KHARISMA Tech

SISTEM MANAJEMEN HOTEL BERBASIS WEB DENGAN INTEGRASI MIDTRANS DAN NOTIFIKASI EMAIL

M. Galvin Prihardi Putra, Irwan, Bradika Almandin Wisesa — Wed, 02 Sep 2026 12:51:15 +0800

This study aims to design and develop a web-based Hotel Management System as part of the digitalization of operational processes at Hotel Letco In, which previously relied on manual procedures. The manual workflow caused several issues, including limited access to room availability, a high risk of data entry errors, and inefficiencies in reservation and reporting processes. The developed system includes modules for user registration and authentication, online room booking, room and facility management, payment integration using Midtrans, and automated email notifications through SMTP. In addition, the system provides a PDF-based transaction receipt feature to support administrative documentation. Functional testing using the Black Box method showed that all features operated according to requirements and supported more efficient hotel operations. Overall, the system improves reservation efficiency, enhances data accuracy, and provides a faster and more structured service experience for both users and hotel administrators.

PERANCANGAN APLIKASI MOBILE ADMINISTRASI MAGANG POLMAN BABEL DENGAN MODEL PROTOTYPING ITERATIF

Riki Afriansyah, Lita Rahmania, Eko Sulistyo — Wed, 02 Sep 2026 12:52:19 +0800

Internships are an important component of vocational education because they provide students with real-world work experience to understand industrial processes firsthand. However, internship administration at the Bangka Belitung State Manufacturing Polytechnic was previously carried out manually through paper logbooks, signed attendance sheets, and physical document validation. This process often caused problems such as delays in verification, risk of data loss, difficulty in daily monitoring, and a lack of transparency of information between students, industry partners, and supervising lecturers. Based on these issues, this study designed a mobile application to digitize the entire internship administration process using the prototyping method. This approach allows for rapid prototyping, direct user feedback, and iterative improvements until the system reaches its final form that meets the needs. The research phase included data collection through interviews, observations, and literature review, needs analysis, interface design, Android application implementation, and system testing. The results showed that the application provides digital logbook features, location-based attendance, document upload, industry partner validation, supervisor monitoring, and trial scheduling. Testing demonstrated that all functions functioned well and user acceptance reached the very acceptable category. Therefore, this application can be an effective solution to improve the accuracy, efficiency, and integration of internship administration in vocational education environments.

OPTIMALISASI PEMBELAJARAN CALISTUNG DENGAN MENGGUNAKAN APLIKASI PEMBELAJARAN CALISTUNG

aisyah affani, Yang Rindri, Indah Pratiwi — Wed, 02 Sep 2026 12:53:30 +0800

Penelitian ini bertujuan untuk mengoptimalkan proses pembelajaran membaca, menulis, dan berhitung bagi anak usia dini melalui pengembangan aplikasi pembelajaran. Keterampilan dasar ini sangat penting sebagai langkah awal untuk memasuki jenjang pendidikan berikutnya. Metode penelitian meliputi analisis kebutuhan, perancangan sistem, implementasi aplikasi, dan pengujian menggunakan metode kotak hitam untuk memastikan setiap fitur berfungsi sebagaimana mestinya. Aplikasi ini dikembangkan berbasis teknologi interaktif dengan menggabungkan elemen animasi, audio, dan desain antarmuka yang sederhana dan sesuai dengan karakteristik pembelajaran anak usia dini. Hasil penelitian menunjukkan bahwa penggunaan aplikasi ini dapat meningkatkan minat belajar, motivasi, dan keterlibatan aktif anak dalam memahami keterampilan literasi dasar. Hal ini terbukti dari hasil pengujian menggunakan metode Normalised Gain yang memperoleh hasil sebesar 0,8 yang termasuk dalam kategori gain tinggi. Selain itu, aplikasi ini juga memudahkan peran orang tua dan pendidik dalam mendampingi proses belajar anak. Optimalisasi pembelajaran dengan aplikasi dari segi tampilan, konten, dan fitur interaktif terbukti efektif dalam menciptakan pengalaman belajar yang lebih menyenangkan.

PENGEMBANGAN APLIKASI TUTORISING BERBASIS ANDROID DENGAN PENDEKATAN SOCIAL LEARNING

christopher phitoyo, Syamsul Bahri, Baizul Zaman — Wed, 02 Sep 2026 12:56:26 +0800

perkembangan teknologi digital mendorong diterapkannya pembelajaran daring, namun masih menghadapi tantangan seperti rendahnya motivasi belajar,kurangnya interaksi sosial ,dan terbatasnya bimbingan langsung. Penelitian ini bertujuan mengembangkan aplikasi tutorising, sebuah platform pembelajaran berbasis video yang mengadopsi teori social learning dari albert bandura. Aplikasi ini di rancang untuk meningkatkan partisipasi siswa melalui fitur video pembelajaran,forum diskusi,penilaian dan ulasan. Metode pengembangan yang di gunakan adalah Research and Development (R&D),sedangkan pengujian di lakukan menggunakan blackbox testing untuk memastikan fungsionalitas sistem. Hasil pengujian menunjukan seluruh fitur utama berjalan dengan baik tanpa kesalahan fungsional. Temuan ini menunjukan pendekatan social learning efektif diimplementasikan dalam aplikasi pembelajaran daring, meskipun diperlukan pengembangan konten lebih lanjut pada jenjang smp dan sma.

PENGEMBANGAN APLIKASI PENDETEKSI AKSARA LONTARA BERBASIS CONVOLUTIONAL NEURAL NETWORKS MENGGUNAKAN FRAMEWORK FLUTTER

Linda Yanti Yo, Mohammad Fajar, Baizul Zaman — Wed, 02 Sep 2026 12:57:29 +0800

Lontara script is a cultural heritage of the Bugis-Makassar people that is increasingly threatened with extinction due to the limited availability of interactive learning media. This study aims to develop a mobile application for detecting Lontara script based on Flutter, integrated with a Convolutional Neural Network (CNN) model. The dataset consists of 5,017 images of Lontara script divided into 23 classes, processed through grayscale and normalization stages. The CNN model is designed with three layers of convolution and pooling, then evaluated using accuracy, precision, recall, and F1-score metrics. Testing results show that the application can detect Lontara script in real-time through Flutter and REST API integration, with the model achieving 97% accuracy. Testing under conditions with visual disturbances showed that the model could still perform detection up to a certain level of noise and blur, but performance declined under high simultaneous disturbances. These findings confirm that the application can support efforts to preserve Lontara script, though it still requires adequate image quality for optimal detection.

ANALISIS DAN DESAIN USER INTERFACE APLIKASI OLAH DATA ABSENSI MENGGUNAKAN CHATGPT 4.0

Marcelino Ponto, Syaiful Rahman, Abdul Munir S — Wed, 02 Sep 2026 21:02:51 +0800

Recently, the use of ChatGPT in software engineering has become increasingly popular, particularly in code development. The utilization of ChatGPT can significantly save time and costs if implemented effectively. This study aims to explore the capabilities of ChatGPT in various aspects of software engineering, specifically in requirements analysis, activity diagram creation, use case modeling, class diagram development, system architecture design, and user interface design for a fingerprint attendance data processing application. The research results are examined using content analysis methods based on primary data generated by ChatGPT. From this study, it can be concluded that ChatGPT has certain limitations in some stages of software engineering. User intervention is required to validate, supplement, and revise errors in the generated responses.

PENGEMBANGAN GAME RPG 2D ANOTHER WORLD REBORN MENGGUNAKAN METODE PROTOTYPING

William Hosal, Abdul Munir S. , Hasniati Hasniati — Wed, 02 Sep 2026 21:09:37 +0800

Abstract: The development of 2D Role-Playing Games (RPGs) often faces significant challenges in translating complex concepts such as epic storylines and flexible character customization into a solid functional product. This research aims to apply and evaluate the prototyping method as a solution to overcome these challenges in the development of the game "Another World Reborn". The development process was carried out through two focused iteration cycles: the first iteration built a storyline prototype, and the second iteration built a character customization system prototype. Functional requirements for each prototype were identified through interviews with target players. Technical validation was performed using the black-box testing method on each prototype built with the RPG Maker MV engine. The test results showed that all features developed in both prototypes, including cinematic scenes, dialogues, tutorial battles, and all character customization functions, successfully ran according to the functional design without any errors found. Thus, it is concluded that the application of the prototyping method is an effective and technically feasible approach for developing games iteratively and validated, especially in the context of projects with limited resources.

RE-DESIGN USER INTERFACE PADA STARTUP KAMI ADA UNTUK MENINGKATKAN USER EXPERIENCE DENGAN METODE USER CENTERED DESIGN

Jevon Kirk Macciano, Mohammad Sofyan S. Thayf, Arianti — Wed, 02 Sep 2026 21:06:41 +0800

KAMI ADA is a digital platform startup that connects the public with service providers such as well drilling, toilet suction, and iron welding through the website kamiada.com. Currently, KAMI ADA has 56 users, but feedback indicates concerns about the website's poor appearance. Measurements using the System Usability Scale (SUS) on 20 users resulted in a score of 42.875, with a grade of F, a rating of "poor" and an acceptance level of "not acceptable." This score indicates that the majority of users experienced difficulties, indicating a very poor user experience and the need for design improvements. To address this issue, KAMI ADA will redesign the system on the website using the User-Centered Design (UCD) method. The UCD approach was chosen because it places the user as the main focus in every design stage, with the hope of creating a system that is functional, satisfying, efficient, and enjoyable for users. Through this redesign, KAMI ADA aims to increase the value of services, strengthen relationships with users, and encourage sustainable business growth.

APLIKASI WEB MANAJEMEN TANAMAN DAN DIAGNOSA HAMA-PENYAKIT BERBASIS RAD

Husnul Fadlilah, Riki Afriansyah, Nur Khasanah — Sun, 06 Sep 2026 17:31:03 +0800

Penggunaan teknologi informasi di bidang pertanian semakin dibutuhkan untuk membantu petani mengelola tanaman dan mendeteksi hama dan penyakit secara cepat dan akurat. Proses identifikasi yang masih dilakukan secara manual seringkali menimbulkan keterlambatan dan potensi kesalahan, sehingga dibutuhkan sistem digital yang dapat menyediakan informasi diagnostik yang akurat. Penelitian ini bertujuan untuk mengembangkan aplikasi web untuk manajemen tanaman dan diagnosis hama-penyakit menggunakan metode Rapid Application Development (RAD). Metode RAD dipilih karena memungkinkan pengembangan sistem yang lebih cepat melalui pembuatan prototipe iteratif dan keterlibatan pengguna secara aktif, sehingga menghasilkan aplikasi yang lebih sesuai dengan kebutuhan lapangan. Aplikasi ini menyediakan fitur untuk mengelola data tanaman, mencatat gejala, dan menentukan hasil diagnostik, lengkap dengan tingkat keyakinan dan rekomendasi penanganannya. Hasil pengujian menunjukkan bahwa semua fungsi utama bekerja dengan baik dan dapat mendukung proses identifikasi dengan lebih mudah dan efisien. Pengujian penerimaan pengguna juga menunjukkan respon yang sangat positif, dengan 86,4% responden menyatakan “Sangat Setuju” terhadap kemudahan penggunaan dan manfaat aplikasi. Secara keseluruhan, aplikasi ini dinilai layak dan efektif sebagai solusi pendukung keputusan dalam pengelolaan tanaman dan deteksi dini hama dan penyakit, serta berpotensi mendukung penerapan pertanian presisi.

SISTEM MONITORING CHINNING UP DAN PULL UP BERBASIS INTERNET OF THINGS

intan ayu, Tasya Ananda, Riki Afriansyah, Ocsirendi — Sun, 06 Sep 2026 17:45:51 +0800

This study was conducted to design and develop an automated counting system for Chinning Up and Pull Up exercises based on the Internet of Things, aimed at improving the accuracy and efficiency of physical fitness assessment. The proposed system integrates a SHARP GP2Y0A21 infrared sensor to detect movement repetitions and an electromyography sensor to measure biceps and triceps activity. All captured data are processed by an ESP32 microcontroller and transmitted directly to Firebase Realtime Database, then displayed through a web interface developed using Laravel. The system supports three user roles—admin, supervisor, and athlete—each responsible for account management, training monitoring, and access to performance records. Testing procedures were carried out using Blackbox Testing and User Acceptance Test to evaluate measurement accuracy and usability. The results indicate that the system can identify repetitions with an accuracy of 96.8% and measure muscle activity with an accuracy of 94.5%. Training data are presented in real time and stored as monitoring records. Based on these findings, the system is considered effective in providing an objective, measurable, and integrated evaluation mechanism for exercise performance

SISTEM KLASIFIKASI SAMPAH ORGANIK, ANORGANIK, DAN BAHAN BERBAHAYA BERACUN (B3)

Sun, 06 Sep 2026 17:47:31 +0800

Penelitian ini mengembangkan sistem klasifikasi sampah real-time untuk sampah organik, anorganik, dan bahan berbahaya beracun (B3) di Jalan Timah Sungailiat, Bangka Belitung, Indonesia menggunakan YOLOv11 untuk mengatasi pencemaran lingkungan akibat pengelolaan sampah yang tidak tepat. Dataset khusus sebanyak 5.000 gambar yang seimbang pada kondisi siang, senja, dan malam dikumpulkan untuk melatih YOLOv11 sehingga mampu menangani variasi pencahayaan. Metodologi meliputi pra-pemrosesan (ubah ukuran 640×640 piksel, normalisasi, augmentasi data), pelatihan YOLOv11 pada dataset seimbang, serta evaluasi menggunakan metrik mean Average Precision (mAP@0.5), presisi, recall, dan F1-score. Sistem mencapai mAP@0.5 sebesar 70%, presisi 69%, recall 70%, dan F1-score 0,70 dengan kecepatan 43 frame per detik (FPS) serta 102 GFLOPs sehingga dapat dijalankan pada GPU kelas menengah. Meskipun akurasi masih moderat karena variasi pencahayaan dan oklusi, kerangka kerja ini menawarkan solusi hemat biaya dan skalabel untuk pengelolaan sampah kota pintar, mengurangi tenaga sorting manual serta mendukung inisiatif daur ulang. Perbaikan mendatang akan fokus pada peningkatan performa malam hari dan penanganan.

EXPLAINABLE MACHINE LEARNING FOR PHISHING URL DETECTION USING SHAP INTERPRETATION

Sun, 06 Sep 2026 17:49:18 +0800

Phishing attacks delivered through malicious URLs represent an increasingly prevalent cyber threat capable of causing significant harm to users. Although machine-learning–based phishing detection has been widely explored, most existing models still operate as black boxes, making their classification decisions difficult to interpret. This study proposes an Explainable Machine Learning framework for phishing URL detection by integrating five algorithms—XGBoost, Random Forest, Gradient Boosting, Decision Tree, and K-Nearest Neighbors—augmented with SHAP (SHapley Additive Explanations) for interpretability. The dataset includes structural URL features such as character length, special symbol counts, number of subdomains, and string entropy. Model performance was evaluated using accuracy, precision, recall, F1-score, and confusion matrix to enable comparative assessment among algorithms. The results show that XGBoost achieves the best performance, obtaining 97.8% accuracy, an F1-score of 0.976, and stable predictions across all classes. Random Forest ranks second with 96.4% accuracy, followed by Gradient Boosting at 95.7%. Meanwhile, Decision Tree and KNN exhibit lower performance due to their higher sensitivity to data variation. SHAP analysis reveals that the most influential features in phishing prediction include URL length, special character frequency, entropy levels, and the number of subdomains. These findings demonstrate that integrating XAI not only enhances model transparency but also ensures that phishing detection systems remain accurate, interpretable, and accountable.

SISTEM DETEKSI OBJEK REAL-TIME BERBASIS WEB DENGAN OUTPUT AUDIO UNTUK TUNANETRA

Mon, 07 Sep 2026 21:59:08 +0800

Limited access to visual information is a major problem faced by visually impaired individuals, making it difficult to recognize surrounding objects and identify currency denominations independently. This issue highlights the need for a system capable of presenting visual information in a more accessible form. Therefore, this study aimed to develop a real-time object detection system based on a web platform with audio output to improve accessibility. The method included requirement analysis, system design, implementation using digital image processing and deep learning techniques, and system testing. The model applied a detection confidence threshold of ≥ 70% and achieved recognition accuracy of ≥ 85% under normal conditions. The system was also integrated with text-to-speech technology to deliver detection results in audio form. The results indicated that the system operated effectively in real-time with good responsiveness through a web browser without requiring additional installation. Therefore, the developed system proved capable of enhancing accessibility and supporting the independence of visually impaired users.

PEMODELAN DECISION TREE YANG INTERPRETATIF UNTUK KLASIFIKASI TINGKAT DEPRESI PADA MAHASISWA MENGGUNAKAN DATA PHQ-9

Munirah, Sunardi, Abdul Fadlil — Thu, 10 Sep 2026 06:31:46 +0800

This study aims to develop an interpretive Decision Tree model to identify depression levels in college students using Patient Health Questionnaire-9 (PHQ-9) data. Depression in college students is a growing mental health issue, while most machine learning models are still difficult to interpret. Therefore, this study uses Decision Tree as an explainable artificial intelligence (XAI) approach that is able to produce transparent and easy-to-understand decision rules. The research method uses a supervised learning approach with PHQ-9 data represented in text form and converted into numeric using Label Encoding. The target variable is formed based on the depression level category from the total PHQ-9 score. The model was evaluated using a 5-fold cross-validation technique with accuracy, precision, recall, and F1-score metrics. The results showed that the model achieved an accuracy of 54.4% in cross-validation and 68% in training data, with a macro F1-score of 0.67. Feature importance analysis showed that the PHQ2 variable was the most dominant factor in classifying depression. In addition, the Decision Tree structure was able to provide a clear interpretation of the pattern of depressive symptoms in college students. This study shows that Decision Tree has the potential to support early detection of student depression in a more transparent and interpretable manner.

DESIGN OF SMART HYDROPONICS INDOOR APPLICATION BASED ON THE INTERNET OF THINGS USING THE PROTOTYPING METHOD

Bagus Muhammad Akbar, Abdul Fadlil, Sunardi — Thu, 10 Sep 2026 06:33:05 +0800

The growing population and limited land availability are driving the development of efficient alternative farming methods. Indoor hydroponics is an innovative soilless cultivation solution; however, manually managing environmental parameters such as pH, TDS/EC, temperature, humidity, CO₂, and tVOC is inefficient. This study designs the SHIRi (Smart Indoor Hydroponics) system based on the Internet of Things (IoT) using the prototyping method. The system utilizes an ESP32 microcontroller connected to pH, TDS/EC, DS18B20, DHT21, and SGP30 sensors, along with actuators including peristaltic pumps and a grow light. Data is transmitted via the MQTT protocol to a Mosquitto broker, stored in a Supabase database, and visualized through a responsive real-time web dashboard. The system supports two operating modes: Manual and Auto (rule engine). The prototyping method was applied iteratively in three cycles. Testing showed average pH sensor error of 0.1 units, TDS/EC 1.2ppm, water temperature 0.2°C, and humidity 1.5% so it has accuracy 97%. All dashboard features were successfully validated with an average update delay of 1.3 seconds. This system is expected to support autonomous and precision indoor hydroponics management.

PEMETAAN ASPEK LAYANAN SENTUH TANAHKU MELALUI ANALISIS SENTIMEN LEKSIKON DAN MACHINE LEARNING

Kusmiarto, Wahyuni Wahyuni — Thu, 10 Sep 2026 06:35:25 +0800

Sentuh Tanahku is one of the digital land information service instruments initiated by the Ministry of Agrarian Affairs and Spatial Planning/National Land Agency in 2017. Since its launch, the application has been downloaded more than one million times and has received approximately 47,000 user ratings on the Google Play Store. This study examined 19,927 Google Play Store reviews from September 21, 2017 to May 13, 2026 to identify sentiment patterns, classification model performance, and the service aspects that most frequently influenced user evaluations. The analysis involved text preprocessing, rating-based labeling, sentiment lexicon analysis, TF-IDF representation, Multinomial Naive Bayes, Linear Support Vector Machine, and service-aspect mapping. The results showed a polarized rating pattern. Five-star reviews accounted for 57.93%, while one-star reviews reached 23.97%, with an average rating of 3.70. Lexicon analysis identified 9,605 positive reviews, 6,537 negative reviews, and 3,785 neutral reviews. Linear SVM produced the best macro F1-score of 62.29%. The most prominent complaints concerned account authentication, application performance, and the connectivity between land certificates and parcel data. These findings indicate that the quality of land service applications depends on technical stability, clear verification flows, and service data readiness.