Article Per Year (5 Year)
p-Index From 2020 - 2025
1.993
P-Index
This Author published in this journals
All Journal Teknika Jupiter Jurnal Teknologi dan Sistem Komputer JMM (Jurnal Masyarakat Mandiri) Jurnal Sistem Komputer & Kecerdasan Buatan Innovation in Research of Informatics (INNOVATICS) Yumary: Jurnal Pengabdian kepada Masyarakat JUSTIN (Jurnal Sistem dan Teknologi Informasi) Jurnal INFOTEL Jurnal abimana (Jurnal Pengabdian Kepada Masyarakat Nasional)
Safitri, Egi
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Humanities Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Electrical & Electronics Engineering Engineering Environmental Science Industrial & Manufacturing Engineering Library & Information Science Social Sciences Other

Published : 13 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 13 Documents
Search

 1   2 
Implementasi Reccurent Neural Network Untuk Memprediksi Harga Saham Harlianto, Didi; Rachardi, Andris; Rusdah, Deandra Aulia; Safitri, Egi; Sudarsono, Ely; Bustamam, Alhadi
Jurnal Teknologi dan Sistem Komputer 2021: Publication In-Press
Publisher : Department of Computer Engineering, Engineering Faculty, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jtsiskom.2021.13898

Abstract

Saham adalah instrumen investasi dengan harga yang sangat fluktuatif. Harga saham dalam kurun waktu tertentu membentuk suatu data runtun waktu. Saat ini, salah satu metode yang cukup populer untuk menangani data runtun adalah Recurrent Neural Network (RNN). Tulisan ini membahas penerapan RNN di masa yang akan datang dalam memprediksi harga saham berdasarkan data harga saham beberapa tahun ke belakang. Tetapi RNN standar memiliki kelemahan yaitu terjadinya kondisi vanishing gradient. Oleh karena itu, arsitektur Long Short Term Memory (LSTM) digunakan pada RNN untuk mengatasi masalah tersebut. Sebagai pembanding, ditampilkan pula hasil prediksi dengan menggunakan model RNN standar. Hasilnya, RNN dengan arsitektur LSTM dapat dengan baik memprediksi harga saham dibandingkan RNN standar yang direfleksikan oleh nilai Mean Absolute Error (MAE) antar kedua model.
Cyber Threat Detection Using an Ensemble Model Approach for Phishing Website Identification Rofianto, Dani; Safitri, Egi; Amaliah, Khusnatul; Fitra, Jaka; Hijriani, Astria
Innovation in Research of Informatics (Innovatics) Vol 6, No 2 (2024): September 2024
Publisher : Department of Informatics, Siliwangi University, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37058/innovatics.v6i2.12530

Abstract

The development of digital technology has had a significant impact on various aspects of life, including an increase in cybersecurity threats, especially phishing attacks. Phishing is a method of cyber fraud that manipulates victims to provide sensitive information by posing as a trusted entity. This research aims to develop and evaluate the effectiveness of several machine learning algorithms in detecting phishing websites. The methods used in this research include the application of Random Forest, Extra Trees, Multiple Layer Perceptron, Ada Boost, and Decision Tree algorithms on website datasets containing the characteristics of phishing and non-phishing sites. Performance evaluation is performed by measuring the accuracy, precision, recall, and F1 value of each algorithm. In addition, a voting technique is applied to combine the results of the best-performing algorithms with the aim of improving the overall detection accuracy. The results showed that the voting technique was able to provide superior results compared to the use of a single algorithm, with significant improvements in accuracy and recall values. These findings reinforce the importance of ensemble approaches in machine learning to improve phishing detection capabilities, which in turn contributes to improved cybersecurity.
Prediksi Pasien Pusat Kesehatan Masyarakat Menggunakan Machine Learning Purwati, Neni; Pramujati, Windya Harieska; Syakur, Syakur; Safitri, Egi
JUSTIN (Jurnal Sistem dan Teknologi Informasi) Vol 12, No 3 (2024)
Publisher : Jurusan Informatika Universitas Tanjungpura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/justin.v12i3.80135

Abstract

The fluctuating nature of patient visits makes it difficult for hospital management to plan, so it is important to predict patient visits by community health centers (PusKesMas) based on gender. The purpose of this study is to predict whether patients who come for treatment at the community health center can be served immediately, the supply/stock of drugs can meet the needs of patients and the availability of sufficient medical equipment, so that community health center services improve for the better. Based on good performance in solving the problems that have been formulated, the methods used are Random Forest (RF) and Extreme Gradient Boosting (XGBoost). The programming language used is Python using Google Colab. The stage of separating tain and test data using the scikit-learn train_test_split module with a percentage of 70% for train data and 30% for test data produces an accuracy in RF of 0.69 while in XGBoost it is 0.93. The results of the confusion matrix from XGBoost are true positive (TP), namely data that is predicted correctly and precisely as much as 53, false negative (FN) worth 3, false positive (FP) worth 2 and 1, true negative (TN) worth 40, 4, 1, 46. Meanwhile, the results of the XGBoost classification report model from the weighted Average precision value of 0.93, the recall value of 0.93 and the F1-Score value is also 0.93. These results indicate that the model used has good quality performance, so it is worthy of use. The application carried out is with the XGBoost data classification to assess patient visits in the next 5 years, with a prediction of achieving 93% accuracy.
Diabetes Mellitus Disease Prediction using Machine Learning Algorithms Safitri, Egi; Rofianto, Dani; Purwati, Neni; Kurniawan, Hendra; Karnila, Sri
JUSTIN (Jurnal Sistem dan Teknologi Informasi) Vol 12, No 4 (2024)
Publisher : Jurusan Informatika Universitas Tanjungpura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/justin.v12i4.84620

Abstract

Diabetes mellitus is a chronic disease with a rapidly increasing global prevalence, affecting around 422 million people, predominantly in low- and middle-income countries. Effective management of diabetes requires early detection and timely intervention. This study aims to develop an accurate predictive model for diabetes mellitus using three machine learning algorithms: Random Forest, Logistic Regression, and Decision Tree. The Pima Indians Diabetes dataset, comprising 768 patient records with various health indicators, was utilized for model training and evaluation. Exploratory data analysis revealed significant correlations between glucose levels, BMI, age, and diabetes risk. The dataset was split into 80% training and 20% testing sets. Models were validated using cross-validation and evaluated based on accuracy, precision, recall, and F1-score. Results indicated that Logistic Regression achieved the highest accuracy (75%) and balanced performance in identifying both positive and negative cases. Decision Tree excelled in recall, while Random Forest showed a slightly lower balance between precision and recall. The ROC curve analysis demonstrated that Random Forest had the highest AUC (0.82), followed by Logistic Regression (0.81) and Decision Tree (0.73). This study confirms that machine learning algorithms can effectively predict diabetes, providing valuable tools for early detection and intervention, ultimately reducing the global burden of diabetes mellitus.
Pelatihan Pemanfaatan Teknologi AI dan Canva untuk Optimalisasi Labeling Produk Gapoktan Kogasera Tani Lampung Tengah Rofianto, Dani; Amaliah, Khusnatul; Win Kenali, Eko; Fitra, Jaka; K Ikshan, Fathurrahman; Safitri, Egi
Jurnal Abimana (Jurnal Pengabdian Kepada Masyarakat Nasional) Vol 1 No 2 (2024): Desember
Publisher : Pusat Penelitian dan Pengabdian Kepada Masyarakat Politeknik Negeri Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25181/abimana.v1i2.3753

Abstract

Desain kemasan dan labeling merupakan aspek penting dalam pemasaran produk, terutama bagi usaha mikro, kecil, dan menengah (UMKM). Gapoktan Kogasera Tani, yang berlokasi di Lampung Tengah, menghadapi tantangan dalam meningkatkan branding produk bawang goreng "Yasera" akibat keterbatasan pengetahuan dan keterampilan dalam desain kemasan yang menarik. Penelitian ini bertujuan untuk mengembangkan dan mengimplementasikan pelatihan pemanfaatan teknologi AI dan Canva untuk optimalisasi desain labeling produk. Pelatihan ini mencakup penggunaan Canva berbasis AI untuk meningkatkan kualitas desain visual serta ChatGPT untuk optimalisasi copywriting yang lebih efektif. Hasil penelitian menunjukkan adanya perubahan signifikan dalam desain kemasan setelah pelatihan. Desain baru lebih menarik secara visual dengan pemilihan warna, tipografi, dan tata letak yang lebih modern dan profesional. Copywriting pada kemasan juga lebih persuasif dan informatif, yang berfungsi meningkatkan daya tarik konsumen. Evaluasi terhadap kemasan baru menunjukkan bahwa penerapan teknologi AI dan Canva berhasil meningkatkan kualitas branding visual, yang pada gilirannya meningkatkan daya saing produk di pasar. Pelatihan ini memberikan dampak positif bagi UMKM, khususnya Gapoktan Kogasera Tani, dalam meningkatkan strategi pemasaran melalui desain kemasan yang optimal.
Pengembangan Keterampilan Associate Data Scientist melalui Pelatihan dengan RapidMiner Safitri, Egi; Nurlistiani, Rini; Kurniawan, Hendra
Yumary: Jurnal Pengabdian kepada Masyarakat Vol. 5 No. 4 (2025): Juni
Publisher : Penerbit Goodwood

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35912/yumary.v5i4.3664

Abstract

Purpose: This study aims to evaluate the effectiveness of an online Associate Data Scientist training program that utilizes RapidMiner as the primary platform for teaching data science and machine learning. The goal is to assess participants' improvements in data preprocessing, algorithm application, and model evaluation skills. Methodology/approach: The training program was conducted via Zoom and included interactive lectures, live demonstrations, hands-on exercises, and individual assignments. RapidMiner was used as the main tool throughout the sessions. Participants were evaluated through tasks assigned in each session and a final project that required them to analyze a dataset, apply relevant algorithms, and assess model performance. Results/findings: The results showed significant improvement in participants’ technical understanding and application skills. The average final project score was 87.0, indicating strong competence in data handling, algorithm selection, and model evaluation. Most participants completed the project successfully, demonstrating their readiness to apply data science concepts in real-world scenarios. Conclusions: The online training effectively bridged the gap between theory and practice, proving that remote learning can deliver quality outcomes in technical education. The combination of RapidMiner and a structured training format enabled participants to gain applicable skills in data science. However, improvements in instructional delivery and interaction are still needed to optimize learning experiences. Limitations: Challenges included internet connectivity issues and limited real-time interaction, which sometimes hindered learning flow and instructor support. Contribution: This study provides valuable insights into data science education, proving that online programs with practical tools like RapidMiner can successfully build core competencies in aspiring data professionals.
Prediksi Kekambuhan Kanker Tiroid Menggunakan Algoritma Random Forest Safitri, Egi; Rofianto, Dani; Karnila, Sri; Nurjoko, Nurjoko; Kurniawan, Hendra; Arkhiansyah, Yuni; Rizal, Ruki
Jurnal SISKOM-KB (Sistem Komputer dan Kecerdasan Buatan) Vol. 8 No. 3 (2025): Volume VIII - Nomor 3 - Mei 2025
Publisher : Teknik Informatika, Sistem Informasi dan Teknik Elektro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47970/siskom-kb.v8i3.833

Abstract

Kekambuhan kanker tiroid pasca terapi Radioactive Iodine (RAI) merupakan tantangan penting dalam penatalaksanaan jangka panjang pasien. Penelitian ini bertujuan membangun model prediktif untuk mengidentifikasi potensi kekambuhan dengan memanfaatkan data klinis dan patologis menggunakan algoritma Random Forest. Dataset terdiri atas 383 data pasien dengan 13 atribut, termasuk usia, jenis kelamin, staging kanker, jenis patologi, klasifikasi risiko, dan respons terhadap terapi. Proses pra-pemrosesan meliputi penyandian data kategorik, eksplorasi fitur, dan pembagian data latih dan uji secara stratifikasi. Hasil evaluasi menunjukkan performa tinggi dari model, dengan akurasi 96,5%, presisi 96,7%, recall 90,6%, dan AUC 0,99. Analisis fitur menggunakan SHAP mengungkap bahwa Stage, Response, dan Risk merupakan faktor paling berkontribusi terhadap prediksi kekambuhan. Penelitian ini menunjukkan bahwa model Random Forest tidak hanya efektif dalam klasifikasi biner, tetapi juga dapat diinterpretasikan secara klinis untuk mendukung pengambilan keputusan medis yang lebih personal dan preventif.
Evaluasi Performa Random Forest, XGBoost, dan LightGBM dalam Diagnosis Dini Diabetes Mellitus Hendra, Hendra Kurniawan; Asmaul Dwi Akbar; Nicholas Svensons; Yandi Jaya Antonio; Karnila, Sri; Safitri, Egi; Nurjoko, Nurjoko
JUPITER (Jurnal Penelitian Ilmu dan Teknologi Komputer) Vol 17 No 2 (2025): Jurnal Penelitian Ilmu dan Teknologi Komputer (JUPITER)
Publisher : Teknik Komputer Politeknik Negeri Sriwijaya

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

Abstract

Diabetes mellitus is a long-term condition marked by elevated blood sugar levels, which can lead to serious complications such as heart disease, kidney failure, and vision impairment. Early detection plays a vital role in minimizing these risks and enhancing patients' quality of life. This research focuses on assessing the performance of three machine learning algorithms—Random Forest, XGBoost, and LightGBM—in predicting diabetes risk. The dataset utilized originates from the National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK), comprising 768 samples with 9 key features. The research methodology involves multiple stages, including data collection, preprocessing, addressing data imbalance using SMOTE, data splitting for training and testing, algorithm implementation, and model evaluation through accuracy, precision, recall, F1-score, and Area Under the Curve (AUC) metrics. Findings reveal that Random Forest delivers the highest performance with an AUC score of 86%, followed by XGBoost (83%) and LightGBM (82%). With its strong accuracy, this model holds potential as a valuable tool for early diabetes diagnosis, contributing to faster and more precise medical decision-making.
PENGENALAN SAINS DATA UNTUK MENINGKATKAN LITERASI DATA DAN KESIAPAN KARIER DIGITAL SISWA SEKOLAH MENENGAH ATAS Karnila, Sri; Kurniawan, Hendra; Irianto, Suhendro Yusuf; Muktiawan, Danang Ade; Septiawan, Yuda; Safitri, Egi; Nurjoko, Nurjoko
JMM (Jurnal Masyarakat Mandiri) Vol 9, No 4 (2025): Agustus
Publisher : Universitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/jmm.v9i4.31940

Abstract

Abstrak: Pengenalan sains data di tingkat sekolah menengah memiliki peran penting dalam membekali siswa menghadapi era digital yang kian berkembang. Kegiatan pengabdian ini dirancang untuk menumbuhkan pemahaman siswa terhadap konsep dasar sains data sekaligus mendorong kesiapan mereka dalam meniti karier di bidang digital. Pelatihan dilangsungkan secara tatap muka di Institut Informatika dan Bisnis Darmajaya dan melibatkan 26 siswa dari empat sekolah di Bandar Lampung. Materi pelatihan meliputi pengantar teori sains data, praktik pengolahan dan visualisasi data serta pengantar bahasa pemrograman Python, hingga pengenalan awal pembelajaran mesin. Sebagai bentuk evaluasi, peserta mengikuti pre-test dan post-test dengan menjawab soal pilihan ganda sebanyak 25 soal. Hasil penilaian menunjukkan bahwa mayoritas siswa mengalami peningkatan kemampuan setelah pelatihan yang diberikan. Persentase peningkatan pengetahuan diperoleh melalui analisis hasil melalui pre-test dan post-test. Peningkatan diperoleh, dimana 18 dari 26 siswa menjawab benar soal atau persentase sebesar 69,23%, meningkat 30,73% dari nilai sebelumnya sebesar 38,5%. Hal ini mencerminkan respon yang sangat positif terhadap isi materi dan fasilitas pendukung yang tersedia. Secara keseluruhan, kegiatan ini memberikan pengalaman belajar yang membekas dan bermanfaat, serta dapat dijadikan model untuk pelatihan serupa di masa mendatang.Abstract: The introduction of data science at the high school level has an important role in equipping students to face the growing digital era. This service activity is designed to foster students' understanding of the basic concepts of data science while encouraging their readiness to pursue careers in the digital field. The training was held face-to-face at Darmajaya Informatics and Business Institute and involved 26 students from four schools in Bandar Lampung. The training materials included an introduction to data science theory, data processing and visualization practices and an introduction to the Python programming language, to an early introduction to machine learning. As a form of evaluation, participants took a pre-test and post-test by answering 25 multiple choice questions. The assessment results showed that the majority of students experienced an increase in ability after the training provided. The percentage of knowledge improvement was obtained through analysis of results through pre-test and post-test. An increase was obtained, where 18 out of 26 students answered the questions correctly or a percentage of 69.23%, an increase of 30.73% from the previous value of 38.5%. This reflects a very positive response to the material content and supporting facilities available. Overall, this activity provided a memorable and useful learning experience, and can be used as a model for similar training in the future.
Application of Ensemble Machine Learning for Infectious Diseases with Vaccine Intervention: A Global COVID-19 Case Study Safitri, Egi; Fikri, Ruki Rizalnul; Nurlistiani, Rini
JURNAL INFOTEL Vol 16 No 4 (2024): November 2024
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v16i4.1263

Abstract

The COVID-19 pandemic has posed significant challenges worldwide, especially in controlling the spread of the disease through vaccination and active case monitoring. This study aims to evaluate the effectiveness of various ensemble machine-learning models in predicting the number of daily vaccinations and the number of active cases of COVID-19 based on global data. The models used include Random Forest, Bagging, Gradient Boosting Machine (GBM), AdaBoost, and XGBoost. The evaluation results show that Random Forest provides the best performance in predicting both the number of daily vaccinations and active COVID-19 cases, with a MSE value of 4.7e+09, MAE of 16,971.1, and RMSE of 68,557.2 for daily vaccinations, as well as an R² Score of 0.989, indicating a high ability to explain data variability. The Bagging model also showed excellent results with MSE of 4.78e+09 and MAE of 17,039.8. In contrast, the AdaBoost model performed the worst in predicting both variables, with an MSE of 5.54e+10 and an MAE of 106,228.6. These findings suggest that Random Forest and Bagging are superior models for predicting the number of daily vaccinations and active COVID-19 cases. This study provides important insights into using machine learning to predict vaccination effectiveness and active case dynamics, aiding decision-making in global pandemic control efforts.
Co-Authors - Nurjoko Amaliah, Khusnatul Asmaul Dwi Akbar Astria Hijriani, Astria Bustamam, Alhadi Dani Rofianto Eko Win Kenali Fikri, Ruki Rizalnul Fitra, Jaka Harlianto, Didi Hendra Kurniawan Hendra, Hendra Kurniawan Julius, Felix K Ikshan, Fathurrahman K, Hendra Muktiawan, Danang Ade Neni Purwati Nicholas Svensons Nurlistiani, Rini Pramujati, Windya Harieska Pratama, Raynaldo Syah Rachardi, Andris Rizal, Ruki Rusdah, Deandra Aulia Saputra, M Hardi Septiawan, Yuda Sri Karnila SUDARSONO, ELY Syakur Syakur Syidada, Amran Rahman Triyasri, Novita Y. Suhendro Yandi Jaya Antonio Yuni Arkhiansyah