Claim Missing Document
Check
Articles

Found 4 Documents
Search
Journal : Journal of Dinda : Data Science, Information Technology, and Data Analytics

Hasil Klasifikasi Algoritma Backpropagation dan K-Nearest Neighbor pada Cardiovascular Disease Nashrulloh Khoiruzzaman; Rima Dias Ramadhani; Apri Junaidi
Indonesian Journal of Data Science, IoT, Machine Learning and Informatics Vol 1 No 1 (2021): February
Publisher : Research Group of Data Engineering, Faculty of Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (628.386 KB) | DOI: 10.20895/dinda.v1i1.141

Abstract

Cardiovascular disease adalah penyakit yang diakibatkan oleh kelainan yang terjadi pada organ jantung. Cardivascular disease dapat menyerang manusia dari usia muda hingga usia tua yang terdapat 13 faktor yang mempengaruhinya yaitu Age, Sex, Chest pain, Trestbps, Chol, Fbs, Restecg, Thalach, Exang, Oldpeak, Slope, Ca, dan Thal. Cardiovascular disease beragam jenisnya antara lain penyakit jantung koroner, gagal jantung, tekanan darah tinggi, tekanan darah rendah dan lain-lain. Oleh karena itu, penelitian ini memiliki tujuan untuk melakukan klasifikasi terhadap cardiovascular disease. Pada penelitian ini menggunakan algoritma backpropagation dan algoritma K-nearest neighbor. Langkah awal dilakukan adalah proses perhitungan euclidean distance pada K-NN untuk mencari jarak k terdekat untuk mendapatkan kategori berdasarkan frequensi terbanyak dari nilai k yang ditentukan dan mencari bobot baru untuk algoritma backpropagation untuk mendapatkan bobot baru yang digunakan untuk mendapatkan nilai yang sesuai dengan yang diharapkan. Pengujian sistem ini terdiri dari pengujian nilai akurasi dengan nilai K, pengujian K-fold X validation dan pengaruh hidden layer. Hasil dari Penelitian ini bahwa algoritma backpropagation menghasilkan nilai akurasi sebesar 64%, presisi sebesar 62%, recall sebesar 64% dan algoritma K-nearest neighbor menghasilkan nilai akurasi sebesar 66%, presisi sebesar 61% dan recall sebesar 66%. Pengaruh hidden layer terhadap algoritma backpropagation dalam mengklasifikasikan cardiovascular disease sangat besar hal ini sesuai dengan hasil dari penelitian yang telah dilakukan bahwa ketika jumlah hidden layer kecil, nilai yang dihasilkan juga kecil akan tetapi ketika jumlah hidden layernya tinggi nilai akurasinya bahkan menjadi rendah .
Analisis Sentimen Masyarakat Terhadap COVID-19 Pada Media Sosial Twitter Ardianne Luthfika Fairuz; Rima Dias Ramadhani; Nia Annisa Ferani Tanjung
Indonesian Journal of Data Science, IoT, Machine Learning and Informatics Vol 1 No 1 (2021): February
Publisher : Research Group of Data Engineering, Faculty of Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (591.332 KB) | DOI: 10.20895/dinda.v1i1.180

Abstract

Akhir tahun 2019 lalu dunia digemparkan oleh munculnya suatu penyakit yang disebabkan oleh virus SARS-CoV-2 yang merupakan jenis virus terbaru dari coronavirus. Penyakit ini dikenal dengan nama COVID-19. Penyebaran penyakit ini terbilang cukup luas dan cepat. Dalam waktu singkat penyakit ini mulai menyebar ke segala penjuru dunia tak terkecuali Indonesia. Dengan tingkat penyebaran yang begitu tinggi dan belum ditemukannya vaksin untuk COVID-19, menyebabkan kekacauan di tengah masyarakat. Hal ini mempengaruhi banyak sektor kehidupan masyarakat. Tak sedikit masyarakat yang aktif bersosial media dan menuliskan pendapat, opini serta pemikirannya di platform media sosial seperti Twitter. Terjadinya pandemi ini mendorong masyarakat untuk menuliskan opini, pemikiran serta pendapatnya terhadap COVID-19 pada media sosial Twitter. Dibutuhkan suatu model sentiment analysis untuk mengklasifikasi tweet masyarakat di Twitter menjadi positif dan negatif. Sentiment analysis merupakan bagian dari Natural Language Processing yang membuat sebuah sistem guna mengenali serta mengekstraksi opini dalam bentuk teks. Pada penelitian ini digunakan algoritma Naive Bayes dan K-Nearest Neighbor untuk digunakan dalam membangun model sentiment analysis terhadap tweet pengguna Twitter terhadap COVID-19. Didapatkan akurasi sebesar 85% untuk algoritma Naïve Bayes dan 82% untuk algoritma K-Nearest Neighbor pada nilai k=6, 8, dan 14.
Prediksi Harga Saham Bank Bri Menggunakan Algoritma Linear Regresion Sebagai Strategi Jual Beli Saham Janur Syah Putra; Rima Dias Ramadhani; Auliya Burhanuddin
Indonesian Journal of Data Science, IoT, Machine Learning and Informatics Vol 2 No 1 (2022): February
Publisher : Research Group of Data Engineering, Faculty of Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/dinda.v2i1.273

Abstract

Shares are securities as proof of ownership of investors in a company. Stocks have a volatile nature, this makes stocks difficult to predict. Stock prediction is an effort to estimate the stock price, especially in the Bank Rakyat Indonesia company that will appear in the future, and to increase investors' profit opportunities in making investment decisions. During the COVID-19 pandemic, Bank BRI's shares experienced significant ups and downs in four months, which illustrates the sensitivity of the stock to an event. Therefore, it is important to predict stock prices to reduce the risk accepted by investors. The prediction itself requires time series data. Time series is data that is collected sequentially from time to time. The method used for time series data is Linear Regression because this method can handle time-series data. Based on these problems, stock prediction research will be conducted at the Bank Rakyat Indonesia company using the Linear Regression method. Bank Rakyat Indonesia share price data were obtained from the investing.com website from the period starting on January 1, 2008, to June 1, 2020. The data is processed starting from preprocessing to determine attributes, remove unnecessary attributes, and change the contents of the data type, then process split data to divide the dataset into training and test data. The attributes used in this study are Date and Price and the distribution of the data used is 60:40, 65:35, 70:30, 75:25, and 80:20. The best ratio is at 80:20 which produces train and test accuracy of 0.89 and 0.91, Then each training data and testing data are entered into the linear regression model for prediction. The error results from the predictions were calculated using MAPE and yielded a percentage of 13.751% for training data, 13.773% for test data, and 13.755% for overall data. The MAPE results indicate that the linear regression method can be used to predict the stock price of BRI Bank.
Perbandingan Performa Antara Algoritma Naive Bayes Dan K-Nearest Neighbour Pada Klasifikasi Kanker Payudara Annisa Nugraheni; Rima Dias Ramadhani; Amalia Beladinna Arifa; Agi Prasetiadi
Indonesian Journal of Data Science, IoT, Machine Learning and Informatics Vol 2 No 1 (2022): February
Publisher : Research Group of Data Engineering, Faculty of Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/dinda.v2i1.391

Abstract

Breast cancer is the second most common cause of death from cancer after lung cancer is in the first place. Breast cancer occurs when cells in breast tissue begin to grow uncontrollably and can disrupt existing healthy tissue. Therefore, there is a need for a classification to distinguish breast cancer patients and healthy people. Based on previous research, the Naïve Bayes and K-Nearest Neighbor algorithms are considered capable of classifying breast cancer. In the research process using the breast cancer dataset from the Breast Cancer Coimbra dataset in 2018 UCI Machine Learning Repository with a total of 116 data, while for the calculation of the feasibility of the method using the Confusion Matrix (Accuracy, Precision, and Recall) and the ROC-AUC curve. The purpose of this study is to compare the performance of the Naïve Bayes and K-Nearest Neighbor algorithms. In testing using the Naïve Bayes algorithm and the K-Nearest Neighbor algorithm, there are several test scenarios, namely, data testing before and after normalization, model testing based on a comparison of training data and testing data, model testing based on K values ​​in K-Nearest Neighbors, and model testing. based on the selection of the strongest attribute with the Pearson correlation test. The results of this study indicate that the Naïve Bayes algorithm has the highest average accuracy of 69.12%, healthy precision 64.90%, pain precision 83%, healthy recall 88%, sick recall 61.11% and AUC 0.82 which is included in the good classification category. Meanwhile, the highest average results of the K-Nearest Neighbor algorithm are 76.83% for accuracy, 76% healthy precision, 80.21% pain precision, 74.18% for healthy recall, 80.81% sick recall and 0.91 AUC which is included in the excellent classification category.