<p>Penelitian ini bertujuan untuk mendapatkan model prediksi terbaik dari data Penerimaan Mahasiswa Baru tahun 2014 hingga 2019 dengan membandingkan Naive Bayes, K-Nearest Neighbor, dan Random Forest. Penelitian ini menggunakan metode klasifikasi untuk memprediksi calon mahasiswa. Mereka diterima atau mundur. Dalam penelitian ini digunakan 19.603 data latih dan 4.901 data uji. Hasil penelitian menunjukkan bahwa algoritma Random Forest adalah yang terbaik dengan akurasi 73,61%, dibandingkan dengan K-Nearest Neighbor dengan akurasi 72,08%, dan Naive Bayes dengan akurasi 70,47%. Disimpulkan juga bahwa optimasi model dengan teknik <em>Hyperparameter</em> menghasilkan nilai akurasi yang lebih baik. Hasil penelitian ini dapat digunakan untuk mendukung bagian pemasaran dalam meminimalisir jumlah calon mahasiswa yang mengundurkan diri.</p><p> </p><p><em><strong>Abstract</strong></em></p><p><em><strong><br /></strong></em></p><p><em>This study aimed to obtain the best predictive model from New Student Admissions data for 2014 to 2019 by comparing Naive Bayes, K-Nearest Neighbor, and Random Forest. This study used the classification method to predict prospective students. They are accepted or withdrawn. In this study, 19,603 training data and 4,901 test data were used. The results showed that the Random Forest algorithm was the best with an accuracy of 73.61%, compared to K-Nearest Neighbor with an accuracy of 72.08%, and Naive Bayes with an accuracy of 70.47%. It is also concluded that optimizing the model with the Hyperparameter technique produces better accuracy values. This study's results can be used to support the marketing department in minimizing the number of withdrawn prospective students. </em></p><p><em><strong><br /></strong></em></p>
Graphology or handwriting analysis can be used to infer the traits of the writers by examining each stroke, space, pressure, and pattern of the handwriting. In this study, we infer a six-dimensional model of human personality (HEXACO) using a Convolutional Neural Network supported by Particle Swarm Optimization. These personalities include Honesty-Humility, Emotionality, eXtraversion, Agreeableness (versus Anger), Conscientiousness, and Openness to Experience. A digital handwriting sample data of 293 different individuals associated with 36 types of personalities were collected and derived from the HEXACO space. A convolutional neural network model called GraphoNet is built and optimized using Particle Swarm Optimization (PSO). The PSO is used to optimize epoch, minibatch, and droupout parameters on the GraphoNet. Although predicting 32 personalities is quite challenging, the GraphoNet predicts personalities with 71.88% accuracy using epoch 100, minibatch 30 and dropout 52% while standard AlexNet only achieves 25%. Moreover, GraphoNet can work with lower resolution (32 x 32 pixels) compared to standard AlexNet (227 x 227 pixels).
Risk Management is an integral part of every project. Risk management must estimate the risks’ significance, especially in the SDLC process, and mitigate those risks. Since 2016, many papers and journals have researched planning, design, and risk control in software development projects over the last five years. This study aims to find the most exciting topics for researchers in risk management, especially in software engineering projects. This paper takes a systematic approach to reviewing articles containing risk management in software development projects. This study collects papers and journals included in the international online library database, then summarizes them according to the stages of the PICOC methodology. This paper results in the focus of research in the last five years on Agile methods. The current issue is that many researchers are trying to explicitly integrate risk management into the Agile development process by creating a comprehensive risk management framework. This SLR helps future research get a theoretical basis to solve the studied problem. The SLR explains the focuses of previous research, analysis of research results, and the weaknesses of the investigation. For further study, take one of the topic papers, do a critical review, and find research gaps.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.