Article Per Year (5 Year)
p-Index From 2020 - 2025
1.168
P-Index
This Author published in this journals
All Journal Jurnal Biologi Udayana Linguistica Indonesian Journal of Artificial Intelligence and Data Mining Jurnal Kridatama Sains dan Teknologi JATI (Jurnal Mahasiswa Teknik Informatika) SKANIKA: Sistem Komputer dan Teknik Informatika
MANSUR AS
Program Studi Ilmu Komputer, FMIPA, Universitas Negeri Medan
Agriculture, Biological Sciences & Forestry Arts Humanities Biochemistry, Genetics & Molecular Biology Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Education Engineering Languange, Linguistic, Communication & Media Social Sciences

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 7 Documents
Search

 1 
TEACHERS’ USE OF TELEGRAM CHATBOT AS LEARNING MEDIA AT SMPN 4 BINJAI JULI RACHMADANI HASIBUAM; MANSUR AS; NAZLAH SYAHAF NASUTION; INDRA KASIH; MAZAYA ZAHIRA HARAHAP
LINGUISTICA Vol 13, No 3 (2024): JULI 2024
Publisher : State University of Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24114/jalu.v13i3.62120

Abstract

This study explores the implementation of Telegram chatbots as learning media at SMPN 4 Binjai, focusing on enhancing teaching and learning processes through digital transformation. Telegram can serve as effective learning tools by facilitating interaction among teachers, students, and parents (Sanaky, 2023), the research involved training and mentoring 21 teachers using methods such as presentations, discussions, and simulations over three meetings. The chatbots aimed to address challenges such as workload management and student engagement by providing automated content distribution, quizzes, and feedback. Findings indicate that Telegram chatbots significantly enhance the efficiency of delivering educational material, boost student interest and engagement, and promote independent learning. This study underscores the importance of digital literacy in modern education and suggests that ongoing training and support are crucial for maximizing the effectiveness of Telegram chatbots. By creating more interactive and responsive learning environments, chatbots offer a promising future for educational settings. The results highlight the necessity for educational institutions to embrace technological changes and provide continuous training for educators to fully utilize digital tools' potential, thereby improving the overall quality of education.
A Induksi pertumbuhan tunas anggrek (Dendrobium sp.) dengan pemberian BAP dan ekstrak jagung manis (Zea mays L.) Fauziyah Harahap; Rehlitna Fransiska Sitepu; Syahmi Edi; Cicik Suriani; Abdul Hakim Daulae; Mansur As; Didi Febrian; Sitti Subaedah
Jurnal Biologi Udayana Vol 28 No 1 (2024): JURNAL BIOLOGI UDAYANA
Publisher : Program Studi Biologi, Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JBIOUNUD.2024.v28.i01.p14

Abstract

Penelitian ini bertujuan untuk mengetahui interaksi perlakuan BAP dan ekstrak jagung manis yang berpengaruh dalam membentuk tunas sebagai upaya perbanyakan anggrek Dendrobium sp. Penelitian ini menggunakan Rancangan Acak Lengkap (RAL) faktorial dengan dua faktor. Faktor pertama adalah konsentrasi BAP yang terdiri dari 4 taraf yaitu (0, 1, 2 dan 3 ppm) dan faktor kedua adalah konsentrasi ekstrak jagung manis yang terdiri dari 4 taraf yaitu (0, 20, 40 dan 60 gr/l). Diperoleh 16 kombinasi perlakuan dan masing-masing perlakuan diulang sebanyak 3 kali sehingga terdapat 48 unit percobaan. Parameter waktu munculnya tunas dan akar dianalisis menggunakan metode deskriptif kuantitatif. Parameter jumlah tunas, jumlah daun, tinggi planlet dan jumlah akar dianalisis dengan Analysis of Variance (ANOVA) dan jika berbeda nyata akan dilakukan uji lanjut dengan Duncan Multiple Range Test (DMRT) pada taraf 5%. Hasil penelitian menunjukkan waktu muncul tunas tercepat terjadi pada 3 MST. Waktu muncul akar tercepat terjadi pada 3 MST. Interaksi perlakuan BAP 2 ppm dan ekstraks jagung 60 % menghasilkan rataan jumlah tunas dan daun terbanyak yaitu 4,67 tunas dan 15,67 daun. Interaksi perlakuan BAP 1 ppm dan ekstraks jagung 60 % menghasilkan rataan tinggi planlet tertinggi yaitu 3,77 cm. Interaksi perlakuan BAP 2 ppm dan ekstraks jagung 40 % menghasilkan rataan jumlah akar terbanyak yaitu 8,33 akar.
Automatic Classifier of Road Condition and Early Warning System for Potholes Manurung, Jeremia; As, Mansur; Nasution, Hamidah; Al Idrus, Said Iskandar; Saputra S, Kana
Indonesian Journal of Artificial Intelligence and Data Mining Vol 8, No 1 (2025): March 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v8i1.31866

Abstract

Damaged roads can have a negative impact on road users and can fatally cause accidents. One sign of a damaged road is the presence of holes in the road. This research aims to develop an Android application that can display the location of potholes and provide early warning to driver in Simalungun Regency - North Sumatra. This research implements the Convolutional Neural Network (CNN) algorithm using the transfer learning techniques on the pre-trained MobileNetV3 model for automatic classification of road conditions. The dataset used in the research consisted of 22.538 images which were divided into two classes, namely pothole and normal. This research uses dataset with a ratio of 60:20:20, 70:20:10 and 80:10:10. MobileNetV3 large variant with a dataset ratio of 60:20:20 shows the best value with an F1-Score of 0,9035. The model was further converted to Tensorflow Lite with an F1-Score of 0.8985. This research succeeded in implementing the trained and evaluated model along with early warning of potholes via audiovisual in Android application. Application functionality testing that is carried out using black box testing, showing that the application can run well.
Pembangunan Website untuk Penjadwalan Maintenance Menggunakan Algoritma Priority Schedulling Harahap, Muhammad Abarorya; Rangkuti, Yulita Molliq; AS, Mansur; Indra, Zulfahmi; Saputra, Kana
Jurnal Kridatama Sains dan Teknologi Vol 7 No 01 (2025): Jurnal Kridatama Sains dan Teknologi
Publisher : Universitas Ma'arif Nahdlatul Ulama Kebumen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53863/kst.v7i01.1504

Abstract

PTPN II Sugar Factory (PG.II) is a company that produces sugar which often experiences difficulties in producing sugar that is not time efficient due to frequent unexpected damage to the machine, which results in a reduced amount of time used to produce sugar. One of the causes of machine damage at PTPN II Kwala Madu is the absence of an information system about scheduling machine maintenance so that production machine damage occurs. The purpose of performing maintenance is so that the network distribution capability can meet the needs of the company, maintaining quality at the right level to meet what is needed by the production itself. Maintenance also aims to achieve the lowest possible cost level and avoid maintenance activities that can endanger the safety of the workforce or employees. help reduce usage or deviations beyond the limit and maintain the capital that has been invested during the specified time in accordance with the policies of the company or organization. The stages of this research are analyzing needs, designing / modeling a scheduling system with the Priority Schedulling algorithm, followed by programming, software testing and testing. Global system design using UML modeling language consisting of Usecase Diagram, Activity Diagram, Class Diagram, and Bari Diagram
KOMBINASI LATENT SEMANTIC INDEXING DAN SUPPORT VECTOR MACHINE PADA KLASIFIKASI DOKUMEN AKREDITASI: STUDI KASUS : PASCASARJANA UNIVERSITAS NEGERI MEDAN Warjaya, Angga; As, Mansur; Muthmainnah, Inna; Mulyana, Sri; Iskandar Al Idrus, Said; Arnita, Arnita; Taufik, Insan
JATI (Jurnal Mahasiswa Teknik Informatika) Vol. 9 No. 4 (2025): JATI Vol. 9 No. 4
Publisher : Institut Teknologi Nasional Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/jati.v9i4.14102

Abstract

Pengelolaan dokumen akreditasi yang efisien menjadi tantangan utama dalam pendidikan tinggi akibat volume dokumen yang besar dan format yang bervariasi. Penelitian ini bertujuan untuk mengembangkan metode klasifikasi otomatis menggunakan kombinasi latent semantic indexing dan support vector machine guna meningkatkan akurasi dan efisiensi pengelolaan dokumen akreditasi. Akurasi dalam penelitian ini mengacu pada ketepatan sistem dalam mengidentifikasi kategori dokumen sesuai kriteria akreditasi, sementara efisiensi mencerminkan percepatan dan penyederhanaan proses klasifikasi dibandingkan dengan metode manual. Dataset terdiri dari 230 dokumen yang dikategorikan berdasarkan kriteria Lembaga Akreditasi Mandiri Kependidikan, dengan 115 dokumen untuk Kriteria 6 (Pendidikan) dan 115 dokumen untuk Kriteria 7 (Penelitian), kemudian dibagi menjadi data latih dan uji dengan rasio 60:40. Proses klasifikasi dilakukan melalui beberapa tahap, termasuk pre-processing teks, ekstraksi fitur semantik, serta optimasi parameter model untuk memperoleh hasil terbaik. Pengujian menunjukkan bahwa metode yang diusulkan mampu mencapai tingkat akurasi sebesar 91%, dengan validasi silang sebesar 94,21%. Hasil ini menunjukkan bahwa pendekatan yang digunakan efektif dalam mengotomatisasi klasifikasi dokumen akreditasi, sehingga dapat mempercepat proses evaluasi serta meningkatkan efisiensi manajemen dokumen dalam institusi pendidikan tinggi.
IMPLEMENTASI CONVOLUTIONAL NEURAL NETWORK DALAM MENDETEKSI TINGKAT KEMATANGAN BUAH KAKAO Wahabi Hasibuan, Rahman; Taufik, Insan; AS, Mansur; Iskandar Al Idrus, Said; Indra, Zulfahmi
JATI (Jurnal Mahasiswa Teknik Informatika) Vol. 9 No. 4 (2025): JATI Vol. 9 No. 4
Publisher : Institut Teknologi Nasional Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/jati.v9i4.14116

Abstract

Indonesia merupakan negara agraris dengan sektor perkebunan yang berperan penting dalam perekonomiannya. Kakao (Theobroma cacao L.) merupakan komoditas strategis yang berkontribusi pada ekspor, lapangan kerja, agribisnis, serta pertanian berkelanjutan. Namun, di Sumatera Utara, meskipun sektor perkebunan berkembang, produksi kakao menghadapi tantangan seperti alih fungsi lahan. Proses pemanenan kakao secara tradisional mengandalkan penilaian kematangan secara manual, yang rentan terhadap kesalahan akibat kelelahan dan subjektivitas manusia. Convolutional Neural Network (CNN) telah banyak digunakan dalam pengolahan citra karena kemampuannya mengenali pola dengan akurasi tinggi. Penelitian ini mengusulkan penggunaan CNN dengan Transfer Learning berbasis EfficientNetB0 untuk mengklasifikasikan tingkat kematangan buah kakao. Dataset terdiri dari 360 gambar dalam kategori Mentah, Matang, Busuk, dan Unclassified, dengan teknik pra-pemrosesan seperti resizing, noise, rotasi, flipping, cropping, dan penghapusan latar belakang. Dataset dibagi menjadi 70% untuk pelatihan dan 30% untuk validasi, dengan optimasi hyperparameter. Model mencapai akurasi tinggi sebesar 99,71% pada data uji. Evaluasi menggunakan confusion matrix dan classification report menunjukkan kemampuan generalisasi yang baik. Selain itu, model berhasil diimplementasikan dalam aplikasi Android dengan fitur klasifikasi, riwayat, informasi, panduan, serta autentikasi pengguna. Sistem ini memungkinkan identifikasi kematangan buah kakao secara real-time dan praktis bagi petani.
Identifikasi Penyakit Tanaman Berdasarkan Citra Daun Berbasis Web dengan Pendekatan Algoritma Convolutional Neural Network Sri Mulyana; Mansur AS; Angga Warjaya; Inna Muthmainnah; Said Iskandar Al Idrus; Zulfahmi Indra
SKANIKA: Sistem Komputer dan Teknik Informatika Vol 8 No 2 (2025): Jurnal SKANIKA Juli 2025
Publisher : Universitas Budi Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36080/skanika.v8i2.3573

Abstract

This research aims to develop a mustard plant disease classification system using the Convolutional Neural Network (CNN) method integrated into a web-based platform. Classification is carried out on three classes, namely Spotted Mustard Leaves, Rotten Mustard Leaves, Healthy Mustard Leaves, with the addition of the Not Mustard Leaf class as a distractor class to test the robustness of the model against images that are not included in the main classification category. The dataset used consists of 800 images, 200 images each per class. The CNN model was built with a sequential architecture consisting of several convolutions, pooling, dropout, and dense layers, and using ReLU and SoftMax activation functions in the output layer. The training process is carried out up to 100 epochs, but with the use of Early Stopping callback, the training stops at the 60th epoch, with the best performance (best epoch) achieved at the 32nd epoch. Evaluation of the model on test data showed an accuracy of 93.75%, with high precision, recall, and F1-score values in each class. The model was then implemented into a web interface so that users could upload leaf images and obtain classification results automatically. The results of this study show that CNN is effective in detecting mustard leaf disease and has the potential to be applied as a digital image-based diagnostic tool in agriculture.
Co-Authors Abdul Hakim Daulae Angga Warjaya Arnita Arnita Cicik Suriani Didi Febrian Fauziyah Harahap Harahap, Muhammad Abarorya Indra Kasih Inna Muthmainnah Insan Taufik JULI RACHMADANI HASIBUAM Kana Saputra S Manurung, Jeremia MAZAYA ZAHIRA HARAHAP Muthmainnah, Inna Nasution, Hamidah . Nazlah Syahaf Nasution Rehlitna Fransiska Sitepu Said . Iskandar Sitti Subaedah Sri Mulyana Sri Mulyana Syahmi Edi Wahabi Hasibuan, Rahman Warjaya, Angga Yulita Molliq Rangkuti Zulfahmi Indra, Zulfahmi