Machine Learning and Statistical Analysis applied on Mechanical Engineering CAD course: A Case Study During ERTE Pahse in the Context of Higher Education

Author(s):  
Zoe Kanetaki ◽  
Constantinos Stergiou ◽  
Georgios Bekas ◽  
Eleni Kanetaki
Author(s):  
Konstantinos Korres

This paper analyzes online discovery learning/ constructivistic approach using cognitive tools in higher Mathematics’ education, via a combination of electronic worksheets designed and implemented in Mathematica and online synchronous communication via the tools of a Learning Management System (LMS) and voice and video group calls. Moreover, the paper presents empirical research results of a case study concerning the approach’s application at the Department of Statistics and Insurance Sciences of the University of Piraeus and focuses on students’ attitudes towards the approach. We used a mixed approach in the study, in particular a quantitative approach with open-ended questions. A questionnaire was handed out and was answered by the students that participated. We performed statistical analysis via SPSS to data obtained by questions with binary answers and answers on a 7-point Likert scale. Also we included several open-ended questions, in order for the students to express their views and attitudes towards the benefits and the disadvantages of the tools and the approach used.


2018 ◽  
Vol 225 ◽  
pp. 06022
Author(s):  
Mark Ovinis ◽  
Saravanan Karuppanan ◽  
Shaharin Anwar Sulaiman ◽  
Puteri Sri Melor ◽  
Mohd Zulhilmi Paiz ◽  
...  

An important consideration in higher education is that graduates meet or exceed the program outcomes (POs). While there exists anecdotal evidence that the use of modern tools i.e. computer modelling and simulation, improve attainment of these outcomes, there is little empirical research available. Where empirical evidence is available, the variables considered would almost certainly have a bearing on the outcomes. In this work, the attainment of the POs by undergraduate engineering students in courses with and without the use of modern tools, based on quantitative data, were compared. It was hypothesized that courses using modern tools would lead to better overall attainment of POs, compared to courses not using these tools. As a case study, the PO attainment of students in the Mechanical Engineering undergraduate program at Universiti Teknologi PETRONAS (UTP) was considered. Quantitative data obtained through UTP's outcomebased education (OBE) software was used to assess the overall attainment of the POs for all courses for a cohort of 126 Mechanical Engineering undergraduate students class of 2017. It was found that, for the case study considered, the usage of modern tools has led to slightly better attainment of some POs, with slightly poorer attainment in other POs. Specifically, attainment in POs where the cognitive or the knowledge domain is more dominant improved, as the usage of modern tools helped students to understand theoretical concepts better. Attainment in POs were the affective domain is more dominant recorded a slight decrease, and the incorporation of modern tools did not aid in the attainment of these POs. The study is at a preliminary stage and a more detailed study, involving more cohorts, is planned to establish a correlation (if any) between the use of modern tools in higher education and attainment of POs.


Entropy ◽  
2021 ◽  
Vol 23 (4) ◽  
pp. 485 ◽  
Author(s):  
Carlos A. Palacios ◽  
José A. Reyes-Suárez ◽  
Lorena A. Bearzotti ◽  
Víctor Leiva ◽  
Carolina Marchant

Data mining is employed to extract useful information and to detect patterns from often large data sets, closely related to knowledge discovery in databases and data science. In this investigation, we formulate models based on machine learning algorithms to extract relevant information predicting student retention at various levels, using higher education data and specifying the relevant variables involved in the modeling. Then, we utilize this information to help the process of knowledge discovery. We predict student retention at each of three levels during their first, second, and third years of study, obtaining models with an accuracy that exceeds 80% in all scenarios. These models allow us to adequately predict the level when dropout occurs. Among the machine learning algorithms used in this work are: decision trees, k-nearest neighbors, logistic regression, naive Bayes, random forest, and support vector machines, of which the random forest technique performs the best. We detect that secondary educational score and the community poverty index are important predictive variables, which have not been previously reported in educational studies of this type. The dropout assessment at various levels reported here is valid for higher education institutions around the world with similar conditions to the Chilean case, where dropout rates affect the efficiency of such institutions. Having the ability to predict dropout based on student’s data enables these institutions to take preventative measures, avoiding the dropouts. In the case study, balancing the majority and minority classes improves the performance of the algorithms.


Author(s):  
Maria Manuela Natario ◽  
Carlos Roque de Almeida

El presente trabajo tiene como objetivo analizar la dinámica y los procesos de innovación en las regiones interiores del centro de Portugal buscando identificar los factores que estimulan la dinámica territorial de la innovación. La preocupación por la dinámica de la innovación ha sido objeto de varios estudios en el contexto de los sistemas regionales de innovación y, más recientemente, se encuadra en el desarrollo del Modelo “Triple Hélix” (Etzkowitz y Leydesdorff, 2000; Dzisah y Etzkowitz, 2009). Este modelo integra el estudio de la interacción entre las hélices para promover la innovación. El estudio empírico se centra en las empresas de tres distritos interiores de la zona Centro de Portugal (Castelo Branco, Guarda y Viseu). Desde el punto de vista de la metodología, para la realización del estudio se envió un cuestionario a las empresas de estos tres distritos y se ha utilizado la aplicación de análisis estadístico multivariante “k-means clustering” para detectar patrones de comportamiento de las empresas relativos a su dinámica de innovación respecto al perfil de la región en términos de innovación, al espíritu de iniciativa empresarial, a la cooperación con las instituciones de enseñanza superior y a la proactividad de las instituciones públicas. Para verificar las hipótesis propuestas se recurrió a aplicación de tests de comparación múltiple de valores medios para estudiar las características únicas de cada grupo.<br /><br /><br />The main objective of this paper is analysis the dynamics and processes of innovation in regions of interior centre of Portugal, seeking to identify factors that stimulate the territorial dynamics of innovation. <br />The dynamics of innovation has been the subject of several studies in the context of regional innovation systems and more recently has been considered in the Model "Triple Helix" (Etzkowitz and Leydesdorff, 2000; Dzisah and Etzkowitz, 2009). This model integrates the interaction between the helices to promote innovation. This empirical study includes three districts in Portugal (Castelo-Branco, Guarda and Viseu). The methodology consisted of a survey involving the companies in these districts and application of multivariate statistical analysis “k-means clusters” to detect their behavioral patterns within the region’s profile in terms of dynamics of innovation, spirit of business initiative, cooperation with the higher education institutions and proactivity of public institutions. In order to verify the formulated hypotheses, we resorted to the application of tests of multiple average differences to assess the unique characteristics of each cluster.<br /><br /><br />O presente trabalho tem como objectivo analisar as dinâmicas e os processos de inovação em regiões do interior centro de Portugal, procurando identificar factores que estimulam a dinâmica territorial de inovação. A preocupação com as dinâmicas de inovação tem sido alvo de diversos estudos no âmbito dos sistemas regionais de inovação e mais recentemente tem sido enquadrada no desenvolvimento do Modelo “Triple Helix” (Leydesdorff e Etzkowitz, 2000; Dzisah e Etzkowitz, 2009). Este modelo integra o estudo da interacção entre as hélices para promover a inovação. O estudo empírico incide sobre as empresas de três distritos do interior centro de Portugal. Como metodologia foi realizado um questionário às empresas destes distritos e utilizou-se a aplicação da análise estatística multivariada “k-means clusters” para detectar padrões comportamentais das empresas relativamente à sua dinâmica de inovação e face ao perfil da região em termos de inovação, espírito de iniciativa empresarial, cooperação com as IES e proactividade das Instituições Públicas. Para verificar as hipóteses formuladas recorremos à aplicação de testes de diferenças múltiplas de médias para aferirmos as características únicas de cada cluster.


2016 ◽  
Vol 7 (1) ◽  
pp. 29-36
Author(s):  
Nitza Davidovitch ◽  
Zvi Shiller

This article presents a case study that illustrates the paradigmatic shift in higher education from content-centered teaching to learning-centered academic programs. This pragmatic change, triggered by the STEM movement, calls for the introduction of success measures in the course development process. The course described in this paper illustrates such a goal-driven approach to the development of an entire multidisciplinary curriculum in mechanical engineering and mechatronics. The effectiveness of this new curriculum was confirmed by findings of a survey of graduates of the first six graduating classes who studied on the basis of this curriculum. 


Sign in / Sign up

Export Citation Format

Share Document