Jurnal Buana Informatika
Not a member yet
274 research outputs found
Sort by
Moving Average untuk Prediksi Harga Saham dengan Linear Regression
Full text linkSaham sebagai instrumen investasi di pasar modal dapat memberikan keuntungan berupa capital gain, namun juga memiliki resiko capital loss. Metode analisis dan peramalan diperlukan untuk membantu investor. Untuk mencapai hal tesebut, data historis dan data rata-rata digunakan untuk mengurangi fluktuasi acak jangka pendek pada harga saham, dan algoritma linear regression untuk mendapatkan hasil yang akurat dengan mengurangi tingkat kesalahan dan nilai Mean Squared Error (MSE). Hasil evaluasi menunjukkan akurasi yang baik dengan korelasi yang kuat dan nilai Mean Absolute Percent Error (MAPE) yang rendah. Selain itu, pengujian terhadap data historis dilakukan untuk menguji model dan menghasilkan keuntungan yang signifikan berdasarkan prediksi dari model tersebut. Menurut temuan yang diperoleh dari penilaian tersebut, memprediksi saham dengan menggunakan metode moving average dan linear regression dapat membantu investor memperoleh keuntungan dan mengurangi risiko
Blackbox Testing on Virtual Reality Gamelan Saron Using Equivalence Partition Method
Full text linkTesting is essential in application development because it helps identify and eliminate defects. One of the most used testing methods is Black Box testing, which involves deeply examining the application’s functionality without knowing its internal workings. The Equivalence Partition method is frequently used in Black Box testing to divide input values into groups and select test cases from each group. Potential errors can be identified by testing the available features with appropriate test cases, and future improvements can be made to ensure seamless application performance. In addition, testing results also serve as documentation and research for future development. By using this method, the developers of the VR Gamelan Saron application can ensure that its quality meets user expectations to improve its quality to provide an optimal user experience. In summary, proper testing is crucial in application development, and the Equivalence Partition method is an effective tool foridentifying and eliminating potential issues.Keywords: black box, equivalence partition, test case, error function, use
Analisis Sentimen Ulasan Aplikasi Jamsostek Mobile Menggunakan Metode Support Vector Machine
Full text linkSentiment Analysis of Jamsostek Mobile Application Reviews Using the Support Vector Machine Method. Today's technology is evolving quickly, leading to new developments that have helped produce JMO and other mobile applications that can be useful to Indonesians. The reviews or comments in the JMO can be used as a gauge for quality and user satisfaction. This study aims to analyze the quality of JMO applications and classify reviews or opinions into positive, negative, and neutral categories through sentiment analysis. The Support Vector Machine method is used in this analysis process with a linear kernel approach to determine the level of accuracy of classifying JMO application reviews. Research shows that classifying the SVM method against sentiment analysis of reviews or JMO application reviews produces the best accuracy scores, obtaining results with accuracy of 96%, precision of 92%, recall of 96%, and f1-score of 94%, while for the results of most reviews are positive category reviews with a total of 17.571.Keywords: sentiment analysis, JMO, SVM, linear kernel
Perkembangan pesat teknologi saat ini memunculkan inovasi baru untuk menciptakan berbagai aplikasi mobile yang dapat memberi kemudahan bagi masyarakat Indonesia, salah satunya yaitu JMO. Penelitian ini bertujuan untuk menganalisis kualitas aplikasi JMO dan mengklasifikasikan ulasan atau opini kedalam kategori positif, negatif dan netral melalui analisis sentimen. Metode Support Vector Machine digunakan pada proses analisis ini dengan pendekatan kernel linear untuk mengetahui tingkat akurasi dari pengklasifikasian ulasan aplikasi JMO tersebut. Penelitian menunjukkan bahwa pengklasifikasian metode SVM terhadap analisis sentimen ulasan atau review aplikasi JMO menghasilkan nilai akurasi terbaik, didapatkan hasil dengan accuracy 96%, precision 92%, recall 96%, dan f1-score 94%, sedangkan untuk hasil ulasan terbanyak adalah ulasan berkategori positif dengan jumlah 17.571.Kata Kunci: analisis sentimen, JMO, SVM, kernel linea
Comparative Analysis of Sound Response from Simple and Fuzzy Algorithm in Saron Virtual Reality
Full text linkVirtual reality games with musical instruments require a dynamic sound response because playing the instrument requires real human feelings. A good sound in a game depends on its suitability for the game situation. Time and place limitations are a problem in recording variations in sound sample recording. If the sound samples taken are limited and a simple algorithm is applied, it may sound repetitive and not match the dynamics of music according to real human life. Therefore, in this study, a comparison of a simple algorithm with the fuzzy algorithm was carried out in the Gamelan Saron game. The data processing method used is a comparative analysis obtained from the experimental results of the respondents. On the agreement scale of one to five, most respondents agree that there is a better significant change after being given a fuzzy algorithm described by a mean value of 4.1.
Keywords: sound, gamelan, Saron, dynamics, fuzz
Identification of Batik in Central Java using Transfer Learning Method
Full text linkBatik was recognized as a human heritage for oral and nonmaterial culture by UNESCO due to its symbolic and philosophical ties to the lives of Indonesians. However, the younger generation is gradually losing its legacy because of technological and sociological changes that have influenced Indonesian batik. Consequently, batik knowledge is disappearing. A convolutional neural network and transfer learning techniques were utilized in deep learning to construct a model recognising batik motifs. The study utilized a dataset of one thousand images, five classes of batik designs (Banji, Kawung, Slope, Parang, and Slobog), and pre-trained architectural models VGG16 and VGG19 on Keras. The best model utilizes the VGG16 architecture, and the number of epochs is 50, with the result of testing accuracy of 0.9200
Emotion Classification in Indonesian Language: A CNN Approach with Hyperband Tuning
Full text linkIn today's world, there is a high demand for accurate techniques to classify emotions in various fields. This study proposed utilizing a Convolutional Neural Network (CNN) optimized with a Hyperband Tuner (HT) to perform the Emotion Classification task in the Indonesian language effectively. Various feature extraction techniques experiments were conducted to explore the best combinations of feature extraction and CNN for the data set, including CountVectorizer (CV), TF-IDF, and Keras Tokenizer (KT). Last, the proposed methodology was evaluated and compared to the stateof-the-art techniques, including K-Nearest Neighbors (KNN), Decision Tree (DT), Naive Bayes (NB), and Boosting SVM. The experimental results revealed that the proposed method in this research outperforms the existing technique as evidenced by the accuracy, precision, recall, and F1-score metrics, which respectively reached 71.5655%, 71.5483%, 71.5655%, and 71.0041%
Analisis Usability Web SIATMA dengan Metode Heuristic Evaluation dan System Usability Scale
Full text linkUser interface dan user experience berperan penting dalam pengembangan aplikasi, yang menjadi tolok ukur keberhasilan memenuhi kebutuhan pengguna. Perlu dilakukan pengukuran usability, pencarian permasalahan dan rekomendasi perbaikan antarmuka web SIATMA, menggunakan metode Heuristic Evaluation (HE), dan System Usability Scale (SUS). Pengambilan data HE menggunakan daftar cek evaluasi yang diisi oleh evaluator dan SUS menggunakan kuesioner yang diisi oleh mahasiswa Universitas Atma Jaya Yogyakarta. Menggunakan HE ditemukan 25 permasalahan usability dengan jumlah terbanyak pada Visibility of System Status dan Aesthetic and Minimalist Design. Permasalahan tersebut terdiri dari 10 masalah cosmetic, lima masalah minor dengan, delapan masalah major, dan dua masalah catastrophe. Diberikan 25 solusi perbaikan yang direkomendasikan oleh evaluator, sedangkan menggunakan SUS dihasilkan skor SUS sebesar 54,4. Kedua hasil tersebut menunjukkan bahwa SIATMA belum memuaskan dari segi usability dan perlu dilakukan perbaikan, seperti memberikan detail minor seperti icon, peringatan sampai dengan perbaikan layout dan menambahkan halaman baru
Implementasi Algoritma K-Nearest Neighbour dalam Menganalisis Sentimen Terhadap Program Merdeka Belajar Kampus Merdeka (MBKM)
Full text linkK-Nearest Neighbor Algorithm Implementation in sentiment analysis towards Merdeka Belajar Kampus Merdeka (MBKM) Program. Merdeka Belajar Kampus Merdeka (MBKM) is a program that supports students to improve their skills by having direct experience in the work environment to prepare for competition and a future career. MBKM program has been implemented by Indonesia's Ministry of Education, Culture, Research, and Technology (Kemendikbudristek) since 2020. Every policy needs to be evaluated; a simple evaluation can be done through sentiment analysis to determine public responses to the MBKM program. The results are used as suggestions for program improvement. Sentiment analysis is done by applying the Natural Language Processing (NLP) algorithm to process crawled data from Twitter, then classified using the K-NN Algorithm. Based on the results, the sentiment is neutral. This illustrates that people are only partially interested in the MBKM program policy. The accuracy of the classification model using the K-NN algorithm is 95%, and an F1-score value of 0.96 for the classification model with a ratio of 80% training data and 20% test data.Keywords: MBKM, NLP, K-NN, F1-Score
Program Merdeka Belajar Kampus Merdeka (MBKM) merupakan suatu kebijakan dalam mendukung pemberian kebebasan terhadap mahasiswa untuk mengasah kemampuan dengan merasakan langsung pengalaman di dunia kerja sebagai bekal untuk menghadapi persaingan dan persiapan berkarir di masa mendatang. Program MBKM mulai diberlakukan oleh Kementerian Pendidikan Kebudayaan Riset dan Teknologi (Kemendikbudristek) Republik Indonesia sejak tahun 2020. Setiap kebijakan tentunya perlu dievaluasi, evalusi sederhana dapat dilakukan melalui analisis sentimen untuk mengetahui tanggapan masyarakat mengenai program MBKM. Hasilnya digunakan sebagai saran perbaikan untuk pengembangan program. Analisis sentimen dilakukan dengan menerapkan algoritma Natural Language Processing (NLP) untuk memproses data hasil crawling dari Twitter, selanjutnya diklasifikasikan menggunakan algoritma K-NN. Berdasarkan hasil analisis diperoleh bahwa sentimen masyarakat bersifat netral. Hal ini menggambarkan bahwa masyarakat tidak sepenuhnya tertarik terhadap kebijakan program MBKM, sedangkan untuk tingkat akurasi model klasifikasi menggunakan algoritma K-NN sebesar 95% dan nilai F1-score sebesar 0,96 untuk model klasifikasi dengan perbandingan 80% data latih dan 20% data uji.Kata Kunci: MBKM, NLP, K-NN, F1-Scor
Classification of Cumulonimbus Cloud Formation based on Himawari Images using Convolutional Neural Network model Googlenet
No full textCumulonimbus clouds (Cb) are dangerous for many human activities. To reduce this effect, a system to classify formations is needed. The formation of Cb clouds can be seen in the Himawari-8 IR image. This research aimed to create a Cb cloud classification system with Himawari-8 IR Enhanced imagery using the GoogleNet model CNN method. The total data used was 2026 image data. Parameter testing was carried out on the CNN GoogleNet model in this study, namely a data distribution ratio of 90:10 and 80:20. The probability of dropout is 0.6, 0.7, and 0.8. and batch sizes of 8, 16, 32, and 64. The trials conducted in this study yielded a sensitivity value of 100.00%, an accuracy of 99.00%, and a specificity of 99.60% obtained from the experimental data distribution of 90:10, probability 0.8, and batch size 8
Deteksi Uang Palsu Rupiah dengan Menggunakan Metode Deteksi Tepi Laplacian of Gaussian (LoG) dan Algoritma K-Means Clustering
Full text linkAbstract. Detection of Counterfeit Rupiah Using the Laplacian of Gaussian (LoG) Edge Detection Method and the K-Means Clustering Algorithm Counterfeit money is a severe problem that is increasing in every country. The reason is the ease of getting information on making counterfeit money and the development of technology such as color printers. This study used data from 20 images of authentic rupiah banknotes and 20 photos of fake rupiah banknotes. Data analysis in this study consisted of four stages: reading the image, converting the image to grayscale, image segmentation, and grouping image values. The dataset of real money images were taken with a cellphone camera, while counterfeit money images were obtained from the website. After the dataset retrieval process, the image conversion process was carried out into a grayscale image; then, the image segmentation process proceeded. The conclusion obtained from this study is that edge detection with Laplacian of Gaussian combined with the K-Means Clustering algorithm is quite effective in detecting an image to determine the picture as whether real money or counterfeit money.Keywords: Counterfeit Money, Laplacian of Gaussian, K-Means Clustering.
Abstrak. Uang palsu adalah masalah serius yang semakin meningkat di setiap negara. Penyebabnya ialah kemudahan mendapatkan informasi cara pembuatan uang palsu serta perkembangan teknologi seperti printer warna. Penelitian ini menggunakan data 20 gambar uang kertas rupiah asli dan 20 gambar uang kertas rupiah palsu. Analisis data pada penelitian ini terdiri dari empat tahap, yaitu membaca gambar, mengubah gambar menjadi skala abu-abu, segmentasi gambar, dan pengelompokan nilai citra. Pengambilan dataset berupa uang asli dilakukan dengan kamera handphone dan gambar uang palsu didapatkan dari website. Setelah proses temu kembali dataset, dilakukan proses konversi citra menjadi citra grayscale, kemudian dilakukan proses segmentasi citra. Kesimpulan yang diperoleh dari penelitian ini adalah deteksi tepi dengan Laplacian of Gaussian yang dikombinasikan dengan algoritma K-Means Clustering cukup efektif mendeteksi suatu citra untuk menentukan gambar tersebut sebagai uang asli atau uang palsu.Kata Kunci: Uang Palsu, Laplacian of Gaussian, K-Means Clustering