Garuda - Garba Rujukan Digital

Designing a Website-Based Technology Winnicode News Portal Application with Prototyping Method to Enhance User Engagement for Technology News Reader Sekar Wangi, Sari Asih; Winarsih, Nurul Anisa Sri
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol. 8 No. 2 (2025): Issues January 2025
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v8i2.13267

A news portal is a platform that usually takes the form of a website that presents various kinds of news according to its type. With the development of technology and the emergence of social media, the audience of these news portal websites has decreased. People prefer to read news through social media pages because they are easier to access. Based on this, it is necessary to develop an efficient and eye-friendly news portal website to attract people to read news through the website. By using the prototype method, the website is designed based on a pre-made design. So that the developers have a benchmark in developing the website to be built. After that, an evaluation is needed from user reviews and testing is carried out gradually to improve the website to make it more efficient and appropriate. Of the 10 test points that have been carried out in the study, a 100 percent success rate has been achieved from the test. This shows that the performance of the website that has been built can meet the criteria to be published and can be used by the wider community. From the development of this application, people can read with the theme of technology that is more comfortable, easily accessible and can send criticism to the publisher if there is a mismatch of news, have additional information about the latest news, or suggestions for the website so that it can be developed

Performance Comparison of LSTM and GRU Methods in Predicting Cryptocurrency Closing Prices Satria Andromeda, Rayhan; Winarsih, Nurul Anisa Sri
Sistemasi: Jurnal Sistem Informasi Vol 14, No 1 (2025): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v14i1.4880

Technological advancements have increased interest in cryptocurrency investments, particularly Bitcoin and Ethereum, despite the high price volatility that remains a major challenge for investors. This study aims to predict cryptocurrency price fluctuations using Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models, both of which are well-regarded for time series data analysis. Model performance was evaluated using parameters such as learning rate, timestamps, batch size, number of epochs, and Early Stopping callbacks. The evaluation metrics included Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), and the coefficient of determination (R²). The results indicate that the GRU model outperforms LSTM in predicting cryptocurrency prices. For Bitcoin data, GRU achieved a MAPE of 0.38%, RMSE of 343.02, and R² of 0.9988, surpassing LSTM, which recorded a MAPE of 0.41%, RMSE of 356.01, and R² of 0.9987. Similarly, for Ethereum data, GRU achieved a MAPE of 0.45%, RMSE of 20.89, and R² of 0.9983, outperforming LSTM with a MAPE of 0.49%, RMSE of 22.29, and R² of 0.9980. These findings demonstrate that GRU is more accurate and efficient in modeling cryptocurrency price patterns, offering strategic opportunities for investors to make more informed decisions in navigating the complexities of the cryptocurrency market.

Array Sorting Algorithm vs Traditional Sorting Algorithm: Memory and Time Efficiency Analysis: Array Sorting Algorithm vs Algoritma Pengurutan Tradisional: Analisis Efisiensi Memori dan Waktu Pujiono, Imam Prayogo; Rachmawanto, Eko Hari; Winarsih, Nurul Anisa Sri
Jurnal Manajemen Informatika JAMIKA Vol 15 No 1 (2025): Jurnal Manajemen Informatika (JAMIKA)
Publisher : Program Studi Manajemen Informatika, Fakultas Teknik dan Ilmu Komputer, Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/jamika.v15i1.13230

The development of information technology has changed various aspects of life, including the way we store and sort data. Data that used to be stored in filing cabinets is now stored in digital form on computers. However, digital data that is not well organised can make it difficult to search and verify. Therefore, data sorting has become very important, and various sorting algorithms have been developed to fulfil this need, such as the Array Sorting Algorithm (ASA), which is claimed to have efficient time complexity and is very competitive when compared to the time complexity of traditional algorithms. This research examines the memory efficiency and computation time between ASA and five traditional sorting algorithms (Bubble Sort, Shell Sort, Merge Sort, Quick Sort, and Heap Sort) using the Java programming language. The research was conducted by utilising random numerical datasets on three different scales (100, 1,000, and 10,000 data) to test the performance of the six algorithms in various scenarios. ASA, which utilises a two-dimensional array structure to manage element frequencies, showed impressive performance in terms of computation time, especially on datasets containing 1,000 and 10,000 data, compared to traditional algorithms that focus more on comparison and recursion methods. The test results confirm that on datasets of 1,000 and 10,000 data, ASA excels in terms of computational speed but loses in terms of memory usage. Therefore, if memory usage is not a major consideration, then ASA is a very suitable sorting algorithm for sorting data of 100 - 10,000. These findings provide important insights for the selection of efficient sorting algorithms based on memory efficiency and computation time on multiple data sizes, which is particularly useful when developing applications using the Java programming language.

Perbandingan Arsitektur VGG16, MobileNetV2, InceptionV3, ResNet50, dan CNN Kustom untuk Klasifikasi Gambar Furnitur Epiphany Shavna Gracia; Nurul Anisa Sri Winarsih
Infotekmesin Vol 16 No 1 (2025): Infotekmesin: Januari 2025
Publisher : P3M Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35970/infotekmesin.v16i1.2500

The rapid development of technology in the current digital era is driving increased demand across various sectors, including the furniture industry. Classifying furniture images is one of the critical challenges in image processing and computer vision, mainly due to the diversity of types. This research aims to understand how pre-trained models can affect image classification accuracy using furniture dataset results. This study uses five CNN architectures and focuses on comparing the performance of a custom architecture with four pre-trained architectures, namely VGG-16, MobileNetV2, InceptionV3, and ResNet-50, using furniture images that have five classes such as chairs, tables, cabinets, sofas, and mattresses. The research results show that the models produced by the pre-trained architectures provide higher accuracy and performance, with VGG-16 reaching 97%, MobileNetV2 at 96%, and InceptionV3 and ResNet-50 at 98%. Meanwhile, the custom model only achieved an accuracy of 85%. This research shows that using pre-trained model algorithms significantly improves performance in image classification.

Perbandingan Kinerja Djaka, Thesa Permatasari Djaka; Nurul Anisa Sri Winarsih
Infotekmesin Vol 16 No 1 (2025): Infotekmesin: Januari 2025
Publisher : P3M Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35970/infotekmesin.v16i1.2504

Polycystic ovary syndrome (PCOS) is a hormonal disorder that is the most common cause of anovulation and infertility in women of reproductive age, affecting approximately 5-10% of the population, with up to 70% of cases undiagnosed. This highlights the need for early detection methods with high accuracy for timely treatment. Previous research utilized a classification method based on the K-Nearest Neighbor (KNN) algorithm, which demonstrated good performance with an accuracy of 93%, precision of 100%, recall of 82%, and F1-Score of 90%. This study proposes using an ensemble learning method with a voting classifier technique that combines several classification models: Random Forest Classifier, Logistic Regression, and XGBoost Classifier. The results show that the proposed method performs better with an accuracy of 95%, precision of 100%, recall of 85%, F1-Score of 92%, and an AUC (Area Under Curve) value of 94.34%

Kinerja Naive Bayes dan SVM pada Data Survei Tidak Seimbang: Studi Klasifikasi Kepuasan Masyarakat Romadhoni, Mellynda Noor; Winarsih, Nurul Anisa Sri
Jurnal Pendidikan Informatika (EDUMATIC) Vol 9 No 2 (2025): Edumatic: Jurnal Pendidikan Informatika
Publisher : Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/edumatic.v9i2.30185

The utilization of Public Satisfaction Survey (SKM) data has not been optimal, highlighting the need for an effective classification method to determine the level of public satisfaction. This study aims to classify satisfaction levels using the 2024 SKM data from the Regional Civil Service and Training Agency (BKPPD) of Grobogan Regency, employing Naive Bayes and Support Vector Machine (SVM) algorithms. This quantitative research uses nine service elements rated on a scale of 1 to 4 as features, with satisfaction level as the target variable. The dataset consists of 303 entries: 156 “very satisfied,” 115 “satisfied,” and 32 “dissatisfied.” Random oversampling was applied to address class imbalance. Model performance was evaluated using accuracy, precision, recall, and F1-score, both before and after oversampling. Results showed Naive Bayes achieved 96.72% accuracy, while SVM scored 95.08%. After oversampling, SVM accuracy significantly improved to 98.36%, while Naive Bayes slightly decreased to 95.08%. Precision, recall, and F1-scores also demonstrated strong performance across all classes. This study is expected to support the improvement of public service delivery at BKPPD Grobogan and similar institutions.

Penerapan Pelatihan Scratch untuk Meningkatkan Literasi Digital pada Siswa Sekolah Dasar melalui Pembelajaran Pemrograman Visual Muhammad Syaifur Rohman; Galuh Wilujeng Saraswati; Nurul Anisa Sri Winarsih; Filmada Ocky Saputra; Danny Oka Ratmana; Adhitya Nugraha
Inovasi Sosial : Jurnal Pengabdian Masyarakat Vol. 2 No. 3 (2025): Agustus : Inovasi Sosial : Jurnal Pengabdian Masyarakat
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62951/inovasisosial.v2i3.2021

The rapid development of technology has made it increasingly important for the younger generation to acquire digital literacy skills at an early age. As technology becomes an integral part of daily life, it is essential to introduce fundamental programming concepts to students to prepare them for the future. This community service program aims to introduce 5th-grade students at Elementary School Emmaus Kediri to basic programming concepts using the Scratch platform. The program adopted the Project-Based Learning (PjBL) method, which emphasizes interactive learning through hands-on activities. The one-day session involved 17 students, who underwent a structured process consisting of a pre-test, material delivery, hands-on practice of creating simple animations, and a post-test. The learning materials included an introduction to the Scratch interface, how to use sprites, and basic coding blocks to develop simple animation projects. The evaluation results indicated a significant increase in students' understanding of basic programming concepts. The majority of participants successfully created simple animation projects using coding blocks and sprites, demonstrating their ability to apply the learned concepts. The students showed high enthusiasm throughout the learning process, indicating a strong interest in digital learning and coding. The high level of engagement further supports the potential for expanding similar programs in the future. This community service activity proved effective in introducing computational thinking and fostering creativity among elementary school students. It also demonstrated the effectiveness of interactive and hands-on learning approaches in enhancing students' digital literacy. As a result, this program has the potential to be implemented in other schools to promote early exposure to programming and support the development of digital skills among young learners

Penerapan Metode Naïve Bayes Classifier Untuk Klasifikasi Sentimen Pada Judul Berita Astuti, Yani Parti; Wibowo, Alrico Rizki; Kartikadarma, Etika; Subhiyakto, Egia Rosi; Sri Winarsih, Nurul Anisa; Rohman, Muhammad Syaifur
LogicLink Vol. 1 No. 1, June 2024
Publisher : Universitas Islam Negeri K.H. Abdurrahman Wahid Pekalongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28918/logiclink.v1i1.7684

News has a major role as a source of information to convey reports on opinions, events, and the latest findings in various aspects of life. News headlines, as an important component, can be a determinant of news content. The sentiment contained in news headlines can be classified using sentiment analysts, as is the case in the online media platform Kompas.TV. News headlines are retrieved using an automated program that utilises the HTML body with the help of NodeJs as the technology for program creation. This research is focused on the application of Naïve Bayes Classifier method to classify sentiment on Kompas.TV news headlines in Semarang City. The results showed an accuracy rate of 91.04%, with a ratio of training data and test data of 90:10. The conclusion of this study is that the Naïve Bayes Classifier method is effective in identifying news headlines with negative sentiment on Kompas.TV, with a precision of 89% and recall of 94%. This finding makes a positive contribution to the understanding of sentiment analysis on news headlines in online media, especially in the context of Kompas.TV news in Semarang City.

Perbandingan Arsitektur VGG16, MobileNetV2, InceptionV3, ResNet50, dan CNN Kustom untuk Klasifikasi Gambar Furnitur Epiphany Shavna Gracia; Nurul Anisa Sri Winarsih
Infotekmesin Vol 16 No 1 (2025): Infotekmesin: Januari 2025
Publisher : P3M Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35970/infotekmesin.v16i1.2500

The rapid development of technology in the current digital era is driving increased demand across various sectors, including the furniture industry. Classifying furniture images is one of the critical challenges in image processing and computer vision, mainly due to the diversity of types. This research aims to understand how pre-trained models can affect image classification accuracy using furniture dataset results. This study uses five CNN architectures and focuses on comparing the performance of a custom architecture with four pre-trained architectures, namely VGG-16, MobileNetV2, InceptionV3, and ResNet-50, using furniture images that have five classes such as chairs, tables, cabinets, sofas, and mattresses. The research results show that the models produced by the pre-trained architectures provide higher accuracy and performance, with VGG-16 reaching 97%, MobileNetV2 at 96%, and InceptionV3 and ResNet-50 at 98%. Meanwhile, the custom model only achieved an accuracy of 85%. This research shows that using pre-trained model algorithms significantly improves performance in image classification.

Analisis Kinerja Ensemble Learning dan Algoritma Tunggal dalam Klasifikasi Sindrom Ovarium Polikistik Menggunakan Random Forest, Logistic Regression, dan XGBoost Djaka, Thesa Permatasari Djaka; Nurul Anisa Sri Winarsih
Infotekmesin Vol 16 No 1 (2025): Infotekmesin: Januari 2025
Publisher : P3M Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35970/infotekmesin.v16i1.2504

Polycystic ovary syndrome (PCOS) is a hormonal disorder that is the most common cause of anovulation and infertility in women of reproductive age, affecting approximately 5-10% of the population, with up to 70% of cases undiagnosed. This highlights the need for early detection methods with high accuracy for timely treatment. Previous research utilized a classification method based on the K-Nearest Neighbor (KNN) algorithm, which demonstrated good performance with an accuracy of 93%, precision of 100%, recall of 82%, and F1-Score of 90%. This study proposes using an ensemble learning method with a voting classifier technique that combines several classification models: Random Forest Classifier, Logistic Regression, and XGBoost Classifier. The results show that the proposed method performs better with an accuracy of 95%, precision of 100%, recall of 85%, F1-Score of 92%, and an AUC (Area Under Curve) value of 94.34%

Title

Found 33 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 33 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 33 Documents
Search