Claim Missing Document
Check
Articles

Found 29 Documents
Search

Sistem Monitoring Penyiraman Tanaman Berbasis Android Menggunakan Protokol MQTT Lusiani; Munawir; Novianda
JURUTERA - Jurnal Umum Teknik Terapan Vol 7 No 01 (2020)
Publisher : Fakultas Teknik Universitas Samudra

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55377/jurutera.v7i01.2417

Abstract

Tanaman adalah tumbuhan yang dibudidayakan agar bisa di ambil manfaatnya. Dalam hal melakukan perawatan serta penyiraman tanaman, sangat membutuhkan waktu serta proses yang lama sehingga kemajuan teknologi di bidang pertanian sangatlah diperlukan untuk meminimalisir waktu sehingga waktu yang diperlukan lebih efisien Tentunya, hal ini sangat membutuhkan suatu sistem teknologi yang mampu mengakomodir semua hal yang berhubungan dengan penyiraman tanaman secara otomatis. Sistem penyiraman tanaman ini merupakan sistem untuk penyiraman tananan yang dapat diatur waktu penyiraman sesuai jadwal ataupun kapan saja yang diinginkan yang terintegrasi ke smartphone atau android dengan menggunakan nodeMCU ESP 8266. Pada penelitian ini sistem penyiram tanaman berbasis android pada bibit terong, cabai dan tomat berjalan dengan baik dengan tingkat keberhasilan 88,05%.
Aplikasi Informasi Kegiatan Webinar Berbasis WEB Rani Khairani; Izzhan Hawary; Nida Nafila; Isra Prastiana Yannas; Khairinnisah; Syaila Fannisa; Munawir
JURUTERA - Jurnal Umum Teknik Terapan Vol 8 No 02 (2021)
Publisher : Fakultas Teknik Universitas Samudra

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55377/jurutera.v8i02.4944

Abstract

Webinars are inseparable activities from the world of education in higher education. However, there are still many webinars that hold conventionally starting from the announcement of the event, registration of participants, to the process of implementing the event. So that it feels less effective. Therefore, this application was created to make it easier to provide information to all students about the latest webinar in the University so that publications can be effective and efficient, this design can help solve problems that occur when webinars are held, such as attendance, information about presenters and others. The research method used in designing this web-based application is a field study, namely by direct observation, interviews with related parties, and also by conducting documentation to obtain the required information. In addition, the author also conducted various discussions as well as from various media containing the information needed, analyzing needs, and designing. The second stage is to build the system using the Waterfall type SDLC (System Development Life Cycle) method. The Waterfall Model provides a sequential or sequential software lifecycle approach starting from analysis, design, coding, testing, and maintenance.
Sistem Informasi Pengelolaan Buku Kas Mahasiswa Berbasis Web Asri Bella Sari; Munawir; Teuku Armel Fahlevi; Siti Nurchaliza; Arman Yuliando; Tawang Fadhila; Rahmina Sari Tinendung; Aulia Zahra
JURUTERA - Jurnal Umum Teknik Terapan Vol 7 No 02 (2020)
Publisher : Fakultas Teknik Universitas Samudra

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55377/jurutera.v7i02.4951

Abstract

With the internet connection, information can be accessed quickly by anyone and anywhere. As well as with automatic and integrated data processing, calculations and data storage can be carried out quickly, and the results will be known directly with accurate data. Currently, the management and recording related to cash in and cash out on campus are carried out very simply and not in accordance with existing accounting records and do not take into account the evidence that supports accounting records. In this university, there is also no financial report in any form. A system is needed that can store all transactions related to cash in and cash out to control all existing transactions and calculate cash data reports so that the owner can find out the ending balance each month. The plan of making a web application to manage cash receipt and disbursements transactions. Making this web-based application, use PHP with MySQL database. With this application, the university can find out every transaction that exists, and the owner can view cash data reports.
PENGEMBANGAN WEBSITE DAN MEDIA SOSIAL GAMPONG PONDOK PABRIK SEBAGAI MEDIA INFORMASI WARGA MENUJU DESA CERDAS Munawir Munawir; Muhammad Zeki; Irwansyah Irwanysah
Martabe : Jurnal Pengabdian Kepada Masyarakat Vol 7, No 4 (2024): MARTABE : JURNAL PENGABDIAN KEPADA MASYARAKAT
Publisher : Universitas Muhammadiyah Tapanuli Selatan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31604/jpm.v7i4.1202-1205

Abstract

Website dan media sosial merupakan salah satu media informasi yang efektif digunakan dalam era digitalisasi saat ini. Penngembangan website dan media social yang interaktif dan merupakan salah satu hal yang harus dilakukan oleh semua instansi atau pelaku usaha supaya lebih inovatif dan produktif sehingga dapat meningkatkan kemajuan di bidang ekonomi . Gampong Pondok Pabrik saat ini belum memiliki website yang memadai serta pengelolaanya belum mandiri hal ini karena kurangnya sumber daya manusia dalam pengelolaannya sehingga perlu adanya pengembangan website serta media sosial yang menarik dan interaktif sebagai media informasi warga supaya dapat terus memantau terus perkembangan desanya. Harapan dengan aktifnya website dan media sosial dapat mewujudkan gampong Pondok Pabrik menuju Gampong Cerdas atau yang lebih dikenal umumnya di seluruh Indonesia sebagai desa cerdas
Pengenalan Kata Bahasa Isyarat Fingerspelling Menggunakan Metode Convolutional Neural Network Siti Abiola Fatika Abiola; Munawir munawir; Nurul Fadillah
Jurnal Informatika dan Teknologi Komputer (J-ICOM) Vol 3 No 2 (2022): Jurnal Informatika dan Teknologi Komputer ( JICOM)
Publisher : Universitas Samudra

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55377/j-icom.v3i2.7565

Abstract

Sign language is a way of visual communication used by people who have limitations in carrying out normal verbal communication. Alphabet sign language is a basic tool used by educators to teach the deaf and mute. However, many people have difficulty communicating with these circles due to a lack of public knowledge about hand sign language. Research on hand sign language has made great progress in processing static images but is still experiencing problems due to difficulties in processing dynamic images/videos considering that most of hand sign language is represented by body, hand and facial movements. This research uses the Convolutional Neural Network (CNN) method in real time. The research was conducted through the stages of acquisition. The results of this study were conducted in 3 experimental categories, namely trials of all sign language word recognition objects based on angles obtained an accuracy of 85% and trials of all sign language word recognition objects based on distance yielded an accuracy of 93.3% and sign language word recognition based on random positions received an accuracy of 85 %.
Inovasi Teknologi Artificial Intelligence sebagai Pendukung Media Pembelajaran di SMP Negeri 1 Sungai Raya Muhammad Yakob; Chairuddin Chairuddin; Munawir Munawir
Jurnal Masyarakat Madani Indonesia Vol. 4 No. 4 (2025): November
Publisher : Alesha Media Digital

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59025/2vvwz360

Abstract

Penggunaan teknologi AI merupakan trend saat ini yang sangat membantu dalam menjalankan aktifitas manusia di semua bidang, tidak terkecuali bidang Pendidikan misalnya untuk membuat media pembelajaran yang interaktif , menarik dan cepat. SMP Negeri 1 Sungai Raya saat masih belum menggunakan teknologi AI di dalam pembelajaran di sekolah. Tim PKM Universitas Samudra melakukan kegiatan pengabdian kepada masyarakat di SMP Negeri 1 Sungai Raya dalam hal ini bertujuan meningkatkan pengetahuan dan keterampilan guru dalam pemanfaatan teknologi AI yang ada seperti Aplikasi ChatGPT, Gemini, DeepL, Grammarly. Media pembelajaran AI merupakan pendukung untuk dalam pembelajaran sehingga dapat lebih optimal, seiring perkembangan teknologi saat ini jika masih menggunakan sistem pengajaran yang biasa dan menggunakan media pembelajaran manual guru nanti akan ketinggalan dan membosankan bagi siswa. Pelatihan teknologi AI ini dilakukan secara interaktif tatap muka di sekolah. Hasil dari pelatihan ini meningkatkan pengetahuan dan keterampilan dalam pengunaan aplikasi AI sehingga dapat dimanfaatkan dalam membuat media pembelajaran di sekolah lebih menarik, interaktif dan inovatif.
PENERAPAN SISTEM PENGUKURAN SUHU TUBUH MENGGUNAKAN PENCITRAAN THERMAL SEBAGAI LANGKAH PENCEGAHAN PENYEBARAN COVID-19 DI PUSKESMAS KECAMATAN LANGSA LAMA Munawir Munawir; Novianda Novianda; Irwansyah Irwansyah
Martabe : Jurnal Pengabdian Kepada Masyarakat Vol 6, No 3 (2023): MARTABE : JURNAL PENGABDIAN MASYARAKAT
Publisher : Universitas Muhammadiyah Tapanuli Selatan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31604/jpm.v6i3.996-1001

Abstract

Penyebaran covid-19 masih menjadi ancaman mulai di mulai tahun 2019 sampai saat ini berbagai cara digunakan untuk mengatasi penyebaran covid-19 oleh pemerintah salah satunya dengan social distancing.  Selama ini pengukuran suhu pada umumnya masih menggunakan thermo gun yang mana pengukurannya masih melibatkan petugas. Tujuan pengabdian masyarakat adalah merancang dan menerapkan teknologi sistem pengukuran suhu tubuh menggunakan pencitraan thermal berbasis internet of things pada mitra dalam hal ini Puskesmas Langsa Lama sehingga diharapkan dapat mencegah penyebaran covid-19 di lingkungan mitra.
Identification of Facial Wrinkles using Gabor Filters and the Naïve Bayes Algorithm Munawir Munawir; Siti Rafah Sa`dia Harahap; Rizalul Akram
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol. 8 No. 1 (2026): Maret
Publisher : Universitas Wahid Hasyim

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Facial Wrinkles are one of the key indicators in identifying signs of aging on the skin. Detecting facial wrinkles poses a challenge in image processing due to their complex, coarse texture, which is often difficult for computers to recognize, especially under varying lighting conditions, camera angles, and facial expressions. This study focuses on the application of features using Gabor Filters for the texture feature extraction, with the final results determined by the Naïve Bayes classification algoritm. In this study, 200 facial images were used, divided into two clases, with 100 images per class serving as training data. For the test data, 100 facial images were used, consisting of 50 wrinkled facial images and 50 non-wrinkled facial images. Based on the test result using the Confusion Matrix, the accuracy was 74%, precision 80%, recall 64% and F1-Score 71%. These results indicate that the combination of Gabor filters and Naïve Bayes is quite effective in recognizing wrinkle patterns on the face based on extracted texture feature, and can serve as a faoundation for developing more accurate facial wrinkle detection systems in the future.
Optimized Ensemble Learning Using Boosting, Stacking, and Voting for Early Stunting Risk Prediction Munawir Munawir; M. Khairul Anam; Liza Fitria; Nurul Fadillah
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.v10i4.7107

Abstract

Stunting remains a pressing health issue in Indonesia’s coastal communities, where uneven access to nutrition services and maternal–child care can limit early prevention efforts. This study develops a machine learning framework to estimate stunting risk among children under five in the eastern coastal region of Aceh. The modeling process began with data cleaning and preparation, followed by class rebalancing with SMOTE and automated parameter tuning using Optuna. Four standalone classifiers were evaluated: Logistic Regression, Gaussian Naïve Bayes, Support Vector Machine, and Random Forest. Their outputs were then extended through three ensemble configurations, namely XGBoost-assisted boosting for each baseline model, a stacking scheme named Stackstun with Logistic Regression as the final learner, and an optimized weighted soft-voting model referred to as Votsstun. Performance was measured using accuracy, precision, recall, and F1-score. Among the single classifiers, Logistic Regression achieved the best result, with an accuracy of about 0.93. The strongest overall performance was obtained by the boosted Random Forest model, which reached an accuracy of 0.9952 and produced almost perfect class-level precision, recall, and F1-score. Votsstun also performed consistently, recording an accuracy of approximately 0.986, while its macro and weighted F1-scores approached 0.99. These results indicate that the combined use of class rebalancing, automated optimization, and ensemble learning can improve the robustness of stunting-risk classification. The proposed framework may assist local health agencies in identifying vulnerable children earlier, prioritizing limited intervention resources, and strengthening prevention programs in coastal communities.