Data Mining Dengan Algoritma Neural Network Dan Visualisasi Data Untuk Prediksi Kelulusan Mahasiswa

Purwati, Neni; Nurlistiani, Rini; Devinsen, Oscar

doi:10.30873/ji.v20i2.2273

Cited by 6 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Hasil dari tingkat akurasi algoritma neural network adalah 92,83%. [4] Penelitian terdahulu yang berkaitan dengan penelitian ini adalah penelitian dari Muhammad Dedek Yalidhan (2018). Penelitian tersebut menggunakan 318 sampel data dengan satu metode data mining, yaitu algoritma neural network.…”

Section: Pendahuluanunclassified

Komparasi Algoritma Naïve Bayes dan Neural Network untuk Menentukan Ketepatan Masa Studi Mahasiswa(Studi Kasus: Program Studi Teknologi Informasi Universitas Udayana)

Bintari

Putra²,

Raharja³

2022

jitter

View full text Add to dashboard Cite

Abstrak Perguruan tinggi memiliki akreditasi sebagai acuan untuk penilaian terhadap kualitas kampus yang ditentukan oleh Badan Akreditasi Nasional Perguruan Tinggi (BAN-PT). Tingkat akreditasi perguruan tinggi salah satunya dinilai dari kualitas lulusan mahasiswa yaitu lama studi mahasiswa. Lama studi mahasiswa dapat diprediksi menggunakan metode data mining. Metode data mining yang digunakan untuk memprediksi masa studi mahasiswa adalah algoritma naïve bayes dan neural network. Data mahasiswa berupa NIM, jenis kelamin, jalur masuk, IP Semester 1, IP Semester 2, IP Semester 3, IP Semester 4, dan kategori. Data sampel merupakan alumni mahasiswa angkatan 2008-2013 sebanyak 363 mahasiswa. Metode data mining akan dilakukan sebanyak empat kali pengujian berdasarkan jumlah data training dan data testing. Hidden layer yang digunakan sebanyak 1 dan 2 dengan dua neuron, training cycles menggunakan angka kisaran 25 hingga 2000, momentum sebesar 0,9 dan learning rate sebesar 0.5. Nilai performa algoritma naïve bayes akan menampilkan confusion matrix berupa akurasi sedangkan nilai performa algoritma neural network akan menampilkan confusion matrix berupa akurasi dan nilai RMSE.

show abstract

Section: Pendahuluanunclassified

Komparasi Algoritma Naïve Bayes dan Neural Network untuk Menentukan Ketepatan Masa Studi Mahasiswa(Studi Kasus: Program Studi Teknologi Informasi Universitas Udayana)

Bintari

Putra²,

Raharja³

2022

jitter

View full text Add to dashboard Cite

show abstract

“…Struktur dari jaringan neuron atau saraf secara terperinci dirancang terlebih dahulu. Neural network adalah model mesin pembelajaran yang meniru aspek pembelajaran dari pengalaman masa lalu untuk memprediksi masa depan [9].…”

Section: Artificial Neural Networkunclassified

Prediksi Kelulusan Mahasiswa Dengan Metode Naive Bayes dan Artificial Neural Network : Studi Kasus Fakultas Teknik UNIS Tangerang

Romlah,

Solichin

2022

FaktorExacta

View full text Add to dashboard Cite

Sheikh -Yusuf Islamic University (UNIS) is one of the leading Islamic Universities in Tangerang City which has a vision of making Islamic Higher Education superior in the field of science and technology in Southeast Asia by 2036. With the vision of the university, the engineering faculty must produce graduates in the engineering field who are superior, strong, and able to compete at national and international levels. The problems faced by the Faculty of Engineering, UNIS Tangerang, are the low percentage of students who graduate on time compared to students who graduate late. This study aims to assist the Faculty of Engineering in predicting student graduation so that it can be anticipated earlier. This study uses the attribute number of credits, IP from semesters 1 to 4. The methods used in this study are Naïve Bayes and Artificial Neural Network. The data used in this study used 330 student records who graduated from 2012 to 2016. Accuracy results obtained after testing with a system using 20% data testing obtained an accuracy of 63.63%, precision 71.05%, recall 67.5%, and AUC 62.6%.

show abstract

“…The classification algorithm is then trained with the dataset which means it can predict the new document category given post-training. The level of classification accuracy will be largely determined by the classification algorithm or strategy used (Davis et al, 2007;Goyal & Vohra, 2012;Purwati et al, 2020;Yuliana et al, 2019). Previous research conducted by Muslihudin and Zahrotun using the shared nearest neighbor algorithm for lecturer research allows the integration of text mining algorithms into research information systems to map research trends.…”

Section: Introductionmentioning

confidence: 99%

Data Mining Using Neural Network for Research Topic Classification Based on Institutional Research Roadmap

Feriandi

Suhartini²,

Permana³

et al. 2023

IJOMS

View full text Add to dashboard Cite

In the last five years, lecturers and students at the Faculty of Medicine at the Islamic University of Bandung have produced hundreds of studies. Still, studies on the suitability of various studies with topics according to the institution's research roadmap have not been carried out. This research aimed to classify research documents based on 12 research roadmap topics. The data used in this study are the research titles of lecturers and students in 2015-2021, amounting to 1064 data. The document extraction process uses text mining, while the document grouping process is carried out using a supervised method with an artificial neural network algorithm. At the text mining stage, preprocessing procedures are carried out in case folding, tokenization, and filtering, followed by analysis through weighting using IDF and evaluating accuracy, precision, and recall. The Neural Network Algorithm can classify by level. The classification results using the neural network algorithm show that overall from the training data, the average precision is 74.7%, recall is 74.3%, and accuracy is 74.3%. Of the 12 research topics, the training dataset obtained high accuracy, precision, and recall values found on herbal medicine, Islamic insert, industrial health, tuberculosis, and vaccination. The four topics are in line with the five institution's leading research topics. The results of dataset testing analysis found that the research topics carried out by students and lecturers of Unisba School of Medicine were distributed among the 12 research topics on the institutional roadmap with the increased trends in institutional leading research topics.

show abstract

Data Mining Dengan Algoritma Neural Network Dan Visualisasi Data Untuk Prediksi Kelulusan Mahasiswa

Cited by 6 publications

References 0 publications

Komparasi Algoritma Naïve Bayes dan Neural Network untuk Menentukan Ketepatan Masa Studi Mahasiswa(Studi Kasus: Program Studi Teknologi Informasi Universitas Udayana)

Komparasi Algoritma Naïve Bayes dan Neural Network untuk Menentukan Ketepatan Masa Studi Mahasiswa(Studi Kasus: Program Studi Teknologi Informasi Universitas Udayana)

Prediksi Kelulusan Mahasiswa Dengan Metode Naive Bayes dan Artificial Neural Network : Studi Kasus Fakultas Teknik UNIS Tangerang

Data Mining Using Neural Network for Research Topic Classification Based on Institutional Research Roadmap

Contact Info

Product

Resources

About