Claim Missing Document
Check
Articles

Found 13 Documents
Search

Pengaruh Media E-Learning Berbasis LMS Moodle dan Motivasi Belajar terhadap Hasil Belajar Mahasiswa di Masa Pandemi Covid-19 Fakhri, M. Miftach; Fadhilatunisa, Della; Rosidah, Rosidah; Fajar B, Muhammad; Satnur, Muh. Alham; Fajrin, Farid
Chemistry Education Review (CER) Volume 5 Nomor 2 Maret 2022
Publisher : Program Pasca Sarjana UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (469.741 KB) | DOI: 10.26858/cer.v5i2.32724

Abstract

Online learning in E-learning Media in Covid-19 conditions involving lecturers as educators and students as educators has an important role in improving student learning outcomes.  The purpose of this study was to find out the influence of E-learning based on LMS Moodle and Motivation to Learn partially and simultaneously on student learning outcomes. This type of research is a mix method that integrates quantitative and qualitative research with sequential explanatory forms. The data collection techniques used are questionnaires or questionnaires and interviews. The instruments used are questionnaire sheets and interviews that are used to collect the data needed. The sample from this study was 75 accounting students. The data analysis used is inferential analysis with Classical Assumption Test (Normality Test and Linearity Test) and Multiple Regression Analysis with partial t test and simultaneous F test. The results showed that there was an influence of LMS Moodle-based E-learning Media, Partial and simultaneous Learning Motivation on student learning outcomes which was indicated by a significant value smaller than 0.05 and the large influence of both variables on dependent variables of 60.6%.
ANALISIS TEKNIK PREPROCESSING PADA SENTIMEN MASYARAKAT TERKAIT KONFLIK ISRAEL-PALESTINA MENGGUNAKAN SUPPORT VECTOR MACHINE Syam, Abd. Azis; Hardy M, Galang; Salim, Agus; Surianto, Dewi Fatmarani; Fajar B, Muhammad
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 9, No 3 (2024)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v9i3.5527

Abstract

Konflik Israel dan Palestina menjadi perhatian di media sosial saat ini terutama di Indonesia. Beragam ulasan yang dapat ditemui pada media sosial baik yang bersifat negatif maupun positif. Oleh sebab itu dilakukanlah sebuah penelitian yang bertujuan untuk menganalisa ulasan yang bersifat positif maupun negatif oleh Masyarakat Indonesia terhadap masalah yang sedang terjadi antara Israel dan Palestina di media sosial menggunakan algoritma Support Vector Machine dengan tiga skema preprocessing. Metode penelitian dilaksanakan dengan berbagai tahap yakni pengumpulan data ulasan, preprocessing data ulasan, klasifikasi, dan evaluasi model. Penelitian ini menggunakan data komentar masyarakat Indonesia pada platform YouTube. Hasil dari penelitian menunjukkan bahwa skema 3 yang menerapkan casefolding dan stemming memiliki nilai akurasi tertinggi dimana nilai F1-Score untuk ulasan positif mencapai 98% dan untuk ulasan negatif mencapai 93%, diikuti oleh skema 1 yang menerapkan casefolding, stopword dan stemming dengan nilai F1-Score untuk ulasan positif mencapai 97% dan ulasan negatif mencapai 85% dan yang terakhir adalah skema 2 yang menerapkan casefolding dan stopword dengan nilai F1-Score untuk ulasan positif mencapai 96% dan ulasan negatif mencapai 85%. Dengan hasil tersebut dapat dilihat bahwa skema preprocessing mempengaruhi hasil dari algoritma Support Vector Machine.
Penentuan Jumlah Produksi Roti Pada Toko Roti Kayla Menggunakan Fuzzy Logic Metode Tsukamoto Bakri, Muh. Fajrin Bakri; Fajar B, Muhammad; Indriani, Gebby; Rahman, Ahmad Fadhli
Journal of Deep Learning, Computer Vision, and Digital Image Processing Volume 2 Issue 1 Maret 2024
Publisher : CV. Sakura Digital Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61255/decoding.v2i1.300

Abstract

Penentuan jumlah produksi merupakan hal yang perlu diperhatikan sebelum memulai sebuah usaha. Menentukan jumlah produksi suatu barang merupakan langkah penting untuk menghindari risiko kerugian. Dengan adanya metode ini, akan meminimalisir kerugian bagi penyedia usaha karena dapat menyesuaikan jumlah persediaan dan produksi sesuai dengan jumlah permintaan, sehingga bahan baku yang disiapkan akan digunakan secara maksimal. Pada era globalisasi saat ini, persaingan pasar dalam dunia industri sangat kompetitif sehingga dibutuhkan kemampuan pengelola perusahaan yang profesional agar dapat memenangkan persaingan dalam pasar global terutama dalam usaha penjualan Roti. Namun, permasalahan yang terjadi adalah saat menentukan jumlah produksi roti. Banyaknya faktor yang masuk dalam perhitungan membuat sulit untuk menetapkan pedoman penentuan jumlah roti yang akan diproduksi. Pengelolaan produksi roti di toko roti Kayla dalam menentukan jumlah produksi terkadang tidak memenuhi pesanan dengan tepat waktu dan jumlah yang sesuai, sehingga berdampak kerugian terhadap toko dikarenakan jumlah produksi yang tidak sesuai dengan permintaan konsumen. Oleh karena itu, pada penelitian ini akan dilakukan penentuan jumlah produksi roti pada toko roti Kayla untuk menentukan jumlah produksi yang tepat, sesuai dengan jumlah permintaan dan persediaan. Metode yang digunakan pada penelitian ini adalah Fuzzy Logic dengan metode Tsukamoto untuk menentukan jumlah produksi roti. Dibandingkan dengan sebelumnya, dengan adanya penerapan Fuzzy Logic metode Tsukamoto pada kasus ini memberikan output jumlah produksi yang lebih optimal dan mencegah produksi yang kurang ataupun berlebih yang dapat menyebabkan kerugian. 
Analisis Sentimen Penghapusan Skripsi sebagai Tugas Akhir Mahasiswa Menggunakan Metode Multi-Layer Perceptron Makmur, Haerunnisya; Wulandari, Wulandari; Surianto, Dewi Fatmarani; Fajar B, Muhammad
Komputika : Jurnal Sistem Komputer Vol 13 No 2 (2024): Komputika: Jurnal Sistem Komputer
Publisher : Computer Engineering Departement, Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/komputika.v13i2.12402

Abstract

Indonesia has levels of education where one of them is undergraduate education. There are requirements that must be done to get a bachelor's degree, one of which is to complete a final project in the form of a thesis. Nadiem Makarim, Minister of Education, Technology and Higher Education in his speech announced a new policy in the field of education regarding the non-obligation for students to prepare a thesis as a requirement for graduation. Based on this, there are pros and cons from the community, the sentiment analysis process related to this is needed. This research aims to map public sentiment contained in TikTok and YouTube social media related to the elimination of thesis using the MLP method. The stages carried out consist of observation, data collection, labeling, data normalization, preprocessing, data partitioning, TF-IDF weighting, classification, and evaluation. The accuracy obtained at the preprocessing scenario stage is 86% with case folding and stemming scenarios. Furthermore, this scenario is used in testing based on data partitioning where the highest accuracy results are obtained with a portion of 90% training data and 10% test data. The accuracy obtained is 94%.
A Machine Learning Model for Local Market Prediction Using RFM Model Yahya, Muhammad; Parenreng, Jumadi Mabe; Fathahillah, Fathahillah; Wahid, Abdul; Wahid, M. Syahid Nur; Fajar B, Muhammad
Elinvo (Electronics, Informatics, and Vocational Education) Vol 9, No 1 (2024): Mei 2024
Publisher : Department of Electronic and Informatic Engineering Education, Faculty of Engineering, UNY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21831/elinvo.v9i1.58671

Abstract

This study explores the application of machine learning for local market prediction in e-commerce. By leveraging the RFM segmentation method, the model predicts product sales based on user shopping patterns. The RFM score, calculated using recency, frequency, and monetary values of customer purchases, segments customers into distinct categories. The research utilizes a dataset obtained through seven parameters and performs data preprocessing. K-Means clustering then classifies customers into Low, Medium, and High levels based on their RFM scores. Customers in the Low category exhibit low purchase activity but high product browsing. The Medium segment displays consistent purchases of a limited product range. High-level customers demonstrate frequent purchases with significant spending. The identified customer segments enable targeted marketing strategies. For Low-level customers, discounts or product feature promotions can incentivize purchases. Combining product offerings can entice Medium-level customers to explore new products. Finally, High-level customers can be engaged through loyalty programs offering rewards. This approach empowers e-commerce sellers to tailor marketing strategies for each customer segment, enhancing market dominance.
Enchancing Batik Classification Leveraging CNN Models and Transfer Learning Perdana, Am Akbar Mabrur; Fajar B, Muhammad; Mappalotteng, Abdul Muis
JOIV : International Journal on Informatics Visualization Vol 9, No 1 (2025)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.9.1.2535

Abstract

Batik is a traditional art originating from Indonesia and recognized by UNESCO. Batik motifs vary depending on the region of origin. The diverse batik motifs reflect the rich cultural heritage and unique traditions owned by each region in Indonesia. From Sabang to Merauke, each motif features a different story and values, depicting the beauty and diversity of nature and the lives of diverse local people. However, in the context of the modern era that continues to develop, batik motifs also experience renewal and creativity that always adapts to the times. As a result, the diversity of batik motifs is increasingly abundant in Indonesia. Thus, complicating efforts to identify and categorize batik motifs appropriately. Therefore, in the context of this study, we chose to combine the MobileNetV2 model with Transfer Learning to classify batik motifs. We used a dataset consisting of 3000 batik images and have categorized them into three main classes, namely Kawung batik, Mega Mendung batik, and Parang batik. This approach not only leads to the introduction and understanding of traditional batik motifs, but also applies the latest technology for a more in-depth and accurate analysis. The results of this model show a very high level of testing accuracy, reaching 0.9946%, and training accuracy of 0.8916%, and the time required by the model to train and test the entire dataset is 18 minutes 1 second. Future research can explore the integration of other technologies or new approaches to improve accuracy and efficiency in classifying batik motifs.
Comparative Analysis of the Performance of Hadith Text Classification Methods: A Case Study with ANN and SVM Surianto, Dewi Fatmarani; Fajar B, Muhammad; Mulia, Musda Rida; Indanasufya, Indanasufya
Journal of Embedded Systems, Security and Intelligent Systems Vol 5, No 1 (2024): March 2024
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v5i1.2942

Abstract

Hadith is the second holy book for Muslims after the Quran, containing instructions from the Prophet Muhammad SAW, and narrated by Ulama / Mufti. As one of the main sources of Islamic teachings, hadith is used to explain and illustrate the teachings of the Quran. This study aims to compare the performance of hadith text classification using Artificial Neural Network (ANN) and Support Vector Machine (SVM) with Hadith Bukhari dataset. The stages include preprocessing, feature extraction with TF-IDF, classification, and evaluation. The evaluation results show different performance between ANN and SVM in two scenarios: with and without stemming. The use of stemming has a significant impact on model performance, reducing word variation and can result in a decrease in accuracy. The SVM model consistently showed higher accuracy than ANN in both scenarios, with the highest accuracy reaching 85% for classification without stemming. This study provides insight into the application of ANN and SVM in hadith text classification, emphasizing the importance of selecting a method that suits the characteristics of the data.
A Hybrid Framework for Plagiarism Detection: Integrating Token-Based Similarity with Density-Based Clustering Fajar B, Muhammad; Lestary, Fitriyanty Dwi; Surianto, Dewi Fatmarani
Journal of Embedded Systems, Security and Intelligent Systems Vol 6, No 1 (2025): March 2025
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v6i1.7664

Abstract

Plagiarism detection in academic assignments remains a critical challenge in maintaining academic integrity in higher education. This study proposes an automated method to detect content similarity between student assignment documents by combining Jaccard Similarity and DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithms. The process begins with the collection of student assignment files in digital format, followed by text extraction to form a set-based representation of each document. Jaccard Similarity is then used to compute the degree of similarity between every document pair, and the resulting similarity matrix is transformed into a distance matrix as input for DBSCAN. Experiments conducted on 23 documents yielded 253 unique document pairs. The results demonstrate that the method successfully identified pairs with high similarity scores—such as 0.9114 and 0.7226—which were visually confirmed through a heatmap and effectively grouped into clusters by DBSCAN. Parameter settings of eps = 0.3 and min_samples = 1 proved optimal for distinguishing original documents from those exhibiting substantial content overlap. This approach is not only accurate and efficient, but also eliminates the need for predefined cluster numbers, making it suitable for deployment in automated plagiarism detection systems for academic texts.
Pengembangan Media Trainer Rekayasa Sistem Robotika Berbasis Internet of Things Wahyudi, Wahyudi; Sabara, Edy; Fajar B, Muhammad
Jurnal MediaTIK Volume 6 Issue 2, Mei (2023)
Publisher : Jurusan Teknik Informatika dan Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/mediatik.v6i2.1390

Abstract

Penelitian ini bertujuan untuk untuk mengidentifikasi langkah-langkah dalam pengembangan media trainer robotika berbasis internet of things sebagai alat pembelajaran pendidikan kejuruan dan vokasi pada Fakultas Teknik Universitas Negeri Makassar, dan menghasilkan media trainer robotika yang valid, praktis, dan efektif. Metode penelitian yang digunakan adalah research and development (R&D) dengan menerapkan model pengembangan 4D, yaitu 1) pendefinisian, 2) perancangan, 3) pengembangan, 4) penyebaran, teknik analisis data pada penelitian ini adalah dengan menggunakan analisis deskriptif persentase yang mendiskripsikan hasil pengembangan, respon validator, hasil uji coba one to one, uji coba kelompok kecil dan uji coba kelompok besar. Hasil penelitian ini menunjukkan bahwa media trainer robotika berbasis internet of things yang dikembangkan dalam hal media dan materi tergolong sangat valid untuk digunakan. Implementasi media trainer ini mendapatkan respon yang sangat praktis dari mahasiswa dalam penggunaannya, dan hasil tes mahasiswa setelah implementasi menunjukkan peningkatan yang signifikan dalam kategori tinggi. Berdasarkan data tersebut, dapat disimpulkan bahwa media trainer robotika berbasis internet of things yang telah dikembangkan memenuhi kriteria valid, praktis rata-rata aspek aplikasi 91,67%, tampilan 95,83%, konten 91,67% dan bahasa 91,67%, sehingga dapat disimpulkan bahwa media trainer robotika berbasis internet of things berada pada kategori sangat praktis dan efektif dalam penggunaannya dengan nilai N-Gain sebesar 0,77 atau dalam kategori tinggi.
Minimizing Multiplication of Kernel Computation in Convolutional Neural Networks Using Strassen Algorithm Rifqie, Dary Mochamad; Surianto, Dewi Fatmarani; Jayanegara, Sudarmanto; Fajar B, Muhammad; Fakhri, M. Miftach
Jurnal MediaTIK Volume 6 Issue 2, Mei (2023)
Publisher : Jurusan Teknik Informatika dan Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/mediatik.v6i2.1397

Abstract

Convolution neural networks (CNN) have been widely applied for the computer vision task. However, the success of CNN is limited by the computational complexity of the network, so it is difficult for the model to run the inference process in real time. In this paper, we apply Strassen matrix multiplication to reduce multiplications in convolution operations in CNN, in order to get faster execution for CNN. First, we transform the convolution operation into a matrix multiplication operation using the Toeplitz mapping method, then after that, we apply the Strassen method to these matrices. In the end, we compare the number of arithmetic operations (multiplication and addition) in the convolutional layer using Strassen and the standard algorithm. We apply this algorithm implementation in convolution layers 1 and 3 in LeNet-5 Architecture.