Garuda - Garba Rujukan Digital

Top Brand Award Ranking Analysis Using Social Network Analysis on Coffee Shops on Twitter Social Media herdiany, alvioneta dinda; Asih, Tri Sri Noor
Unnes Journal of Mathematics Vol. 14 No. 1 (2025): Unnes Journal of Mathematics Volume 1, 2025
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/ujm.v14i1.4408

The coffee shop business is one of the very busy businesses. A number of coffee shop brands in Indonesia have begun to emerge. One of the fastest growing fast food coffee chains in Indonesia is Kopi Kenangan. Top Brand is conducting a poll in 2023 to determine the preferred level of consumption for local coffee. According to the findings of the Top Brand Award 2023 survey, Kenangan coffee with a value of 39.70% occupies the first position in the online and offline food and beverage category, while Janji Jiwa coffee is in second place with a value of 39.50%. Janji Jiwa Coffee is one of the fast-growing franchise companies in Indonesia. This study uses the Social Network Analysis (SNA) method to find out which coffee shop brands have higher activity by comparing network properties on Twitter social media. The source of this research data was obtained from the results of crawling data on Twitter social media with the keywords "Kopi Kenangan" and "Kopi Janji Jiwa" for 2 months from November 1, 2023 – December 30, 2023 using Python, with the results of Kenangan copies of 1605 tweets, and Janji Jiwa copies of 1653 tweets. Then text preprocessing is done using Python. Furthermore, visualization was carried out for both coffee shop brands using Python consisting of top word, wordcloud top word, top actor poster, and top mentioned account. After that, making a network pattern graph model using the Gephi application with the Yifan Hu Proportional layout. Followed by an analysis of the network property values of the two brands to be compared. The comparison of the value obtained between the two coffee shop brands, namely the Janji Jiwa coffee shop, excels in 3 network property values such as size, avg. degree, and modularity. While the Kenangan coffee shop is only superior to 1 network property value, namely avg. path length. Other network property values, namely network density and diameter of Kenangan coffee shop and Janji Jiwa coffee shop have the same value. The results of the ranking analysis get different results from brand ranking using the Top Brand Award, namely Janji Jiwa coffee shop ranked 1st and Kenangan coffee shop ranked 2nd. While in the Top Brand Award, Kenangan coffee shop ranked 1st and Janji Jiwa coffee shop ranked 2nd.

Determine the Determinant of 4xn Non-Square Matrix Using Radić’s Determinant Intan Wahyuningsih; Wijayanti, Kristina
Unnes Journal of Mathematics Vol. 13 No. 2 (2024): Unnes Journal of Mathematics Volume 2, 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/ujm.v13i2.6698

A non-square matrix is a matrix that has a different number of rows and columns. In the modified double-guard Hill cipher algorithm, a non-square matrix is used as the private key matrix that plays a role in the message encryption and decryption process. Therefore, the determinant of the key matrix is needed to obtain the inverse of the key matrix. Mirko Radić defined the determinant of matrix Amxn, m<=n as the signed sum of the determinants of the mxm submatrices as many as C (n, m). Radić’s determinant can be used to determine the general formula for the determinant of certain non-square matrices. The purpose of this research is to find out the determinant of matrix R = [\matrix (1&0&0&...&0&0@0&1&0&...&0&0@0&a_1&a_2&...&a_i&0@0&0&0&...&0&1)], ai ∈ R, ∀i=1,2,...,n-2 where n>4, using Radić’s determinant and an example of its use. The result of this research are the following theorem. If a non-square matrix R = [\matrix (1&0&0&...&0&0@0&1&0&...&0&0@0&a_1&a_2&...&a_i&0@0&0&0&...&0&1)], ai ∈ R, ∀i=1,2,...,n-2 where n>4 then |R|= Σ (-1)i+1 ai , for n odd and Σ (-1)i ai, for n even where i=2 to n-2. The use of the theorem is shown in an example problem using the modified double-guard Hill cipher where matrix R is chosen as the private key matrix. Several conditions must be met by the matrix R to be selected as the key matrix, including all elements of matrix R being positive integers, |R|\neq 0 , and R invertible in modulo 128.

Mathematical Model Analysis of Cervical Cancer Disease with Immunotheraphy Eliya Ijtihadiyatun Fisabila; St. Budi Waluya
Unnes Journal of Mathematics Vol. 14 No. 1 (2025): Unnes Journal of Mathematics Volume 1, 2025
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/ujm.v14i1.10717

Cervical cancer is one type of disease that has the highest risk of death in the female population in Indonesia. Almost 95% of cervical cancer in women is caused by Human Papillomavirus (HPV) infection, which is common in women of reproductive age. In this study, a mathematical model is discussed for the case of the spread of the HPV virus to become pre-cancerous with immunotheraphy treatment. This research was conducted by building a mathematical model, analyzing the equilibrium point, and interpreting the mathematical model with numerical simulations using Maple software. This study divides the population into 5 sub-populations including susceptible (S), infected (I), precancer (P), and treatment (T) sub-populations. From the model formed, the disease-free equilibrium point and endemic equilibrium point are obtained as well as the basic reproduction number . The disease-free equilibrium point is locally asymptotically stable when and the endemic equilibrium point is locally asymptotically stable when . Based on the results of numerical simulation analysis, it is obtained that the immunotheraphy treatment is greatly affects on individual recovery.

Lucas’s Matrix Approach in Solving First Order Linear Volterra Integro-Differential Equations Kamoh, Nathaniel; Dang, Bwebum; Soomiyol, Comfort
Unnes Journal of Mathematics Vol. 13 No. 2 (2024): Unnes Journal of Mathematics Volume 2, 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/ujm.v13i2.11243

In this paper, matrix calculus of the Lucas polynomials is derived for the numerical solution of first order linear Volterra integro-differential equations. The equation is solved by transforming the differential part of the equation using the Lucas polynomials matrix of derivatives and the integral part is evaluated base on the Lucas polynomials function. The new method possesses the desirable feature of being a strong and dependable technique for solving many Volterra integro-differential equations of the first order. The developed technique was illustrated on some test problems in literature and results confirmed that the developed technique is more accurate than those developed by some considered authors

Bayesian Optimization for Stock Price Prediction Using LSTM, GRU, Hybrid LSTM-GRU, and Hybrid GRU-LSTM Utami, Mira Dwi; Kharisudin, Iqbal
Unnes Journal of Mathematics Vol. 13 No. 2 (2024): Unnes Journal of Mathematics Volume 2, 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/ujm.v13i2.11253

Stocks have high price fluctuations, which include high risks and high potential returns for investors. This high potential return has attracted significant interest from investors. This study proposes the use of Bayesian optimization methods with Gaussian Process (GP), Random Forest (RF), Extra Trees (ET), and Gradient Boosted Regression Trees (GBRT) surrogate models to enhance the accuracy of stock price predictions using Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and hybrid models (LSTM-GRU and GRU-LSTM). This study tests the effectiveness of various combinations of hyperparameters optimized using the Bayesian optimization method. The model optimized with the Bayesian approach and the GP surrogate model demonstrates superior results compared to the others. Evaluation is conducted using Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and R-squared (R2) metrics. The results indicate that Bayesian optimization with the GP surrogate model for the GRU-LSTM hybrid model outperforms all other methods in terms of MSE, RMSE, MAE, MAPE, and R2. These findings provide significant contributions to parameter selection for stock price prediction and demonstrate the great potential of using Bayesian optimization methods to improve the accuracy of prediction models.

Stacking Ensemble Modeling of Bidirectional LSTM and Bidirectional GRU for Air Temperature Prediction in Ngawi Nike Yustina Oktaviani; Iqbal Kharisudin
Unnes Journal of Mathematics Vol. 13 No. 2 (2024): Unnes Journal of Mathematics Volume 2, 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/ujm.v13i2.11518

Artificial Neural Networks (ANN) have rapidly developed and are used in forecasting, classification, and regression by mimicking how the human brain processes data. Recurrent Neural Networks (RNN), such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), are effective in processing sequential data and handling long-term dependencies. Bidirectional LSTM (BiLSTM) and Bidirectional GRU (BiGRU) process data in both directions to enhance accuracy. This study evaluates the implementation of the Stacking Ensemble method using BiLSTM and BiGRU as base learners and Random Forest as the meta learner to predict air temperature in Ngawi Regency. Air temperature prediction is crucial as it affects agriculture, health, and energy sectors. The data used comprises 2282 records from January 1, 2028, to March 31, 2024, processed using Google Colab. The results show that the Stacking BiLSTM-BiGRU model with Random Forest provides the best performance with a Mean Squared Error of 0.0005, Root Mean Squared Error of 0.0233, Mean Absolute Error of 0.0179, and R-squared of 0.9832, outperforming other individual models. This study confirms that the Stacking Ensemble method with BiLSTM and BiGRU significantly improves air temperature prediction accuracy.

Implementation of Auto ARIMA, PSO-LSTM, and PSO-GRU for Time Series Modeling of 3 Telecommunication Company Stock Prices LQ45 Index Astutiningtyas, Luthfiyah; Kharisudin, Iqbal
Unnes Journal of Mathematics Vol. 13 No. 1 (2024): Unnes Journal of Mathematics Volume 1, 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/ujm.v13i1.11939

The Indonesia Stock Exchange (IDX) issues stock indices to make it easier for investors to choose company shares such as the LQ45 Index. This study focuses on forecasting the share prices of 3 telecommunications companies listed in the LQ45 Index, namely PT Telkom Indonesia Tbk with the stock code TLKM, PT Tower Bersama Infrastructure Tbk with the stock code TBIG and PT Sarana Menara Nusantara Tbk with the stock code TOWR in the future. The algorithms used for forecasting are Auto ARIMA, LSTM and GRU algorithms. In addition, the PSO method is used to find the optimal hyperparameters in the LSTM and GRU algorithms. The results of this study show that the GRU model has the best performance and produces the best model evaluation value compared to other models on TLKM and TBIG stock data, while on TOWR stock data the LSTM model is the best model. The GRU model on TLKM data results in an R Square value of 0,961, RMSE 122,291 on training data and MAPE 3,027% and an R Square value of 0,859, RMSE 114,703 and 2,109% on testing data. On TBIG data, the GRU model results in an R Square value of 0,984, RMSE 71,945 and MAPE 4,206% on training data and R Square an value of 0,967, RMSE 73,627 and 2,165% on testing data. The LSTM model on TOWR data results in an R Square value of 0,943, RMSE 43,824 and MAPE 4,274% on training data and an R Square value of 0,796, RMSE 42,597 and 3,117% on testing data.

On the Efficient Approach for the Solution of General Second Order Linear and Nonlinear Fredholm Integro-Differential Equations Kamoh, Nathaniel; Sunday, Joshua; Simooyol, Comfort
Unnes Journal of Mathematics Vol. 13 No. 1 (2024): Unnes Journal of Mathematics Volume 1, 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/ujm.v13i1.12851

In this paper, Fredholm integro-differential equations are solved using the derivative of the Lucas polynomials in matrix form. The equation is first transformed into systems of nonlinear algebraic equations using the Lucas polynomials. The unknown parameters required for approximating the solution of Fredholm integro-differential equations are then determined using Gaussian elimination. The method has proven to be an active and dependable technique for solving many Fredholm integro-differential equations of different order. The novelty in this technique is that it is capable of solving Fredholm integro differential equation of any order by simply updating the matrix of derivative of the Lucas polynomials also surprisingly the technique was tried on mix Fredholm-Volterra integro differential equation and the result obtained was amazing. Some test problems contained in the literature were solved using the developed technique and the results confirmed the applicability and efficiency of the method. The accuracy of the method was observed to be better when compared with some existing methods.

Time Series Modeling of Stock Price Using CNN-BiLSTM with Attention Mechanism Nur Fitrianingsih, Riska; Kharisudin, Iqbal
Unnes Journal of Mathematics Vol. 13 No. 1 (2024): Unnes Journal of Mathematics Volume 1, 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/ujm.v13i1.13451

Indonesia's capital market has experienced rapid development in recent years, marked by an increase in transaction value, the number of investors, and market capitalization. One of the sectors that has garnered attention is the telecommunications industry, which is rapidly growing alongside the increasing number of internet users and the public's demand for more advanced telecommunications services. PT Indosat Ooredoo Hutchison, as one of the leading telecommunications companies in Indonesia, has become an attractive investment choice for investors. However, the stock market is known for its fluctuating and irregular nature. Stock data has complex characteristics such as large data volume, ambiguous information, and non-linearity. Therefore, it is important for investors to understand stock price movements before making investments in order to reduce the risk of significant losses. One method that can be used to address that risk is by forecasting stock prices. Time series forecasting is a prediction about future values based on historical data. Statistical methods in forecasting allow for the identification of patterns and trends in historical data, as well as modeling the relationships between variables over time. One of the techniques that is becoming increasingly popular in forecasting is deep learning. In this study, a combination of \textit{Convolutional Neural Network} (CNN) and \textit{Bidirectional Long Short-Term Memory} (BiLSTM) with an attention mechanism is used. CNN excels at extracting data features, while BiLSTM is better at handling data with long time ranges. The addition of the attention mechanism allows the model to assign different weights to data features, enabling it to focus on the most relevant information. The combination of these three elements (CNN-BiLSTM with an attention mechanism) has the potential to yield higher prediction accuracy. To measure the accuracy of the forecasts, this study uses evaluation metrics such as Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), and R-squared (R²). The research results indicate that the CNN-BiLSTM model with an attention mechanism has proven to be the most superior model compared to other models in forecasting the stock price of PT Indosat Ooredoo Hutchison.

Breast Cancer Prediction Using Artificial Neural Network Birru Asia Rayani; Faiza Al Laily Nasron; Neli Septiana Putri; Novita Sari Parapat; Virgania Sari
Unnes Journal of Mathematics Vol. 14 No. 1 (2025): Unnes Journal of Mathematics Volume 1, 2025
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/ujm.v14i1.14212

Cancer is one of the medical conditions that causes many deaths in different parts of the world. Based on information obtained from GLOBOCAN, the International Agency for Research on Cancer (IARC) in 2022, there were at least 19.976.499 individuals diagnosed with cancer, and the disease caused death in 9.743.832 people. The detection of breast cancer malignancy relies on the prognosis process, requiring forecasting and automated detection to mitigate diagnostic errors. This facilitates swift and comprehensive analysis of medical data. The study employs the Neural Network, specifically the Artificial Neural Network model, implemented using python and the backpropagation algorithm. Utilizing data from the WDBC Database at the University of Wisconsin, the research achieves a 96,49% accuracy in breast cancer prediction, with an area under curve (AUC) value of 0,992, demonstrating the model's overall efficacy in accurate predictions.

Home Page

OAI Link

Editorial Team

Contact

Reviewer

Google Scholar

Contact Name
-

Contact Email
ujm@mail.unnes.ac.id

Phone
-

Journal Mail Official
ujm@mail.unnes.ac.id

Editorial Address
Sekaran, Kec. Gn. Pati, Kota Semarang, Jawa Tengah 50229

Location
Kota semarang,

Jawa tengah

INDONESIA

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Home Page

OAI Link

Editorial Team

Contact

Reviewer

Google Scholar

Contact Name -

Contact Email ujm@mail.unnes.ac.id

Phone -

Journal Mail Official ujm@mail.unnes.ac.id

Editorial Address Sekaran, Kec. Gn. Pati, Kota Semarang, Jawa Tengah 50229

Location Kota semarang, Jawa tengah INDONESIA

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Contact Name
-

Contact Email
ujm@mail.unnes.ac.id

Phone
-

Journal Mail Official
ujm@mail.unnes.ac.id

Editorial Address
Sekaran, Kec. Gn. Pati, Kota Semarang, Jawa Tengah 50229

Location
Kota semarang,

Jawa tengah

INDONESIA