 fuzzy systems for the classification of the heart rate in patients. The fuzzy rule base was designed based on the knowledge of experts. Optimization of the membership functions of the fuzzy systems is done in order to improve the classification rate and provide a more accurate diagnosis, and for this goal the Bird Swarm Algorithm was used. Two different type-1 fuzzy systems are designed and optimized, the first one with trapezoidal membership functions and the second with Gaussian membership functions. Once the best type-1 fuzzy systems have been obtained, these are considered as a basis for designing the interval type-2 fuzzy systems, where the footprint of uncertainty was optimized to find the optimal representation of uncertainty. After performing different tests with patients and comparing the classification rate of each fuzzy system, it is concluded that fuzzy systems with Gaussian membership functions provide a better classification than those designed with trapezoidal membership functions. Additionally, tests were performed with the Crow Search Algorithm to carry out a performance comparison, with Bird Swarm Algorithm being the one with the best results.

Implement a fuzzy inference system for a nocturnal profile classification model, for knowing the nocturnal blood pressure behavior of the patients and with this gain knowledge of the current health condition of such patients, in order to prevent a cardiovascular event. A fuzzy system for the classification of nocturnal blood pressure is implemented, and this because the original tests that were performed with a traditional system of rules did not produced the desired results.The fuzzy system was empirically designed based on a medical article of nocturnal hypertension, in which the author defines that in order to obtain the profile of nocturnal blood pressure, the information of the ABPM obtained in the day and night should be separated. From which the quotient to obtain the night profile of patients is calculated, and from this the range of each membership function is obtained, which are those that provide us each level of classification. The fuzzy system has two inputs which are the quotient of the systolic pressure and the quotient of the diastolic pressure and as output the night profile of the patient. Tests were performed with a group of 200 patients, comparing the results of the traditional system rules with the fuzzy system, and having better results with the second, because the traditional system rules requires precise information. Tests are carried out with different architectures in which different types of membership functions were used, such as: trapezoidal and Gaussian, having better results with the fuzzy system with trapezoidal membership functions. A random sample of 30 patients was collected obtaining 90% of correct classification with the fuzzy system in comparison with the traditional system rule, which correctly classified 53.3% of the patients, with a standard deviation of 3.86. The table shows the comparison of the different experiments, being those marked with bold those that classified correctly. Fuzzy logic allows us to handle inaccurate information, which helps us obtain good results, which can be noted in the reported experiments, where this type of classification is more efficient than the traditional system rules.

The main objective is using fuzzy classifiers to provide accuracy in the handling of information, which will help to be more accurate when classifying the blood pressure level of a patient. Classifiers are based on the parameters provided by the guidelines, and make the comparison given by the European and the American guide and observe the behavior that each of them can take at the time of making a diagnosis. Based on this study we want to identify the way in which a patient is diagnosed using two different guidelines of blood pressure levels, the first is the European guidelines and the second it is the American guides, the latter mentioned was recently updated and it is important to see the impact that each of them can have on society. Currently there is a database with 200 patients, each patient has an average 45 measurements, these 24-hour screenings have been obtained in collaboration with a cardiologist, and this information is then processed with neural networks to obtain the tendency, which enters in fuzzy classifier, which gives us the blood pressure level depending on the base guideline. The following result was obtained based on the parameters and levels given by each of the guidelines and using fuzzy classifiers respectively for each, which have a correct classification accuracy rate of 100% for the 30 patients processed and classified. For the European guidelines the classification of patients with hypertension is 43.3% with a standard deviation of 2.71 and using the new American guidelines is 56.6%with a standard deviation of 2.71 using the same patients. The performed study reports a higher rate of hypertensive people, which based on European guidelines are within normal to high normal ranges, but based on the new American guidelines it was observed that some patients directly enter the stage 1 or stage 2 hypertensive classes, which generates an impact on their daily life, in which they need to change their lifestyle to avoid a cardiovascular event.

A neuro-fuzzy hybrid model (NFHM) as a new computational method to classify blood pressure (BP) is presented. The objective of the study is to model the behavior of blood pressure in 24 hours per patient and to obtain the trend, which is classified using a fuzzy system based on rules given by an expert, and these rules were optimized by a genetic algorithm to obtain the appropriate number of rules for the system. Intelligent computing techniques include neural networks, fuzzy logic and evolutionary computation. In this case, we use a neural network with a modular architecture to model the behavior of BP and obtain the trend. Also we use a fuzzy system in which we have as inputs the systolic and diastolic pressures, and the output is the BP level. The fuzzy system based on experts for the classification of BP gives as classification of BP level such as: Hypotension, Optimal, Normal, High Normal, Grade 1 hypertension, Grade 2 hypertension, Grade 3 hypertension and isolated systolic hypertension Grade 1, Grade2 and Grade 3; Finally we use evolutionary computation, in this case we use genetic algorithm to reduce the number of rules based on an expert, which is based on combinations that are not necessary for the system. Of the 50 patients who were monitored, the classification in the first fuzzy system with 24 rules given by an expert, the result was: accuracy rate of 90% with a 10% error and in the second fuzzy system optimized with the new method reduced it was reduced to 21 rules giving as a result: 98% accuracy rate and 2% error. Neuro fuzzy hybrid models actually implement the human reasoning, using a set of optimized decision rules based on an expert, we can give a diagnosis of BP level. This is a very efficient, less time consuming and more accurate method to determine the risk of having bad BP. This is a effective method for diagnosis of bad BP, which can help a physician achieve better accuracy when giving a diagnosis to the patient.