Jurnal INSYPRO (Information System and Processing)

RANCANG BANGUN APLIKASI E-PRAKERIN PADA SMKN 3 LUWU BERBASIS WEB

Ulvah Ulvah — 2024-10-26

Information technology that is developing so rapidly requires all fields in human life to utilize technology to help people's daily activities. Likewise, the education sector must follow the momentum of the development of the era of increasingly advanced technology use which will provide convenience for all parties. SMKN 3 Luwu is a vocational high school that collaborates with industry through an industrial work practice program or commonly called prakerin during education. SMKN 3 Luwu needs an application that supports the management of pre-kindergarten. The Prakerin registration process for SMKN 3 Luwu is still carried out by students going to the Prakerin organizing committee to propose a location or place where they want to do Prakerin later, this is considered inefficient by looking at the current use of technology that can be used to efficiently register for students who want to do Prakerin. Currently, the use of information technology (computers and the internet) has been adjusted to its needs in improving the performance of admins in certain schools. The information system development methodology used is the Waterfall model. The information system is designed and built based on a website using the PHP programming languages MyAdmin and MySQL as its database. By designing and building this application, it will make it easier for students and the committee in the pre-registration process.

PERANCANGAN LAMPU JALAN BERBASIS SOLAR CELL DI LABORATORIUM TEKNIK UNIVERSITAS ISLAM MAKASSAR

Sriwati — 2024-10-28

Indonesia is located on the equator, so Indonesia has abundant sources of solar energy with an average solar radiation intensity of around 4.8 kWh/m2 per day throughout Indonesia. This research aims to make the Sollar Cell an alternative for Public Street Lighting (PJU) which is a Solar Public Street Lighting (PJUTS) system, the ability of this system to generate and store electrical energy makes it a reliable system to supply street lamp energy. Testing is carried out with two types of tests, namely primary data measurement and secondary data measurement. In the field test, it is carried out through direct measurement of the potential for solar radiation and at the location of the street light pole to be installed, while secondary data is obtained from a body or authority that has the authority to publish radiation data, in the case we use satellite image data from NASA through the NASA-Langley Distributed Archive. The test was carried out by testing where the street lamp was tested for one day by being directly loaded with the battery and the two solar panels to charge the battery. In field testing, the panel will charge the battery with an average input of 298.79 W and an output of 298.76 with an average effectiveness of 10.02%, the battery is charged with LED lights at night which uses 7% of the total electrical power needed, which is 30 Watts from 300 Watts. When testing in the field peak load or when all loads are operating has never occurred, when a peak load occurs , the required electrical power is 380.6 Watts.

Desain Model Pembelajaran SAVAR (Substitution, Augmentation, Virtual Learning, Apply, Re-evaluation) Berbasis Augmented Reality

A. Muhammad Syafar — 2024-10-30

Model pembelajaran SAVAR (Substitution, Augmentation, Virtual Learning, Apply, Re-evaluation) berbasis Augmented Reality (AR) merupakan inovasi dalam bidang pendidikan yang bertujuan meningkatkan hasil belajar melalui pendekatan interaktif dan teknologi canggih. Penelitian ini bertujuan untuk merancang dan mengimplementasikan model SAVAR yang mengintegrasikan AR dalam proses pembelajaran untuk mendukung pemahaman konsep secara mendalam dan meningkatkan motivasi belajar. Model ini terdiri dari lima tahap utama: Substitution (penggantian metode konvensional dengan AR), Augmentation (peningkatan visualisasi konten), Virtual Learning (simulasi dalam lingkungan AR), Apply (penerapan konsep dalam konteks praktis), dan Re-evaluation (evaluasi ulang untuk mengukur pemahaman peserta didik). Studi ini menggunakan metode Research and Development (R&D) dengan pendekatan uji eksrimen. Hasil penelitian menunjukkan bahwa model SAVAR berbasis AR berperan signifikan dalam meningkatkan keterlibatan siswa, pemahaman konsep, serta hasil belajar secara keseluruhan. Dengan hasil yang positif, model ini memiliki potensi besar untuk diimplementasikan secara luas sebagai strategi pembelajaran yang memanfaatkan teknologi digital di era modern.

Kata Kunci: Model SAVAR, Augmented Reality, Pembelajaran Interaktif, Hasil Belajar, Teknologi Pendidikan.

MENINGKATKAN PENGUASAAN DIAGNOSTIK MESIN KAPAL MELALUI APLIKASI PEMBELAJARAN BERBASIS ANDROID DAN SISTEM PAKAR

Abdul Basir — 2024-11-08

Penelitian ini mengembangkan aplikasi pembelajaran berbasis Android yang mengintegrasikan sistem pakar untuk meningkatkan penguasaan diagnostik mesin kapal di kalangan taruna pada mata kuliah Engine Simulator. Aplikasi ini dirancang untuk membantu taruna memahami dan mendiagnosis masalah mesin secara mandiri, dengan pendekatan Research and Development (R&D) menggunakan model Prototyping, meliputi tahap analisis kebutuhan, pengembangan, evaluasi, dan pengujian. Hasil uji coba di Politeknik Ilmu Pelayaran Makassar menunjukkan bahwa aplikasi ini memudahkan pengguna dalam simulasi situasi nyata, terbukti dari hasil System Usability Scale (SUS) yang mengindikasikan kegunaan yang cukup baik meskipun memerlukan beberapa perbaikan dalam konsistensi fitur dan navigasi. Secara keseluruhan, aplikasi ini diharapkan dapat meningkatkan keterampilan diagnostik taruna dan mempersiapkan mereka menghadapi tantangan di industri pelayaran.

Kata Kunci: Media Pembelajaran, Android, Sistem Pakar, Diagnostik Mesin Kapal, Pendidikan Maritim

PERANCANGAN APLIKASI MONITORING PROSES BIMBINGAN SKRIPSI BERBASIS WEB PADA PROGRAM STUDI SISTEM INFORMASI FAKULTAS SAINS DAN TEKNOLOGI UIN ALAUDDIN MAKASSAR

Farida Yusuf — 2024-11-13

Penelitian ini muncul dari kebutuhan akan peningkatan efisiensi dan efektivitas dalam proses bimbingan skripsi di Program Studi Sistem Informasi Fakultas Sains dan Teknologi UIN Alauddin Makassar. Saat ini, proses bimbingan skripsi masih menghadapi beberapa tantangan, seperti kesulitan dalam pemantauan perkembangan mahasiswa, kurangnya transparansi antara mahasiswa dan dosen pembimbing, serta keterbatasan akses informasi terkait progres skripsi. Metode dan teknik pengumpulan data mencakup berbagai cara untuk mengumpulkan informasi, baik dalam bentuk kuantitatif maupun kualitatif. Metode kuantitatif, seperti survei dan eksperimen, mengandalkan data numerik yang dapat diukur dan dianalisis secara statistik. Sebaliknya, metode kualitatif, seperti wawancara mendalam dan observasi partisipatif, berfokus pada pengumpulan data non-numerik untuk memahami fenomena secara mendalam. Aplikasi ini dirancang untuk memenuhi kebutuhan monitoring proses bimbingan skripsi yang efektif dan efisien. Sistem ini menyediakan fitur-fitur yang memudahkan dosen pembimbing dalam mengelola dan memantau perkembangan skripsi mahasiswanya.

Efektivitas Game Edukasi Matematika Berbasis Android dan Desktop untuk Meningkatkan Kemampuan Kognitif Siswa

Syahbudin — 2024-11-28

The integration of technology in education, especially through educational games, has emerged as an alternative approach to motivating students, particularly those with special needs, to learn. In this research, a mathematics educational game was designed and implemented on both Android and desktop platforms to assess its impact on the cognitive abilities of students in special education (SLB). The study utilized a quasi-experimental method, with one group of students using the educational game and a control group using traditional teaching methods. Statistical analysis was applied to compare cognitive improvements between the two groups. The findings revealed that students who used the mathematics educational game on Android and desktop showed significantly greater cognitive gains compared to those taught using conventional methods. This suggests that educational games can be a powerful tool for enhancing mathematics learning in special needs students by improving conceptual understanding, critical thinking, and problem-solving skills. The results highlight the importance of further developing and implementing educational games in special education to support cognitive growth. Therefore, technology-driven educational games can significantly enhance learning quality and offer a more interactive and enjoyable educational experience for students

Pengembangan Aplikasi Pencarian Ayat Terintegrasi dalam Kajian Sains dan Teknologi

Nahrun Hartono — 2024-11-30

This study explores the key issue of ineffective integration between science and technology studies and religious values at Universitas Islam Negeri (UIN) Alauddin Makassar, with a focus on the Faculty of Science and Technology (FST). Although there have been efforts to integrate these fields, inconsistencies and variations persist, particularly in how Qur'anic verses are used in scientific research. Often, these verses are added superficially without thorough analysis, compounded by students' challenges in manually finding relevant verses. To address this challenge, the study developed a digital platform aimed at easing the search and integration of religious verses within scientific and technological research. The approach included analyzing user needs, gathering relevant verse data, and testing the platform's effectiveness and user-friendliness. The findings indicate that the new platform significantly improves the integration of science and technology studies with religious values. Users, including students and researchers, found the platform to be an effective tool for accessing and incorporating Qur'anic verses into their research. As a result, this platform shows promise as a widely adoptable model for fostering a more robust and enduring integration in higher education across Indonesia.

IMPLEMENTASI SISTEM MONITORING PELAKSANAAN KULIAH KERJA NYATA BERBASIS APLIKASI MOBILE PADA UNIVERSITAS ISLAM NEGERI ALAUDDIN MAKASSAR

Faisal Akib — 2024-12-04

Penelitian ini bertujuan untuk membangun teknologi monitoring berbasis aplikasi mobile guna memantau keberadaan dan kegiatan mahasiswa di lokasi Kuliah Kerja Nyata (KKN) di Universitas Islam Negeri (UIN) Alauddin Makassar. Sistem ini diharapkan dapat meningkatkan validitas dan akurasi monitoring lapangan, serta mempermudah dosen pembimbing dalam melakukan pengawasan terhadap aktivitas mahasiswa selama periode KKN. Metode pengembangan sistem yang digunakan adalah model waterfall, yang mencakup tahapan perencanaan, analisis kebutuhan, desain sistem, implementasi, dan pengujian. Hasil dari penelitian ini adalah sebuah aplikasi mobile yang terintegrasi dengan sistem akademik UIN Alauddin, hal ini akan memungkinkan pelaksanaan monitoring KKN dilakukan secara real-time dan efisien.

ANALISIS PERFORMA CONVOLUTIONAL NEURAL NETWORK DENGAN HYPERPARAMETER TUNING DALAM MENDETEKSI GAMBAR DEEPFAKE

Darmatasia Darmatasia — 2024-11-28

This research analyzes the performance of Convolutional Neural Network (CNN) in detecting deepfake images with a focus on hyperparameter tuning. The study consists of two classes: fake images and real images, with each class containing 5000 data samples. Hyperparameter tuning is conducted using the Keras-tuner library, a framework used for automatic hyperparameter tuning on models built with Keras, eliminating the need for manual trial and error tuning. The hyperparameter search strategy employed is random search. The results of the study indicate that hyperparameter tuning significantly improves the model's detection accuracy. Various experiments were conducted to evaluate the impact of hyperparameter settings, such as the number and size of filters, learning rate, and optimizer. Analysis of different optimizers showed significant variations in performance, with Adam Optimizer achieving the highest accuracy of 83% using a combination of 32 filters sized 3x3 in the first layer and 128 filters sized 5x5 in the second layer. RMSProp and AdamW each achieved 82% accuracy, SGD Optimizer achieved 75% accuracy, while Adadelta Optimizer achieved 71% accuracy. The findings of this study affirm that the selection of optimizer and appropriate hyperparameter settings have a significant impact on the model's performance in detecting patterns in the data. This study also emphasizes the importance of optimizing filters and sizes in each layer to enhance model accuracy.

Facial Expression Detection System Based on Convolutional Neural Network (CNN) for Human Emotion Recognition

Arya Wibawa. Ar — 2024-11-25

The development of human facial expression detection systems has become a growing research topic, particularly in efforts to create applications capable of automatically understanding and responding to human emotions. This research aims to develop and evaluate a human facial expression detection system using the Convolutional Neural Network (CNN) method. The dataset used consists of facial images with various expressions sourced from diverse origins. The data undergoes several preprocessing stages, including normalization, augmentation, and splitting into training and test sets. This study employs several CNN architectures to identify emotions such as happy, sad, angry, and scared. Testing is conducted using various parameters, including training and test data splits, as well as different CNN architectures. The results show that the CNN model can achieve over 90% accuracy on training data, with the best performance on the "Happy" emotion, achieving an f1-score of 0.93. However, there is a decrease in accuracy on validation data, with an overall average accuracy of 78%, indicating challenges in model generalization. Additionally, the "Sad" emotion has the lowest recall of 0.49, indicating the need for model improvement in classifying specific emotions. This study contributes to the development of CNN-based facial expression detection systems, but further exploration of more complex architectures, evaluation with diverse datasets, and real-time testing are needed to improve system performance.

Topic Modelling of Student Suggestions on SIMAK UNISMUH Using BERTopic

Lis Indriani — 2024-11-28

This study examines the use of the BERTopic algorithm for topic modeling on student feedback data collected through the SIMAK UNISMUH. The research aims to identify and visualize thematic patterns in student feedback to improve academic services and campus facilities. This study utilizes Natural Language Processing (NLP) techniques, particularly BERTopic, which combines the advantages of Bidirectional Encoder Representations from Transformers (BERT) with clustering algorithms to produce contextually rich and easily interpretable topic representations. The research data comprises 232,430 feedback entries that were processed to remove noise and irrelevant information, resulting in 26,009 valid entries. These entries were then processed using the BERTopic algorithm, generating nine distinct topics related to various aspects of academic life, including teaching methods, campus facilities, and administrative services. The coherence score of 0.637 indicates strong internal consistency within the identified topics, while the analysis reveals key areas where the university can enhance its services. The findings from this study provide actionable insights for university administrators, enabling them to make informed decisions and improve student academic performance. Additionally, this research contributes to the field of topic modeling in educational contexts and demonstrates the effectiveness of BERTopic in processing large-scale textual data.

PENGGUNAAN WORD EMBEDDING WORD2VEC DALAM PENGEMBANGAN MODEL CNN STUDY KASUS ANALISIS SENTIMEN TEMPAT WISATA MAKASSAR

Titin Wahyuni — 2024-11-28

This research aims to evaluate the effect of applying the Word Embedding Word2Vec technique on the accuracy of the Convolutional Neural Network (CNN) model in sentiment analysis of tourist attraction reviews in Makassar. Sentiment analysis is the process of identifying and classifying emotions or opinions contained in text, whether positive, negative, or neutral. The research dataset consists of 4500 tourist attraction reviews taken from Google Maps. The data was then processed using the Word2Vec technique to generate vector representations of the words in the reviews. These vectors were used as input to the CNN model for sentiment classification. The study employed three data splitting scenarios, namely 90:10, 80:20, and 70:30, for training and testing the model. The results showed that the application of Word2Vec in the CNN model improved sentiment prediction accuracy. The CNN model with Word2Vec achieved an accuracy of 79%, while the CNN model without Word2Vec only reached an accuracy of 74%. This indicates that the use of Word2Vec can enhance the performance of the model in classifying sentiment in tourist attraction reviews.