Claim Missing Document
Check
Articles

Found 8 Documents
Search

TRANSPORTASI DAN NAVIGASI WISATA DENGAN KENDALI ROBOTFUZZY Naili Suri Intizhami; Faisal; Faisal Akib
AGENTS: Journal of Artificial Intelligence and Data Science Vol 1 No 1 (2021): September - Februari
Publisher : Prodi Teknik Informatika Universitas Islam Negeri Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (307.93 KB) | DOI: 10.24252/jagti.v1i1.17

Abstract

The automatic transportation robotis one of the mobile robotsdesigned to be able to take visitors around the zoo area. This robot uses the Arduino Nano as a robot control system, uses a DC motor as a wheel drive motor and is also equipped with a proximity sensor (ping) which will read if there are obstacles in front of the robot, because the zoo has the concept of freeing the animals from roaming around, so that when an animal is is on the track, this robot can find out and immediately stop so there is no collision. The research method used is quantitative research. The quantitative research conducted is an experimental research method. By conducting experiments on control variables (input) to analyze the resulting output. The result of this research is an automatic transportation robotwith8photodiodesensorsaslinefollowersbyimplementingfuzzy logicasthecontrolsystem
Pelatihan Model Pembelajaran Interaktif Berbasis Aplikasi SLIDO di SMAN 5 Parepare Eka Qadri Nuranti; Naili Suri Intizhami; Putri Ayu Maharani; Mardhiyyah Rafrin; Muh. Agus
Jurnal Pengabdian Masyarakat Bangsa Vol. 1 No. 5 (2023): Juli
Publisher : Amirul Bangun Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59837/jpmba.v1i5.190

Abstract

Seorang pendidik selalu berusaha menciptakan suasana kelas yang menarik, kreatif, dan efektif sepanjang jadwal pembelajaran. Menyadari pentingnya keterlibatan siswa dalam proses belajar-mengajar, diperlukan penerapan metode pembelajaran interaktif yang memungkinkan terjadinya komunikasi dua arah antara guru dan siswa. Hal ini memungkinkan para siswa untuk aktif berpartisipasi dalam proses belajar-mengajar, dan menyampaikan pendapat, serta respon terhadap materi yang diajarkan. Namun, tanpa dukungan teknologi dan media yang tepat, pelaksanaan metode ini menjadi sulit dan menghambat tercapainya tujuan pembelajaran secara optimal. Meskipun banyak pendidik sudah familiar dengan konsep dan model pembelajaran interaktif, penerapannya masih belum mencapai potensinya dengan baik. Oleh karena itu, kegiatan pengabdian yang penulis lakukan difokuskan pada pemanfaatan media pembelajaran interaktif dengan menggunakan platform SLIDO, yang telah terbukti efektif dan menarik bagi para penggunanya. Kegiatan pengabdian ini diimplementasikan di sebuah Sekolah Menengah Atas, dengan tujuan untuk memberikan pelatihan dan pembekalan kepada para guru dalam mengoptimalkan penggunaan media interaktif ini.
Multi-Head Attention in Residual Networks to Improve Coral Reef Structure Classification Nuranti, Eka Qadri; Intizhami, Naili Suri; Tassakka, Muhammad Irpan Sejati; Areni, Intan Sari; Al Ghozy, Osama Iyad; Jefri, Muhammad Rivaldi
JOIV : International Journal on Informatics Visualization Vol 8, No 2 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.2.2392

Abstract

Residual Networks (ResNet) mark a crucial advancement in convolutional neural network architecture, effectively tackling challenges like vanishing gradients for improved pattern detection in various image classification tasks. This study introduces a novel adaptation of the ResNet50 architecture that integrates a multi-head attention mechanism (MHA), coined MHA-ResNet50, for discerning coral reef structures within images. Strategic modifications are applied to the input of each stage, leading to the development of an MHA block, which is augmented by separable convolution. The deliberate inclusion of the MHA block at various stages in identity-block Resnet50, in adherence to multiscale gate principles, precedes its traversal through fully connected layers. Furthermore, we implemented the Stratified K-fold concept to ensure that each fold has a comparable proportion of each class. We successfully assessed the efficacy of the MHA-Resnet50 model in several MHA-block placement scenarios and saw improvements in the accuracy of coral reef structure predictions. The most optimal results were achieved by incorporating four attention blocks (MHA-ResNet50-4), yielding an accuracy rate of 85.23% in recognition of coral structure images, comprising a mere 409 images. This model showcases adaptability to small datasets while delivering commendable performance. The ResNet50 architecture undergoes enhancement in our proposed model by integrating multi-head attention, separable convolution, and multiscale gate principles. The MHA-ResNet50 model substantially advances accurately predicting coral reef structures, demonstrating adaptability to limited datasets. Future lines of this research involve digging deeper into the model design and using more significant amounts and classes of data to strengthen a more comprehensive range of generalizations.
OPTIMIZATION OF BACKTRACKING ALGORITHM WITH HEURISTIC STRATEGY FOR LOGIC-BASED SORTING PUZZLE GAME SOLVING Nuranti, Eka Qadri; Intizhami, Naili Suri; Hasanah, Primadina
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 6 (2024): JUTIF Volume 5, Number 6, Desember 2024
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.6.4031

Abstract

Puzzle Game Sorting is a logic-based puzzle game where players must transfer colored balls into tubes until each tube contains only one color. Although it appears simple, the game becomes increasingly challenging at higher levels, testing players’ logical thinking and patience. This study proposes using the backtracking algorithm combined with optimization strategies, such as conflict heuristics and lookahead, to address players’ challenges at advanced levels. The test results indicate that the optimized backtracking algorithm can solve the game faster and with more efficient steps compared to manual methods. Specifically, heuristic optimization strategies significantly improved performance, reducing execution time by up to 91.4% and the number of steps by up to 76.9% at the most complex levels. These findings demonstrate that combining the backtracking algorithm and optimization strategies is an effective solution for solving puzzles in Sorting, particularly at levels with increasing complexity.
Improving Semantic Segmentation of Flood Areas Using Rotation and Flipping-Based Feature Augmentation Intizhami, Naili Suri; Nuranti, Eka Qadri; Bahar, Nur Inaya
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 3 (2025): JUTIF Volume 6, Number 3, Juni 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.3.4564

Abstract

Semantic segmentation is one of the powerful methods for analyzing flood video or picture data captured by smartphones. However, achieving accurate semantic segmentation requires the application of several methods. In this work, we address the task of feature augmentation approach using rotation (90°, 180°, 270°) and flipping (horizontal, vertical) to improve semantic segmentation of flood areas in Parepare city using a Fully Convolutional Network (FCN). The experimental results demonstrate that the best augmentation scenario 270° rotation achieved an accuracy of 88%  and 90° rotation achieved an mean Intersection over Union (mIoU) of 43%, significantly outperforming the baseline FCN model without augmentation, which achieved 86% accuracy and 35% mIoU.  
Pelatihan Pembuatan Modul Pembelajaran Interaktif Berbasis Aplikasi Quizizz dan Google Slide bagi Guru SMAN 5 Parepare Naili Suri Intizhami; Indar Chaerah Gunadin; Eka Qadri Nuranti; Putri Ayu Maharani; Mardhiyyah Rafrin; Muh Agus; Osama Iyad Al Ghozy; Nur Inaya Bahar; Muhammad Rivaldi Jefri; Muhammad Aldi Alfatih
Jurnal Pengabdian UNDIKMA Vol. 4 No. 4 (2023): November
Publisher : LPPM Universitas Pendidikan Mandalika (UNDIKMA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33394/jpu.v4i4.9218

Abstract

This community service project aims to enhance the knowledge and skills of SMAN 5 Parepare teachers in developing interactive learning modules based on Google Slide and Quizizz applications and implementing Image Recognition technology. This method of implementation used training and reinforcement. This activity's evaluation instrument employed questionnaires, which were then descriptively analyzed using pre-test and post-test data. The results of this study indicated that teachers at SMAN 5 Parepare could develop interactive learning modules based on Google Slides and Quizizz adapted to the subject matter being taught. 38% of all questions answered correctly by the participants in this activity improved their teacher's skills.
Pelatihan MIT App Inventor sebagai Upaya Meningkatkan Kemampuan Berpikir Logis Siswa SMAN 4 Parepare Maharani, Putri Ayu; Gunadin, Indar Chaerah; Intizhami, Naili Suri; Nuranti, Eka Qadri; Rafrin, Mardhiyyah; Agus, Muh.; Iskandar, M. Fauzan; Yunus, Sitti Rahma; Al-Fauzi S., Muhammad Faruq; Tunru, Muh. Abubakar
Jurnal Pengabdian UNDIKMA Vol. 5 No. 1 (2024): February
Publisher : LPPM Universitas Pendidikan Mandalika (UNDIKMA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33394/jpu.v5i1.9786

Abstract

This community service activity aims to improve the logical thinking abilities of SMAN 4 Parepare students by teaching the application of mathematical logic in compiling computer instructions based on MIT App Inventor. The method for implementing this service was problem-based learning training by taking the example of the traditional game of rock-paper-scissors as a learning case. Next, create a rock-paper-scissors game program using MIT App Inventor as a student learning experience in applying mathematical logic concepts. The evaluation instrument employed was a questionnaire to collect pre-test and post-test results, which were then analyzed using descriptive statistics and paired sample t-tests. The results of this service showed an increase in the average participant score on the post-test results, where the average pre-test score was 7.24 out of 15, while the average post-test score was 9.17 out of 15.
Pelatihan Pemanfaatan Teknologi Augmented Reality dan Virtual Reality Sebagai Media Pembelajaran Inovatif bagi Guru di SMP Negeri 10 Parepare Rafrin, Mardhiyyah; Maharani, Putri Ayu; Muh. Agus; Amar, Muh. Ikhsan; Intizhami, Naili Suri; Nuranti B, Eka Qadri; Bahar, Nur Aini Sri Oktaviani; Armansyah, Muhammad Dicky; S., St. Aisyah; Kandi, Damar; Malika, Saphira Nur
Jurnal Pengabdian UNDIKMA Vol. 6 No. 4 (2025): November
Publisher : LPPM Universitas Pendidikan Mandalika (UNDIKMA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33394/jpu.v6i4.18210

Abstract

This community service program aims to enhance teachers’ skills in utilizing AR and VR technologies as innovative instructional media in the classroom. The program was implemented using a structured training model involving 20 teachers from SMPN 10 Parepare. The evaluation instrument consisted of a questionnaire, and the responses were analyzed using descriptive techniques. The results show that the training was highly aligned with teachers’ needs at the school (average response score: 4.75), easy to follow (4.66), very beneficial in improving the quality of learning (4.85), and motivating for teachers to adopt AR and VR technologies in their instructional practices (4.58). Overall, this training activity provided a significant contribution to enhancing teachers’ digital literacy, particularly in the use of innovative learning media.