Garuda - Garba Rujukan Digital

Web-based student Course Registration System (KRS) using the Extreme Programming (XP) method Ali, Iman; Faizah, Novianti Madhona; Nurcahyo, Widyat; Fabrianto, Luky
Jurnal Mandiri IT Vol. 13 No. 3 (2025): January: Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v13i3.363

This research aims to design and develop a web-based Study Plan Card (KRS) system. The background of this study arises from challenges in the manual KRS process, which is time-consuming, prone to errors, and complicates information access. The development method employed is Extreme Programming (XP), which enables iterative system development and responsiveness to changing requirements. Data collection was conducted through observations, interviews, and document studies. The system was developed using PHP with the CodeIgniter 4 framework and MySQL database. The results indicate that the web-based KRS system enhances the efficiency of the KRS process, reduces data entry errors, and facilitates information access for students. Key features of the system include online KRS completion, digital signing by academic advisors, and integration with other academic information systems. System evaluation shows a significant improvement in data accuracy, accessibility, and information security. In conclusion, the implementation of this web-based KRS system successfully addresses issues in the manual KRS process, improves the quality of academic services, and provides an effective solution for KRS management

OPTIMIZING HADITH CLASSIFICATION WITH NEURAL NETWORKS: A STUDY ON BUKHARI AND MUSLIM TEXTS Rasenda, Rasenda; Fabrianto, Luky; Faizah, Novianti Madhona
JIKO (Jurnal Informatika dan Komputer) Vol 7, No 2 (2024)
Publisher : Universitas Khairun

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33387/jiko.v7i2.8732

The Bukhari and Muslim hadith collections encompass a total of 7008 hadith sentences, but it is not immediately clear which of these hadiths fall into the categories of prohibitions or orders. To enhance understanding and accessibility for readers, this study focuses on classifying these hadiths through a systematic process. The classification involves several key stages: Text Pre-processing, pre-processing the raw text data to clean and normalize (Stemming, Stopword Removal and Tokenization), Word vector features are extracted to capture the semantic relationships and contextual meanings of the words, then processed into a neural network model based on a multilayer perceptron (MLP) architecture (Model Architecture, Training and Optimization). The approach leverages the strength of neural networks, particularly through the use of multiple layers and feature extraction via word vectors, which significantly contributes to the accuracy of the classification process. The results of the study is very good, with a high accuracy rate of 97.72% achieved by employing a model with two layers and 256 neurons

Facial image protection with visual cryptography and random least significant bit (LSB) steganography Karo Karo, Panser; Simarmata , Simon; Faizah, Novianti Madhona; Fabrianto, Luky
Jurnal Mandiri IT Vol. 13 No. 4 (2025): April: Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v13i4.392

The confidentiality of sensitive data—such as personal information of individuals who may pose security threats to client assets—must be strictly maintained. This data includes personal details such as name, ID number, address, date of birth, occupation, and photographs (images). The data protection process involves combining textual data (ID number, name, date of birth) with a photo into a single image, which is then processed using visual cryptography. The visual cryptography technique applied is the (k, n) scheme with a 2-out-of-k configuration. To enhance data security and confidentiality through dual-layer protection, the output from the visual cryptography process is further secured using steganography with the random LSB (Least Significant Bit) method, applied to one of the shares obtained from the previous step. The best result achieved during testing was a PSNR of 71.9977 and an MSE of 0.0041. It is expected that the combination of visual cryptography and steganography methods will significantly enhance the security of data storage to protecting it from unauthorized access.

Attention-based convolutional neural networks for interpretable classification of maritime equipment fabrianto, luky; Prihandayani, Tiwuk Wahyuli; Rasenda, Rasenda; Faizah, Novianti Madhona
Jurnal Mandiri IT Vol. 14 No. 1 (2025): July: Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i1.426

This study introduces a Convolutional Neural Network with an Attention Mechanism (CNN+AM), utilizing the Squeeze-and-Excitation (SE) block, to classify critical ship components: generators, engines, and oil-water separators (OWS). The SE block enhances the model's ability to focus on discriminative features, thereby improving classification performance. To overcome the limitation of the original dataset, which contained only 199 images, extensive data augmentation techniques were applied, expanding the dataset to 2,648 images. The augmented dataset was divided into training (70%), validation (15%), and testing (15%) sets to ensure reliable evaluation. Experimental results show that the CNN-AM achieved an accuracy of 72.39%, surpassing the baseline CNN model with 68.16%. These findings confirm that the attention mechanism significantly improves generalization and the ability to differentiate visually similar classes. Furthermore, the integration of interpretability tools, such as Gradient-weighted Class Activation Mapping (Grad-CAM), provides visual explanations of model predictions, increasing trust and reliability for safety-critical maritime applications. The proposed approach demonstrates strong potential for real-time ship component monitoring, offering meaningful contributions to predictive maintenance and operational safety within the maritime industry.

Aplikasi Pengaduan Sarana dan Prasarana: Studi Kasus di SMK Bhayangkari Delog Berbasis Web dengan Metode Rapid Application Development Menggunakan Sublime Text dan MySQL Wicaksono, Rizki; Rakryan, Ryan; Faizah, Novianti Madhona
Jurnal Ilmu Komputer dan Teknologi Informasi Vol. 2 No. 1 (2025): Maret
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/jikti.v2i1.1335

With the increasing number of students and the infrastructure supporting educational activities, the complaint service system at SMK Bhayangkari requires improvement. Identified issues include slow response times for feedback, limited flexibility for students to submit complaints, and the manual management of complaint data. This study aims to facilitate students in submitting complaints anytime and anywhere, while simplifying the management of complaint data to expedite the process of checking and following up on complaints. The methodology used in this study is Rapid Application Development (RAD), with system design tools utilizing UML (Unified Modeling Language), PHP programming, and MySQL for the database.

Perancangan dan Pengembangan Aplikasi Deteksi Anomali pada Jaringan Internet Gedung Disaster Recovery Center Badan Diklat Kejaksaan RI dengan Implementasi Sistem Manajemen Informasi dan Keamanan (SIEM) Berbasis Web Issenoro; Trisnawati, Herlina; Tarigan, Sakius Octavianus; Faizah, Novianti Madhona; Veranita
Jurnal Ilmu Komputer dan Teknologi Informasi Vol. 2 No. 1 (2025): Maret
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/jikti.v2i1.1341

This research develops an anomaly detection application for the internet network of the Disaster Recovery Center (DRC) building at the Training Agency of the Indonesian Prosecutor's Office (Badan Diklat Kejaksaan RI), implemented with Security Information and Event Management (SIEM) using the Python programming language. The resulting application aims to assist network administrators at the DRC in monitoring network communication flows and detecting potential threats to the system. The approach involves developing an application that enhances network security through anomaly detection and monitoring devices to protect the network. SIEM technology is used to collect and analyze log data from the network, applications, and hardware. This technology allows for the large-scale collection of log data and the analysis of events from multiple sources. With the implementation of this system, the DRC Kejaksaan RI is expected to gain the ability to monitor internet network traffic and the security devices applied, as well as evaluate the effectiveness of SIEM in protecting information assets. The focus of this research is on improving network security, collecting logs and events related to network traffic, and developing a dashboard application to display monitoring results. The system aims to detect harmful anomalies and provide up-to-date information regarding network conditions, thus facilitating network administrators in performing monitoring tasks and reporting findings to leadership.

Perancangan Aplikasi Sistem Informasi Wisata Alam di Kota Pandeglang, Provinsi Banten, Berbasis Web dengan Metode Waterfall Menggunakan PHP dan MySQL Supriadi, Edi; Nurcahyo, Widyat; Faizah, Novianti Madhona
Jurnal Ilmu Komputer dan Teknologi Informasi Vol. 2 No. 1 (2025): Maret
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/jikti.v2i1.1342

A web-based information system plays a crucial role in providing access to information without requiring visitors to physically visit a location. Pandeglang City, located in Banten Province, is home to various natural tourist attractions that remain largely unknown to travelers. Therefore, there is a need for an application that allows both local and international visitors to obtain information about the natural tourist spots in the area. This study aims to design a web-based information system to provide data about the locations and facilities of tourist attractions in Pandeglang City. The Waterfall method is applied in the development process, starting with needs analysis, system design, code writing, testing, and system implementation. The application will assist visitors in learning about tourist spots and supporting facilities around these locations. With the availability of this application, it is expected that tourists can more easily plan their visits. The results of this system's development will simplify access to information about natural tourist attractions in Pandeglang City, potentially increasing tourist visits. This information system is anticipated to positively contribute to the growth of the tourism sector in the region.

OPTIMIZING HADITH CLASSIFICATION WITH NEURAL NETWORKS: A STUDY ON BUKHARI AND MUSLIM TEXTS Rasenda, Rasenda; Fabrianto, Luky; Faizah, Novianti Madhona
JIKO (Jurnal Informatika dan Komputer) Vol 7, No 2 (2024)
Publisher : Universitas Khairun

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33387/jiko.v7i2.8732

The Bukhari and Muslim hadith collections encompass a total of 7008 hadith sentences, but it is not immediately clear which of these hadiths fall into the categories of prohibitions or orders. To enhance understanding and accessibility for readers, this study focuses on classifying these hadiths through a systematic process. The classification involves several key stages: Text Pre-processing, pre-processing the raw text data to clean and normalize (Stemming, Stopword Removal and Tokenization), Word vector features are extracted to capture the semantic relationships and contextual meanings of the words, then processed into a neural network model based on a multilayer perceptron (MLP) architecture (Model Architecture, Training and Optimization). The approach leverages the strength of neural networks, particularly through the use of multiple layers and feature extraction via word vectors, which significantly contributes to the accuracy of the classification process. The results of the study is very good, with a high accuracy rate of 97.72% achieved by employing a model with two layers and 256 neurons

Title

Found 8 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 8 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 8 Documents
Search