Garuda - Garba Rujukan Digital

Prediction Of Flight Delays Using Feature Engineering, Catboost, And Bayesian Optimization To Improve Model Performance Maulana, Ilham; Ernawati, Siti; Wati, Risa
Jurnal Riset Informatika Vol. 7 No. 2 (2025): Maret 2025
Publisher : Kresnamedia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34288/jri.v7i2.346

Flight delays have become a major issue in the aviation industry, impacting operational efficiency and customer satisfaction. This study proposes a CatBoostClassifier-based approach combined with Feature Engineering, Bayesian Optimization, and Random Over Sampling techniques to improve the accuracy of flight delay predictions. Based on model evaluation results, the use of Feature Engineering and Bayesian Optimization enhances performance compared to the baseline CatBoost model. The CatBoost+FE+Bayes combination achieves an accuracy of 83.32%, higher than the unmodified CatBoost model, which only reaches 82.95%. However, applying the Random Over Sampling technique in the CatBoost+FE+Bayes+ROS combination decreases model performance, reducing accuracy to 81.44%. Regarding other metrics, the CatBoost+FE+Bayes model demonstrates the highest F1-score of 0.62, indicating a balance between precision and recall. Additionally, the Area Under Curve (AUC) analysis reveals that CatBoost+FE+Bayes has the highest AUC value of 0.7793, followed by CatBoost+FE at 0.7768, and the unmodified CatBoost model at 0.7643. Meanwhile, the application of ROS leads to a decrease in AUC value to 0.6787. These findings suggest that utilizing Feature Engineering and Bayesian Optimization significantly enhances flight delay predictions. However, resampling techniques such as ROS do not always positively impact the tested model and can even degrade classification performance. The objective of this research is to develop a more accurate flight delay prediction model through the application of appropriate optimization techniques. The resulting model is expected to improve prediction quality and benefit the aviation industry by optimizing operational efficiency and minimizing the negative impact of delays on passengers.

Digitalization Of Survey And Mapping Service Processes Through The Development Of A Web-Based System Ernawati, Siti; Hermawan, Deni
Jurnal Riset Informatika Vol. 7 No. 1 (2024): December 2024
Publisher : Kresnamedia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34288/jri.v7i1.352

PT. Cakrawala Pilar Nusantara is a private company engaged in survey and mapping consultancy services. Several challenges have been identified in its business processes, one of which is that service delivery for collaboration is still conducted manually. This study adopts a Design Science Research (DSR) approach, focusing on the development of an artifact in the form of a web-based service system for PT. Cakrawala Pilar Nusantara, in accordance with the objectives of the research. The DSR methodology consists of the following stages: Problem Identification and Research Motivation, Definition of Solution Objectives, Design and Development of the Artifact, Demonstration, Evaluation, and Communication. Data collection was carried out through observation and interviews with relevant parties. System design visualization was conducted using UML, represented by use case diagrams and activity diagrams. The programming language used is PHP, implementing the CodeIgniter framework. System testing was performed using the black-box testing method.The result of this research is a web-based information system that facilitates data entry, quotation submissions, reporting, and improves service processes by transforming manual record-keeping into a computerized system. The presence of this information system provides greater convenience for the company in managing its operational activities.

Analisis Sentimen Persepsi Publik Mengenai PPKM Pada Twitter Berbasis SVM Menggunakan Python Wati, Risa; Ernawati, Siti
Jurnal Teknik Informatika UNIKA Santo Thomas Vol 6 No. 2 : Tahun 2021
Publisher : LPPM UNIKA Santo Thomas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54367/jtiust.v6i2.1465

Covid-19 merupakan penyakit menular melalui mulut dan hidung seseorang yang terinfeksi saat sedang berbicara, batuk maupun bersin dan menyebar secara luas didunia sehingga ditetapkan sebagai pandemi. Banyak upaya pemerintah yang dilakukan untuk menekan penyebaran Covid-19, salah satunya adalah penerapan PPKM untuk wilayah Jawa dan Bali. Pemberlakuan PPKM ini menimbulkan pro-kontra antar masyarakat, ada yang setuju dan ada yang tidak setuju diberlakukannya PPKM. Oleh sebab itu peneliti melakukan penelitian sentimen masyarakat terhadap pemberlakuan PPKM wilayah Jawa dan Bali. Komentar masyarakat diambil dari media sosial yaitu twitter berupa komentar positif dan negatif, kemudian data diolah menggunakan text editor Jupyter dan bahasa pemrograman Python serta menggunakan algoritma SVM. Penelitian ini memiliki tujuan apakah algoritma SVM dapat menjadi pengklasifikasi teks yang baik untuk analisis sentimen pemberlakuan PPKM, membandingkan Kernel pada SVM antara Kernel Linier dengan Kernel RBF, serta menilai apakah penerapan PPKM untuk wilayah Jawa dan Bali terbukti berhasil menekan angka penyebaran virus Covid-19. Algoritma SVM dengan kernel linier terbukti menjadi algoritma pengklasifikasi text yang baik pada analisis sentimen pemberlakuan PPKM wilayah Jawa dan Bali dengan nilai akurasi sebesar 86%. Serta Dilihat dari hasil analisis sentimen penerapan PPKM untuk wilayah Jawa dan Bali terbukti berhasil menekan angka penyebaran Covid-19

Penerapan Metode Analytical Hierarchy Process Untuk Menentukan Jasa Pengiriman Pada PT. Kharisma Yona Mulia Ernawati, Siti; Alfahran Islami, Hasby
Jurnal Teknik Informatika UNIKA Santo Thomas Vol 7 No. 2 : Tahun 2022
Publisher : LPPM UNIKA Santo Thomas

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

Delivery services are one of the most important things in the company’s business process in the warehousing service sector. The warehouse company stores goods from the seller so that they are stored properly and sent to delivery service when there is an order for goods from the seller. Companies that run in the field of warehousing services, on of which is PT. Kharisma Yona Mulia. PT. Kharisma Yona Mulia is still having problems in determining the best shipping services to be more rational. The AHP method is a process of comparing criteria into alternatives, if the resulting value is higher, the higher the priority for delivery service to choose. The criteria used in this study are shipping costs, delivery speed, delivery security, services and facilities. There are alternatives that are used, namely JNT, JNE, TIKI and SICEPAT. By using the AHP method for determining the delivery service, the results of the order of criteria values are obtained, namely delivery security 0.434 0r 43.4%, shipping costs 0.264 or 26.4%, delivery speed 0.160 or 16%, service 0.091 or 9.1% and 0.051 or 5.1% facilities. Then the results obtained the largest value for the alternative is TIKI with a value of 0.39 or 39%.

Analisis Sentimen Persepsi Publik Mengenai PPKM Pada Twitter Berbasis SVM Menggunakan Python Wati, Risa; Ernawati, Siti
Jurnal Teknik Informatika UNIKA Santo Thomas Vol 6 No. 2 : Tahun 2021
Publisher : LPPM UNIKA Santo Thomas

Covid-19 merupakan penyakit menular melalui mulut dan hidung seseorang yang terinfeksi saat sedang berbicara, batuk maupun bersin dan menyebar secara luas didunia sehingga ditetapkan sebagai pandemi. Banyak upaya pemerintah yang dilakukan untuk menekan penyebaran Covid-19, salah satunya adalah penerapan PPKM untuk wilayah Jawa dan Bali. Pemberlakuan PPKM ini menimbulkan pro-kontra antar masyarakat, ada yang setuju dan ada yang tidak setuju diberlakukannya PPKM. Oleh sebab itu peneliti melakukan penelitian sentimen masyarakat terhadap pemberlakuan PPKM wilayah Jawa dan Bali. Komentar masyarakat diambil dari media sosial yaitu twitter berupa komentar positif dan negatif, kemudian data diolah menggunakan text editor Jupyter dan bahasa pemrograman Python serta menggunakan algoritma SVM. Penelitian ini memiliki tujuan apakah algoritma SVM dapat menjadi pengklasifikasi teks yang baik untuk analisis sentimen pemberlakuan PPKM, membandingkan Kernel pada SVM antara Kernel Linier dengan Kernel RBF, serta menilai apakah penerapan PPKM untuk wilayah Jawa dan Bali terbukti berhasil menekan angka penyebaran virus Covid-19. Algoritma SVM dengan kernel linier terbukti menjadi algoritma pengklasifikasi text yang baik pada analisis sentimen pemberlakuan PPKM wilayah Jawa dan Bali dengan nilai akurasi sebesar 86%. Serta Dilihat dari hasil analisis sentimen penerapan PPKM untuk wilayah Jawa dan Bali terbukti berhasil menekan angka penyebaran Covid-19

Penerapan Metode Analytical Hierarchy Process Untuk Menentukan Jasa Pengiriman Pada PT. Kharisma Yona Mulia Ernawati, Siti; Alfahran Islami, Hasby
Jurnal Teknik Informatika UNIKA Santo Thomas Vol 7 No. 2 : Tahun 2022
Publisher : LPPM UNIKA Santo Thomas

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

Delivery services are one of the most important things in the company’s business process in the warehousing service sector. The warehouse company stores goods from the seller so that they are stored properly and sent to delivery service when there is an order for goods from the seller. Companies that run in the field of warehousing services, on of which is PT. Kharisma Yona Mulia. PT. Kharisma Yona Mulia is still having problems in determining the best shipping services to be more rational. The AHP method is a process of comparing criteria into alternatives, if the resulting value is higher, the higher the priority for delivery service to choose. The criteria used in this study are shipping costs, delivery speed, delivery security, services and facilities. There are alternatives that are used, namely JNT, JNE, TIKI and SICEPAT. By using the AHP method for determining the delivery service, the results of the order of criteria values are obtained, namely delivery security 0.434 0r 43.4%, shipping costs 0.264 or 26.4%, delivery speed 0.160 or 16%, service 0.091 or 9.1% and 0.051 or 5.1% facilities. Then the results obtained the largest value for the alternative is TIKI with a value of 0.39 or 39%.

EMPOWERING YOUTH WITH DESIGN: WORKSHOP FIGMA UNTUK REMAJA KREATIF Asri Utami, Lilyani; Ernawati, Siti; Rini Yulia, Eka
Martabe : Jurnal Pengabdian Kepada Masyarakat Vol 8, No 7 (2025): MARTABE : JURNAL PENGABDIAN KEPADA MASYARAKAT
Publisher : Universitas Muhammadiyah Tapanuli Selatan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31604/jpm.v8i7.%p

Generasi muda saat ini menunjukkan keterlibatan yang tinggi dalam pemanfaatan teknologi, media sosial, dan dunia digital. Selain keterampilan teknis, mereka juga memiliki potensi kreatif yang dapat dikembangkan melalui platform desain seperti Figma. Namun, masih banyak yang memerlukan pelatihan untuk mengoptimalkan penggunaan alat tersebut secara profesional. Untuk menjawab kebutuhan ini, kegiatan workshop Figma diselenggarakan bagi Ikatan Remaja RW 007 (IKRAR 007) Margonda, sebuah komunitas pemuda Islam yang aktif dalam kegiatan keagamaan dan sosial. Melalui program Pengabdian Kepada Masyarakat oleh dosen Fakultas Teknologi Informasi Universitas Nusa Mandiri, peserta dibekali keterampilan desain yang terstruktur dengan tujuan mendukung pengembangan aplikasi yang dinamis, interaktif, dan ramah pengguna. Hasil yang diharapkan adalah peningkatan kapasitas organisasi dalam mengelola kegiatan sosial, memperluas jaringan, serta mendukung dakwah secara digital.

Analisis Struktural dan Nilai Pendidikan Karakter pada Novel Si Anak Savana karya Tere Liye serta Pemanfaatannya Sebagai Bahan Ajar di SMA Ernawati, Siti; Al Gadri, Henri Henriyan
Jurnal Artikula Vol 6 No 1 (2023)
Publisher : Universitas Mathla'ul Anwar Banten

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30653/006.202361.104

This research aims to describe the structure of the novel Si Anak Savana by Tere Liye and the value of character education and its use as teaching material in schools. The research method used is descriptive qualitative by describing the results of the analysis in the form of the structure and value of character education in the novel Si Anak Savana by Tere Liye which is then used as learning material for Indonesian Language and Literature in Schools. The novel Si Savana Child by Tere Liye has a novel structure that focuses on theme, characters and characterization, setting, plot, language style, point of view and message and there are character education values, namely religious, honest, tolerant, disciplined, hard work, creative, independence, curiosity, love of the country, respect for achievements, friendship (communicative), love of peace, environmental care, social care, and responsibility

Redesain Kemasan Keripik Tempe Menggunakan Metode Quality Function Deployment dan Value Engineering Ernawati, Siti; Muhammad, Katon; Asyari, Hasyim
INVENTORY: Industrial Vocational E-Journal On Agroindustry Vol. 5 No. 2 (2024)
Publisher : Politeknik ATI Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52759/inventory.v5i2.209

The existing Gandhes tempeh chips packaging is not air- and water-tight so it is at risk of damage such as not crispy, easily destroyed, and rancid odor. These packaging problems require packaging development in order to improve the function of the packaging. The purpose of this study is to determine packaging attributes based on consumer preferences to increase the value of Ghandes tempeh chips packaging based on the highest value. Improvement is done by integrating Quality Function Deployment and Value engineering techniques with the help of House of Quality, FAST diagram, and concept combination table. Quality Function Deployment method to identify customer needs by finding weights and technical responses, while Value engineering to analyze packaging functions needed by consumers and recommend the best packaging based on the highest value. The results are 10 attributes that become consumer needs (whats) and 12 technical responses (hows). The results showed 4 alternative packaging concepts that can be made and sorted to determine the best concept in terms of cost and performance. The selected alternative concept is Alternative C with a score of 1.78. The selected packaging specifications include 100 micron metalized paper material, information label, matte finishing, standing pouch, size 17×29 cm, weight 200 grams, ziplock packaging, price per package Rp 2,850, using a combination of red and orange colors. It can be concluded that this proposal is the best proposal in terms of the highest value. This recommendation can be considered capable of fulfilling consumer desires for Gandhes tempeh chips packaging.

APLIKASI ANDROID PENGENALAN HEWAN MULTI BAHASA UNTUK MENINGKATKAN KOGNITIF ANAK Ernawati, Siti; Wati, Risa; Maulana, Ilham
Jurnal Informatika dan Rekayasa Elektronik Vol. 6 No. 2 (2023): Jire Nopember 2023
Publisher : LPPM STMIK Lombok

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36595/jire.v6i2.1012

Pendidikan anak usia dini sangat penting untuk pembentukan kognitif, emosional, dan sosial seseorang. Aplikasi pembelajaran untuk perangkat mobile, khususnya Android, telah berkembang menjadi salah satu aplikasi pembelajaran terbaik dan paling populer. Pengenalan hewan pada anak usia dini meningkatkan pemahaman tentang dunia dan kosakata. Dalam menghadapi dunia yang semakin digital dan terintegrasi saat ini sangat penting untuk belajar multi bahasa sejak dini. Tujuan dari penelitian ini adalah untuk membangun sebuah aplikasi android yang dapat mengenalkan berbagai hewan kepada anak-anak dalam multi bahasa (Indonesia, Inggris, Jepang, Korea dan Arab) sehingga dapat meningkatkan keterampilan bahasa anak terutama dalam pengenalan hewan serta dapat memberikan pengalaman belajar yang lebih interaktif dan menarik bagi anak-anak. Sistem perangkat lunak dibangun menggunakan metode waterfall. Menggunkan framework flutter dan dart sebagai bahasa pemrograman. Kuesioner digunakan sebagai pengujian kelayakan aplikasi. Aplikasi yang dibangun terbukti dapat meningkatkan kognitif anak usia dini serta peningkatan kemampuan untuk memahami infomasi yang disajikan dan terbukti dapat meningkatkan kemampuan bahasa pada anak. Hal tersebut dibuktikan dengan hasil penyebaran kuesioner kepada responden yaitu orang tua yang memiliki anak usia dini dan menghasilkan persentase 74% responden sangat setuju dan 24% setuju.

Title

Found 39 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 39 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 39 Documents
Search