Claim Missing Document
Check
Articles

Building a Worship Demand Application with The Waterfall Method Using Flutter Framework at The Al-Muttaqin Mosque Suralaga, Indonesia Ahmad Subki; Muhamad Masjun Efendi; Erfan Wahyudi
International Journal of Scientific Research Vol. 1 No. 01 (2024): March 2024
Publisher : Yayasan Hisnul Muslim Lombok

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62894/223psh41

Abstract

With the rapid development of modern technology such as smartphones, it has positive and negative impacts in this modern era. The positive impact is easy access to information. Meanwhile, the negative impact is misuse of the smartphone itself, such as opening websites that are not suitable for viewing, one of which is addiction to internet games which makes you lazy about studying. Apart from that, there is also a significant problem, namely travelers and children or teenagers at the Al-Muttaqin Mosque in Suralaga who seem to have quite difficulty carrying religious guidance in the form of a book. To overcome this, an Android-based prayer guidance application was created. It is hoped that this can provide understanding for children and teenagers at the Al-Muttaqin Mosque in Suralaga. As a result, this application was built using the Flutter Framework and the Waterfall method which consists of the user needs analysis stage, namely analyzing what needs and features are needed when creating the application. The design stage is the system design stage using System Flowcharts, UML (Use Case, Class and Activity) diagrams. The implementation stage is the stage of implementing the UI/UX design into a programming language using Visual Studio Code. The final testing stage is the stage of testing the functionality of the application using black box testing and using usability. The results of black box testing show that all menus were successfully executed and the results of usability testing using a Likert scale were 84.8%. This shows that in terms of utility the application built is in the "Very Good" category.
Transformasi Kompetensi Digital Siswa melalui Pelatihan MikroTik di SMK Darussholihi NW Kalijaga Muhamad Masjun Efendi; Nasirudin Karim; Gilang Ramdani; Nurfadilah Nurfadilah
Cahaya Pengabdian Vol. 3 No. 1 (2026): Juni
Publisher : Apik Cahaya Ilmu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61971/cp.v3i1.302

Abstract

Mastering computer networking cannot rely solely on theory. Students at SMK Darussholihi NW Kalijaga still face limited access to hands-on practical training, even though skills in managing MikroTik devices are essential for entering the workforce or even starting a business in the technology sector. This community service program was designed to bridge that gap through a structured and application-oriented training approach. The main objectives are to enhance students' understanding and technical skills in installing, performing basic configurations, managing bandwidth, and implementing simple network security using MikroTik. The program was carried out in three stages: first, lectures and demonstrations to explain core concepts and show configuration examples; second, hands-on practice with instructor guidance using both simulation tools and actual hardware; and third, evaluation through simple network building trials and problem-solving discussions. The expected outcomes include improved digital competence in network administration, the development of a practical guide module as a learning resource, and the availability of video tutorials for self-paced learning. With these skills, students are expected not only to be more confident in pursuing certification exams, but also better prepared to meet the demands of the industry and the business world in the digital era.
Perancangan Sistem Pemberian Pakan Otomatis Pada Sapi Menggunakan Teknologi Internet Of Things Ismayani; Lalu Delsi Samsumar; Muhamad Masjun Efendi
Journal of Computer Science and Technology (JOCSTEC) Vol 3 No 1 (2025): JOCSTEC - Januari
Publisher : PT. Padang Tekno Corp

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59435/jocstec.v3i1.416

Abstract

Di Lombok Barat, banyak peternak mengalami kesulitan karena minimnya lahan untuk menggembalakan ternak akibat konversi lahan menjadi perumahan dan area industri. Dalam situasi ini, peternak mungkin lupa atau tidak tepat waktu dalam memberikan pakan, serta menghadapi kesulitan dalam mencari rumput. Sebagai solusinya, dikembangkanlah sistem pemberian pakan pelet otomatis untuk sapi yang berbasis Internet of Things (IoT). Metode yang diterapkan dalam pengembangan sistem ini adalah metode prototype. Hasil penelitian menunjukkan bahwa sistem pemberian pakan otomatis berbasis IoT berfungsi dengan baik sesuai dengan komponen yang digunakan. Sistem ini memanfaatkan servo, sensor ultrasonik, sensor RTC, dan dilengkapi dengan LCD untuk menampilkan informasi mengenai sisa pakan dan status pakan (on atau off).
Enhancing Software Defect Prediction Performance using NR-Clustering SMOTE to Address Class Imbalance Hairani Hairani; Muhamad Masjun Efendi; Gede Yogi Pratama; Rahayun Amrullah Husaini; M.Khaerul Ihsan
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 4 (2026): August 2026
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i7558

Abstract

Software defect detection is important to prevent system failures and increased maintenance costs. However, the complexity of modern software makes manual testing inefficient, so machine learning approaches are used. The main challenge of this approach is data imbalance, where defective cases are far fewer, causing the model to overlook the minority class and reducing detection capability, even though accuracy appears high. This study aims to address class imbalance in software defect detection by applying the NR-Clustering SMOTE method to improve machine learning performance—the classification methods using Random Forest. NR-Clustering SMOTE not only oversamples the minority class but also incorporates a noise-reduction mechanism to remove minority data that may degrade classification performance. The results show that NR-Clustering SMOTE improves the performance of Random Forest compared with the original data, SMOTE, and NR-Modified SMOTE across all evaluation metrics, namely accuracy, recall, and F1-score. These findings indicate that integrating noise reduction and SMOTE-based data balancing using Manhattan distance within each cluster produces a more representative data distribution, thereby improving the model’s ability to classify software defect cases more accurately. Therefore, this study confirms that NR-Clustering SMOTE effectively improves Random Forest performance for software defect detection compared with existing approaches.
Development of a Web-Based Health Information System Integrated with Artificial Intelligence Using Agile Methodology at Dasan Agung Primary Health Center Muhamad Masjun Efendi; Ardiyallah Akbar; Lalu Mutawalli
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 3 (2026): September 2026 In progress.
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i3.567

Abstract

The recording of health data at the Dasan Agung Community Health Center(Puskesmas) in Mataram City is still carried out manually, giving rise tovarious problems such as data entry errors, data loss, delays in data retrieval,and inaccuracies in health reports. This study aims to develop a Web-BasedHealth Data Recording Information System using the Agile method to enhancethe effectiveness of health data management at the community health center.The method employed encompasses the stages of requirements gathering, analysis,design, coding, testing, deployment, and feedback. Data collection wasconducted through observation, interviews, and documentation studies. Thesystem was built using the PHP programming language with the CodeIgniter3.1.13 framework and a MySQL database. The findings indicate that the developedsystem is able to facilitate a more effective, faster, and integrated healthdata recording process. Available features include patient data management,personnel data management, patient registration, drug data management,laboratory management, medical records, patient prescriptions, and digitalhealth reports. With the implementation of this system, health administrationprocesses become more optimal and support the digital transformation ofhealth services at the community health center. The outputs of this researchare a web-based information system and the publication of a scientific articlein a national journal.
Interpreting Text-Enriched Dual-Head Multitask Learning for Indonesian Hateful Meme Detection Using Explainable AI Selamet Riadi; Emi Suryadi; Muhamad Masjun Efendi; Bahtiar Imran; Muhammad Zamroni Uska
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 3 (2026): September 2026 In progress.
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i3.576

Abstract

Internet memes in Indonesia are frequently weaponized to disseminate implicithate speech through sarcasm and cultural nuances. Automatically detectingsuch content is computationally challenging, and existing deep learningframeworks predominantly operate as opaque black boxes, lacking decisiontransparency. This study implements and optimizes a text-enriched dual-headmultitask learning architecture utilizing IndoBERTweet to concurrently classifyhatefulness and appropriateness within the INDOMEME dataset. Ratherthan processing raw image pixels, we employ a text-enrichment strategy wherevisual semantics are transcribed into textual descriptors via Optical CharacterRecognition and vision-language captioning. To bridge the interpretability gap,we deploy Local Interpretable Model-agnostic Explanations (LIME) to decodethe internal feature attributions of the architecture. Furthermore, advancedtraining optimizations, encompassing cosine annealing, gradient accumulation,class-weighted loss, and dynamic threshold calibration, were engineered toenhance model generalization. Experimental evaluations demonstrate thatthe optimized model achieves a Macro-F1 score of 0.812 for hatefulness and0.820 for appropriateness, surpassing the established baseline. Crucially, theLIME analysis unveils a pivotal finding: despite sharing an identical textualbackbone, the hate-specific head predominantly focuses on lexicons carryingsocial agitation, whereas the appropriateness head prioritizes general normviolations. These empirical findings substantiate that multitask learning enrichessemantic representation quality, offering a transparent framework fortrustworthy content moderation.