Article Per Year (5 Year)
p-Index From 2021 - 2026
1.768
P-Index
This Author published in this journals
All Journal Jurnal Sistem Informasi dan Sistem Komputer Syntax: Journal of Software Engineering, Computer Science and Information Technology Journal of Artificial Intelligence and Engineering Applications (JAIEA) JRIIN :Jurnal Riset Informatika dan Inovasi Jurnal Sains Student Research Cosmic Jurnal Teknik Journal of Educational Science and E-Learning Jurnal Ilmiah Ilmu Komputer dan Teknologi Informasi (JIKOMTI) JUTEKOM - Jurnal Teknologi dan Ilmu Komputer Jurnal Ilmu Teknologi Informasi Indonesia (JITIFNA)
Lailan Sofinah Harahap
Universitas Islam Negeri Sumatera Utara
Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Other

Published : 12 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 12 Documents
Search

 1   2 
Facial Emotion Recognition Based on Convolutional Neural Network Using FER2013 Dataset Muhammad Al Faris Syabil; Lailan Sofinah Harahap; Muhammad Rafiq Nasution
Jurnal Teknologi informasi dan Ilmu Komputer Vol. 2 No. 1 (2026): Januari 2026
Publisher : Nolsatu Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65258/jutekom.v2.i1.44

Abstract

Facial emotion recognition is an important research area in computer vision and artificial intelligence, with applications in human–computer interaction, affective computing, and intelligent systems. This study aims to evaluate the performance of a Convolutional Neural Network (CNN) for facial emotion recognition using the FER2013 dataset. The FER2013 dataset consists of grayscale facial images with a resolution of 48×48 pixels and includes seven emotion classes: angry, disgust, fear, happy, neutral, sad, and surprise. Due to its low image resolution and imbalanced class distribution, FER2013 presents significant challenges for emotion classification tasks. An experimental research approach was employed by implementing a baseline CNN architecture composed of convolutional, pooling, and fully connected layers. Image normalization and batch-based data generation were applied during preprocessing. The model was trained using the Adam optimizer with categorical cross-entropy loss, and an early stopping mechanism was utilized to prevent overfitting. Model performance was evaluated using accuracy, precision, recall, F1-score, and confusion matrix analysis. The experimental results show that the proposed CNN model achieved an overall test accuracy of 55.50%. Emotions with distinctive facial features, such as happy and surprise, obtained higher F1-scores, while minority and visually subtle classes, particularly disgust and fear, exhibited lower performance. These findings indicate that a simple CNN architecture can provide reasonable performance on challenging facial emotion datasets while highlighting the impact of class imbalance and limited image resolution. The proposed model can serve as a baseline for further improvements in facial emotion recognition systems.
Identifikasi Pengenalan Tanda Tangan Menggunakan Algoritma Backpropagation dan GLCM (Grey Level Co-Occurrence Matrix) Dea Alya; Lailan Sofinah Harahap; Dodyk Fahlome
Jurnal Sistem Informasi dan Sistem Komputer Vol 11 No 1 (2026): Vol 11 No 1 - 2026
Publisher : STIMIK Bina Bangsa Kendari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51717/simkom.v11i1.1215

Abstract

Tanda tangan adalah salah satu biometrik berbasis perilaku yang sering digunakan dalam proses autentikasi. Namun, berbagai jenis tanda tangan menyebabkan proses identifikasi menjadi kompleks, sehingga memerlukan penggunaan teknologi komputer yang baik. Studi ini dibuat sebagai upaya untuk menganalisis tanda tangan yang dimiliki oleh pemilik tanda tangan berdasarkan tekstur citra menggunakan metode ekstraksi Grey Level Co-occurrence Matrix (GLCM) dan klasifikasi Backpropagation. Empat fitur GLCM (contrast, correlation, energy, homogeneity) dihitung dalam empat arah (0°, 45°, 90°, 135°). Data terdiri dari sekitar 80 data dari 4 kelas, dibagi menjadi 20 data uji dan 60 data latih. Pengujian dilakukan lima kali untuk setiap konfigurasi neuron guna memperoleh hasil rata-rata. Hasil penelitian ini menunjukkan bahwa konfigurasi lapisan tersembunyi dengan 50 neuron memberikan kinerja terbaik dengan akurasi rata-rata sekitar 80%. Meningkatkan jumlah neuron cenderung mengurangi akurasi karena kemungkinan overfitting. Meskipun demikian, kombinasi GLCM dan Backpropagation dapat mengidentifikasi tanda tangan dengan cukup baik.
Classification of Herbal Plants Based on Leaf Images Using Gray Level Co-Occurrence Matrix and K-Nearest Neighbor Fahmi Nur Alimsyah Purba; Fathi Athallah Z; Alfin Alfarizi; Lailan Sofinah Harahap
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 5 No. 3 (2026): June 2026
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v5i3.2291

Abstract

Herbal plants have long been used as traditional medicine. However, many people struggle to tell different herbal leaves apart because they look quite similar. This study tries to build a system that can recognize two types of herbal leaves, Moringa and Katuk, simply from their photos. We used GLCM to extract texture features from the leaves, then classified them using KNN. The dataset came from Kaggle, with 480 leaf images in total. Before processing, we cropped the images, resized them to 256x256 pixels, and converted them to grayscale. GLCM features were taken from four angles (0°, 45°, 90°, 135°) and then averaged. This gave us four texture values: contrast, correlation, energy, and homogeneity. We tested KNN with k values from 1 to 15 and five different distance metrics. The best result we got was 94% accuracy, using Manhattan distance with k=1. This system could help everyday people identify medicinal plants more easily without needing lab tests.
Comparative Analysis of Sobel, Prewitt, and Canny Methods in Detecting Object Edges in Betta Fish Images Alfin Alfarizi; Cici El Dirrah Syafitri Simanungkalit; Fahmi Nur Alimsyah Purba; Lailan Sofinah Harahap
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 5 No. 3 (2026): June 2026
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v5i3.2293

Abstract

Edge detection is a crucial stage in digital image processing for recognizing the shape and structure of an object. The application of edge detection to betta fish images presents a unique challenge due to their layered, intricately textured, and often semi-transparent fin morphology. This study aims to analyze and compare the performance of three edge detection algorithms, namely Sobel, Prewitt, and Canny, in extracting shape features from betta fish images. The research methodology involved converting the dataset images into a grayscale format and subsequently implementing the three algorithms using the OpenCV library in the Python programming language. The evaluation was conducted visually by observing the sharpness of the edge lines, object continuity, and the occurrence of noise. The results indicate that the Canny algorithm provides the most optimal performance, as it is capable of detecting the thin edge lines of the fish fins with greater detail and continuity due to its hysteresis thresholding process. Meanwhile, the Sobel and Prewitt methods produced thicker edge lines but were less sensitive to the details of the transparent fins. This study is expected to serve as a reference in selecting the appropriate segmentation method for biological objects with complex morphologies.
Prediksi Curah Hujan Bulanan Di Medan Menggunakan Metode Long Short-Term Memory (LSTM) Dedek; Lailan Sofinah Harahap; Muhammad Rayhans Adrian
Jurnal Ilmu Teknologi Informasi Indonesia Vol. 2 No. 1 (2026): JITIFNA - Januari
Publisher : CV. SINAR HOWUHOWU

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70134/jitifna.v2i1.969

Abstract

This study aims to predict monthly rainfall in Medan City using the Long Short-Term Memory (LSTM) method. The data utilized in this research comprises monthly rainfall figures and the number of rainy days for the 2015–2023 period, obtained from the Meteorology, Climatology, and Geophysics Agency (BMKG) Region I Medan via official publications of the Central Statistics Agency (BPS) of North Sumatra Province. The pre-processing stage involves data cleaning, normalization, and the construction of a time series dataset using a sliding window structure. The LSTM model was developed with two hidden layers and optimized using the Adam algorithm. Evaluation results indicate that the LSTM model effectively captures seasonal patterns and rainfall trends, as evidenced by a low Root Mean Square Error (RMSE) value. This study is expected to serve as a reference for hydrometeorological disaster mitigation in the Medan region.
PENINGKATAN AKURASI PREDIKSI PENJURUSAN SISWA SMK DENGAN OPTIMASI JARINGAN SYARAF TIRUAN BACKPROPAGATION Muhammad Nabhan Akbar Marpaung; Lailan Sofinah Harahap; Fajar Al Fahri
JOURNAL SAINS STUDENT RESEARCH Vol. 4 No. 1 (2026): Februari: Jurnal Sains Student Research
Publisher : CV. KAMPUS AKADEMIK PUBLISING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61722/jssr.v4i1.7975

Abstract

The development of artificial intelligence (AI) technology has had an increasingly significant impact on various industries, including education, particularly in terms of data processing and decision making. However, in reality, students' choice of major is often determined without proper and measurable analysis, which means that students' potential is not always in line with their chosen major. The mismatch between academic abilities and chosen fields of study is one of the problems arising from this situation. To address this issue, this study predicts majors based on subject grade data using Artificial Neural Network techniques and the Backpropagation algorithm. Backpropagation was chosen because it can produce more accurate predictions by gradually learning data patterns through a directed learning process. This approach significantly improves prediction accuracy based on model training and testing results, making it a useful tool for more objective, flexible, efficient, adaptive, and data-driven decision-making in optimally selecting majors for students to support their overall and sustainable academic success.
Analisis Performa Transfer Learning Menggunakan MobileNetV2 untuk Klasifikasi Citra X-Ray Paru-Paru M Choirul Amri; Lailan Sofinah Harahap; Abdul Rasyid
JOURNAL SAINS STUDENT RESEARCH Vol. 4 No. 1 (2026): Februari: Jurnal Sains Student Research
Publisher : CV. KAMPUS AKADEMIK PUBLISING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61722/jssr.v4i1.8306

Abstract

Pneumonia is a lung disease that requires early detection to prevent serious complications. Chest X-ray images are widely used for diagnosis; however, their interpretation still depends on medical experts. This study aims to analyze the performance of transfer learning using MobileNetV2 for classifying chest X-ray images. The Chest X-Ray Pneumonia dataset from Kaggle was used and divided into 75% training data, 15% validation data, and 10% testing data. Image preprocessing included resizing, pixel normalization, and data augmentation. The model was trained for 20 epochs using the Adam optimizer. Experimental results achieved an accuracy of 95.40%, precision of 95.62%, recall of 95.40%, and an F1-score of 95.46%. These results indicate that MobileNetV2 provides effective and stable performance for chest X-ray image.
DETEKSI POLA WAJAH OTOMATIS DALAM PENGOLAHAN CITRA DIGITAL MENGGUNAKAN METODE HAARCASCADE CLASSIFIER Laila Ali Putri; Lailan Sofinah Harahap; Maria Ulfa
Syntax : Journal of Software Engineering, Computer Science and Information Technology Vol 6, No 1 (2025): Juni 2025
Publisher : Universitas Dharmawangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46576/syntax.v6i1.6742

Abstract

Deteksi wajah merupakan salah satu topik yang banyak diteliti dalam bidang visi komputer dan pengolahan citra digital. Metode Haar Cascade adalah salah satu metode yang sering digunakan untuk mendeteksi wajah pada suatu citra atau video. Metode ini menggunakan fitur Haar untuk mengidentifikasi wajah dengan cara membandingkannya dengan wajah yang ada pada database. Penelitian ini bertujuan untuk mengimplementasikan metode Haar Cascade untuk mendeteksi wajah menggunakan library OpenCV. Tahapan yang dilakukan meliputi akuisisi citra, pemrosesan citra, deteksi wajah menggunakan Haar Cascade, dan evaluasi hasil deteksi. Hasil penelitian menunjukkan bahwa metode Haar Cascade dapat mendeteksi wajah dengan cukup baik dalam berbagai kondisi pencahayaan dan sudut pandang. Kata Kunci : Deteksi Wajah; Haar Cascade; OpenCV ABSTRACTAbstract Face detection is one of the most researched topics in the field of computer vision and digital image processing. The Haar Cascade method is one method that is often used to detect faces in an image or video. This method uses Haar features to identify faces by comparing them with existing faces in the database. This research aims to implement the Haar Cascade method to detect faces using the OpenCV library. The stages include image acquisition, image processing, face detection using Haar Cascade, and evaluation of detection results. The results show that the Haar Cascade method can detect faces quite well in various lighting conditions and viewing angles. Keyword : Face Detection; Haar Cascade; OpenCV
Analisis Algoritma Convolutional Neural Network (CNN) untuk Pengenalan Pola Tangan Berdasarkan Citra Garis Telapak Tangan Fazila Nazifa Edilia; Lailan Sofinah Harahap; Andita Utami; Zianah Nafisah Simbolon
Cosmic Jurnal Teknik Vol 3 No 1 (2026): Februari
Publisher : Ali Institute or Research and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/cosmic.v3i1.1495

Abstract

Individual identification is an important aspect of security and biometric authentication systems. One biometric characteristic with high potential is palm print patterns, as each individual has a unique pattern that is difficult to forge. Therefore, it is necessary to develop an individual identification system based on palm print images using a pattern approach with the Convolutional Neural Network (CNN) method. Test results show that this method is capable of identifying individuals with a fairly high level of accuracy, depending on the image quality and training parameters as well as the network architecture used.
Analisis Performa CNN Berbasis MobileNetV2 pada Dataset Citra Dokumen Laporan Praktikum Hafiz Aryanda; Lailan Sofinah Harahap; Dimas Aqila Aptanta
Journal of Educational Science and E-Learning Vol. 2 No. 2 (2025): Desember
Publisher : CV Rena Cipta Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62354/jese.v2i2.44

Abstract

Penelitian ini bertujuan untuk menganalisis performa CNN berbasis MobileNetV2 dalam klasifikasi citra dokumen laporan praktikum. Pendekatan yang digunakan adalah transfer learning dengan bobot pra-latih dari ImageNet, serta fine-tuning pada lapisan atas untuk menyesuaikan model terhadap karakteristik dokumen akademik. Dataset terdiri dari ribuan citra dokumen yang telah melalui tahap pra-pemrosesan berupa resizing, normalisasi, dan augmentasi. Hasil eksperimen menunjukkan bahwa pada baseline, akurasi validasi mencapai 64,88% namun akurasi evaluasi manual hanya 10,54%, menandakan adanya masalah domain gap dan kesulitan separasi antar kelas. Fine-tuning meningkatkan akurasi validasi training menjadi 70,43%, tetapi akurasi evaluasi biner justru menurun menjadi 47,50%, sehingga performa model tetap rendah. Temuan ini menegaskan bahwa CNN kurang tepat untuk tugas validasi kepatuhan dokumen yang membutuhkan analisis semantik dan aturan tata letak yang kompleks serta dinamis. Sebagai solusi, integrasi OCR dengan rule-based validation direkomendasikan karena mampu memberikan akurasi lebih tinggi, interpretasi jelas, serta umpan balik detail sesuai pedoman penulisan akademik modern.
Co-Authors Abdul Rasyid Alfin Alfarizi Andita Utami Cici El Dirrah Syafitri Simanungkalit Dea Alya Dedek Dimas Aqila Aptanta Dodyk Fahlome Fahmi Nur Alimsyah Purba Fajar Al Fahri Fathi Athallah Z Fauhan Alfarizi Saragih fazila nazifa edilia Hafiz Aryanda Khaila Mukti Harahap Mukti Laila Ali Putri M Choirul Amri M. Rifqi Arrafi Maria Ulfa Muhammad Al Faris Syabil Muhammad Nabhan Akbar Marpaung Muhammad Rafiq Nasution Muhammad Rayhans Adrian Zianah Nafisah Simbolon