Loading...
28 results
Search Results
Now showing 1 - 10 of 28
- A multi-objective clustering approach based on different clustering measures combinationsPublication . Azevedo, Beatriz Flamia; Rocha, Ana Maria A.C.; Pereira, Ana I.Clustering methods aim to categorize the elements of a dataset into groups according to the similarities and dissimilarities of the elements. This paper proposes the Multi-objective Clustering Algorithm (MCA), which combines clustering methods with the Nondominated Sorting Genetic Algorithm II. In this way, the proposed algorithm can automatically define the optimal number of clusters and partition the elements based on clustering measures. For this, 6 intra-clustering and 7 inter-clustering measures are explored, combining them 2-to-2, to define the most appropriate pair of measures to be used in a bi-objective approach. Out of the 42 possible combinations, 6 of them were considered the most appropriate, since they showed an explicitly conflicting behavior among the measures. The results of these 6 Pareto fronts were combined into two Pareto fronts, according to the measure of intra-clustering that the combination has in common. The elements of these Pareto fronts were analyzed in terms of dominance, so the nondominanted ones were kept, generating a hybrid Pareto front composed of solutions provided by different combinations of measures. The presented approach was validated on three benchmark datasets and also on a real dataset. The results were satisfactory since the proposed algorithm could estimate the optimal number of clusters and suitable dataset partitions. The obtained results were compared with the classical kmeans and DBSCAN algorithms, and also two hybrid approaches, the Clustering Differential Evolution, and the Game-Based k-means algorithms. The MCA results demonstrated that they are competitive, mainly for the advancement of providing a set of optimum solutions for the decision-maker.
- Dataset of mathematics learning and assessment of higher education students using the MathE platformPublication . Azevedo, Beatriz Flamia; Pacheco, Maria F.; Fernandes, Florbela P.; Pereira, Ana I.Higher education institutions are promoting the adoption of innovative methodologies and instructional approaches to engage and promote personalized learning paths to their students. Several strategies based on gamification, artificial intelligence, and data mining are adopted to create an interactive educational setting centred around students. Within this personalized learning environment, there is a notable boost in student engagement and enhanced educational outcomes. The MathE platform, an online educational system introduced in 2019, is specifically crafted to support students tackling difficulties in comprehending higher-education-level mathematics or those aspiring to deepen their understanding of diverse mathematical topics - all at their own pace. The MathE platform provides multiple-choice questions, categorized under topics and subtopics, aligning with the content taught in higher education courses. Accessible to students worldwide, the platform enables them to train their mathematical skills through these resources. When the students log in to the training area of the platform, they choose a topic to study and specify whether they prefer basic or advanced questions. The platform then selects a set of seven multiple choice questions from the available ones under the chosen topic and generates a test for the student. After completing and submitting the test, the answers are recorded and stored on the platform. This paper describes the data stored in the MathE platform, focusing on the 9546 answers to 833 ques- tions, provided by 372 students from 8 countries who use the platform to practice their skills using the questions (and other resources) available on the platform. The information in this paper will help research about active learning tools to support the improvement of future education, especially at higher educational level. Furthermore, these data are valu- able for understanding student learning patterns, assessing platform efficacy, gaining a global perspective on mathemat- ics education, and contributing to the advancement of active learning tools for higher education. (c) 2024 Published by Elsevier Inc. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/)
- Optimum sensors allocation for a forest fires monitoring systemPublication . Azevedo, Beatriz Flamia; Brito, Thadeu; Lima, José; Pereira, Ana I.Every year forest fires destroy millions of hectares of land worldwide. Detecting forest fire ignition in the early stages is fundamental to avoid forest fires catastrophes. In this approach, Wireless Sensor Network is explored to develop a monitoring system to send alert to authorities when a fire ignition is detected. The study of sensors allocation is essential in this type of monitoring system since its performance is directly related to the position of the sensors, which also defines the coverage region. In this paper, a mathematical model is proposed to solve the sensor allocation problem. This model considers the sensor coverage limitation, the distance, and the forest density interference in the sensor reach. A Genetic Algorithm is implemented to solve the optimisation model and minimise the forest fire hazard. The results obtained are promising since the algorithm could allocate the sensor avoiding overlaps and minimising the total fire hazard value for both regions considered.
- Study of genetic algorithm for optimization problemsPublication . Azevedo, Beatriz Flamia; Pereira, Ana I.; Bressan, Glaucia MariaThis work consists in to explore the Genetic Algorithms to solve non-linear optimization problems. The aim of this work is to study and develop strategies in order to improve the performance of the Genetic Algorithm that can be applied to solve several optimization problems, as time schedule, costs minimization, among others. For this, the behavior of a traditional Genetic Algorithm was observed and the acquired information was used to propose variations of this algorithm. Thereby, a new approach for the selection operator was proposed, considering the abilities of population individuals to generate offspring. In addition, a Genetic Algorithm that uses dynamic operators rates, controlled by the amplitude and the standard deviation of the population, is also proposed. Together with this algorithm, a new stopping criterion is also proposed. This criterion uses population and the problem information to identify the stopping point. The strategies proposed are validated by twelve benchmark optimization functions, defined in the literature for testing optimization algorithms. The dynamic rate algorithm results were compared with a fixed rate Genetic Algorithm and with the defaultMatlab Genetic Algorithm, and in both cases, the proposed algorithm presented excellent results, for all considered functions, which demonstrates the robustness of the algorithm for solving several optimization problems.
- Bio-inspired multi-objective algorithms applied on production scheduling problemsPublication . Azevedo, Beatriz Flamia; Vega, Rubén; Varela, Maria Leonilde Rocha; Pereira, Ana I.Production scheduling is a crucial task in the manufacturing process. In this way, the managers must decide the job's production schedule. However, this task is not simple, often requiring complex software tools and specialized algorithms to find the optimal solution. In this work, a multi-objective optimization model was developed to explore production scheduling performance measures to help managers in decision-making related to job attribution under three simulations of parallel machine scenarios. Five important production scheduling performance measures were considered (makespan, tardiness and earliness times, number of tardy and early jobs), and combined into three objective functions. To solve the scheduling problem, three multi-objective evolutionary algorithms are considered (Multi-objective Particle Swarm Optimization, Multi-objective Grey Wolf Algorithm, and, Non-dominated Sorting Genetic Algorithm II), and the set of optimum solutions named Pareto Front, provided by each one is compared in terms of dominance, generating a new Pareto Front, denoted as Final Pareto Front. Furthermore, this Final Pareto Front is analysed through an automatic bio-inspired clustering algorithm based on the Genetic Algorithm. The results demonstrated that the proposed approach efficiently solves the scheduling problem considered. In addition, the proposed methodology provided more robust solutions by combining different bio-inspired multi-objective techniques. Furthermore, the cluster analysis proved fundamental for a better understanding of the results and support for choosing the final optimum solution.
- Mathematics learning and assessment using MathE platform: a case studyPublication . Azevedo, Beatriz Flamia; Pereira, Ana I.; Fernandes, Florbela P.; Pacheco, Maria F.Universities are encouraging the implementation of innovative methodologies and teaching strategies to develop an interactive and appealing educational environment where students are the focus of the learning process. In such a personalised learning environment, an increase of the students’ engagement and the improvement of the outcomes arise. MathE has been developed to help achieve this goal. Based on collaborative procedures, internet resources – both pre-existing and freely available as well as resources specifically conceived by the project team – and communities of practices, MathE intends to be a tool to nurture and stimulate the learning of Mathematics in higher education. This study introduces and describes the MathE platform, which is divided into three sections: Student’s Assessment, Library and Community of Practice. An in-depth description of the Student’s Assessment section is presented and an analysis of the results obtained from students, when using this feature of the platform, is also provided. After this, and based on the answers to an online survey, the impact of the MathE platform among students and teachers of eight countries is shown. Although the number of collected results is still scarce, it allows the recognition of a trend regarding the use of the material of the Student’s Assessment section for autonomous study. The results indicate the platform is well organized, with a satisfactory amount and diversity of questions and good interconnection between the various parts. Nevertheless, both teachers and students indicate that more questions should be introduced. The overall opinion about the MathE platform is very favourable
- Hybrid approaches to optimization and machine learning methods: a systematic literature reviewPublication . Azevedo, Beatriz Flamia; Rocha, Ana Maria A.C.; Pereira, Ana I.Notably, real problems are increasingly complex and require sophisticated models and algorithms capable of quickly dealing with large data sets and finding optimal solutions. However, there is no perfect method or algorithm; all of them have some limitations that can be mitigated or eliminated by combining the skills of different methodologies. In this way, it is expected to develop hybrid algorithms that can take advantage of the potential and particularities of each method (optimization and machine learning) to integrate methodologies and make them more efficient. This paper presents an extensive systematic and bibliometric literature review on hybrid methods involving optimization and machine learning techniques for clustering and classification. It aims to identify the potential of methods and algorithms to overcome the difficulties of one or both methodologies when combined. After the description of optimization and machine learning methods, a numerical overview of the works published since 1970 is presented. Moreover, an in-depth state-of-art review over the last three years is presented. Furthermore, a SWOT analysis of the ten most cited algorithms of the collected database is performed, investigating the strengths and weaknesses of the pure algorithms and detaching the opportunities and threats that have been explored with hybrid methods. Thus, with this investigation, it was possible to highlight the most notable works and discoveries involving hybrid methods in terms of clustering and classification and also point out the difficulties of the pure methods and algorithms that can be strengthened through the inspirations of other methodologies; they are hybrid methods.
- Collaborative learning platform using learning optimized algorithmsPublication . Azevedo, Beatriz Flamia; Amoura, Yahia; Kantayeva, Gauhar; Pacheco, Maria F.; Pereira, Ana I.; Fernandes, Florbela P.Aware that the lack of mathematical knowledge and skills is a major problem for the development of a modern, inclusive and informed society, the MathE partnership has developed a tool that is aimed at bridging the gap that moves students away from courses that rely on a mathematical core. The MathE collaborative learning platform offers higher education students a package of scientific and pedagogical resources that allow them to be active agents in their learning pathway, by self-managing their study. The MathE platform is currently being used by a significant number of users, from all over the world, as a tool to support and engage students, ensuring new and creative ways to encourage them to improve their mathematical skills and therefore increasing their confidence and capacities. In order to enhance this platform, a visual representation of the performance of the students is already implemented, based on the recorded performance historic data for each student. This paper contains a literature review about the implementation of data mining techniques in education, followed by a description of the features of the MathE learning system and suggestions of data parameters to support the improvement of the students’ performance. Future work includes the application of optimization and learning algorithms so that the MathE platform will have a dynamical structure and act as a virtual tutor for the users.
- Bayesian Approach to Infer Types of Faults on Electrical Machines from Acoustic SignalPublication . Bressan, Glaucia; Azevedo, Beatriz Flamia; Santos, Herman Lucas dos; Endo, Wagner; Agulhari, Cristiano; Goedtel, Alessandro; Scalassara, PauloConsidering the classification of failures in electrical machines, the present paper aims to use supervised machine learning techniques in order to classify faults in electrical machines, using attributes from audio signals. In order to analyze data and recognize patterns, the considered supervised learning methods are: Bayesian Network, together with the BayesRule algorithm, Support Vector Machine and k-Nearest Neighbor. The performances and the results provided from these algorithms are then compared. The main contributions of this paper are the acquisition process of audio signals and the elaboration of Bayesian networks topologies and classifiers structures using the acquired signals, since the algorithms provide the generalization of the classification model by revealing the network structure. Also, the utilization of audio signals as input attributes to the classifiers is infrequent in the literature. The results show that the Support Vector Machine and k-Nearest Neighbor present a high accuracy. On the other hand, the Bayesian approach is advantageous due to the possibility of showing, through graph representations, the generalized structure to represent the trend of faults in real cases on industry applications.
- Data acquisition filtering focused on optimizing transmission in a LoRaWAN network applied to the WSN forest monitoring systemPublication . Brito, Thadeu; Azevedo, Beatriz Flamia; Mendes, João; Zorawski, Matheus; Fernandes, Florbela P.; Pereira, Ana I.; Rufino, José; Lima, José; Costa, Paulo Gomes daDeveloping innovative systems and operations to monitor forests and send alerts in dangerous situations, such as fires, has become, over the years, a necessary task to protect forests. In this work, a Wireless Sensor Network (WSN) is employed for forest data acquisition to identify abrupt anomalies when a fire ignition starts. Even though a low-power LoRaWAN network is used, each module still needs to save power as much as possible to avoid periodic maintenance since a current consumption peak happens while sending messages. Moreover, considering the LoRaWAN characteristics, each module should use the bandwidth only when essential. Therefore, four algorithms were tested and calibrated along real and monitored events of a wildfire. The first algorithm is based on the Exponential Smoothing method, Moving Averages techniques are used to define the other two algorithms, and the fourth uses the Least Mean Square. When properly combined, the algorithms can perform a pre-filtering data acquisition before each module uses the LoRaWAN network and, consequently, save energy if there is no necessity to send data. After the validations, using Wildfire Simulation Events (WSE), the developed filter achieves an accuracy rate of 0.73 with 0.5 possible false alerts. These rates do not represent a final warning to firefighters, and a possible improvement can be achieved through cloud-based server algorithms. By comparing the current consumption before and after the proposed implementation, the modules can save almost 53% of their batteries when is no demand to send data. At the same time, the modules can maintain the server informed with a minimum interval of 15 min and recognize abrupt changes in 60 s when fire ignition appears.
- «
- 1 (current)
- 2
- 3
- »