Article Per Year (5 Year)
p-Index From 2021 - 2026
1.152
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) Jurnal Ilmiah Informatika Komputer Jurnal Ilmiah Teknologi dan Rekayasa CESS (Journal of Computer Engineering, System and Science) Jurnal Ilmiah KOMPUTASI KLIK: Kajian Ilmiah Informatika dan Komputer
Iffatul Mardhiyah
Gunadarma University
Automotive Engineering Computer Science & IT Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Materials Science & Nanotechnology

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

Found 8 Documents
Search

 1 
VEHICLE DETECTION USING PRINCIPAL COMPONENT ANALYSIS Rifki Kosasih; Achmad Fahrurozi; Iffatul Mardhiyah
Jurnal Ilmiah KOMPUTASI Vol 19, No 2 (2020): Juni
Publisher : STMIK JAKARTA STI&K

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

Abstract

The detection of a vehicle in video is a activity that is important to help the security forces keep an eye on the traffic flow. However, it is hard to security forces to keep watching the video (CCTV) of traffic flow in all day long. Artificial intelligence can be use to help the security to monitoring and analyze the traffic of vehicles, such as to know the level of vehicle traffic density at a certain time period or find out detailed information about the vehicle that want to observe. In this study, Principle Component Analysis (PCA) method used to doing background substraction process to detect vehicles in a real time. To improve the results of PCA method, morphological operation is implemented. The experiment result shown that PCA method is well used to detect the vehicle in a real time with accuracy at 95%.
Vehicle Detection Using Principal Component Analysis: Array Rifki Kosasih; Achmad Fahrurozi; Iffatul Mardhiyah
Jurnal Ilmiah Komputasi Vol. 19 No. 2 (2020): Jurnal Ilmiah Komputasi Volume: 19 No. 2, Juni 2020
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32409/jikstik.19.2.83

Abstract

The detection of a vehicle in video is an activity that is important to help the security forces keep an eye on the traffic flow. However, it is hard to security forces to keep watching the video (CCTV) of traffic flow in all day long. Artificial intelligence can be use to help the security to monitoring and analyze the traffic of vehicles, such as to know the level of vehicle traffic density at a certain time period or find out detailed information about the vehicle that want to observed. In this study, Principle Component Analysis (PCA) method used to doing background substraction process to detect vehicles in a real time. To improve the results of PCA method, morphological operation is implemented. The experiment result shown that PCA method is well used to detect the vehicle in a real time with accuracy at 95%. Abstrak Pendeteksian kendaraan menggunakan video merupakan kegiatan yang penting untuk membantu pihak keamanan untuk mengawasi arus lalu lintas. Akan tetapi, sangat sulit bagi pihak keamanan untuk terus mengawasi video arus lalu lintas sepanjang hari melalui CCTV. Oleh karena itu kecerdasan buatan dapat digunakan untuk membantu pihak keamanan dalam memantau dan menganalisis lalu lintas kendaraan, seperti untuk mengetahui tingkat kepadatan lalu lintas kendaraan pada periode waktu tertentu atau mengetahui informasi terperinci tentang kendaraan yang ingin diamati. Dalam penelitian ini, metode Principle Component Analysis (PCA) digunakan untuk melakukan proses substraksi latar belakang untuk mendeteksi kendaraan secara real time. Untuk meningkatkan hasil metode PCA, operasi morfologi diimplementasikan. Hasil percobaan menunjukkan bahwa metode PCA baik digunakan untuk mendeteksi kendaraan secara real time dengan tingkat akurasi 95%.
Implementation of K Nearest Neighbor in Detecting Heart Disease with Various Training Data Rifki Kosasih; Iffatul Mardhiyah
CESS (Journal of Computer Engineering, System and Science) Vol 8, No 2 (2023): July 2023
Publisher : Universitas Negeri Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24114/cess.v8i2.44303

Abstract

Salah satu organ penting dalam tubuh manusia adalah jantung, Jika jantung mengalami gangguan maka dapat menyebabkan penyakit jantung. Untuk mendeteksi adanya penyakit jantung biasanya dilakukan dengan berkonsultasi dengan tenaga medis. Akan tetapi dengan semakin banyaknya pasien di rumah sakit akan dapat memperlambat pendeteksian penyakit jantung. Oleh karena itu dibutuhkan suatu sistem yang dapat membantu tenaga medis dalam mempercepat pendeteksian penyakit jantung. Dalam penelitian ini diusulkan untuk menggunakan pendekatan machine learning seperti metode K Nearest Neighbor (KNN) dalam mendeteksi penyakit jantung. Data yang digunakan sebanyak 1025 pasien dengan 13 fitur seperti umur, jenis kelamin, rasa sakit di dada, tekanan darah saat sedang istirahat, kadar kolesterol, gula darah, hasil elektrografik saat sedang istirahat, detak jantung maksimal, jika mengalami nyeri dada saat latihan, depresi yang diinduksi oleh latihan relatif, kemiringan puncak ST segmen, jumlah pembuluh darah yang berwarna setelah diwarnai flourosopy dan tipe kerusakan pembuluh darah. Pada penelitian ini dilakukan tiga skema pembagian data latih dan data uji dengan rasio 60:40, 70:30 dan 80:20. Berdasarkan hasil pengujian diperoleh bahwa tingkat akurasi, presisi dan recall tertinggi terjadi Ketika rasio data latih dan data uji 70:30 yaitu sebesar 97,0779% untuk akurasi, 97,9166% untuk presisi dan 95,9183% untuk recall.One of the important organs in humans is the heart. If the heart is disturbed, it can cause heart disease. To detect the presence of heart disease is usually done in consultation with doctor. However, with the increasing number of patients in the hospital, it will be able to slow down the detection of heart disease. Therefore, we need a system that can assist doctors in accelerating the detection of heart disease. In this study, we propose to use a machine learning approach i.e., K Nearest Neighbor (KNN) method in detecting heart disease. The data used were 1025 patients with 13 features i.e., age, gender, chest pain, blood pressure, cholesterol, blood sugar, electrographic results, maximum heart rate, if you experience chest pain during exercise, depression which exercise-induced relative, peak slope, number of blood vessels after fluoroscopy and type of vessel damage. In this study, we have three schemes in divide training data and test data with ratios of 60:40, 70:30 and 80:20. Based on the test results, it was found that the highest levels of accuracy, precision and recall occurred when the ratio of training data and test data was 70:30, which was 97.0779% for accuracy, 97,9166 for precision and 95,9183% for recall.
Implementasi Chatbot FAQ pada Aplikasi Monev Kinerja Direktorat Jenderal Anggaran Menggunakan Framework Rasa Open Source Arif Rachman; Iffatul Mardhiyah; Miftahul Jannah
KLIK: Kajian Ilmiah Informatika dan Komputer Vol. 4 No. 1 (2023): Agustus 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/klik.v4i1.1020

Abstract

Direktorat Jenderal Anggaran (DJA) is an organizational unit within the Ministry of Finance with the task of providing an information system related to budgeting performance. The dynamics of policy changes that have occurred recently have resulted in changes to the information system that has been developed by DJA. DJA has socialized the existing business processes and systems, but many users still ask questions through the DJA customer service channel which can only respond during business hours. This research will propose a solution for optimizing these services by creating a chatbot based on Natural Language Processing using the Rasa Open Source framework, which will be installed on one of the DJA's core systems, namely the Performance Monitoring and Evaluation Application. The chatbot will spontaneously answer user questions related to the application. The data used in this study are Frequently Asked Questions (FAQ) data, knowledge base Kemenkeupedia, Focus Group Discussions (FGD) and Performance Monev Application data taken via the API (Application Programming Interface). The results of this study are Chatbot FAQs embedded in the performance monitoring and evaluation application. The intent prediction test produces an accuracy value of 0.986, a weighted precision value of 0.973, a recall of 0.986, and an f1-score of 0.980 then the response prediction produces an accuracy value of 0.980, a weighted precision value of 0.986, a recall of 0.980, and an f1-score of 0.980. This shows that the chatbot is able to identify intent very well and respond appropriately to the user.
PERBANDINGAN KLASIFIKASI KERUSAKAN JALAN MODEL CNN VGG19 DAN RESNET50 Revanza Raditya Putra Yanni; Iffatul Mardhiyah; Dyah Cita Irawati; Rifki Kosasih; Dyan Prawita Sari
Jurnal Ilmiah Informatika Komputer Vol 30, No 1 (2025)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/ik.2025.v30i1.14230

Abstract

Masalah kerusakan jalan pada jalan utama adalah salah satu gangguan saat berkendara dan dapat menyebabkan kecelakaan. Identifikasi kerusakan jalan masih dilakukan secara manual oleh pemerintah daerah dengan penyisiran jalan. Penggunaan teknologi kecerdasan buatan untuk identifikasi kerusakan jalan, sangat diperlukan. Algoritma CNN dapat melakukan identifikasi dan klasifikasi kerusakan jalan. Beberapa arsitektur pada CNN yang sering digunakan untuk klasifikasi diantaranya VGG19 dan ResNet50. Penelitian ini bertujuan untuk mengetahui perbandingan klasifikasi antara VGG19 dan ResNet50 pada kerusakan jalan. Perbandingan dilakukan dengan membedakan jumlah epochnya untuk setiap arsitektur. Jumlah dataset yang digunakan sebanyak 1656 citra. Model yang dibentuk bertujuan mengklasifikasikan kerusakan jalan menjadi tiga klasifikasi yaitu, kerusakan_besar, kerusakan_sedang, dan kerusakan_kecil. Jumlah epoch yang digunakan pada model adalah sebesar 10, 50, dan 100. Hasil dari penelitian arsitektur VGG19 dengan epoch 10 mendapatkan akurasi sebesar 79%, epoch 50 sebesar 73%, dan epoch 100 sebesar 76%. Arsitektur ResNet50 memperoleh hasil akurasi sebesar 75% dengan epoch 10, untuk epoch 50 sebesar 78%, dan epoch 100 sebesar 79%. Kesimpulan penelitian perbandingan klasifikasi kerusakan jalan, VGG19 dapat mengklasifikasikan lebih baik jika proses pelatihan yang lebih sederhana, sedangkan ResNet50 dapat melakukan klasifikasi lebih baik jika proses pelatihan yang lebih kompleks.
Image feature extraction for road surface damage classification Octaviani Hutapea; Sarifuddin Madenda; Hustinawaty Hustinawaty; Iffatul Mardhiyah
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 15, No 2: April 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v15.i2.pp1578-1592

Abstract

Road surface deterioration poses a critical risk to driving safety and comfort, necessitating timely and accurate detection to support effective maintenance. Manual inspection methods are often inefficient, underscoring the need for automated approaches based on computer vision. This study investigates the integration of feature extraction techniques histogram of oriented gradients (HOG) and local binary pattern (LBP) with convolutional neural network (CNN) architectures ResNet50 and InceptionV3 for the classification of road damage. A dataset of 1,580 images was categorized into five damage types: alligator crack, longitudinal crack, other crack, patching, and potholes. Experimental results indicate that HOG–ResNet50 achieved 79% accuracy, while LBP–InceptionV3 yielded the best performance at 97%. The contributions of this study are threefold: i) an automated framework is proposed that combines texture-based features with deep learning for road damage detection, ii) the LBP–InceptionV3 combination is shown to provide superior accuracy compared to conventional pairings, and iii) the approach offers a scalable and reliable alternative to manual inspection methods, supporting more efficient road maintenance planning.
Optimalisasi Deteksi Tingkat Kematangan Tanda Buah Segar Kelapa Sawit Menggunakan YOLOV8 Dengan Platform Web Iffatul Mardhiyah; Dyan Prawita Sari; Zahwa Genoveva; Rifki Kosasih; Dyah Cita Irawati
Jurnal Ilmiah Teknologi dan Rekayasa Vol. 30 No. 3 (2025)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/tr.2025.v30i3.67

Abstract

Oil palm represents one of Indonesia’s principal commodities. Traditionally, farmers manually monitor the ripeness level of palm oil, but this method is neither effective nor efficient for large-scale harvests. Therefore, a system that can automatically detect the ripeness level of fresh fruit bunches (FFB) is needed. In this study, the YOLOv8 algorithm was used which was integrated into a web-based application. The system is designed to improve accuracy and efficiency in the grading process of oil palm fruits, which directly impacts the quality of processed products and palm oil production. The dataset used consists of 6.592 images obtained through the Roboflow platform, covering various ripeness categories. The system development follows the CRISP-DM approach, consisting of business understanding, data understanding, data preparation, modeling, evaluation and deployment. The model training process approximately 3,1 hours, with evaluation results showing a precision of 94,5%, recall of 94,7%, and a mean Average Precision (mAP) of 98%. The model’s performance is further supported by an F1-confidence curve of 95% and a precision-recall curve of 98%, indicating stable and accurate classification capabilities. The model is deployed through a Streamlit-based web interface, allowing users to perform real-time detection from images or videos without requiring additional installations.
Penerapan Algoritma Support Vector Machine Dalam Pengenalan Wajah Berdasarkan Fitur Isomap Rifki Kosasih; Iffatul Mardhiyah; Dina Indarti
CESS (Journal of Computer Engineering, System and Science) Vol. 11 No. 1 (2026): Januari 2026
Publisher : Universitas Negeri Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24114/cess.v11i1.68568

Abstract

Pengenalan wajah merupakan salah satu bidang yang digunakan untuk mengenali seseorang melalui citra ataupun video. Pengenalan wajah ini dapat digunakan untuk absensi kehadiran yang lebih efektif dan efisien dibandingkan dengan absensi menggunakan cara manual. Pada penelitian ini data yang digunakan merupakan data citra wajah yang terdiri dari 6 orang dengan tiap orang memiliki 4 variasi ekspresi wajah. Tahapan selanjutnya adalah melakukan ekstraksi fitur wajah dengan menggunakan metode isomap. Metode isomap adalah salah satu metode yang dapat mereduksi dimensi dari dimensi yang tinggi ke dimensi yang lebih rendah. Dalam studi ini dimensi yang dihasilkan sebanyak 4 sehingga terdapat 4 fitur yang akan digunakan dalam pengklasifikasian wajah. Fitur-fitur tersebut dibagi menjadi fitur latih dan fitur uji. Untuk pengklasifikasian wajah, digunakan metode support vector machine (SVM). Metode support vector machine merupakan metode supervised learning yang dapat digunakan dalam pengenalan pola dan klasifikasi. Metode support vector machine memperhatikan perhitungan jarak kedekatan fitur satu dengan fitur lainnya dalam pengenalan pola dan klasifikasi. Berdasarkan hasil klasifikasi diperoleh tingkat akurasi sebesar 87,5%, rata-rata terbobot presisi sebesar 79,1675% dan rata-rata terbobot recall sebesar 87,5%.   
Co-Authors Achmad Fahrurozi Arif Rachman Dina Indarti Dyah Cita Irawati Dyah Cita Irawati Dyan Prawita Sari Dyan Prawita Sari Hustinawaty Hustinawaty, Hustinawaty Miftahul Jannah Octaviani Hutapea Revanza Raditya Putra Yanni Rifki Kosasih Rifki Kosasih Sarifuddin Madenda Zahwa Genoveva