Claim Missing Document
Check
Articles

Aplikasi Mentor Pembelajaran Berbasis Sistem Rekomendasi Content-Based Filtering dengan Metode TF-IDF dan Cosine Similarity Akhdan, Fairuz; Fitriani, Leni
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2493

Abstract

This study aims to develop the Mentorku application as a learning support tool for students through a mentor recommendation system based on expertise. The recommendation system uses a Content-Based Filtering (CBF) approach with TF-IDF and Cosine Similarity algorithms to match user needs with mentor profiles. The application development process follows the agile method using the Scrum framework, which includes the stages of Product Backlog, Sprint Planning, Sprint Execution, Sprint Review, and Sprint Retrospective. This application provides key features such as mentor search, live mentoring sessions, private discussions, chat, and one-on-one mentoring. Beta testing results show that 79% of respondents stated that the application is usable and capable of providing relevant recommendations according to learning needs. These findings indicate that the Mentorku application is effective in helping to overcome unstructured learning problems through direct interaction with mentors.
Rancang Bangun Aplikasi Monitoring Kebutuhan Masyarakat Untuk Relawan TIK Berbasis Web dan Mobile Fitriani, Leni; Alfarisi, Muhammad Tsalman
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2574

Abstract

Information and Communication Technology (ICT) volunteers face significant challenges in recording community needs because the process is still carried out manually and unstructured. This approach results in collected data often being scattered, difficult to analyze systematically, and ultimately hindering the effectiveness and speed of coordination in distributing aid. To overcome these problems, this study aims to design and build an integrated web- and mobile-based community needs monitoring system. This system was developed using the Rapid Application Development (RAD) method, which enables a fast and iterative development process. The mobile application serves as a tool for volunteers in the field to report needs in real time, while the web platform is used by managers for validation, assignment, and monitoring. Key features such as data visualization through heat maps, forms with automatic GPS, and photo uploads are integrated to improve data accuracy. Beta testing using the System Usability Scale (SUS) approach resulted in an average score of 76.25, which falls into the “Good” (Grade B) category. These results show that the system, built using Next.js, React Native, and PostgreSQL, has a high level of stability and has the potential to become a strategic tool for improving data collection efficiency and optimizing the distribution of social assistance digitally.
Aplikasi Pengingat Minum Obat Dengan Monitoring Tenaga Kesehatan Berbasis Mobile Menggunakan Metode Prototype Firdaus Al Anwari, M Riadi; Nuraeni, Fitri; Cahyana, Rinda; Fitriani, Leni; Setiawan, Ridwan; Septiana, Yosep
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2580

Abstract

The process of administering medication to patients requires timeliness and consistency to ensure optimal therapeutic outcomes. In practice, many patients struggle to remember their medication schedules, particularly when treatment extends over a long period. Addressing this issue, the present study aims to develop an Android-based medication reminder application that assists patients in adhering to their treatment schedules while enabling healthcare providers to digitally monitor patient activity. The application was designed using a prototyping method, which emphasizes iterative system development based on user feedback. The development process was conducted in two phases. The first phase involved initial design and testing of core features, such as reminder notifications and patient medication intake reporting forms. The second phase focused on improvements based on user feedback, particularly the addition of a disease information feature that provides educational content about patient diagnoses following checkups, such as hypertension and tuberculosis. Testing was carried out using a black-box testing approach to ensure proper functionality, alongside feedback collection through interviews. The results showed that the application performed effectively; its features were usable by both patients and healthcare providers as intended, and the information displayed was considered helpful in enhancing patients’ understanding of their health conditions. Furthermore, the system contributed to improving patient adherence to medication regimens and facilitated continuous monitoring by healthcare providers.
Rancang Bangun Media Pembelajaran Pengenalan Hewan Nokturnal Untuk Anak Autisme Sriayuwahyuni, Putri; Sutedi, Ade; Latifah, Ayu; Fitriani, Leni
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2588

Abstract

Children with autism often experience difficulties in focusing, communicating, and processing abstract information, making conventional learning methods less effective. This requires learning media that can accommodate special needs through visual, auditory, and exploratory approaches. This study aims to design and develop Android-based interactive learning media to introduce nocturnal animals to children with autism. The method used is the Multimedia Development Life Cycle (MDLC), which consists of the stages of concept, design, material collecting, assembly, testing, and distribution. This media has two main features, namely “Learn,” which presents text, images, sounds, and voice-overs, and “Puzzle,” which trains children's memory and fine motor skills through animal picture assembly activities. Testing results through alpha testing using the black-box method showed that all application features ran according to design without errors. The implication of this research is the availability of learning media that is more interactive, enjoyable, and suitable for the characteristics of children with autism, thus providing an innovative alternative in supporting their learning process.
Rancang Bangun Aplikasi Stok Opname Berbasis Web Sutedi, Ade; Fitriani, Leni; Nuraeni, Fitri; Suryani, Isma
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2732

Abstract

PT Usaha Garda Arta (UG Arta) Jakarta Branch currently still uses a manual system for cassette stock-taking, which results in the risk of data discrepancies, delays in reporting, and potential recording errors. The operational process begins with the creation of a cash replenishment request by the admin and scheduler to the bank, followed by the collection of cash by the Cash In Transit (CIT) team, sorting by the Cash Processing Center (CPC) team, and finally the replenishment of cash into Automated Teller Machine (ATM) cassettes by the Cash Replenishment (CR) team. This operational process requires team coordination and relies on manual recording, which makes it prone to errors. This research was conducted with the aim of designing a web-based stocktaking system to optimize the cassette stock management process at PT UG Arta's Jakarta Branch. This system is designed with features to input staff and officers, input cassette data, monitor cassette stock, global data and history to improve data accuracy, data recording activities, facilitate monitoring of goods in and out, and reduce manual processes. Therefore, this study is expected to make the stocktaking management process easily accessible to parties involved in the operational process. Additionally, this system is also expected to reduce the risk of recording and reporting errors, thereby improving company performance.
Sistem Manajemen Pembelajaran Berbasis Web Menggunakan Metode RAD Musa, Abdul Basri; Fitriani, Leni
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2812

Abstract

Perkembangan teknologi informasi mendorong perubahan signifikan dalam dunia pendidikan, khususnya pada penerapan pembelajaran daring. SMK PGRI Selaawi masih menghadapi kendala seperti penyampaian materi secara manual, keterbatasan akses bagi siswa yang berhalangan hadir, serta proses evaluasi yang konvensional dan memakan waktu. Penelitian ini merancang dan membangun Learning Management System (LMS) dan dibangun sebagai aplikasi berbasis web dengan pendekatan Rapid Application Development (RAD). Hasil implementasi menunjukkan bahwa sistem mampu membantu guru dalam penyebaran materi, penugasan, absensi, serta penilaian secara terpusat. Uji fungsionalitas dengan black box testing membuktikan semua fitur berjalan baik, sementara pengujian usability menggunakan System Usability Scale (SUS) memperoleh skor 90,5 dengan kategori “Excellent”. Dengan demikian, sistem ini dapat menjadi solusi efektif dalam mendukung digitalisasi pembelajaran di SMK PGRI Selaawi.
Arsitektur Model SSDMobileNet V2 untuk Klasifikasi Bahasa Isyarat BISINDO Nurzaman, Muhammad Zein; Fitriani, Leni
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2850

Abstract

In this study, we used a commonly used object detection algorithm to classify sign language gestures, namely BISINDO or Indonesian Sign Language. The process of learning sign language is still limited, especially with the use of traditional methods such as direct conversation or using a dictionary. However, there are still obstacles with this approach, for example, some students have difficulty interpreting what they see in the dictionary. Therefore, this study aims to overcome this problem by using a real-time image classification model. The dataset used in this study was collected by the researchers themselves, with a total of 520 images consisting of 26 classes of BISINDO alphabet gestures. We also used transfer learning in this study to utilize the pre-trained SSDMobileNet V2 architecture. Using the COCO evaluation metric, the results show that this model achieved 94% mean average precision, 91% average precision, and 85% recall. This model can also classify sign language gestures in real-time.