Article Per Year (5 Year)
p-Index From 2021 - 2026
1.325
P-Index
This Author published in this journals
All Journal Proceeding SENDI_U JSI (Jurnal sistem Informasi) Universitas Suryadarma MEANS (Media Informasi Analisa dan Sistem) Tematik : Jurnal Teknologi Informasi Komunikasi JINAV: Journal of Information and Visualization Journal of Artificial Intelligence and Engineering Applications (JAIEA) Intechno Journal : Information Technology Journal
Kurnia, Dian Ade
Unknown Affiliation
Automotive Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Library & Information Science Mathematics

Published : 8 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 8 Documents
Search

 1 
ANALISA BAKAT ANAK MELALUI PENERAPAN SISTEM PAKAR DENGAN METODE FORWARD CHAINING Laksana, Tri Ginanjar; Utama, Rizki Bintang; Kurnia, Dian Ade
Proceeding SENDI_U 2016: SEMINAR NASIONAL MULTI DISIPLIN ILMU DAN CALL FOR PAPERS
Publisher : Proceeding SENDI_U

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

Abstract

Banyak orang tua belum mengetahui bakat anaknya sehingga mempengaruhi pengembanganbakat yang dimiliki oleh anaknya. Hal ini mengakibatkan anak akan sulit untuk berkembang.Dan sulitnya menemukan psikolog anak untuk berkonsultasi juga menjadi salah satu penyebabhal ini. Penelitian ini menggunakan metode forward chaining. Alat yang digunakan dalampenelitian ini adalah bahasa pemrograman PHP dan database menggunakan MySQL. Metode inibekerja dengan cara sistem akan menerima fakta-fakta dari pengguna, kemudian akan ditarikkesimpulan dari fakta-fakta tersebut. Penelitian ini memberikan analisa bakat yang dimiliki anak.Dengan adanya sistem ini, diharapkan para orang tua tidak kesulitan untuk menganalisa bakatyang dimiliki anaknya. Sehingga para orang tua akan mampu mengembangkan bakat yangdimiliki anaknya.Kata Kunci: sistem pakar, psikolog, forward chaining, pemrograman php, database mysql
Pengenalan Wajah menggunakan Principle Component Analysis (PCA) dengan Model Algoritma Machine Learning untuk Mengidentifikasi Jenis Kelamin pada Kartu Identitas Mahasiswa Kurnia, Dian Ade; Hayati, Umi; Hartati, Tuti; Manikari, Salsa Loni; Afandi, Fahmi
TEMATIK Vol 9 No 2 (2022): Tematik : Jurnal Teknologi Informasi Komunikasi (e-Journal) - Desember 2022
Publisher : LPPM POLITEKNIK LP3I BANDUNG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38204/tematik.v9i2.1029

Abstract

Kajian tentang pengenalan wajah sampai saat ini masih banyak orang yang melakukan eksplorasi, hal ini dapat dilihat dari perkembangan teknologi Computer Vision yang diterapkan diberbagai aplikasi kehidupan. Tujuan penelitian ini adalah untuk mengidentifikasi wajah seseorang berdasarkan ciri atau featur jenis kelamin pada kartu identitas mahasiswa di sebuah perguruan tinggi. Metode yang digunakan melalui pendekatan data sains atau machine learning yaitu SEMMA (Sample, Explore, Modify, Model dan Asses) dengan penerapan pemodelan 2 (dua) algoritma yakni Support Vector Machine (SVM) dan Artificial Neural Network (ANN). Namun pemodelan tersebut juga didukung dengan pre-processing dengan teknik Principle Component Analysis (PCA) yang tujuannya mereduksi dimensi dari berbagai fitur gambar yang ada menjadi fitur yang terpilih. Hasil yang diperoleh dari penelitian ini bahwa adanya peningkatan performance pada aspek akurasi 77.50% untuk algoritma SVM dan 78.10%. Perolehan kinerja tersebut lebih baik dari penelitian sebelumnya yang tidak melibatkan teknik dimensi reduksi menggunakan PCA
UI/UX Development Using Figma based on Inclusive Design Kimseng, Ngov; Kurnia, Dian Ade; Vuthy, Ith; Arifin, Rita Wahyuni; Setiyadi, Didik
JINAV: Journal of Information and Visualization Vol. 4 No. 2 (2023)
Publisher : PT Mattawang Mediatama Solution

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35877/454RI.jinav2257

Abstract

The existence of User Interface (UI) and User Experience (UX) Designer has been highly increasing and needed in recent times. One of the reasons is that many companies are starting to use Website and Mobile Application all of these actions occurred in a convincing way that attracted users, however, each of them support the objective of business development. In answering this problem, knowledge of UI/UX is needed in terms of conduction for using it. Therefore, needed designer must use several processes in the research method that the author uses, namely empathize, define, ideate, prototype, and test. The purpose for designers, there are many resources to fulfil the lack of education and to prevent working hard, it assists designers in working and creating for all frameworks and inclusive design. Also, the contributes to designers with a practical framework, aligning with industry standards, and fostering a user-centric approach. It ensures digital products are inclusive, promoting diversity, and advancing design in the technology industry. In addition, how a designer can incorporate their unique ideate for building Websites and Mobile Applications. The result of the Design Thinking method in this research is to expertly improve the user’s experience better than before. And the result application was efficient based on the participants rate are successful effective. Satisfying based on overall rate 98.4% after see this and when using the application.
Clustering Data Penjualan Produk Makanan pada Toko Toserba Yogya Siliwangi dengan Menggunakan Metode K-Means Noviati; Mulyawan; Kurnia, Dian Ade; Rinaldi, Ade Rizki
MEANS (Media Informasi Analisa dan Sistem) Volume 7 Nomor 1
Publisher : LPPM UNIKA Santo Thomas Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (874.498 KB) | DOI: 10.54367/means.v7i1.1850

Abstract

Product availability is one of the important factors to increase sales and maintain customer satisfaction in meeting their needs. With this, the company needs to analyze sales data, both for the best-selling products or those that are not selling well from sales reports every month, especially for food products. Of course, this is not easy, especially for a large enough retailer such as the Yogya Siliwangi Toserba which has thousands of product items and thousands of sales data every month. The above problems can be solved by grouping the data using the k-means clustering algorithm on rapidminer with variables taken by the name of goods, incoming goods, outgoing goods and stock. The goal is to maximize sales and maintain product stock availability to meet the diverse needs of consumers. From the calculation of the k-means algorithm using the rapidminer application, the results obtained are in the form of three clusters, cluster_1 3 items, cluster_2 13 items and cluster_0 454 items with Devies Bouldin results being 0.478.
Analisis Komparatif Multinomial Naïve Bayes dan Logistic Regression untuk Klasifikasi Sentimen Ulasan Pengguna Aplikasi TIX ID Rachmatullah, Mochamad Miftah; Irawan, Bambang; Faqih, Ahmad; Pratama, Denni; Kurnia, Dian Ade
JSI (Jurnal Sistem Informasi) Universitas Suryadarma Vol. 13 No. 1 (2026): JSI (Jurnal sistem Informasi) Universitas Suryadarma
Publisher : Fakultas Ilmu Komputer dan Desain - Unsurya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35968/jsi.v13i1.1723

Abstract

Penelitian ini bertujuan untuk membandingkan performa algoritma Multinomial Naïve Bayes (MNB) dan Logistic Regression (LR) dalam klasifikasi sentimen multi-kelas pada ulasan pengguna aplikasi TIX ID. Sebanyak 2.500 ulasan dikumpulkan melalui proses scraping dari Google Play Store dan diproses melalui tahapan preprocessing, yang meliputi pembersihan teks, case folding, tokenisasi, stopword removal, dan stemming. Dua teknik ekstraksi fitur digunakan, yaitu CountVectorizer dan TF-IDF, sebelum model dilatih menggunakan kedua algoritma. Proses hyperparameter tuning dilakukan menggunakan GridSearchCV dengan lima lipatan cross-validation untuk memperoleh konfigurasi parameter terbaik. Hasil penelitian menunjukkan bahwa MNB dengan CountVectorizer pada tahap sebelum tuning memberikan performa paling unggul, dengan akurasi mencapai 84,80% dan F1-score macro tertinggi dibandingkan kombinasi lainnya. Sementara tuning meningkatkan stabilitas performa model, nilai akurasi tidak melampaui model awal tersebut. Temuan ini menunjukkan bahwa kombinasi MNB dan CountVectorizer lebih sesuai untuk karakteristik teks ulasan aplikasi berbahasa Indonesia yang bersifat sparse dan memiliki pola repetitif. Model terbaik kemudian diimplementasikan dalam sistem analisis sentimen berbasis web yang mampu memproses ulasan secara real time. Penelitian ini memberikan kontribusi pada pengembangan metode analisis sentimen di Indonesia dan penerapannya pada aplikasi layanan digital.
The Effectiveness of Dropout Layers in LSTM Architecture for Reducing Overfitting in Sony Stock Prediction Saputra, Roni; Kurnia, Dian Ade; Wijaya, Yudhistira Arie
Intechno Journal : Information Technology Journal Vol. 7 No. 2 (2025): December
Publisher : Universitas Amikom Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24076/intechnojournal.2025v7i2.2369

Abstract

This study investigates the effectiveness of dropout layers in reducing overfitting within Long Short-Term Memory (LSTM) neural networks for Sony stock price prediction. Financial time series forecasting presents significant challenges due to market volatility and noise, often leading to models that overfit historical data while failing to generalize to unseen market conditions. We implemented two LSTM models: one without dropout layers and another with dropout layers (rate=0.2) applied after each LSTM layer. Using historical Sony stock data from 2015-2025, we evaluated both models using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) metrics. The model with dropout demonstrated superior performance on testing data, achieving RMSE of 0.5971, MAE of 0.4411, and MAPE of 2.1502%, compared to the model without dropout which obtained RMSE of 0.7124, MAE of 0.5636, and MAPE of 2.6684%. Furthermore, the dropout model exhibited significantly reduced overfitting, with smaller performance gaps between training and testing datasets across all metrics, particularly in MAPE where the difference approached zero (0.0509%). This research provides empirical evidence that dropout regularization effectively enhances LSTM model generalization for stock prediction, offering practical value for developing more reliable financial forecasting models. Future research could explore optimal dropout rates for different market conditions and investigate combinations of dropout with other regularization techniques.
Analysis of the Effectiveness of Manual Deployment and CI/CD Github Actions in the Braisee Application Seputra, Nenda Alfadil; Nurdiawan, Odi; Dikananda, Arif Rinaldi; Pratama, Denni; Kurnia, Dian Ade
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 5 No. 2 (2026): February 2026
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v5i2.1916

Abstract

In the modern cloud-based software development ecosystem, the speed and reliability of the deployment process are critical elements. This study aims to evaluate the effectiveness of implementing Continuous Integration/Continuous Deployment (CI/CD) using GitHub Actions compared to manual methods for the machine learning API of the Braisee application hosted on Google Cloud Run. Using a quantitative approach with a comparative experimental design across ten testing iterations, this research measures deployment time efficiency, error rates, and system stability. The experimental results show a significant performance disparity, where the automated method based on GitHub Actions is considerably more efficient, with an average total duration of 111–167 seconds, reducing operational time by 40–60% compared to the manual method, which requires 297–364 seconds. In terms of reliability, the automated method achieves a 100% success rate with high consistency, whereas the manual method demonstrates substantial vulnerability to human errors such as mistyped project IDs and inconsistent image tagging. It is concluded that implementing CI/CD through GitHub Actions is a superior solution that improves time efficiency and ensures the stability of cloud-based applications compared to manual procedures.
Comparison of TF-IDF and Word2Vec Feature Representations for Emotion Classification of Tokopedia E-Commerce Review Using LinearSVC Azzahra, Fitriyani; Irawan, Bambang; Faqih, Ahmad; Pratama, Denni; Kurnia, Dian Ade
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 5 No. 2 (2026): February 2026
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v5i2.2215

Abstract

This study aims to compare the performance of TF-IDF and Word2Vec feature representations for emotion classification of Tokopedia e-commerce reviews using the LinearSVC algorithm. The dataset used is PRDECT-ID, which consists of 5,400 Indonesian-language reviews labeled with positive and negative emotions. The preprocessing stages include case folding, non-alphabet character cleaning, slang normalization, stopword removal, Sastrawi stemming, and emoji handling. Feature extraction was performed using TF-IDF and Word2Vec, after which the models were trained using LinearSVC and evaluated through 5-Fold Cross Validation and holdout testing. The experimental results show that TF-IDF achieves better performance, with an accuracy of 0.65, a macro-F1 score of 0.645, and a Cohen’s Kappa value of 0.294. Meanwhile, Word2Vec attains an accuracy of 0.58 and a macro-F1 score of 0.540. These findings indicate that TF-IDF is more effective for short and informal texts characteristic of Indonesian e-commerce reviews.
Co-Authors Ade Rizki Rinaldi Afandi, Fahmi Ahmad Faqih Azzahra, Fitriyani Bambang Irawan Didik Setiyadi Dikananda, Arif Rinaldi Hayati, Umi Kimseng, Ngov Manikari, Salsa Loni Mulyawan Noviati Odi Nurdiawan Pratama, Denni Rachmatullah, Mochamad Miftah Rita Wahyuni Arifin, Rita Wahyuni Roni Saputra, Roni Seputra, Nenda Alfadil Tri Ginanjar Laksana Tuti Hartati Utama, Rizki Bintang Vuthy, Ith Yudhistira Arie Wijaya