Claim Missing Document
Check
Articles

Found 4 Documents
Search
Journal : Building of Informatics, Technology and Science

Perbandingan Kinerja Klasifikasi Penyakit Ginjal Menggunakan Algoritma Support Vector Machine (SVM) dan Decision Tree (DT) Madani, Puja Milenia Sriwildan; Rohana, Tatang; Baihaqi, Kiki Ahmad; Fauzi, Ahmad
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5206

Abstract

Chronic Kidney Disease is one of the deadliest diseases. In the early stages, the disease may go undetected, so patients tend to take it lightly, however, the disease can progress little by little and become serious without being detected. This can lead to complications of other diseases and can cause permanent damage to the kidney organs. Therefore, this study aims to classify individuals who are at risk of having Chronic Kidney Disease which can help medical personnel in an effort to reduce the number of people with the disease. This study uses Chronic Kidney Disease data obtained from the UCI Repository web. The data has 25 attributes with 400 rows. This research compares the Support Vector Machine and Decision Tree algorithms and uses the Confusion Matrix evaluation method. The results showed that the Support Vector Machine algorithm has superior accuracy, precision, recall, and f1-score results compared to the Decision Tree algorithm. The accuracy of the Support Vector Machine algorithm is 97.5, precision is 0.98, recall is 0.96, and f1-score is 0.97. While the Decision Tree algorithm obtained accuracy of 92.5, precision of 0.92, recall of 0.90, and f1-score of 0.91. with these results, this research can be continued into an application that can classify individuals at risk of Chronic Kidney Disease
Analisis Sentimen Ulasan Aplikasi Identitas Kependudukan Digital Menggunakan Algoritma Logistic Regression dan K-Nearest Neighbor Setiawan, Bagus; Baihaqi, Kiki Ahmad; Nurlaelasari, Euis; Handayani, Hanny Hikmayanti
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5389

Abstract

The government has launched the latest innovation in data collection in the realm of population data which relies on digital technology through mobile applications using photos or QR codes which aims to reduce the use of physical prints of identity cards and the availability of blank KTPs with the aim of simplifying the administrative process and no longer requiring population documents. printing or saving in physical format such as an KTP file. In implementing the population identity application, some people feel anxious due to limited internet access, lack of knowledge about the application, as well as concerns about the security and privacy of identity data in digital format. This research aims to conduct sentiment analysis on reviews of digital population identity applications by comparing logistic regression and k-nearest neighbor algorithms. The dataset was taken using the Google Play Scraper library in Python which got 1700 raw data taken from 12-February to 26 March 2024 and then pre-processed and got 1108 clean data. The results of this research show that the comparison between the logistic regression algorithm and k-nearest neighbor algorithm shows that the k-nearest neighbor algorithm is better than the logistic regression algorithm with an accuracy result of 80.43%, a difference of 3.60% compared to k-nearest neighbor. So it can be concluded that the digital population identity application is still considered poor in its use because it has a negative sentiment of 73.9% and it can be seen in this research that the comparison results of the k-nearest neighbor algorithm prove that its performance is better than logistic regression
Analisis Kinerja Algoritma Decision Tree Dan Random Forest Dalam Klasifikasi Penyakit Kardiovaskular Utami, Nisa; Baihaqi, Kiki Ahmad; Awal, Elsa Elvira; Waiddin, Deden
Building of Informatics, Technology and Science (BITS) Vol 6 No 2 (2024): September 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i2.5722

Abstract

Cardiovascular disease is a disease with a fairly high number of deaths. In Indonesia, the term cardiovascular is more popular with heart disease, which is a condition that can cause narrowing and blockage of blood vessels. Cardiovascular disease has two risks, the first is a risk that can be changed, such as stress, increased blood pressure, unhealthy diet, increased glucose levels, abnormal cholesterol and lack of physical activity. Meanwhile, risks that cannot be changed include family disease, gender, age and obesity. In this research, we can examine and analyze the performance of the two best classification algorithms, namely the decision tree algorithm and the random forest algorithm, in classifying cardiovascular disease based on the cause of the disease. The aspects studied are the performance results of each algorithm and evaluated using Area Under the Curve (AUC), classification report, k-Fold Cross Validation and Confusion matrix. The dataset used was taken from the Kaggle website with the data used being Cardiovascular Disease data which consists of 68.205 rows (patient data) and 17 attributes. . Based on the evaluation results using the Area Under The Curve (AUC) value, the highest result was obtained at 0.761 by the Random Forest algorithm with balanced data conditions with Random oversampling. Meanwhile, the lowest AUC value was obtained by the Decision Tree algorithm with unbalanced data of 0.592. Based on these results, it is known that the Random Forest algorithm with a balanced data scheme is a better algorithm, with a balanced data scenario using SMOTE and Random Oversampling techniques.
Implementasi Algoritma Convolutional Neural Network dan YOLOV8 Untuk Klasifikasi Ras Kucing Adinata, Abdul Rohim; Rohana, Tatang; Baihaqi, Kiki Ahmad; Faisal, Sutan
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.5913

Abstract

The cat with the scientific name Felis catus is a very popular pet and is often kept in various parts of the world. There are many types or breeds of cats, each of which has its own characteristics and characteristics, such as style, body shape, fur and color. However, because of the many breeds and the uniqueness of each breed, it is often difficult for ordinary people to differentiate between the types of cat breeds that exist. Therefore, technology is needed to identify and differentiate cat breeds. By comparing the Convolutional Neural Network (CNN) and YOLOV8 methods, this research aims to develop a cat breed classification model. This research uses data from six different cat breeds, namely Bengal, Bombay, Himalayan, Local, Persian and Sphynx. There are 1,200 images in all, with 200 images for each race. Before the data is used for training with the CNN and YOLOV8 methods, a preprocessing stage is carried out which includes resize and rescale for the CNN method, while for YOLOV8 a data labeling process is carried out. There are two parts to the dataset: 20% validation data and 80% training data. The training process is carried out with the same parameters for each model, namely a learning rate of 0.001, batch size of 15, and 100 epochs. From the test results with the confusion matrix, the YOLOV8 model shows the best performance with an accuracy value of 99%, precision 96.1%, recall 98.4%, and F1-score 97.2%.