Deep-Learning-Based Agile Teaching Framework of Software Development Courses in Computer Science Education

Yang, Jian; Zhang, Xiaoling; Peng, Su

doi:10.1016/j.procs.2019.06.021

Cited by 18 publications

(13 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This deep learning-based learning model can automatically assess this. Yang et al (2018)  This deep learning-based learning model is able to present an overview of ecological learning to students. This model has been adapted to provide students with sources of ecological evolution to match their perceptions and their education to start creating an ecological platform.…”

Section: Purpose Resultsmentioning

confidence: 99%

“…The last deep learning method is RNN which able to process text data. RNN will produce outputs in the form of evaluating students' abilities based on general and specific abilities Yang et al (2018), predictions that a news story is fake news Sastrawan et al (2021), and good sentence design by paying attention to correlations and correct sentence synonyms Chowanda and Chowanda (2017). Further discussion of the cases solved by deep learning can be seen in Table 4.…”

Section: Depp Learning Methodsmentioning

confidence: 99%

See 1 more Smart Citation

How do we choose the appropriate deep learning method for our case? A systematic literature review

Saputra

Riza

Setiawan

et al. 2022

Preprint

View full text Add to dashboard Cite

In the era of technology 4.0, there are many problems in multiple sectors of life that are difficult for humans to solve, ranging from issues in the education quality performance system, difficulties in disease diagnosis, problems in manufacturing systems, construction, food grading, quality control, Etc. Various efforts have been made to solve these problems, from the conventional method of manually retrieving data to obtain the best solution to using a big data-based approach with deep learning. Deep learning has successfully solved problems in various sectors, proving that using big data on deep learning algorithms gives significant results. This systematic review aims to review the studies that have been carried out on applying deep learning to solve or help problems in various sectors. This systematic review shows an overview of deep learning neural networks created in the completion process, the differences in the artificial intelligent methods used, and the advantages and disadvantages of deep learning in various models. It identifies challenges and recommendations for the future. The methods used in this systematic review include search strategies, selecting literature studies, and managing and extracting data. Based on the systematic review results, we know that Convolutional Neural Network (CNN) is the most widely used model for this deep learning algorithm to recognize the feature, along with the image-based data transformation strategy. Finally, deep learning has become very popular because it can transform various data types to get the desired result.

show abstract

Section: Purpose Resultsmentioning

confidence: 99%

Section: Depp Learning Methodsmentioning

confidence: 99%

How do we choose the appropriate deep learning method for our case? A systematic literature review

Saputra

Riza

Setiawan

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Despite the difficulty of teaching Agile, there are proven benefits to using Agile practices with students [5]. Agile projects featuring feedback after each iteration increase students' software development skills more than traditional group projects [6]. Students find Agile practices such as pair programming beneficial [7].…”

Section: Related Workmentioning

confidence: 99%

Using a Low Code Development Environment to Teach the Agile Methodology

Lebens

2021

Lecture Notes in Business Information Processing

View full text Add to dashboard Cite

The Agile development methodology is soaring in popularity in the business world. Companies are turning to Agile to develop products quickly and to achieve digital transformation of their organization. Because of this push, companies need employees who understand Agile. Therefore, higher education is obligated to provide an understanding of Agile to students as they enter the workplace. Providing Agile experience to students who are new to programming is difficult because they are so worried about the coding aspects of the assignment, they cannot take time to think about the methodology they are using. The coding crowds out the time needed to get an understanding of how Agile actually works. One remedy for this is to use a low or no-code development platform. With this type of platform students spend less time learning to create apps, freeing them to experience the rituals and roles of Agile. This study examines using the Agile methodology along with the Microsoft Power Apps platform to provide an Agile experience to students. Two course sections were surveyed to learn if students perceived that they acquired a better understanding of Agile and to learn their perceptions of a no-code platform experience. The students completed surveys to ascertain their comfort with the Agile methodology and whether the no-code environment increased their comfort level. The results showed students perceived the no-code platform increased their comfort with using the Agile methodology. The implication is that no-code platforms can be used broadly to help students to gain experience with Agile.

show abstract

“…Muito se tem pesquisado sobre Aprendizagem Profunda, sobretudo na área médica e biológica, em que esta técnica é proeminente em diferentes domínios, em especial para explorar o Big Data, para análises de diferentes aplicações como: reconhecimento de padrões, reconhecimento de fala, visão computacional, processamento de linguagem natural, detecção de intrusões e previsões médicas (Boulemtafes, Derhab & Challal, 2020). Nesse sentido, muitos autores definem esta técnica em seus estudos (Goodfellow, Bengio & Courville, 2016;Xin et Souza, V. F., Santos, T. C. B. RBIE v.29 -2021523 al., 2018Yang, Zhang & Su, 2018;Soffer et al, 2019;Le, Torrisi & Pollastri, 2020;Sengupta et al, 2020;Murat et al, 2020;Badar, Haris & Fatima, 2020;Boulemtafes, Derhab & Challal, 2020;Sezer, Gudelek & Ozbayoglu;. Destas definições, vale apena evidenciar a visão de Le, Torrisi & Pollastri (2020) sobre a AP, para eles esta técnica é um subcampo de AM baseado em Redes Neurais Artificiais Multicamadas, que enfatizam o uso de múltiplas camadas conectadas para transformar entradas em recursos passíveis de prever saídas correspondentes; os autores completam dizendo que diante de um conjunto de dados suficientemente grande de pares entrada-saída, um algoritmo de AP pode ser usado para aprender automaticamente o mapeamento de entradas com relação as saídas, ajustando um conjunto de parâmetros em cada camada da rede.…”

Section: Aprendizagem Profundaunclassified

Processo de Mineração de Dados Educacionais aplicado na Previsão do Desempenho de Alunos: Uma comparação entre as Técnicas de Aprendizagem de Máquina e Aprendizagem Profunda

Souza

Santos

2021

RBIE

View full text Add to dashboard Cite

Com o aumento da disponibilidade de dados, sobretudo no contexto educacional, surgiram áreas específicas para extração de informações relevantes, como a Mineração de Dados Educacionais (MDE), que integra inúmeras técnicas que dão suporte à captação, processamento e análises desses conjuntos de registros. A principal técnica associada a MDE é a Aprendizagem de Máquina (AM), que vem sendo empregada a décadas no processamento de dados em diversos contextos, mas com a evolução tecnológica outras técnicas têm se sobressaído como a Aprendizagem Profunda (AP), baseada na aplicação de Redes Neurais Artificiais Multicamadas. Com foco neste contexto, esse estudo tem como objetivo realizar a previsão do desempenho de alunos, em um conjunto de dados públicos, e comparar as técnicas de AM e AP, ademais indicar quais os principais atributos preditores para o desempenho dos alunos. Para isso foi implementado um processo de MDE baseado em 4 etapas: 1) Coleta de dados; 2) Extração de recursos e limpeza de dados (pré-processamento e transformação); 3) Processamento analítico e algoritmos; e 4) Análise e interpretação dos resultados. Como resultado foi identificado que os modelos gerados a partir dos algoritmos tradicionais de AM têm um bom desempenho, mas inferior ao modelo AP que teve uma acurácia de 94%, bem como foi constatado que atributos relacionados às atividades escolares são mais preditores para o desempenho dos alunos do que os dados de características demográficas e socioeconômicas.

show abstract

Deep-Learning-Based Agile Teaching Framework of Software Development Courses in Computer Science Education

Cited by 18 publications

References 8 publications

How do we choose the appropriate deep learning method for our case? A systematic literature review

How do we choose the appropriate deep learning method for our case? A systematic literature review

Using a Low Code Development Environment to Teach the Agile Methodology

Processo de Mineração de Dados Educacionais aplicado na Previsão do Desempenho de Alunos: Uma comparação entre as Técnicas de Aprendizagem de Máquina e Aprendizagem Profunda

Contact Info

Product

Resources

About