Claim Missing Document
Check
Articles

Prediksi Harga Emas Dunia Menggunakan Deep Learning GRU dengan Optimasi Nadam Harmain, Ismail Saputra R.; Nurwan, Nurwan; Hasan, Isran K.; Wungguli, Djihad; Yahya, Nisky Imansyah
Jurnal Riset Mahasiswa Matematika Vol 4, No 6 (2025): Jurnal Riset Mahasiswa Matematika
Publisher : Mathematics Department, Maulana Malik Ibrahim State Islamic University of Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18860/jrmm.v4i6.36007

Abstract

Volatilitas harga emas yang tinggi menuntut adanya metode prediksi yang andal untuk mendukung pengambilan keputusan investasi. Penelitian ini mengimplementasikan algoritma Gated Recurrent Unit (GRU) berbasis deep learning yang dioptimalkan menggunakan Nesterov-Accelerated Adaptive Moment Estimation (Nadam) untuk memprediksi harga emas harian.Model terbaik diperoleh dengan nilai Mean Squared Error (MSE) sebesar 0, 00012 pada data univariat dan 0, 00027 pada data multivariat. Mean Absolute Percentage Error (MAPE) yang diperoleh masing-masing sebesar 1,107% untuk data univariat dan 1,59% untuk data multivariat. Hasil tersebut mengindikasikan bahwa model GRU dengan optimasi Nadam memiliki performa prediksi yang tinggi, baik pada data deret waktu tanpa penambahan fitur maupun dengan penambahan fitur.
Pemodelan Regresi Robust dengan Estimasi Generalized-M untuk Penanganan Outlier pada Kasus Kusta di Indonesia Loleh, Linda Purnama Sari; Wungguli, Djihad; Rezky Friesta Payu, Muhammad; Nashar, La Ode
Griya Journal of Mathematics Education and Application Vol. 5 No. 3 (2025): September 2025
Publisher : Pendidikan Matematika FKIP Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/griya.v5i3.811

Abstract

which attacks the skin, peripheral nerves, and other body organs except the central nervous system. New leprosy cases with visible disabilities are classified as Grade 2 disabled leprosy. The number of Grade 2 disabled leprosy cases is an indicator used to show success in early detection of new leprosy cases. However, the leprosy data in Indonesia for 2023 contains outliers that can affect the results of linear regression analysis. To address this issue, this study utilizes the robust regression method of generalized-M estimation, which is an extension of M-estimation. The objectives of this study are to obtain a robust regression model using generalized-M estimation and to identify significantly influential variables. The research findings indicate that these factors have a significant simultaneous impact on the number of leprosy cases with grade 2 disability, and partially, the factor of access to basic sanitation facilities has an influence on the number of leprosy cases with grade 2 disability with an R^2 value of 73%, which can be explained by the predictor variables in this study. Meanwhile, 27% is explained by other predictor variables not included in this study. From these results, it is hoped that the efforts of the government and relevant agencies can improve access to basic sanitation facilities for the prevention and control of leprosy cases in Indonesia.
Sifat Fundamental Pada Granum Eulerian Suaib A. Siraj; Asriadi; Djihad Wungguli; Hasan S. Panigoro; Nurwan; Nisky I. Yahya
Limits: Journal of Mathematics and Its Applications Vol. 21 No. 2 (2024): Limits: Journal of Mathematics and Its Applications Volume 21 Nomor 2 Edisi Ju
Publisher : Pusat Publikasi Ilmiah LPPM Institut Teknologi Sepuluh Nopember

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

Abstract

Mathematical analysis has several important connections with graph theory. Although initially, they may seem like two separate branches of mathematics, there are relationship between them in several aspects, such as graphs as mathematical objects that can be analyzed using concepts from analytic mathematics. In graph theory, one often studies distance, connectivity, and paths within a graph. These can be further analyzed using analytic mathematics, such as in the structure of natural numbers. Literature studies on graph theory, especially Eulerian graphs, are interesting to explore. An Eulerian path in a graph G is a path that includes every edge of graph G exactly once. An Eulerian path is called closed if it starts and ends at the same vertex. The concept of granum theory as a generalization of undirected graphs on number structures provides a rigorous approach to graph theory and demonstrates some fundamental properties of undirected graph generalization. The focus of this study is to introduce the connectivity properties of Eulerian granum. The granum G(e,M) is called connected if for every u,v E M with u != v there exists a path subgranumG^' (e,M^' )c G(e,M)  where u,v E M^' and is called an Eulerian granum if there exists a surjective mapping O: [||E(G(e,M))|| + 1]-> M such that e(o(n),o(n+1))=1 for every n E [||E(G(e,M))||]. This property provides a deeper understanding of the structure and characteristics of Eulerian granum, which have not been fully comprehended until now.
Klasifikasi Preferensi Mahasiswa dalam Pemilihan Laptop Menggunakan Analisis Diskriminan Kernel Gaussian Meilan Sigar; Lailany Yahya; Salmun K. Nasib; Nisky Imansyah Yahya; Djihad Wungguli
Bilangan : Jurnal Ilmiah Matematika, Kebumian dan Angkasa Vol. 3 No. 5 (2025): Oktober : Bilangan : Jurnal Ilmiah Matematika, Kebumian dan Angkasa
Publisher : Asosiasi Riset Ilmu Matematika dan Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62383/bilangan.v3i5.804

Abstract

Rapid developments in information technology have made laptops an essential device for students, especially those in their final year of study. Choosing the right laptop plays an important role in supporting academic productivity, such as writing theses, analyzing data, and developing software. This study aims to classify the preferences of mathematics students at Gorontalo State University in choosing laptops based on usage characteristics and factors that influence purchasing decisions. The method used is Kernel Discriminant Analysis (KDA) with a Gaussian kernel function and an optimal bandwidth of 0.8. The research data involved 268 respondents divided into training and testing data. The analysis results show that the KDA model has an accuracy rate of 60% on the training data and 52% on the testing data, which indicates the model's ability to recognize student preference patterns despite a decrease in accuracy on new data. Based on the kernel density estimation results, Acer is the most widely used laptop brand, while Zyrex and Apple are rarely chosen. The most influential factor in purchasing decisions is processor specifications, with a contribution of 35.739%, followed by brand, warranty, and price. These findings indicate that hardware characteristics are the main consideration in laptop selection, with most students choosing laptops with Intel Core i5 processors, a minimum of 8GB of RAM, and SSD storage. The results of this study can also be used by universities to provide recommendations for selecting laptops that suit students' academic needs.  
Development of “Stafolding”: A Computer-Based Scaffolding Interactive Learning Media to Enhance Students’ Mathematical Problem-Solving Ability Damayanti, Taulia; Takaendengan, Bertu Rianto; Wungguli, Djihad; Tambiyo, Karman; Utina, Elsa Ekaputri
Jambura Journal of Mathematics Education Vol 6, No 2: September 2025
Publisher : Department of Mathematics, Universitas Negeri Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37905/jmathedu.v6i2.34648

Abstract

The low level of students’ mathematical problem-solving ability remains a challenge in the learning process, particularly in statistics topics. One effective approach to address this issue is scaffolding, which provides temporary support that helps students understand problems and find solutions independently. However, in classroom settings, individualized scaffolding is often suboptimal due to the large number of students compared to the limited number of teachers and the relatively short instructional time. This study aims to develop a computer-based scaffolding interactive learning medium that is feasible and practical for enhancing students’ mathematical problem-solving ability. The research employed a Research and Development (RD) design using the ADDIE model, consisting of five stages: Analysis, Design, Development, Implementation, and Evaluation. The media were developed using Canva, Microsoft PowerPoint, and iSpring Suite, and published via GitHub Pages for online accessibility. The validation results showed a feasibility score of 91.11% from material experts and 93.33% from media experts, both categorized as excellent. The practicality tests conducted by teachers and students each obtained a score of 92%, indicating that the media are easy to use and effective in facilitating learning. Therefore, the interactive learning media “Stafolding” are considered feasible and practical to be used as a computer-based scaffolding tool in mathematics learning.
Analisis Sensitivitas Model Goal Programming Pada Optimasi Produksi Roti Menggunakan Metode Branch and Bound Ahmad, Rindawati; Katili, Muhammad Rifai; Mahmud, Sri Lestari; Wungguli, Djihad; Nashar, La Ode
Euler : Jurnal Ilmiah Matematika, Sains dan Teknologi EULER: Volume 11 Issue 2 December 2023
Publisher : Universitas Negeri Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37905/euler.v11i2.22299

Abstract

Sya'qila Bakery is a manufacturing industry that produces bread in five flavor variants. The planning carried out by Sya'qila Bakery in the bread production process is considered suboptimal due to the limitation in the quantity of production for each flavor variant, resulting in occasional shortages of raw materials. Additionally, the order production process requires a long total completion time (makespan), resulting in delays in production completion (meaning tardiness). This research aims to optimize the total completion time, the average lateness, the use of raw materials, and production revenue. In this research, the Goal Programming model is utilized with the Branch and Bound method. The analysis results with the Goal Programming model using the Branch and Bound method obtain an optimal solution, which includes an excess of 36 minutes in total completion time (makespan), an excess of 6 minutes in average lateness (mean tardiness), no excess in the availability of raw materials, and zero sales revenue shortfall. Sensitivity analysis results indicate that bread production at Sya'qila Bakery will remain optimal if changes occur in the production completion time, production delay time, and raw material availability, as long as these changes remain within their tolerance limits.
Implementasi Algoritma Random Forest dengan Forward Selection untuk Klasifikasi Indeks Pembangunan Manusia Posangi, Tiara; Yahya, Lailany; Wungguli, Djihad
Jambura Journal of Probability and Statistics Vol 4, No 2 (2023): Jambura Journal Of Probability and Statistics
Publisher : Department of Mathematics, Universitas Negeri Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37905/jjps.v4i2.18460

Abstract

Development is essentially a process of continuous change carried out to achieve better living condition. So that the benchmark for the success of a development is seen in its human development. 3 The basic dimensions that form human development are long and healthy life, knowledge, and a decent life. The indicators that represent the three dimensions are summarized in a single value, namely the Human Development Index (IPM). In 2021 the HDI figure in Indonesia is 72.29, which means it is high. However, due to the diverse geographical location of regions in Indonesia, this also influences the HDI rate in each region in Indonesia, so this study uses the Random Forest Algorithm to obtain accurate results from the HDI classification and uses Forward Selection to determine features that influence the classification. The results of the study show that the features that influence the classification are per capita spending, expected length of schooling, life expectancy, and average length of schooling, and get a final accuracy of 80%.
ANALISIS PERPINDAHAN MEREK DAN STRATEGI PEMASARAN UMKM MENGGUNAKAN METODE RANTAI MARKOV DAN TEORI PERMAINAN Mokoginta, Karmila; K. Nasib, Salmun; Djakaria, Ismail; Wungguli, Djihad
MATHunesa: Jurnal Ilmiah Matematika Vol. 12 No. 1 (2024)
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/mathunesa.v12n1.p57-66

Abstract

Usaha mikro, kecil dan menyengah (UMKM) merupakan kegiatan usaha yang mampu memperluas lapangan kerja dan memberikan pelayanan ekonomi yang luas pada masyarakat. Di provinsi Gorontalo, UMKM berkembang semakin pesat. Banyaknya pilihan UMKM berdampak pada tingkat keinginan konsumen terhadap suatu produk sehingga konsumen berpeluang untuk melakukan perpindahan merek. Dalam mengatasi masalah perpindahan merek, para pelaku UMKM harus memilih strategi pemasaran yang tepat, sehingga dapat mempertahankan dan meningkatkan minat pelanggan. Tujuan penelitian ini adalah untuk menganalisis perpindahan pelanggan dan strategi pemasaran UMKM di Temu Social Space Gorontalo menggunakan metode rantai markov dan teori permainan. UMKM yang dimaksud adalah Drinking Of You (DOY), Mhimhithaitea dan Sruput. Hasil penelitian menunjukkan perpindahan pelanggan dari Drinking Of You (DOY) ke Mhimhithaitea sebesar 0,143, Mhimhithaitea ke Drinking Of You (DOY) sebesar 0,120, Drinking Of You (DOY) ke Sruput sebesar 0,032, Sruput ke Drinking Of You (DOY) sebesar 0,167, Mhimhithaitea ke Sruput sebesar 0,200, Sruput ke Mhimhithaitea sebesar 0,250. Sementara itu, strategi pemasaran optimal Drinking Of You (DOY) adalah promosi dan kualitas rasa. Strategi pemasaran optimal Mhimhithaitea adalah harga, kualitas rasa dan pelayanan. Strategi pemasaran optimal Sruput adalah kualitas rasa dan kemasan.
Analisis Sensitivitas Model Linear Programming Untuk Optimalisasi Produksi Pia Cendana Menggunakan Metode Branch and Bound Firdaus, Novarianti; Nasib, Salmun K.; Wungguli, Djihad
Research in the Mathematical and Natural Sciences Vol. 4 No. 2 (2025): May-October 2025
Publisher : Scimadly Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55657/rmns.v4i2.273

Abstract

This study aims to optimize the production of Pia Cendana enterprise using a linear programming model based on the Branch and Bound method. In order to achieve maximum profit, a mathematical formulation is constructed, including an objective function and constraint functions based on data regarding raw material composition, resource availability, production costs, and selling prices of each product variant. The Branch and Bound method was applied to obtain an optimal solution in the form of integers that are operationally valid. In addition, a sensitivity analysis was conducted to evaluate the impact of changes in coefficients within the objective function and constraints on the optimal solution. The findings show that the Pia Cendana enterprise can achieve an optimal profit of IDR 1,620,000 or 1.86 % per month. This amount is higher than the previous actual profit of only IDR 86,888,000, indicating a profit increase of IDR 88,508,000. The study indicates that this method improves resource efficiency and yields more profitable production. The optimal solution demonstrates that production can be increased while still considering capacity and raw material limitations. The sensitivity analysis also proves that the model is sufficiently stable against parameter variations. This study provides practical contributions to Pia Cendana enterprise in formulating more efficient and profitable production strategies.
Penjadwalan karyawan Qmart Super Store menggunakan metode Goal Programming secara Preemptive dan Nonpreemptive Syafrudin, Marisa; Djakaria, Ismail; Nuha, Agusyarif Rezka; Wungguli, Djihad
AKSIOMA : Jurnal Matematika dan Pendidikan Matematika Vol 14, No 3 (2023): AKSIOMA: Jurnal Matematika dan Pendidikan Matematika
Publisher : Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/aks.v14i3.17005

Abstract

Penjadwalan karyawan adalah salah satu masalah organisasi yang rumit dipecahkan. Faktor yang membuat penjadwalan karyawan menjadi rumit adalah karakteristik organisasi, ketidakhadiran, serta kualifikasi dan keahlian karyawan. Karena banyaknya faktor tersebut masalah penjadwalan menjadi sangat luas dan bervariasi. Tujuan dari penelitian ini adalah untuk mengoptimalkan penjadwalan karyawan. Hasil dari penelitian ini diperoleh dengan menggunakan 2 skenario, skenario satu (Preemptive) dan skenario dua (Nonpreemptive), nilai fungsi tujuan bernilai 0 dengan solusi optimal  dan , artinya semua kendala yang dimodelkan terpenuhi sehingga penjadwalan dengan Preemptive Goal Programming dan Weighted Goal Programming dikatakan lebih optimal dibandingkan penjadwalan secara manual.