cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Agung Suharyanto
Contact Email
suharyantoagung@gmail.com
Phone
+628126493527
Journal Mail Official
suharyantoagung@gmail.com
Editorial Address
Perumahan Griya Nafisa 2, Blok A no 10, Percut Sei Tuan, Deli Serdang
Location
Unknown,
Unknown
INDONESIA
INCODING: Journal of Informatics and Computer Science Engineering
Published by Mahesa Research Center
ISSN : -     EISSN : 2776432X     DOI : 10.34007
Core Subject : Science,
Computer Science & IT
INCODING: Journal of Informatics and computer science engineering, is a journal of informatics is the study of the structure, behavior, and interactions of natural and engineered computational systems.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 62 Documents
 3   4   5   6   7 
Perancangan Sistem Pengajuan Pemasangan Baru Layanan Wifi.Id Di PT. Telkom Regional-1 Sumatera Noor, Fredy; Khairani, Nurul
INCODING: Journal of Informatics and Computer Science Engineering Vol 4, No 2 (2024): INCODING OKTOBER
Publisher : Mahesa Research Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34007/incoding.v4i2.728

Abstract

The rapid development of information technology encourages telecommunication companies to continue to innovate, including PT. Telkom Regional-1 Sumatra which provides Wifi.id services. This study aims to design a new installation submission system for web-based Wifi.id services to improve the efficiency and speed of the installation process. The system is designed using PHP and CSS programming languages, as well as MySQL as the database. The design method involves the use of flowcharts, sitemaps, context diagrams, entity relationship diagrams (ERDs), and data flow diagrams (DFDs) to ensure the system is well structured. The results of the study show that the designed system can make it easier for the people of North Sumatra to apply for the installation of Wifi.id services efficiently and transparently. This system also increases the speed and effectiveness of the installation process, thus providing benefits for both customers and PT. Telkom Regional-1 Sumatra. With the implementation of this system, the installation application process becomes more organized, supports the improvement of service quality, and has a positive impact on the customer experience
Penerapan Mobilenetv3 untuk Klasifikasi Jenis Bahan Pakaian Sinaga, Doni Poulus; Khairina, Nurul
INCODING: Journal of Informatics and Computer Science Engineering Vol 5, No 2 (2025): Oktober
Publisher : Mahesa Research Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34007/incoding.v5i2.829

Abstract

This study aims to develop an efficient and accurate model for classifying clothing material types using the MobileNetV3 architecture. Clothing material images were collected from open sources and processed through resizing, normalization, and data augmentation. The model was trained using transfer learning and evaluated using accuracy, precision, recall, and F1-score metrics. The evaluation results showed an accuracy of 92%, with the best performance in the silk and polyester categories. However, misclassifications still occurred for materials with similar textures, such as linen and cotton. Compared to previous studies, this approach offers advantages in computational efficiency for mobile and edge computing applications. This research contributes to the development of an automated clothing material classification system to support the textile and fashion industries. Further improvements are needed by enhancing dataset quality and fine-tuning the model to better distinguish materials with visually similar characteristics.
Pendekatan Arsitektur Eficientnet Pada CNN Untuk Meningkatkan Pengenalan Tulisan Tangan Angka: Studi Kasus Dataset MNIST Amin Matondang, Rahmadani Syahriful; Susilawati, Susilawati
INCODING: Journal of Informatics and Computer Science Engineering Vol 5, No 1 (2025): INCODING APRIL
Publisher : Mahesa Research Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34007/incoding.v5i1.824

Abstract

This study aims to evaluate the performance of the EfficientNetB1 architecture in recognizing handwritten digits using the MNIST dataset, which consists of 60,000 training images and 10,000 testing images in 28×28 grayscale format. The methodology includes preprocessing steps such as image resizing, grayscale to RGB conversion, pixel normalization, and data augmentation. EfficientNetB1 is used as a feature extractor, followed by dense layers and a softmax output layer for classification. The model is trained using three optimizers—Adam, SGD, and RMSprop—with varying learning rates (0.001, 0.01, and 0.1). Experimental results indicate that the combination of RMSprop and a 0.001 learning rate yields the highest validation accuracy of 97.9%. Classification errors mostly occur on digits with similar visual structures, such as 2 and 5. This research contributes valuable insights into the effective use of EfficientNetB1 and hyperparameter optimization for handwritten digit classification tasks.
Analisis Performa Convolution Neural Network untuk Klasifikasi Hewan Berdasarkan Perbedaan Ukuran Kernels Pane, Ilham Maratua; Sembiring, Arnes
INCODING: Journal of Informatics and Computer Science Engineering Vol 5, No 2 (2025): Oktober
Publisher : Mahesa Research Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34007/incoding.v5i2.849

Abstract

This study aims to analyze the impact of kernel size variation in Convolutional Neural Network (CNN) architectures on the performance of animal image classification. The kernel sizes evaluated include 3x3, 5x5, 7x7, and 9x9. Performance was assessed using accuracy metrics and confusion matrix analysis to determine the effectiveness of each model. The results indicate that the 5x5 kernel achieved the highest accuracy and the most balanced classification distribution, while the 9x9 kernel resulted in a significant decline in performance. Excessively large kernels led to the model’s inability to capture local features, causing a high rate of misclassification. In contrast, moderately sized kernels maintained a balance between capturing global context and preserving local detail. These findings highlight the importance of selecting an appropriate kernel size in CNN architecture design to achieve optimal classification results.
Penerapan Algoritma K-Means dalam Segmentasi Pelanggan untuk Meningkatkan Strategi Pemasaran di E-Commerce Andrian, Yohannes; Susilawati, Susilawati
INCODING: Journal of Informatics and Computer Science Engineering Vol 5, No 1 (2025): INCODING APRIL
Publisher : Mahesa Research Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34007/incoding.v5i1.825

Abstract

This study aims to implement the K-Means Clustering algorithm for customer segmentation in e-commerce to enhance marketing strategy effectiveness. By utilizing customer transaction data such as purchase frequency, product quantity, and total spending, the study classifies customers into three main segments: high, medium, and low transaction groups. The research method includes data preprocessing, cluster center initialization, Euclidean distance calculation, and iterative clustering to achieve optimal segmentation. The segmentation results are integrated into a web-based system, facilitating interactive customer data management. Testing on application features, including login, data input, clustering process, and reporting, confirms that the application functions as expected. These findings reinforce the role of K-Means-based segmentation in supporting more targeted marketing decision-making in the e-commerce sector.
Merancang Sistem Informasi dan Pemasaran Produk UMKM Berbasis Web di Dinas Koperasi Sumut Br Berutu, Elimiana; Syah, Rahmad
INCODING: Journal of Informatics and Computer Science Engineering Vol 4, No 2 (2024): INCODING OKTOBER
Publisher : Mahesa Research Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34007/incoding.v4i2.730

Abstract

MSME actors at the North Sumatra Cooperative Office often experience difficulties in their business. The difficulty that arises in this business is the difficulty of MSMEs/SMEs in marketing their products and finding suitable buyers. This research aims to design and build a web-based marketing information system for MSME actors under the auspices of the North Sumatra Cooperative Office to overcome the limitations of market reach and access to technology. The system uses PHP, MySQL, and XAMPP with the SDLC approach of the waterfall model. The K-medoids clustering method was applied to group MSME data, resulting in a quality cluster with a Davies-Bouldin Index (DBI) value of 0.368812. The grouping results showed that 314 MSME actors deserved a 30% reward, 540 received a 20% reward, and 231 received a 10% reward. This system helps expand marketing reach, make it easier for customers to find products, and increase the competitiveness of MSMEs. This research supports the digital transformation of MSMEs and can be replicated to encourage sustainable economic growth.
KLASIFIKASI KESEHATAN JANIN PADA IBU HAMIL MENGGUNAKAN METODE SUPPORT VECTOR MACHINE Darkani, M. Farhan; Khairina, Nurul
INCODING: Journal of Informatics and Computer Science Engineering Vol 5, No 2 (2025): Oktober
Publisher : Mahesa Research Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34007/incoding.v5i2.830

Abstract

Monitoring fetal health is a crucial aspect of pregnancy, requiring accurate and efficient methods for early detection of potential complications. This study aims to develop a fetal health classification system using the Support Vector Machine (SVM) algorithm. The data analyzed includes various fetal physiological parameters obtained through routine examinations, such as heart rate, fetal movements, and other relevant indicators. SVM was chosen due to its capability to handle non-linear data and its high classification accuracy. The classification process involves data preprocessing, feature selection, model training, and performance evaluation using metrics such as accuracy, precision, recall, and F1-score. The results indicate that SVM can effectively classify fetal health conditions with high accuracy, making it a promising diagnostic support tool for medical professionals. This study contributes to maternal and fetal healthcare by offering a machine learning-based approach that enhances the effectiveness of fetal health monitoring systems.  
Meningkatkan Deteksi Email Phising Melalui Pendekatan SVM yang Dioptimalkan NLP Tanjung, Rino Nurcahyo Fauzi; Rahman, Sayuti
INCODING: Journal of Informatics and Computer Science Engineering Vol 5, No 1 (2025): INCODING APRIL
Publisher : Mahesa Research Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34007/incoding.v5i1.831

Abstract

Phishing email attacks are a serious threat in the digital ecosystem because they can trick users into leaking sensitive information or accessing malicious links. This study aims to develop a phishing email classification model based on the Support Vector Machine (SVM) algorithm combined with Natural Language Processing (NLP) techniques to improve detection accuracy. The process begins with the tokenization, text cleansing, and feature extraction stages using the TF-IDF approach, which is further used as input into the classification model. Various SVM kernels, including linear, radial basis function (RBF), and polynomial, are tested through the grid search method with parameter tuning such as C, gamma, and degree. The results showed that SVMs with polynomial kernels produced the highest accuracy of 97.85%, surpassing other algorithms such as Naïve Bayes, Random Forest, and Logistic Regression. These findings indicate that the integration of NLP and SVM with proper parameter tuning provides an effective solution in mitigating phishing email attacks. This model can be the foundation for the development of a more adaptive and efficient cybersecurity system.
Analisis Kondisi Polusi Udara Berdasarkan Perubahan Waktu Menggunakan IoT dan Logika Fuzzy: Solusi Mencegah Dampak Polusi Terhadap Kesehatan Yudha, Muhammad; Susilawati, Susilawati
INCODING: Journal of Informatics and Computer Science Engineering Vol 5, No 2 (2025): Oktober
Publisher : Mahesa Research Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34007/incoding.v5i2.862

Abstract

Identifying air pollution is a serious problem in various cities including Medan city. In this article, the use of IoT sensor-based mamdani fuzzy inference rules to identify air pollution in Medan city is discussed. Data collection is done through devices and systems built using IoT sensor devices. The IoT devices are installed in three different locations namely on Sei Deli, Tembung and KIM roads to monitor and collect air pollution data in real-time. Fuzzy inference rules are then used to process the sensor data and identify air pollution based on predefined threshold values. In addition to pollution factors, the determination of the time scale, namely early morning, morning, afternoon, evening and night is also a variable to identify air pollution based on time. The results show that the system built can identify air pollution based on data obtained through 3 devices with an average value of pollution in the "Medium" category.
Pengenalan Tulisan Tangan Angka menggunakan CNN dengan Arsitektur DenseNet-201 pada Dataset MNIST Fadillah Lubis, Muhammad Fajril; Susilawati, Susilawati
INCODING: Journal of Informatics and Computer Science Engineering Vol 5, No 1 (2025): INCODING APRIL
Publisher : Mahesa Research Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34007/incoding.v5i1.826

Abstract

Handwritten digit recognition using the MNIST dataset is one of the applications in digital image processing. The selection of hyperparameters in the CNN architecture for handwriting recognition presents a challenge in achieving better recognition accuracy. This research focuses on the implementation of the DenseNet-201 architecture for recognizing handwritten digits in the MNIST dataset. The research stages include dataset preprocessing, model training, model testing, and model evaluation. The MNIST dataset consists of 60,000 training data and 10,000 testing data. Dataset preprocessing involves resizing the images to a larger size. The model training applies the DenseNet-201 architecture with selected hyperparameters such as activation functions (Softmax and ReLU), optimizers (Adam, RMSprop, and SGD), and learning rates (0.1, 0.01, and 0.001). The model testing uses one of the nine best-performing trained models. Model evaluation uses a confusion matrix to assess the accuracy and recognition performance on the MNIST dataset. The results show that the DenseNet-201 architecture with the RMSprop optimizer and a learning rate of 0.001 achieved a handwritten digit recognition accuracy of 99.49%. This study provides insights into CNN architectures and optimal hyperparameter selection for digital image processing

Page 5 of 7 | Total Record : 62

 3   4   5   6   7 

Filter by Year

2021 2025


Reset
Filter By Issues
All Issue Vol 5, No 2 (2025): Oktober Vol 5, No 1 (2025): INCODING APRIL Vol 4, No 2 (2024): INCODING OKTOBER Vol 4, No 1 (2024): INCODING APRIL Vol 3, No 2 (2023): INCODING OKTOBER Vol 3, No 1 (2023): INCODING APRIL Vol 2, No 2 (2022): INCODING OKTOBER Vol 2, No 1 (2022): INCODING APRIL Vol 1, No 2 (2021): INCODING OKTOBER Vol 1, No 1 (2021): INCODING APRIL