Article Per Year (5 Year)
p-Index From 2021 - 2026
3.403
P-Index
This Author published in this journals
All Journal KLIK: Kajian Ilmiah Informatika dan Komputer Scientific Student Journal for Information, Technology and Science Scientific Journal of Informatics
Tatang Rohana
Sekolah Tinggi Manajemen Informatika dan Komputer
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering

Published : 24 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 24 Documents
Search

 1   2   3 
Implementasi Algoritma Support Vector Regression dan Polynomial Regression dalam Memprediksi Harga Saham PT Telekomunikasi Indonesia Windyani Eka Putri; Sutan Faisal; Tatang Rohana
Scientific Student Journal for Information, Technology and Science Vol. 6 No. 1 (2025): Scientific Student Journal for Information, Technology and Science
Publisher : Scientific Student Journal for Information, Technology and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Investasi saham di Indonesia telah menjadi salah satu investasi yang cukup terkenal. Saham yang bersifat fluktuatif atau naik turun yang tidak konsisten dipengaruhi oleh faktor internal maupun eksternal, seperti kondisi perekonomian, kinerja perusahaan, faktor panik, dan kebijakan perusahaan. Oleh sebab itu, calon investor perlu memahami saham dan melakukan analisis teknikal saham untuk mengetahui serta meminimalisir risiko dalam berinvestasi. Salah satu cara bagi calon investor yang masih awam terhadap saham adalah dengan melakukan analisis teknikal untuk mengetahui pergerakan harga saham berdasarkan informasi saham masa lampau, yaitu dengan memprediksi harga saham. Pada penelitian ini, akan dilakukan prediksi harga penutupan saham PT Telekomunikasi Indonesia menggunakan algoritma Support Vector Regression dan Polynomial Regression. Dataset yang digunakan termasuk data time series dengan rentang data selama lima tahun. Penelitian ini bertujuan untuk mengetahui kinerja algoritma mana yang lebih direkomendasikan. Hasil penelitian menunjukkan bahwa algoritma Support Vector Regression memiliki nilai RMSE 72.565 dan MAPE 1.486%. Sedangkan algoritma Polynomial Regression dengan orde 4 menghasilkan nilai RMSE 63.914 dan MAPE 1.273%. Berdasarkan hasil tersebut, algoritma Polynomial Regression memiliki performa yang lebih baik, sehingga lebih direkomendasikan dalam memprediksi harga penutupan saham PT Telekomunikasi Indonesia.
Sistem Pakar Diagnosis Penyakit Kehamilan dengan Metode Forward Chaining Syamsul Tri Andika; Tatang Rohana; Rahmat
Scientific Student Journal for Information, Technology and Science Vol. 6 No. 1 (2025): Scientific Student Journal for Information, Technology and Science
Publisher : Scientific Student Journal for Information, Technology and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Penyakit kehamilan merupakan kondisi kesehatan yang sering terjadi pada ibu hamil yang dapat mempengaruhi kesehatan dan kehamilan yang sedang berlangsung. Beberapa penyakit kehamilan yang umum terjadi antara lain preeklamsi, diabetes gestasional, anemia, infeksi saluran kemih, dan depresi prenatal. Masalah yang terjadi pada penyakit kehamilan merupakan kondisi kesehatan yang dapat mempengaruhi kesehatan ibu dan janin selama kehamilan. Ketika seorang ibu hamil mengalami penyakit kehamilan, penting untuk segera mendapatkan perawatan medis yang tepat dan sesuai dengan kondisinya. Oleh karena itu, penting untuk memahami penyakit kehamilan, faktor risiko, serta gejala dan tanda yang terkait dengan kondisi ini. Berdasarkan masalah dan penelitian sebelumnya, solusi yang dapat diberikan oleh penulis terkait fenomena diagnosis penyakit kehamilan yaitu membantu sosialisasi terkait gejala dan penyakit kehamilan yang dapat ditangani dengan cepat dan tepat. Hasil perancangan sistem pakar diagnosis penyakit kehamilan dengan algoritma forward chaining menggunakan bahasa pemrograman PHP dan berbasis website. Hasil rata-rata pada pengujian blackbox yaitu 100% dari jumlah 26 pengujian yang berhasil dan tingkat keberhasilan pada sistem pakar diagnosis penyakit kehamilan dengan algoritma forward chaining mendapatkan nilai akurasi sebesar 90% dari jumlah 18 pengujian yang sesuai.
Deteksi Nominal Mata Uang Rupiah Menggunakan Metode Convolutional Neural Network dan Feedforward Neural Network Dede Aprillia; Tatang Rohana; Tohirin Al Mudzakir; Deden Wahiddin
KLIK: Kajian Ilmiah Informatika dan Komputer Vol. 4 No. 4 (2024): Februari 2024
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/klik.v4i4.1711

Abstract

This research aims to develop a nominal detection system for the Rupiah currency for the 2022 emission year using the Convolutional Neural Network (CNN) and Feedforward Neural Network (FNN) methods, especially in the context of applications for vending machines. This research explores the potential of computer vision technology to facilitate the introduction of Rupiah banknotes and contribute to the development of vending machines. The dataset used includes variations in lighting conditions, orientation, and position of banknotes, thus involving various augmentation and preprocessing processes. The model evaluation results include nominal detection accuracy in various conditions, considering the success of the system to support the performance of the vending machine. This research is expected to contribute to the development of more comprehensive technology and expand the application of CNN and FNN in the context of currency detection. In this research, the CNN method produced the best accuracy of 100% for testing in bright conditions, then in sufficient light conditions it produced an accuracy of 96.43%. Meanwhile, testing in dark conditions got quite low results, only 78.56%. Then the FNN method produces the same accuracy of 53.57% in bright light, sufficient light and low light conditions.
Comparison Model Optimal Machine Learning Model With Feature Extraction for Heart Attack Disease Classification Salsa Desmalia; Amril Mutoi Siregar; Kiki Ahmad Baihaqi; Tatang Rohana
Scientific Journal of Informatics Vol. 11 No. 2: May 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i2.4561

Abstract

Purpose: The purpose of this study is to classify the number of people affected by heart disease and those not affected by heart disease based on various categories of heart attack causes. This study aims to urge people to take better care of their health and to serve as a reference for doctors to educate patients about the dangers of heart attacks. Methods: The model will be constructed via a machine learning methodology. The algorithms utilized in its development encompass the Support Vector Machine (SVM) algorithm, the K-Nearest Neighbor (k-NN) algorithm, and the Random Forest (RF) algorithm.  This study utilizes principal component analysis (PCA) as a means of extracting optimized features from the dataset, employing techniques for dimension reduction prior to modeling the data. Result: Cumulative explication of the concept of variance constitutes a foundational aspect of PCA (principal component analysis) within the scope of the current research, namely a dimensionality reduction technique employed in multivariate data analysis to facilitate model development, thereby enabling the creation of more optimal and comprehensive models. In this research, the dimensions of training data are incorporated during the process of model creation.   The results show KNN model exhibits the highest performance, with an accuracy of 86%, precision of 86%, recall of 91%, and F1-score of 88%. Furthermore, evaluation using the ROC metric also provides a relatively favorable value, 0.85. Novelty: Researchers used 1190 patient data sourced from Kaggle. Before modeling the algorithm, researchers conducted EDA & Preprocessing which includes missing values to find data that does not have information, then duplicate data to find duplicated data, there are 270 duplicated data, then the duplicated data is deleted so that the data becomes 737, then PCA implementation is carried out.  PCA is reducing features automatically without changing the data.
Co-Authors Adi Rizky Pratama Aditya Zatnika Ahmad Fauzi Azis Fikri Marsandi Baihaqi, Kiki Ahmad Cici Sukmawati Dede Aprillia Deden Wahiddin DWI KUSUMANINGRUM Dwi Sulistya Kusumaningrum Dwiki Riksa Maulana Elsa Awal Farhan Poetra Indah Listiyowati Ishal Saepulloh Kiki Baihaqi Muhammad Agustian Muhammad Rizal Agustian Mustabinnur Nurwijayanti Puteri Maheda Rafi Sidik Rahmat Rahmat Rahmat Riki Fauzi Anansyah Salsa Desmalia Santi Lestari Setiyo Eko Budiyono Siregar, Amril Mutoi Suningwar Mujiana Sutan Faisal Syamsul Tri Andika Tohirin Al Mudzakir Vera Shelina Wardi Karto Destian Winda Safitri Windyani Eka Putri Yana Cahyana