Claim Missing Document
Check
Articles

Analisis Sentimen Terhadap Kebijakan Pemerintah Tentang Larangan Mudik Hari Raya Idulfitri di Indonesia Tahun 2021 Menggunkan Metode Naïve Bayes Aziz, Abdul; Fauziah, F; Fitri, Iskandar
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 5, No 2 (2021): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v5i2.381

Abstract

Social media as a place to access and disseminate information has grown very rapidly, one of which is Twitter. Twitter, as a place for information flow, is a rich source for seeking public opinion and sentiment analysis. Twitter in this study was used as a source to obtain data about the 2021 homecoming in Indonesia. The purpose of this study is to determine public satisfaction with government policies regarding the ban on going home in Indonesia in 2021. The data to be processed is Indonesian-language tweets, the keywords are #mudik and #diarangmudik, the length of data collection is 1 week, with lots of data generated as many as 1000. Sentiment analysis in this study using the Naïve Bayes Classification method. The steps in this study are first crawling Twitter data which is then stored in csv format, second preprocessing which consists of tokenizer, case folding, cleansing and stop removal, third Naive Bayes classification which will be carried out after going through the Pre-processing stage, where the results of the classification tweets tend to be positive or negative or neutral. The results of this study obtained an accuracy of 56.52% with each positive sentiment value of 62.28%, negative sentiment as much as 46.72% and neutral sentiment as much as 66.50%.
Development of ResNet-18 architecture to lesion identification in breast ultrasound images Andini, Silfia; Sumijan, Sumijan; Fitri, Iskandar
Indonesian Journal of Electrical Engineering and Computer Science Vol 39, No 2: August 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v39.i2.pp1236-1248

Abstract

Breast ultrasound (USG) is widely used for early breast cancer detection, but challenges such as noise, low contrast, and resolution limitations hinder accurate lesion identification. This study proposes a modified residual network-18 (ResNet-18) architecture for breast lesion segmentation, aimed at improving detection accuracy. The methodology involves preprocessing steps including red green blue (RGB) to Grayscale conversion, contrast stretching, and median filtering to enhance image quality. The modified ResNet-18 model introduces additional convolutional layers to refine feature extraction. The proposed model was trained and validated on 30 breast ultrasound images, with evaluation metrics including accuracy, sensitivity, and specificity. Experimental results indicate that the modified architecture outperforms the baseline model, achieving an average accuracy of 0.97093, sensitivity of 0.90056, and specificity of 0.97705. Validation by a radiology specialist confirms the model’s clinical relevance. These findings suggest that the enhanced ResNet-18 model has the potential to assist radiologists in more accurately identifying breast lesions. Future research should focus on expanding the dataset, integrating multi-modal imaging, and optimizing model generalizability for real-time clinical applications. The study contributes to advancing artificial intelligence (AI)-driven breast cancer diagnostics, supporting early detection, and improving patient outcomes.
Development of Apple Fruit Classification System using Convolutional Neural Network (CNN) MobileNet Architecture on Android Platform Masparudin, Masparudin; Fitri, Iskandar; Sumijan, Sumijan
Sistemasi: Jurnal Sistem Informasi Vol 13, No 1 (2024): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v13i1.3533

Abstract

In the current digital era, image classification of fruits, particularly apples, has become crucial for various applications, ranging from agriculture to retail. This research focuses on the utilization of Convolutional Neural Network (CNN) with the MobileNet architecture to classify apple fruit images. Using the Python programming language, three models were successfully trained: Model 1 for apple fruit types, Model 2 for apple fruit diseases, and Model 3 for apple fruit ripeness levels. All three models underwent training and validation, with the final results at epoch 10: Model 1 for apple types achieved an accuracy of 100% and a loss of 0.0046, Model 2 for apple diseases achieved an accuracy of 100% and a loss of 0.0075, while Model 3 for apple ripeness levels achieved an accuracy of 99.76% and a loss of 0.0439. Subsequently, these models were tested on an Android device, and there were two testing scenarios. In the first scenario, each model was tested with 15 images individually. The results showed 100% accuracy for Models 1 and 2, while Model 3 achieved a lower accuracy of 86.67%. In the second scenario, all three models were tested simultaneously using 30 test images, resulting in an accuracy of 55.55%. Several factors, such as limitations in the apple image dataset, particularly in the ripeness dataset, object backgrounds, image capture distances, color and texture similarities, as well as lighting quality, influenced the classification outcomes. To enhance future performance, improved data preprocessing and a combination of detection and classification techniques are needed. This research provides valuable insights for researchers and practitioners looking to implement image classification technology in real-world applications.provides valuable insights for researchers and practitioners looking to implement image classification technology in real-world applications.
Penerapan Face Recognition Pada Aplikasi Akademik Online Utomo, Budi Tri; Fitri, Iskandar; Mardiani, Eri
Informatik : Jurnal Ilmu Komputer Vol 16 No 3 (2020): Desember 2020
Publisher : Fakultas Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52958/iftk.v16i3.2259

Abstract

Di era big data seperti sekarang ini, proses identifikasi biometrik berkembang dengan sangat cepat dan semakin banyak diimplementasikan pada banyak aplikasi. Teknologi pengenalan wajah memanfaatkan kecerdasan artificial intelligence (AI) untuk mengenali wajah. Didalam penelitian ini diajukan sebuah perancangan sistem login akademik online di Universitas Nasional dengan memanfaatkan face recognition secara real time yang berbasis OpenCV dengan algoritma Local Binary Pattern Histogram, dan metode Haar Cassade Clasifier. Sistem akan mendeteksi, mengenali dan menbandingkan wajah yang tertangkap kamera dengan database wajah yang tersimpan. Citra gambar wajah yang digunakan berukuran 480 x 680 pixel berekstensi .jpg dalam bentuk citra RGB yang akan dirubah menjadi citra Grayscale, untuk mempermudah perhitungan nilai histrogram dari setiap wajah yang akan dikenali. Dengan pemodelan sistem seperti ini diharapkan dapat mempermudah mahasiswa untuk login ke akademik online.
OPTIMALIZATION OF MICROSTRIP SLOT ARRAY ANTENNAS FOR MULTI-WIDEBAND Fitri, Iskandar
Indonesian Journal of Aerospace Vol. 5 No. 1 (2007): Vol 5, No.1 Juni (2007)
Publisher : BRIN Publishing

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

Abstract

Microstrip slot antenna fed by matching network of microstrip line to increase very wide-bandwidth and multiband is proposed. The microstrip line composed of multi tuning stubs is used to control slots antenna real impedance to match with impwdance cahracteristic of feeding line so that it could increase the bandwidth. The design are achieves good input impedance in the ranges frequency of 1.3 - 5.1 GHz for single slot and 1.1 - 6.4 GHz for two slots. The bandwidths of antennas become very wide if the slots made in array configuration. The measured return loss S11 agrees well with the simulation results for single slot as axample. Keywords: microstrip slot antenna, array configuration, network impedance, multi tuning stub.
Development of a machine learning model with optuna and ensemble learning to improve performance on multiple datasets Efendi, Akmar; Fitri, Iskandar; Nurcahyo, Gunadi Widi
Indonesian Journal of Electrical Engineering and Computer Science Vol 41, No 1: January 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v41.i1.pp375-386

Abstract

Machine learning, a subset of artificial intelligence (AI) is vital for its ability to learn from data and improve system performance. In Indonesia, advancements in ML have significant potential to boost competitiveness and foster sustainable development. However, issues like overfitting and suboptimal parameter settings can hinder model effectiveness. This study aims to improve the classification performance of ML models on various datasets. Advanced techniques like hyperparameter tuning with Optuna and ensemble learning with extreme gradient boosting (XGBoost) are integrated to enhance model performance. The study evaluates the performance of K nearest neighbors (KNN), support vector machine (SVM), and Gaussian naïve Bayes (GNB) algorithms across three datasets: academic records from the Islamic University of Riau (UIR), diabetes data from Kaggle, and Twitter data related to the 2024 elections. The findings reveal that the GNB algorithm outperforms KNN and SVM across all datasets, achieving the highest accuracy, precision, recall, and F1-score. Hyperparameter tuning with Optuna significantly improves model performance, demonstrating the value of systematic optimization. This study highlights the importance of advanced optimization techniques in developing high-performing ML models. The results suggest that robust algorithms like GNB, combined with hyperparameter tuning and ensemble learning, can significantly enhance classification performance.
Implementation of Augmented Reality for Introduction To Android Based Mammalian Animals Using The Marker Based Tracking Method Kristian, Mikhael; Fitri, Iskandar; Gunaryati, Aris
JISA(Jurnal Informatika dan Sains) Vol 3, No 1 (2020): JISA(Jurnal Informatika dan Sains)
Publisher : Universitas Trilogi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31326/jisa.v3i1.623

Abstract

Augmented Reality is a technology on 2-dimensional and 3-dimensional virtual objects that are combined into the real environment that is around us. With the ability of Augmented Reality that is able to change the atmosphere of children’s learning that can be used as a medium of learning in the introduction of mammals for kindergarten children. This AR can provide interesting facilities such as displaying 3-dimensional objects of these mammals along with animal sounds and animations using Smartphones, so that children can interact and be more creative in recognizing these mammals, because children experience their golden age at the age of 4 to 7 years which is a time when children begin to receive stimuli, so that children will be faster to receive and catch on learning from the introduction of these mammals by using Augmented Reality Technology. The results of testing on the Vuforia plugin and making the AR application on Unity can provide a good information result, where the use of AR can bring up mammalian objects by pointing the Smartphone at the marker, so that all mammals can be recognized properly. This shows that children’s interest around 85% in terms of UI/UX appearance, and 70% of children have no problems in running the Mammal Animal AR application
Perancangan Design Website E-Commerce Dan Pemesanan Pada Rumah Makan Terang Masakan Padang Dengan Mengimplementasikan Bahasa Pemograman PHP Dan Database MySQL Saputra, Ade; Fitri, Iskandar
Jurnal Sains Informatika Terapan Vol. 5 No. 1 (2026): Jurnal Sains Informatika Terapan (Februari, 2026)
Publisher : Riset Sinergi Indonesia (RISINDO)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62357/jsit.v5i1.1089

Abstract

Pengolahan online ini dibutuhkan sebuah sistem secara e-comerce. E-comerce dapat melayanan internet yang dimanfaatkan untuk jual-beli (Nugroho, 2016). Dengan didukung adanya internet e-commerce dapat dimanfaatkan untuk mempromosikan masakan. Dengan adanya e-commerce nanti masakan-masakan pada Rumah Makan Terang Masakan Padang bisa lebih mudah dikenal dan bisa mudah dipromosikan kepada kalangan masyarakat luas, bisa sampai luar daerah Sumbar, luar pulau Sumbar, bahkan bisa sampai Luar Negeri untuk menaikan kembali hasil penjualan yang lebih banyak dari sebelumnya. Pemilik “Rumah Makan Terang Masakan Padang” yang sudah berkecimpung didunia usaha kuliner ini selama bertahun-tahun belum pernah mencoba melakukan media promosi melalui web. Kemajuan teknologi membuat usaha ini harus dapat mengikuti perkembangan di jaman sekarang oleh karena itu perlu dibuatkan situs untuk Rumah Makan Terang Masakan Padang agar mampu bersaing dengan usaha kuliner lainnya yang mungkin telah lebih dikenal di masyarakat, selain itu juga untuk menunjukkan bahwa masakan dari “Rumah Makan Terang Masakan Padang” ini rasanya juga nikmat sehingga menarik perhatian dari masyarakat sekitar dan berguna mengembangkan lagi usaha kuliner ini dan dapat melayani pembeli dari luar daerah bahkan luar negeri.
Development of Color Segmentation and Texture Analysis Algorithms for Early Detection of Green Vegetable Deterioration in Retail Environments Akhiyar, Dinul; Fitri, Iskandar; Nurcahyo, Gunadi Widi
Journal of Applied Data Sciences Vol 7, No 2: May 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i2.1094

Abstract

Vegetable deterioration in retail environments is often accelerated by improper storage conditions, leading to quality degradation, economic losses, and reduced consumer trust. Early detection of deterioration is therefore essential to enable timely preventive actions before visible spoilage becomes severe. This study proposes an integrated image-based framework for early detection of spinach leaf deterioration by combining K-Means++ for robust color segmentation, Gray Level Co-occurrence Matrix (GLCM) for texture feature extraction, and Convolutional Neural Network (CNN) for classification. K-Means++ improves segmentation stability through optimized centroid initialization, GLCM captures subtle texture variations associated with early spoilage, and CNN enables accurate classification by learning complex visual patterns from segmented images. The dataset consists of 642 spinach leaf images captured under controlled lighting for initial calibration and under varying lighting conditions to simulate real-world retail environments. Experimental results show that the standard K-Means algorithm achieved an average classification accuracy of 77%, while the proposed K-Means++ segmentation improved accuracy to 81.86%. Furthermore, CNN-based validation achieved the highest classification accuracy of 94.82%, demonstrating strong generalization capability. The novelty of this work lies in the optimized integration of K-Means++ segmentation under lighting variability, selective GLCM feature utilization validated through ablation analysis, and end-to-end CNN-based validation with real-time deployment feasibility. The proposed framework offers a practical, scalable, and non-destructive solution for automated freshness monitoring in retail environments and can be extended to other leafy vegetables.